CN119438813A - A DC fault arc detection method and device - Google Patents
A DC fault arc detection method and device Download PDFInfo
- Publication number
- CN119438813A CN119438813A CN202411400861.9A CN202411400861A CN119438813A CN 119438813 A CN119438813 A CN 119438813A CN 202411400861 A CN202411400861 A CN 202411400861A CN 119438813 A CN119438813 A CN 119438813A
- Authority
- CN
- China
- Prior art keywords
- signal sequence
- similarity measurement
- measurement value
- current
- voltage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 42
- 108010076504 Protein Sorting Signals Proteins 0.000 claims abstract description 457
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 59
- 238000000034 method Methods 0.000 claims abstract description 34
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 238000000605 extraction Methods 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims description 300
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 238000005070 sampling Methods 0.000 claims description 22
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 230000004927 fusion Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 5
- 238000011524 similarity measure Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention provides a direct current fault arc detection method and device, which are used for processing an electric signal sequence to be analyzed by combining wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and classical modal decomposition and reconstruction three feature extraction technologies to respectively obtain a first electric feature signal sequence, a second electric feature signal sequence and a third electric feature signal sequence. The method can reveal the fault characteristics of the electrical signals from multiple dimensions, realize characteristic fusion, effectively improve the accuracy and robustness of fault detection, reduce false alarm and missing report phenomena, has strong adaptability, is suitable for analysis of various electrical signals, and provides accurate and reliable technical support for arc fault detection of a direct current power supply system.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a direct current fault arc detection method and device.
Background
In recent years, as direct current electric equipment is rapidly increased and distributed energy is increased, the application of direct current power supply in a power distribution network is increasingly wide. Compared with alternating current power supply, direct current power supply has the advantages of small energy loss, high power supply efficiency, low line cost and the like, and is widely applied to the fields of large-scale data centers, electric automobiles, space planes, electrified ships and the like. However, in the dc distribution network, due to the small wire cross section, low mechanical strength, low line insulation level, etc., insulation damage, line aging and wire breakage are very likely to occur during the system operation, which results in the generation of a dc arc. Power supply systems for spacecraft, electrical systems for automobiles, etc., which are also disaster areas where dc arc faults occur. The direct current arc does not have a current zero crossing point and cannot be extinguished by itself, if the fault cannot be detected and eliminated in time, the direct current arc will harm the power supply system and the control system, and fire and explosion accidents can be caused in severe cases, which threatens the stable operation of equipment and the system and the personal safety of operators.
Disclosure of Invention
The technical problem to be solved by the embodiment of the invention is to provide a method and a device for detecting the direct current fault arc, which improve the accuracy and the efficiency of the direct current fault arc detection.
In order to solve the technical problems, an embodiment of the present invention provides a method for detecting a dc fault arc, including the following steps:
Sampling an electric signal of a monitored load according to a preset sampling frequency to obtain an electric signal sequence, wherein the electric signal sequence comprises a loop current signal sequence and an arc voltage signal sequence;
The method comprises the steps that an electrical signal sequence to be analyzed, which is matched with a preset time window, is taken out from the electrical signal sequence, wherein the electrical signal sequence to be analyzed comprises a current signal sequence and a voltage signal sequence to be analyzed;
Performing wavelet packet decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a first electric characteristic signal sequence, performing inherent time scale decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a second electric characteristic signal sequence, and performing classical modal decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a third electric characteristic signal sequence;
When the load type of the monitored load is unknown, similarity measurement is carried out on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequences corresponding to the loads of the multiple preset types to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of electrical characteristics between the monitored load and the loads of the multiple preset types, and the first similarity measurement value, the second similarity measurement value and the third similarity measurement value of the electrical characteristics between the monitored load and the loads of the multiple preset types are input into a first probability neural network trained in advance to obtain the load type of the monitored load;
When the load type of the monitored load is known, similarity measurement is carried out on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load respectively to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis are input into a pre-trained second probabilistic neural network to obtain a direct current fault arc detection result of the monitored load, and the direct current fault arc detection result is normal operation or direct current fault arc.
Optionally, the first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence;
The electrical characteristic sample sequence corresponding to each preset type of load comprises a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load operates normally.
Optionally, the performing similarity measurement on the electrical feature sample sequences corresponding to the first electrical feature signal sequence, the second electrical feature signal sequence, and the third electrical feature signal sequence and the loads of the multiple preset types to obtain a first similarity measurement value, a second similarity measurement value, and a third similarity measurement value of electrical features between the monitored load and the loads of the multiple preset types, further includes:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
The Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load is calculated, the calculated Euclidean distance is output as a third current similarity measurement value, and the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the electrical characteristics between the monitored load and the plurality of preset types of loads comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
Optionally, the performing similarity measurement on the first electrical feature signal sequence, the second electrical feature signal sequence, and the third electrical feature signal sequence and the electrical feature sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value, and a third similarity measurement value for fault analysis, further includes:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating the Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
Calculating the Euclidean distance between the third current characteristic signal sequence and a third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity measurement value; the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
Optionally, the method further comprises:
after carrying out wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and obtaining a first electrical characteristic signal sequence, a second electrical characteristic signal sequence and a third electrical characteristic signal sequence on the electrical signal sequence to be analyzed, dividing the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence into equal-length subsections respectively, and calculating the average value of each subsection to correspondingly represent each subsection, so that the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are converted into low-dimension signal sequences.
The embodiment of the invention also provides a direct current fault arc detection device, which comprises:
The sampling module is used for sampling the electric signal of the monitored load according to a preset sampling frequency to obtain an electric signal sequence, wherein the electric signal sequence comprises a loop current signal sequence and an arc voltage signal sequence;
The preprocessing module is used for taking out an electric signal sequence to be analyzed, which is matched with a preset time window, from the electric signal sequence, wherein the electric signal sequence to be analyzed comprises a current signal sequence and a voltage signal sequence to be analyzed;
The characteristic extraction module is used for carrying out wavelet packet decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a first electric characteristic signal sequence, carrying out inherent time scale decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a second electric characteristic signal sequence, and carrying out classical modal decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a third electric characteristic signal sequence;
The load type identification module is used for respectively carrying out similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and electrical characteristic sample sequences corresponding to various preset types of loads when the load type of the monitored load is unknown to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of electrical characteristics between the monitored load and the various preset types of loads, and inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value of the electrical characteristics between the monitored load and the various preset types of loads into a first probability neural network trained in advance to obtain the load type of the monitored load;
And the load fault identification module is used for respectively carrying out similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis when the load type of the monitored load is known, inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis into a pre-trained second probabilistic neural network to obtain a direct current fault arc detection result of the monitored load, wherein the direct current fault arc detection result is normal operation or direct current fault arc.
Optionally, the first electrical characteristic signal sequence includes a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence includes a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence includes a third current characteristic signal sequence and a third voltage characteristic signal sequence;
The electrical characteristic sample sequence corresponding to each preset type of load comprises a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load operates normally.
Optionally, the load type identification module is further configured to:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
The Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load is calculated, the calculated Euclidean distance is output as a third current similarity measurement value, and the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the electrical characteristics between the monitored load and the plurality of preset types of loads comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
Optionally, the load fault identification module is further configured to:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating the Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
Calculating the Euclidean distance between the third current characteristic signal sequence and a third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity measurement value; the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
Optionally, the feature extraction module is further configured to:
after carrying out wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and obtaining a first electrical characteristic signal sequence, a second electrical characteristic signal sequence and a third electrical characteristic signal sequence on the electrical signal sequence to be analyzed, dividing the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence into equal-length subsections respectively, and calculating the average value of each subsection to correspondingly represent each subsection, so that the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are converted into low-dimension signal sequences.
The embodiment of the invention has the following beneficial effects:
The embodiment of the invention adopts various feature extraction methods, namely wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and classical modal decomposition and reconstruction, and processes the electric signal sequence to be analyzed, thereby obtaining a plurality of dimension electric feature signal sequences, and fusing the features to improve the accuracy of fault detection. The embodiment of the invention effectively reduces the risk of fire, explosion and other safety accidents caused by arc faults through real-time monitoring and rapid processing of the direct current arc faults, ensures the stable operation of equipment and systems, is applicable to various direct current power supply systems, such as large-scale data centers, electric automobiles, spaceflight planes, electrified ships and the like, and has wide application prospects.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that it is within the scope of the invention to one skilled in the art to obtain other drawings from these drawings without inventive faculty.
Fig. 1 is a flowchart of a dc fault arc detection method according to an embodiment of the present invention.
Fig. 2 is a block diagram of a dc fault arc detection apparatus according to an embodiment of the present invention.
Detailed Description
The detailed description of the drawings is intended as an illustration of the present embodiment of the application and is not intended to represent the only form in which the present application may be practiced. It is to be understood that the same or equivalent functions may be accomplished by different embodiments that are intended to be encompassed within the spirit and scope of the application.
Referring to fig. 1, an embodiment of the present invention provides a method for detecting a dc fault arc, including the following steps:
step S10, sampling the electric signal of the monitored load according to a preset sampling frequency to obtain an electric signal sequence, wherein the electric signal sequence comprises a loop current signal sequence and an arc voltage signal sequence.
In particular, the description in step S10 refers to the basic process of sampling an electrical signal, the sampling frequency being the number of samples per unit time, typically in hertz (Hz), and the preset sampling frequency being a parameter set before the signal acquisition, which determines the time interval of the sampling, this frequency being high enough to ensure that the original signal is recovered correctly.
The electrical signal of the monitored load refers to an electrical signal generated by the monitored object (i.e., the load) during operation, including current and voltage signals, and the load may be any device or system using direct current.
Sampling refers to recording the value of an electrical signal at a specific point in time at a preset sampling frequency, which is the first step in digitizing, converting a continuous analog signal into a discrete digital signal.
The electrical signal sequence is formed by sampling a series of values which are arranged in time sequence, and in this step, a loop current signal sequence and an arc voltage signal sequence are obtained, wherein the loop current signal sequence refers to the change condition of current in the working process of a load and reflects the electrical behavior and power requirement of the load, and the arc voltage signal sequence refers to the change condition of voltage measured at two ends of the load and can reveal the existence and the characteristics of an arc because the arc can cause specific change of a voltage signal.
And S20, taking out an electric signal sequence to be analyzed, which is matched with a preset time window, from the electric signal sequence, wherein the electric signal sequence to be analyzed comprises a current signal sequence and a voltage signal sequence to be analyzed.
In particular, before the analysis is performed, a specific time window has been set, which is determined on the basis of the analysis and monitoring requirements for the characteristics of the fault arc, which represents the duration of the signal segments extracted from the electrical signal sequence. The electrical signal sequence to be analyzed is the part which is extracted from the whole electrical signal sequence and matches with the preset time window, and the part of the signal sequence is used as an analysis object for detecting the characteristics of the fault arc. The current signal sequence to be analyzed is a part of the electrical signal sequence to be analyzed and is specially representative of the current change condition in a preset time window. The voltage signal sequence to be analyzed is a part of the electric signal sequence to be analyzed, and represents the voltage change condition in a preset time window.
And step S30, carrying out wavelet packet decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a first electric characteristic signal sequence, carrying out inherent time scale decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a second electric characteristic signal sequence, and carrying out classical modal decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a third electric characteristic signal sequence.
Specifically, wavelet packet decomposition is a finer signal processing method that decomposes not only the low frequency part of a signal but also the high frequency part. This approach can more efficiently extract detailed information in the signal. Specifically, the electrical signal sequence to be analyzed is decomposed into a plurality of sub-bands by wavelet packet transformation, each sub-band containing signal components of a different frequency range. The decomposed subbands are selected and reconstructed to extract specific frequency features that aid in identifying the signal characteristics of the arc fault. The first electrical signature signal sequence is obtained by this process and contains important time-frequency information of the signal, which facilitates subsequent fault detection and analysis.
The inherent time scale decomposition is a nonlinear signal processing technology, can decompose according to the inherent characteristics of signals, and is suitable for time-frequency analysis of non-stationary signals. In particular, the electrical signal sequence to be analyzed is decomposed into several inherent rotational components (PROD) and one trend term, each PROD component representing a different time scale characteristic of the signal. The resolved PROD component and trend term are reconstructed to obtain a second electrical characteristic signal sequence which reflects the time scale variation of the signal and is very useful for detecting transient characteristics of arc faults.
Classical modal decomposition is an adaptive time-frequency analysis technique that can decompose a complex signal into a series of eigenmode functions (IMFs), each IMF representing one eigenmode of vibration of the signal. In particular, EMD decomposition is performed on the electrical signal sequence to be analyzed, so as to obtain a plurality of IMFs and a residual component. The decomposed IMFs are selected and reconstructed to form a third sequence of electrical signature signals. This sequence can reveal the inherent vibration characteristics of the signal, helping to identify weak signals of arc faults.
Through the three different decomposition and reconstruction technologies, the method of the embodiment can extract the characteristics of the electrical signals from different angles, provides abundant characteristic information for subsequent fault detection, and uses the characteristic signal sequences as input data for subsequent similarity measurement and fault detection analysis, thereby improving the detection accuracy and reliability.
And S40, when the load type of the monitored load is unknown, performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and electrical characteristic sample sequences corresponding to the loads of the plurality of preset types to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of the electrical characteristics between the monitored load and the loads of the plurality of preset types, and inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value of the electrical characteristics between the monitored load and the loads of the plurality of preset types into a first probability neural network trained in advance to obtain the load type of the monitored load.
Specifically, step S40 is to determine the type of the monitored load by comparing the similarity between the electrical characteristic signal sequence and the electrical characteristic sample sequences of the plurality of preset types of loads in the case where the load type of the monitored load is unknown.
The similarity measure is a method of evaluating the degree of similarity between two data sets. In step S40, a similarity measure needs to be performed on the three extracted electrical characteristic signal sequences and the electrical characteristic sample sequences of the loads of the multiple preset types, where the similarity measure may use multiple methods, such as euclidean distance, cosine similarity, correlation coefficient, and the like.
And carrying out similarity measurement on the first electrical characteristic signal sequence (the characteristics obtained by wavelet packet decomposition and reconstruction) and the first electrical characteristic sample sequences of the loads of the various preset types one by one to obtain first similarity measurement values corresponding to the loads of the various preset types.
And carrying out similarity measurement on the second electrical characteristic signal sequence (the characteristics obtained by inherent time scale decomposition and reconstruction) and the second electrical characteristic sample sequences of the loads of the various preset types one by one to obtain second similarity measurement values corresponding to the loads of the various preset types.
And carrying out similarity measurement on the third electrical characteristic signal sequence (characteristics obtained by classical modal decomposition and reconstruction) and the third electrical characteristic sample sequences of the loads of the various preset types one by one to obtain third similarity measurement values corresponding to the loads of the various preset types.
The obtained similarity measurement value is used as an input characteristic and is input into a pre-trained first probability neural network model, and the probability neural network is a neural network based on probability statistics and is suitable for classification problems, and particularly, the probability neural network is excellent in processing uncertainty and probability data. Prior to implementing step S40, the first probabilistic neural network needs to be trained using electrical feature samples of known load types, during which the network learns how to distinguish between different load types based on the input similarity metric. The first probabilistic neural network outputs the type of load being monitored based on the input first, second and third similarity metric values, the network output results being based on pattern recognition capabilities learned during training, which are capable of recognizing the load type that best matches the input characteristics.
For example, assuming that there are n preset types of loads, there are n sets of similarity measurement values, each set of similarity measurement values includes a first similarity measurement value, a second similarity measurement value and a third similarity measurement value, the n sets of similarity measurement values are input into a first probabilistic neural network, the first probabilistic neural network outputs probabilities that the monitored load belongs to the n preset types of loads, and the identified load type has the highest probability.
And S50, when the load type of the monitored load is known, performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load respectively to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis into a pre-trained second probabilistic neural network to obtain a direct current fault arc detection result of the monitored load, wherein the direct current fault arc detection result is normal operation or direct current fault arc.
Specifically, step S50 is to detect the presence of a dc fault arc by comparing the similarity of the extracted electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the load type, in the case that the type of the monitored load is known. In this step, the type of load being monitored has been determined, which means that fault detection can be performed using the sequence of electrical characteristic samples associated with that particular load type as a reference. According to the previous step (e.g. S30) three different sequences of electrical signature signals have been extracted from the original electrical signal, and then the three sequences of electrical signature signals need to be subjected to respective similarity measures with sequences of electrical signature samples of known load types to obtain a first, a second and a third similarity measure value for fault analysis, the purpose of which is to quantify the degree of similarity between the two sequences. The three obtained similarity measurement values are fed as input features into a pre-trained second Probabilistic Neural Network (PNN) which has learned during the training process how to distinguish between a normal operating state and a fault state based on the similarity measurement values, which processes the input similarity measurement values and outputs a detection result. This detection is typically a classification flag that indicates whether the load being monitored is in a "normal running" state or "dc fault arc present. If the output indicates "normal operation," no fault arc is detected by the monitored load. If the output indicates that a direct current fault arc exists, the monitored load is likely to be in fault, and further inspection or maintenance measures are needed.
Further, the first electrical characteristic signal sequence comprises a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence comprises a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence comprises a third current characteristic signal sequence and a third voltage characteristic signal sequence;
The electrical characteristic sample sequence corresponding to each preset type of load comprises a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load operates normally.
In particular, the first, second and third electrical signature signal sequences are further comprised of a current signature signal sequence and a voltage signature signal sequence, as well as electrical signature sample sequences corresponding to each preset type of load.
The first current signature sequence is a signature sequence extracted from the original current signal by wavelet packet decomposition and reconstruction. It contains key information in the current signal for characterizing the current characteristics of the load. The first voltage characteristic signal sequence is a characteristic sequence extracted from the original voltage signal by a wavelet packet decomposition and reconstruction method. It reflects an important feature of the voltage signal.
The second current signature sequence is a signature sequence extracted from the original current signal by an inherent time scale decomposition and reconstruction method. It provides another view of the current signal, possibly capturing information that the wavelet packet decomposition fails to extract. The second voltage characteristic signal sequence is a characteristic sequence extracted from the original voltage signal by an inherent time scale decomposition and reconstruction method, and is also used for revealing the characteristics of the voltage signal.
The third current characteristic signal sequence is a characteristic sequence extracted from the original current signal by a classical modal decomposition and reconstruction method. It provides an additional dimension for analysis of the current signal. The third voltage characteristic signal sequence is a characteristic sequence extracted from the original voltage signal by a classical modal decomposition and reconstruction method, so that the characteristic information of the voltage signal is further enriched.
For each preset type of load there is a corresponding sequence of electrical signature samples recorded during normal operation of the load for use as a reference standard.
The first current characteristic sample sequence is a sample of a first current characteristic signal sequence recorded by a preset type of load in normal operation, and is obtained by a wavelet packet decomposition and reconstruction method. The second current characteristic sample sequence is a sample of the second current characteristic signal sequence recorded by the preset type of load in normal operation, and is obtained by an inherent time scale decomposition and reconstruction method. The third current characteristic sample sequence is a sample of a third current characteristic signal sequence recorded by a preset type of load in normal operation, and is obtained through a classical modal decomposition and reconstruction method.
The first voltage characteristic sample sequence is a sample of a first voltage characteristic signal sequence recorded by a preset type of load in normal operation, and is obtained through a wavelet packet decomposition and reconstruction method. The second voltage characteristic sample sequence is a sample of the second voltage characteristic signal sequence recorded by the preset type of load in normal operation, and is obtained through an inherent time scale decomposition and reconstruction method. The third voltage characteristic sample sequence is a sample of a third voltage characteristic signal sequence recorded by a preset type of load in normal operation, and is obtained through a classical modal decomposition and reconstruction method.
In step S50, for each preset type of load, the following similarity metric is calculated:
Similarity measurement values of the first current characteristic signal sequence and the corresponding first current characteristic sample sequence.
And the similarity measurement value of the second current characteristic signal sequence and the corresponding second current characteristic sample sequence.
And the similarity measurement value of the third current characteristic signal sequence and the corresponding third current characteristic sample sequence.
Similarity measurement values of the first voltage characteristic signal sequence and the corresponding first voltage characteristic sample sequence.
Similarity measurement values of the second voltage characteristic signal sequence and the corresponding second voltage characteristic sample sequence.
And the similarity measurement value of the third voltage characteristic signal sequence and the corresponding third voltage characteristic sample sequence.
These similarity metric values are fed as input features into a pre-trained second probabilistic neural network to detect the presence of a dc fault arc, and by such refined feature extraction and comparison, the accuracy and reliability of fault detection can be improved.
Further, the performing similarity measurement on the first electrical feature signal sequence, the second electrical feature signal sequence, and the third electrical feature signal sequence and electrical feature sample sequences corresponding to the loads of the multiple preset types to obtain a first similarity measurement value, a second similarity measurement value, and a third similarity measurement value of electrical features between the monitored load and the loads of the multiple preset types, further includes:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
The Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load is calculated, the calculated Euclidean distance is output as a third current similarity measurement value, and the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the electrical characteristics between the monitored load and the plurality of preset types of loads comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
Specifically, for each of the similarity metrics of the pre-set type of load, six similarity metric values are derived, a first current similarity metric value, a second current similarity metric value, a third current similarity metric value, a first voltage similarity metric value, a second voltage similarity metric value, and a third voltage similarity metric value, which together form a comprehensive assessment of the similarity of the electrical characteristics between the monitored load and the corresponding pre-set type of load, which are then input into a pre-trained probabilistic neural network to identify the type of load being monitored. By such careful comparison and measurement, the load type can be more accurately identified, thereby improving the operation and maintenance efficiency and safety of the electrical system.
Further, the performing similarity measurement on the first electrical feature signal sequence, the second electrical feature signal sequence, and the third electrical feature signal sequence and the electrical feature sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value, and a third similarity measurement value for fault analysis, further includes:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating the Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
Calculating the Euclidean distance between the third current characteristic signal sequence and a third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity measurement value; the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
The similarity measurement is carried out on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load respectively to obtain six similarity measurement values for fault analysis, wherein the six similarity measurement values comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value, the similarity measurement values jointly form comprehensive evaluation of electrical characteristic similarity between the monitored load and the corresponding known type load, and the measurement values are then input into a pre-trained probabilistic neural network to detect whether direct current fault arcs exist.
Further, the step S30 further includes:
after carrying out wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and obtaining a first electrical characteristic signal sequence, a second electrical characteristic signal sequence and a third electrical characteristic signal sequence on the electrical signal sequence to be analyzed, dividing the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence into equal-length subsections respectively, and calculating the average value of each subsection to correspondingly represent each subsection, so that the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are converted into low-dimension signal sequences.
Specifically, in step S30, in addition to wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction of the electrical signal sequence to obtain electrical characteristic signal sequences, further processing of these characteristic signal sequences, i.e. segmentation and dimension reduction, is included. The first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are divided into equal-length subsections. The length of the sub-segments depends on the total length of the signal and the required resolution. For example, if the original signal sequence had 1000 data points and we decided that each sub-segment contained 100 data points, then the entire sequence would be partitioned into 10 equal-length sub-segments. For each sub-segment, the average of its data points is calculated. The average value is used as the representative value of the subsection, so that the dimension of the data can be effectively reduced. The original electrical signature signal sequence is converted into a low-dimensional signal sequence by calculating the average value of each sub-segment. This low-dimensional sequence contains critical information of the original signal, but the number of data points is greatly reduced. For example, if there are 1000 data points per original signature signal sequence, after segmentation and averaging, the new low-dimensional signal sequence will have only 10 data points (assuming 100 data points per sub-segment). The dimension reduction can reduce the data volume of the subsequent similarity measurement calculation and the neural network processing, and improve the calculation efficiency. By calculating the sub-segment average value, the main characteristics of the signal can be highlighted, and the influence of noise and details on analysis is reduced. The low-dimensional data is easier to analyze and understand, and the accuracy of fault detection and load type identification is improved. Through this series of processes, the original electrical signal is converted into a sequence of low-dimensional signature signals that are easier to process and analyze, providing an efficient data input for subsequent fault detection and load type identification.
Referring to fig. 2, another embodiment of the present invention further provides a dc fault arc detection apparatus, including:
The sampling module 1 is used for sampling an electric signal of a monitored load according to a preset sampling frequency to obtain an electric signal sequence, wherein the electric signal sequence comprises a loop current signal sequence and an arc voltage signal sequence;
The preprocessing module 2 is used for taking out an electric signal sequence to be analyzed, which is matched with a preset time window, from the electric signal sequence, wherein the electric signal sequence to be analyzed comprises a current signal sequence and a voltage signal sequence to be analyzed;
The feature extraction module 3 is configured to perform wavelet packet decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a first electrical feature signal sequence, perform inherent time scale decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a second electrical feature signal sequence, and perform classical modal decomposition and reconstruction on the electrical signal sequence to be analyzed to obtain a third electrical feature signal sequence;
The load type identification module 4 is configured to, when the load type of the monitored load is unknown, perform similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence and electrical characteristic sample sequences corresponding to multiple preset types of loads to obtain a first similarity measurement value, a second similarity measurement value, and a third similarity measurement value of electrical characteristics between the monitored load and the multiple preset types of loads, and input the first similarity measurement value, the second similarity measurement value, and the third similarity measurement value of electrical characteristics between the monitored load and the multiple preset types of loads into a first probability neural network trained in advance to obtain the load type of the monitored load;
And the load fault identification module 5 is configured to, when the load type of the monitored load is known, perform similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, and input the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis into a pre-trained second probabilistic neural network to obtain a direct current fault arc detection result of the monitored load, where the direct current fault arc detection result is normal operation or direct current fault arc.
Further, the first electrical characteristic signal sequence comprises a first current characteristic signal sequence and a first voltage characteristic signal sequence, the second electrical characteristic signal sequence comprises a second current characteristic signal sequence and a second voltage characteristic signal sequence, and the third electrical characteristic signal sequence comprises a third current characteristic signal sequence and a third voltage characteristic signal sequence;
The electrical characteristic sample sequence corresponding to each preset type of load comprises a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load operates normally.
Further, the load type identification module 4 is further configured to:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
The Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load is calculated, the calculated Euclidean distance is output as a third current similarity measurement value, and the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the electrical characteristics between the monitored load and the plurality of preset types of loads comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
Further, the load fault identification module 5 is further configured to:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating the Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
Calculating the Euclidean distance between the third current characteristic signal sequence and a third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity measurement value; the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
Further, the feature extraction module 3 is further configured to:
after carrying out wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and obtaining a first electrical characteristic signal sequence, a second electrical characteristic signal sequence and a third electrical characteristic signal sequence on the electrical signal sequence to be analyzed, dividing the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence into equal-length subsections respectively, and calculating the average value of each subsection to correspondingly represent each subsection, so that the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are converted into low-dimension signal sequences.
It should be noted that, the apparatus in this embodiment corresponds to the method in the foregoing embodiment, so details not described in this embodiment may be obtained by referring to the details of the method in the foregoing embodiment, and will not be described in detail in this embodiment.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (10)
1. The direct current fault arc detection method is characterized by comprising the following steps of:
Sampling an electric signal of a monitored load according to a preset sampling frequency to obtain an electric signal sequence, wherein the electric signal sequence comprises a loop current signal sequence and an arc voltage signal sequence;
The method comprises the steps that an electrical signal sequence to be analyzed, which is matched with a preset time window, is taken out from the electrical signal sequence, wherein the electrical signal sequence to be analyzed comprises a current signal sequence and a voltage signal sequence to be analyzed;
Performing wavelet packet decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a first electric characteristic signal sequence, performing inherent time scale decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a second electric characteristic signal sequence, and performing classical modal decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a third electric characteristic signal sequence;
When the load type of the monitored load is unknown, similarity measurement is carried out on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequences corresponding to the loads of the multiple preset types to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of electrical characteristics between the monitored load and the loads of the multiple preset types, and the first similarity measurement value, the second similarity measurement value and the third similarity measurement value of the electrical characteristics between the monitored load and the loads of the multiple preset types are input into a first probability neural network trained in advance to obtain the load type of the monitored load;
When the load type of the monitored load is known, similarity measurement is carried out on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load respectively to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis, the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis are input into a pre-trained second probabilistic neural network to obtain a direct current fault arc detection result of the monitored load, and the direct current fault arc detection result is normal operation or direct current fault arc.
2. The direct current fault arc detection method of claim 1, wherein the first electrical signature signal sequence comprises a first current signature signal sequence and a first voltage signature signal sequence, the second electrical signature signal sequence comprises a second current signature signal sequence and a second voltage signature signal sequence, and the third electrical signature signal sequence comprises a third current signature signal sequence and a third voltage signature signal sequence;
The electrical characteristic sample sequence corresponding to each preset type of load comprises a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load operates normally.
3. The method of claim 2, wherein the performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence with electrical characteristic sample sequences corresponding to a plurality of types of loads to obtain a first similarity measurement value, a second similarity measurement value, and a third similarity measurement value of electrical characteristics between the monitored load and the plurality of types of loads, respectively, further comprises:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
The Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load is calculated, the calculated Euclidean distance is output as a third current similarity measurement value, and the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the electrical characteristics between the monitored load and the plurality of preset types of loads comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
4. The method of claim 2, wherein performing similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence, and the third electrical characteristic signal sequence with the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value, and a third similarity measurement value for fault analysis, respectively, further comprises:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating the Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
Calculating the Euclidean distance between the third current characteristic signal sequence and a third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity measurement value; the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
5. The direct current fault arc detection method of claim 2, further comprising:
after carrying out wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and obtaining a first electrical characteristic signal sequence, a second electrical characteristic signal sequence and a third electrical characteristic signal sequence on the electrical signal sequence to be analyzed, dividing the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence into equal-length subsections respectively, and calculating the average value of each subsection to correspondingly represent each subsection, so that the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are converted into low-dimension signal sequences.
6. A direct current fault arc detection apparatus, comprising:
The sampling module is used for sampling the electric signal of the monitored load according to a preset sampling frequency to obtain an electric signal sequence, wherein the electric signal sequence comprises a loop current signal sequence and an arc voltage signal sequence;
The preprocessing module is used for taking out an electric signal sequence to be analyzed, which is matched with a preset time window, from the electric signal sequence, wherein the electric signal sequence to be analyzed comprises a current signal sequence and a voltage signal sequence to be analyzed;
The characteristic extraction module is used for carrying out wavelet packet decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a first electric characteristic signal sequence, carrying out inherent time scale decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a second electric characteristic signal sequence, and carrying out classical modal decomposition and reconstruction on the electric signal sequence to be analyzed to obtain a third electric characteristic signal sequence;
The load type identification module is used for respectively carrying out similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and electrical characteristic sample sequences corresponding to various preset types of loads when the load type of the monitored load is unknown to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value of electrical characteristics between the monitored load and the various preset types of loads, and inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value of the electrical characteristics between the monitored load and the various preset types of loads into a first probability neural network trained in advance to obtain the load type of the monitored load;
And the load fault identification module is used for respectively carrying out similarity measurement on the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence and the electrical characteristic sample sequence corresponding to the monitored load to obtain a first similarity measurement value, a second similarity measurement value and a third similarity measurement value for fault analysis when the load type of the monitored load is known, inputting the first similarity measurement value, the second similarity measurement value and the third similarity measurement value for fault analysis into a pre-trained second probabilistic neural network to obtain a direct current fault arc detection result of the monitored load, wherein the direct current fault arc detection result is normal operation or direct current fault arc.
7. The direct current fault arc detection device of claim 6, wherein the first electrical signature signal sequence comprises a first current signature signal sequence and a first voltage signature signal sequence, the second electrical signature signal sequence comprises a second current signature signal sequence and a second voltage signature signal sequence, and the third electrical signature signal sequence comprises a third current signature signal sequence and a third voltage signature signal sequence;
The electrical characteristic sample sequence corresponding to each preset type of load comprises a first current characteristic sample sequence, a second current characteristic sample sequence, a third current characteristic sample sequence, a first voltage characteristic sample sequence, a second voltage characteristic sample sequence and a third voltage characteristic sample sequence when the preset type of load operates normally.
8. The direct current arc fault detection device of claim 7, wherein the load type identification module is further configured to:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to each preset type of load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
The Euclidean distance between the third current characteristic signal sequence and the third current characteristic sample sequence corresponding to each preset type of load is calculated, the calculated Euclidean distance is output as a third current similarity measurement value, and the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to each preset type of load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the electrical characteristics between the monitored load and the plurality of preset types of loads comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
9. The direct current fault arc detection device of claim 7, wherein the load fault identification module is further configured to:
Calculating Euclidean distance between the first current characteristic signal sequence and a first current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a first current similarity measurement value; the Euclidean distance between the first voltage characteristic signal sequence and the first voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a first voltage similarity measurement value;
Calculating the Euclidean distance between the second current characteristic signal sequence and a second current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a second current similarity measurement value; the Euclidean distance between the second voltage characteristic signal sequence and the second voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a second voltage similarity measurement value;
Calculating the Euclidean distance between the third current characteristic signal sequence and a third current characteristic sample sequence corresponding to the monitored load, and outputting the calculated Euclidean distance as a third current similarity measurement value; the Euclidean distance between the third voltage characteristic signal sequence and the third voltage characteristic sample sequence corresponding to the monitored load is calculated, and the calculated Euclidean distance is output as a third voltage similarity measurement value;
The similarity measurement values of the first electrical characteristic signal sequence, the second electrical characteristic signal sequence and the third electrical characteristic signal sequence of the monitored load and the electrical characteristic sample sequence comprise a first current similarity measurement value, a second current similarity measurement value, a third current similarity measurement value, a first voltage similarity measurement value, a second voltage similarity measurement value and a third voltage similarity measurement value.
10. The direct current fault arc detection method of claim 7, wherein the feature extraction module is further configured to:
after carrying out wavelet packet decomposition and reconstruction, inherent time scale decomposition and reconstruction and obtaining a first electrical characteristic signal sequence, a second electrical characteristic signal sequence and a third electrical characteristic signal sequence on the electrical signal sequence to be analyzed, dividing the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence into equal-length subsections respectively, and calculating the average value of each subsection to correspondingly represent each subsection, so that the first current characteristic signal sequence, the second current characteristic signal sequence, the third current characteristic signal sequence, the first voltage characteristic signal sequence, the second voltage characteristic signal sequence and the third voltage characteristic signal sequence are converted into low-dimension signal sequences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411400861.9A CN119438813A (en) | 2024-10-09 | 2024-10-09 | A DC fault arc detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411400861.9A CN119438813A (en) | 2024-10-09 | 2024-10-09 | A DC fault arc detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119438813A true CN119438813A (en) | 2025-02-14 |
Family
ID=94512342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411400861.9A Pending CN119438813A (en) | 2024-10-09 | 2024-10-09 | A DC fault arc detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119438813A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120142825A (en) * | 2025-05-14 | 2025-06-13 | 国网山西省电力公司长治供电公司 | Power system metering secondary circuit detection and early warning method and device |
-
2024
- 2024-10-09 CN CN202411400861.9A patent/CN119438813A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120142825A (en) * | 2025-05-14 | 2025-06-13 | 国网山西省电力公司长治供电公司 | Power system metering secondary circuit detection and early warning method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | ArcNet: Series AC arc fault detection based on raw current and convolutional neural network | |
| RU2484487C2 (en) | Method and device for determination of electric arc occurrence on at least one electric cable | |
| US8779928B2 (en) | Systems and methods to detect generator collector flashover | |
| CN119438813A (en) | A DC fault arc detection method and device | |
| CN106597160B (en) | Electronic equipment fault detection method and device | |
| CN115078912B (en) | Real-time detection method, system and train for abnormality detection of roof high-voltage cable joints | |
| CN117239942B (en) | Ammeter with monitoring function | |
| CN117289067B (en) | Transformer running state on-line monitoring system | |
| CN119414172A (en) | A DC fault arc state monitoring method and device, and computer program product | |
| CN117269660A (en) | Fault arc detection method and system based on variation coefficient difference algorithm | |
| CN115128345A (en) | Power grid safety early warning method and system based on harmonic monitoring | |
| CN119322242A (en) | Intelligent power equipment fault diagnosis system and method based on image recognition and partial discharge feature extraction | |
| CN119147861A (en) | Security monitoring method, device, equipment and storage medium of DTU | |
| Yang et al. | Brown measure based spectral distribution analysis for spatial-temporal localization of cascading events in power grids | |
| CN117827511A (en) | Fault diagnosis method and device for radio frequency circuit board | |
| Zhang et al. | A Fault Detection Method for Analog Circuits Based on the Wavelet Features and One-class KNN | |
| CN112001326B (en) | Vibration fingerprint-based high-voltage switch equipment fault diagnosis and prediction method and system | |
| Li et al. | A multiple anomaly detection scheme and random forest algorithm for identifying the incipient faults in transmission network | |
| Belkov et al. | Advanced approach for automatic PRPD pattern recognition in monitoring of HV assets | |
| CN106443238A (en) | High-voltage equipment state evaluation method, high-voltage equipment on-line monitoring device evaluation method and apparatuses | |
| CN114139753A (en) | Fault prediction method for power distribution network | |
| CN118501613B (en) | AC/DC series-parallel power line fault signal detection method | |
| CN118112416B (en) | Carbon brush sparking detection method, system and storage medium for hydroelectric generating set | |
| Barmada et al. | Use of advanced signal processing techniques for arcing detection on AC pantograph catenary systems | |
| Fang et al. | Optimized Non-Maximum Suppression for Multi-Source Local Discharge PRPD Pattern Identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |