CN116540019A - A partial discharge detection method and device - Google Patents

Abstract

The application relates to a partial discharge detection method and a partial discharge detection device, which are characterized in that partial discharge signals from a plurality of sensors are acquired, wherein the plurality of sensors are arranged at different positions of electrical equipment for generating partial discharge; positioning the partial discharge signal sources based on the arrival time differences of the partial discharge signals to obtain the positions of the partial discharge signal sources; and determining the type of the partial discharge signal source based on the characteristic information of the plurality of partial discharge signals. According to the method and the device, the local discharge signal source is positioned correspondingly by fusing the arrival time differences of the various sensor signals, the type of the local signal source is determined by fusing the characteristic information of the various sensor signals, so that the local discharge signal can be monitored by utilizing the advantages of the various sensors, and the monitoring effect is better.

Description

A partial discharge detection method and device

technical field

This application relates to the technical field of substation testing, in particular to a partial discharge detection method and device.

Background technique

As the scale of my country's power system continues to expand, the network structure becomes more and more complex, and the pace of the power Internet of Things continues to accelerate, higher technical performance requirements are put forward for the safety, reliability, and energy-saving economy of power system regulation and operation. The safety and stability of some power equipment, such as power cables and power transformers, determine the safe and stable operation of the entire power system. The results of practical work experience and relevant case analysis show that insulation performance is the core factor affecting the safe and reliable operation of power equipment. Partial discharge has become a key factor that causes the insulation performance of power equipment to decrease or even deteriorate, and is the main reason that affects the safety, stability, energy-saving and economical operation of power equipment and even the entire power system.

At present, the development of partial discharge monitoring methods using a single sensor is relatively mature, but there are certain technical bottlenecks in the multi-mode detection method. The compatibility between various sensors is poor, and they cannot be used on a unified platform, making it impossible to simultaneously play various aspects during detection. Because of the advantages of this kind of sensor, it cannot adapt to different power equipment.

Contents of the invention

In view of this, the purpose of this application is to provide a partial discharge detection method and device, which can solve the technical problem in the prior art that the advantages of multiple sensors cannot be used to monitor partial discharge.

In order to achieve the above object, the application adopts the following technical solutions:

A partial discharge detection method of the present application, comprising:

acquiring partial discharge signals from a plurality of sensors, wherein the plurality of sensors are located at different locations of the electrical equipment generating the partial discharge;

The partial discharge signal source is located based on the arrival time difference of the plurality of partial discharge signals, and the position of the partial discharge signal source is obtained; and the type of the partial discharge signal source is determined based on the characteristic information of the plurality of partial discharge signals.

In an embodiment of the present application, the electrical equipment is a cable, and the various sensors include a plurality of HFCT sensors and a plurality of UHF sensors, wherein the source of the partial discharge signal is located based on the time difference of arrival of the plurality of partial discharge signals, include:

determining a time difference at which the plurality of HFCT sensors receive corresponding partial discharge signals;

Determine the distance between the multiple HFCT sensors and the partial discharge signal source based on the time difference between the multiple HFCT sensors receiving the corresponding partial discharge signal; and determine the partial discharge signal based on the distance between the multiple HFCT sensors and the partial discharge signal source the location interval of the source;

determining the time difference of receiving the corresponding partial discharge signal by a plurality of UHF sensors in the location interval;

Determine the distance between the plurality of UHF sensors in the location interval and the partial discharge signal source based on the time difference between the plurality of UHF sensors in the location interval receiving the corresponding partial discharge signal, and based on the plurality of UHF sensors in the location interval and the partial discharge signal The distance to the source determines the location of the source of the partial discharge signal.

In an embodiment of the present application, the method for determining the position of the partial discharge signal source based on the distance between a plurality of sensors and the partial discharge signal source includes:

Take the distance between each HFCT sensor or UHF sensor and the partial discharge signal source as the radius, and use the corresponding sensor as the center of the circle to establish multiple circles;

The intersection of the multiple circles is determined, and the intersection is used as the position of the partial discharge signal source or the position interval of the partial discharge signal source.

In an embodiment of the present application, determining the time difference of receiving the corresponding partial discharge signal by multiple UHF sensors in the location interval includes:

extracting characteristic parameters of partial discharge signals of a plurality of UHF sensors in the position interval;

normalizing the characteristic parameters of the partial discharge signals of the plurality of UHF sensors in the position interval;

establishing cross-correlation functions of the plurality of partial discharge signals based on the plurality of characteristic parameters after normalization processing;

The peak positions of the plurality of partial discharge signals are determined based on the cross-correlation function, and the time difference of receiving the partial discharge signals by the plurality of UHF sensors is determined based on the peak positions of the plurality of partial discharge signals.

In an embodiment of the present application, the electrical equipment is a switch cabinet or a transformer, and the various sensors include UHF sensors and AE sensors, wherein the source of the partial discharge signal is located based on the time difference of arrival of the various partial discharge signals ,include:

determining the time difference between the UHF sensor and the AE sensor receiving the partial discharge signal;

determining the distance between the UHF sensor, the AE sensor and a partial discharge signal source based on the time difference between the UHF sensor and the AE sensor receiving the partial discharge signal;

The time when the UHF sensor and the AE sensor receive the partial discharge signal, the distance between the UHF sensor and the partial discharge signal source, and the distance between the AE sensor and the partial discharge signal source are input into the pre-established neural network model, obtaining the relative positions of the UHF sensor, the AE sensor and the partial discharge signal source;

The absolute position of the partial discharge signal source is determined based on the coordinate information of the UHF sensor, the coordinate information of the AE sensor and the relative position.

In an embodiment of the present application, the following method is also included to establish a neural network model:

Acquiring training data and tags of the training data, wherein the training data includes the time difference between multiple sensors receiving the partial discharge signal and the distance between the multiple sensors and the source of the partial discharge signal, and the tag is the sensor and the partial discharge signal The relative position of the signal source;

The BP neural network is trained based on the training data and the labels of the training data to obtain a neural network model.

In an embodiment of the present application, determining the type of a partial discharge signal source based on characteristic information of a plurality of partial discharge signals includes:

Based on the feature information of the plurality of partial discharge signals and a pre-established Bayesian probability model, multiple fault types of the partial discharge signal source and the probability of each fault type are determined, wherein the Bayesian probability model is Established based on multiple fault types and feature information of multiple fault types, the Bayesian probability model is used to characterize the expected occurrence probability of each fault type in the overall fault, and the corresponding feature information of each fault type;

establishing a belief function based on the probability of each failure type;

Converting the trust function into DS evidence, and combining the DS evidence to obtain the confidence degree of each fault type;

The type of the partial discharge signal source is determined based on the confidence level of each fault type.

The present application also provides a partial discharge detection device, including:

An acquisition module, configured to acquire partial discharge signals from various sensors, wherein the various sensors are set at different positions of the electrical equipment that generates partial discharge;

The detection module is used for locating the partial discharge signal source based on the arrival time difference of the plurality of partial discharge signals, and obtaining the position of the partial discharge signal source; and determining the type of the partial discharge signal source based on the feature information of the plurality of partial discharge signals.

The present application also provides an electronic device, the electronic device comprising:

one or more processors;

The storage device is configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the partial discharge detection method as described above.

The present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor of a computer, the computer is made to execute the partial discharge detection method as described above.

The beneficial effects of the present application are: a partial discharge detection method and device of the present application, by obtaining partial discharge signals from various sensors, wherein the various sensors are set at different positions of electrical equipment that generate partial discharge; based on multiple The partial discharge signal source is located based on the arrival time difference of two partial discharge signals, and the position of the partial discharge signal source is obtained; and the type of the partial discharge signal source is determined based on the characteristic information of multiple partial discharge signals. This application locates the partial discharge signal source by fusing the arrival time difference of multiple sensor signals, and determines the type of local signal source by fusing the characteristic information of multiple sensor signals, so that the advantages of multiple sensors can be used to monitor partial discharge signal, the monitoring effect is better.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application. Apparently, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative efforts. In the attached picture:

Fig. 1 is a flowchart of a partial discharge detection method shown in an exemplary embodiment of the present application;

Fig. 2 is a specific implementation flow chart of partial discharge positioning shown in an exemplary embodiment of the present application;

Fig. 3 is a structural diagram of a partial discharge detection device shown in an exemplary embodiment of the present application;

Fig. 4 is a structural diagram of a partial discharge detection device shown in another exemplary embodiment of the present application;

Fig. 5 shows a schematic structural diagram of a computer system suitable for implementing the electronic device of the embodiment of the present application.

Detailed ways

The implementation of the present application will be described below with reference to the accompanying drawings and preferred embodiments, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation modes, and various modifications or changes can be made to the details in this specification based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only used to illustrate the present application, but not to limit the protection scope of the present application.

It should be noted that the diagrams provided in the following embodiments are only schematically illustrating the basic idea of the application, and only the components related to the application are shown in the diagrams rather than the number, shape and Dimensional drawing, the type, quantity and proportion of each component can be changed arbitrarily during actual implementation, and the component layout type may also be more complicated.

In the following description, numerous details are discussed in order to provide a more thorough explanation of the embodiments of the present application, however, it will be apparent to those skilled in the art that the embodiments of the present application can be practiced without these specific details, In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail in order to avoid obscuring the embodiments of the present application.

Fig. 1 is a flow chart of a partial discharge detection method shown in an exemplary embodiment of the present application, as shown in Fig. 1: a partial discharge detection method of this embodiment, including steps S110 to step S120, is described in detail as follows:

S110. Acquire partial discharge signals from various sensors, wherein the various sensors are set at different positions of the electrical equipment that generates partial discharge;

S120. Locate the partial discharge signal source based on the arrival time difference of the plurality of partial discharge signals to obtain the position of the partial discharge signal source; and determine the type of the partial discharge signal source based on the characteristic information of the plurality of partial discharge signals.

Wherein, the types of the various sensors are determined based on the type of the electrical equipment. Types of electrical equipment include power cables, switchgear, transformers, etc. In this application, when users need to detect PD signals in power equipment such as transformers, switch cabinets, and power cables, they only need to arrange sensors in advance and connect them to the transmission network. When the terminal receives the transmitted PD signals, it will The signal is analyzed for data. According to the address bit information, it is first judged which electrical equipment the PD source comes from. On this basis, the specific location and PD type are judged through intelligent information fusion.

Fig. 2 is a specific implementation flowchart of partial discharge positioning shown in an exemplary embodiment of the present application. As shown in Fig. 2, when the electrical equipment is a cable, multiple HFCT (high frequency current, high frequency current) sensors and Multiple UHF (Ultra High Frequency, ultra-high frequency) sensors perform joint positioning, wherein the partial discharge signal source is located based on the arrival time difference of multiple partial discharge signals, including:

determining a time difference at which the plurality of HFCT sensors receive corresponding partial discharge signals;

Among them, when partial discharge occurs in the power cable, different HFCT sensors will receive partial discharge signals at different times. By comparing the signal arrival time between different HFCT sensors, the propagation time difference of partial discharge signals can be calculated.

Determine the distance between the multiple HFCT sensors and the partial discharge signal source based on the time difference between the multiple HFCT sensors receiving the corresponding partial discharge signal; and determine the partial discharge signal based on the distance between the multiple HFCT sensors and the partial discharge signal source the location interval of the source;

In the present application, a partial discharge signal source is located by a time difference of arrival (Time delay of arrival, TDOA) positioning method. Time difference of arrival positioning is a method of positioning using time difference. By measuring the time it takes for the signal to reach the monitoring station, the distance to the source of the signal can be determined.

The measurement accuracy of the HFCT sensor is relatively poor, and there will be a large error between the measured PD position and the real PD position, but the approximate position of PD can be obtained. For example, by deploying two HFCT sensors on a line, it can be known whether partial discharge has occurred on the line between the two HFCT sensors. The UHF sensor has high positioning accuracy, but the measurement range is not large. If the UHF sensor is deployed between several HFCT sensors, the partial discharge can be measured by the UHF sensor in the corresponding interval after the HFCT sensor measures the partial discharge occurrence interval. The precise location of the occurrence. Deploying the above two sensors can reduce the cost on the basis of obtaining the precise location of the partial discharge.

Specifically, the positioning process includes:

Taking the distance between each HFCT sensor and the partial discharge signal source as the radius, and using the corresponding sensor as the center of the circle, multiple circles are established;

The intersection of the multiple circles is determined, and the intersection is used as the location interval of the partial discharge signal source of the partial discharge signal source.

A time difference at which the plurality of UHF sensors in the location interval receive corresponding partial discharge signals is determined.

Determine the distance between the plurality of UHF sensors in the location interval and the partial discharge signal source based on the time difference between the plurality of UHF sensors in the location interval receiving the corresponding partial discharge signal, and based on the plurality of UHF sensors in the location interval and the partial discharge signal The distance to the source determines the location of the source of the partial discharge signal.

After the location interval is determined, each UHF sensor in the location interval is called to compare and match the PD signal characteristic parameters collected by different UHF sensors, and calculate the time difference of the signal. Based on time difference and sensor location information.

The method of UHF sensor positioning is consistent with the method of HFCT sensor positioning. It is also first to determine the distance between each UHF sensor and the partial discharge signal source by using the time difference of arrival. The exact location is then determined by the following methods, including:

Take the distance between each UHF sensor and the partial discharge signal source as the radius, and use the corresponding sensor as the center to establish multiple circles;

The intersection of the plurality of circles is determined, and the intersection is used as the position of the partial discharge signal source of the partial discharge signal source.

Wherein, determining the time difference of receiving the corresponding partial discharge signal by a plurality of UHF sensors in the location interval includes:

Extracting characteristic parameters of partial discharge signals of multiple UHF sensors in the location interval, wherein the characteristic parameters include pulse number, pulse repetition rate, pulse amplitude, peak amplitude, energy, frequency, mean value, variance, etc. of partial discharge signals.

normalizing the characteristic parameters of the partial discharge signals of the plurality of UHF sensors in the position interval;

Normalize the collected partial discharge signals to ensure that the mean value of the signal is 0 and the variance is 1. The specific process includes:

Calculate the mean value of the signal amplitude: For the collected partial discharge signal, calculate its mean value. The mean of the signal is obtained by dividing the sum of all sample values in the signal by the number of samples.

Calculate the variance of the signal: For the collected partial discharge signal, calculate its variance. The variance is the average of the squares of the differences of each sample from the mean. You can square the difference of each sample from the mean, sum all the differences, and divide by the number of samples to get the variance of the signal.

Perform normalization processing: for each collected sample value, use the following formula to perform normalization processing: normalized sample value=(original sample value−mean value)/square root of variance.

After doing this, the mean of the normalized signal will become 0 and the variance will become 1.

establishing cross-correlation functions of the plurality of partial discharge signals based on the plurality of characteristic parameters after normalization processing;

The specific establishment process of the cross-correlation function includes:

Determine the signal length: first determine the length of the normalized PD signal, assuming that the length is N.

Calculate the cross-correlation function: For the normalized signals of the two UHF sensors, assume x and y respectively.

Compute the cross-correlation function:

a. Zero-fill x and y: add N-1 zeros at the end of the signal to extend the length of the signal to 2N-1.

b. Perform Fourier transform on x and y: Perform fast Fourier transform (FFT) on x and y to obtain frequency domain representation.

c. Calculate the frequency domain representation of the cross-correlation: multiply the frequency domain representation of x by the frequency domain representation of y element by element.

d. Perform an inverse Fourier transform on the frequency domain representation of the cross-correlation: perform an inverse Fourier transform (IFFT) on the product result to obtain a cross-correlation function in the time domain.

The resulting cross-correlation function is a time-domain signal of length 2N-1, which represents the correlation between the two signals.

The peak positions of the plurality of partial discharge signals are determined based on the cross-correlation function, and the time difference of receiving the partial discharge signals by the plurality of UHF sensors is determined based on the peak positions of the plurality of partial discharge signals.

As shown in Figure 2, when the electrical equipment is a switchgear or a transformer, UHF sensors and AE sensors are used for positioning monitoring, wherein the localization of the partial discharge signal source is performed based on the arrival time difference of the various partial discharge signals, including :

determining the time difference between the UHF sensor and the AE sensor receiving the partial discharge signal;

Use the signal data collected by the UHF sensor and the AE sensor to calculate the time difference between the two.

determining the distance between the UHF sensor, the AE sensor and a partial discharge signal source based on the time difference between the UHF sensor and the AE sensor receiving the partial discharge signal;

Wherein, a time difference of arrival positioning method is used to determine the distances between the UHF sensor, the AE sensor and the partial discharge signal source.

The time when the UHF sensor and the AE sensor receive the partial discharge signal, the distance between the UHF sensor and the partial discharge signal source, and the distance between the AE sensor and the partial discharge signal source are input into the pre-established neural network model, obtaining the relative positions of the UHF sensor, the AE sensor and the partial discharge signal source;

The absolute position of the partial discharge signal source is determined based on the coordinate information of the UHF sensor, the coordinate information of the AE sensor and the relative position.

In this embodiment, the partial discharge signal source is located using the TDOA method combined with BP neural network data fusion. The BP neural network model is used to establish the distance between multiple sensors and the partial discharge signal source, the relationship between the receiving time difference of multiple sensors and the position of the partial discharge signal source.

In an embodiment of the present application, the following method is also included to establish a neural network model:

Acquiring training data and tags of the training data, wherein the training data includes the time difference between multiple sensors receiving the partial discharge signal and the distance between the multiple sensors and the source of the partial discharge signal, and the tag is the sensor and the partial discharge signal The relative position of the signal source;

The BP neural network is trained based on the training data and the labels of the training data to obtain a neural network model.

The calculated time difference data, the distance between multiple sensors and the partial discharge signal source are used as the input of the BP neural network, and the network structure is designed and trained. During the training process, the position data of the known PD signal source is used as the sample label, and the network parameters are trained so that it can accurately predict the position of the unknown PD signal source. The trained BP neural network is used to predict the position of the unknown PD signal source. Compare the prediction results with the actual measurement data of the UHF sensor and AE sensor to further optimize the accuracy of the prediction results. Repeat the above steps to detect and locate multiple partial discharge signals. Finally, a spatial distribution map of partial discharge signals in the switchgear can be obtained.

In this application, whether it is to detect power cables, or to detect switch cabinets or transformers. Both use DS evidence theory to determine the type of partial discharge. DS evidence theory is a mathematical tool used to deal with uncertainty, which can integrate evidence from different sources to draw more reliable conclusions. When using the DS evidence theory, it is necessary to extract the features of the PD signals collected by different sensors, use the extracted features as evidence, and then use the DS evidence theory for fusion to obtain the judgment result of the PD type. Specifically, AE and UHF sensors collect partial discharge signals respectively, and extract the statistical features of UHF and AE signals, including mean, variance, standard deviation, etc. These features can be used as different evidence to construct DS The trust distribution function in the evidence theory is then fused with the DS evidence theory to obtain the judgment result of the PD type.

Determine the type of the partial discharge signal source based on the feature information of multiple partial discharge signals, including:

Based on the feature information of the plurality of partial discharge signals and a pre-established Bayesian probability model, multiple fault types of the partial discharge signal source and the probability of each fault type are determined, wherein the Bayesian probability model is Established based on multiple fault types and feature information of multiple fault types, the Bayesian probability model is used to characterize the expected occurrence probability of each fault type in the overall fault, and the corresponding feature information of each fault type;

Wherein, when the power cable is detected, the characteristic information of multiple partial discharge signals may include:

Amplitude: Both HFCT and UHF sensors can measure the amplitude of the PD signal, which reflects the strength and size of the PD signal.

Frequency: UHF sensors can measure and analyze the frequency of PD signals, and frequency spectrum information can help identify PD types.

Pulse Velocity: UHF sensors can measure the propagation velocity of the PD signal in the cable, and the pulse velocity can help determine the location of the PD.

Number of pulses: The number of pulses refers to the number of pulses that appear within a certain period of time. The HFCT sensor can measure the number of pulses, which can be used to evaluate the severity of partial discharge.

Waveform characteristics: HFCT and UHF sensors can capture the waveform information of PD signals, including rise time, fall time, duration, etc. Waveform characteristics can be used to identify the type of PD and determine the location of PD.

When testing a transformer or a switchgear, the characteristic information of multiple partial discharge signals may include:

Energy characteristics: For AE signals, the energy characteristics of the signal can be calculated, such as peak energy, effective energy, etc. For UHF signals, characteristics such as the instantaneous power of the signal can be calculated. These features can reflect the strength and magnitude of the PD signal.

Spectrum features: Spectrum analysis can be performed on AE and UHF signals, and features such as frequency and amplitude of the signals can be extracted. For AE signals, features such as the main frequency and harmonics of the signal can also be calculated. These features can reflect the frequency distribution of PD signals.

Waveform characteristics: It can analyze the waveform of AE and UHF signals, and extract the characteristics of the signal such as rise time, fall time, peak time, and half-peak time. These characteristics can reflect the waveform characteristics of the partial discharge signal.

Statistical features: AE and UHF signals can be statistically analyzed to extract signal mean, variance, skewness, kurtosis and other features. These features can reflect the statistical characteristics of PD signals.

Time features: Time series analysis can be performed on AE and UHF signals, and the time domain features of the signals can be extracted, such as autocorrelation coefficients, cross-correlation coefficients, etc. These features can reflect the timing relationship of PD signals.

The establishment process of the Bayesian probability model includes:

Collect prior knowledge and actual measurement data related to each fault type and characteristics, where prior knowledge refers to prior knowledge and empirical knowledge about PD fault types, characteristics, sensor response, etc. It can come from on-site measurements, experiments, etc. Build a Bayesian probability model based on collected prior knowledge and training data. In this embodiment, prior probability, conditional probability distribution, etc. are set in the Bayesian probability model. The prior probability represents the expected occurrence probability of each fault type in the overall fault, and the conditional probability distribution represents the distribution of features when a certain fault type is given.

Then calculate the posterior probability, according to the Bayesian formula, calculate the posterior probability of each fault type, that is, the probability of occurrence of each fault type given the observed characteristic information.

A belief function is established based on the probability of each fault type, specifically, the calculated posterior probability is standardized to ensure that the sum of the probabilities of each fault type is equal to 1. Normalization is done by dividing by the sum of probabilities;

Converting the trust function into DS evidence, and combining the DS evidence to obtain the confidence degree of each fault type;

In this embodiment, it is first necessary to specify the hypothesis space, that is, all possible states of the object to be detected. In PD detection, the assumed space is the presence or absence of PD, the type of discharge, etc.

The evidence space is then defined, which includes all possible evidence or sensor measurements. In PD detection, the evidence space can be PD signatures measured by different sensors.

Finally, the DS evidence is calculated according to the trust function: the posterior probability of each hypothesis is calculated through the Bayesian formula, and then the posterior probability is converted into DS evidence.

The specific conversion process and confidence determination process include:

(1) Define the hypothesis space: As in the calculation of the posterior probability, it is first necessary to clarify the hypothesis space, that is, all possible states of the object to be detected.

(2) Calculate the amount of evidence: According to the Bayesian formula, the posterior probability of each hypothesis can be calculated. The posterior probability of each hypothesis is converted into the amount of evidence for the corresponding hypothesis and the non-corresponding hypothesis. The specific calculation method is as follows:

(3) For each hypothesis h in the hypothesis space, calculate its evidence m(h)=P(h)/[1-P(h)]

For a non-hypothesis h' in the hypothesis space, calculate its evidence m(h')=1-m(h)

where P(h) is the posterior probability of hypothesis h.

(4) Combining DS evidence: According to the combination rules in DS theory, all the evidence can be combined into one DS evidence. Specifically, Dempster composition rules can be used to synthesize all the evidence volumes. Assuming that all evidence quantities are m ₁ , m ₂ ,...,m _n , the synthesized DS evidence is:

m(A)=1-∑m(B), for all B≠A

m(Ω)=1-∑m(A), for all

Among them, A represents a hypothesis in the hypothesis space, and Ω represents the hypothesis space.

(5) Calculation of confidence and uncertainty: According to DS evidence, the confidence and uncertainty of assumptions can be calculated. Specifically, it can be calculated using the following formula:

Confidence: Bel(h)=∑m(A)

Uncertainty: Pl(h)＝1-Bel(h)-m(Ω)

Among them, Bel(h) represents the confidence of hypothesis h, and Pl(h) represents the uncertainty of hypothesis h.

The type of the partial discharge signal source is determined based on the confidence level of each fault type.

In this embodiment, the determination of the type of partial discharge signal source based on the confidence of each fault type can be determined through the deterministic synthesis method to obtain the final PD type judgment result, and can also be sorted according to the confidence to confirm the highest confidence type.

A partial discharge detection method of the present application, by acquiring partial discharge signals from various sensors, wherein the various sensors are set at different positions of electrical equipment that generate partial discharge; based on the arrival time difference of multiple partial discharge signals The discharge signal source is positioned to obtain the position of the partial discharge signal source; and the type of the partial discharge signal source is determined based on the feature information of multiple partial discharge signals. This application locates the partial discharge signal source by fusing the arrival time difference of multiple sensor signals, and determines the type of local signal source by fusing the characteristic information of multiple sensor signals, so that the advantages of multiple sensors can be used to monitor partial discharge signal, the monitoring effect is better.

Fig. 3 is a structural diagram of a partial discharge detection device shown in an exemplary embodiment of the present application. As shown in Fig. 3, the present application also provides a partial discharge detection device, including:

An acquisition module, configured to acquire partial discharge signals from various sensors, wherein the various sensors are set at different positions of the electrical equipment that generates partial discharge;

The detection module is used for locating the partial discharge signal source based on the arrival time difference of the plurality of partial discharge signals, and obtaining the position of the partial discharge signal source; and determining the type of the partial discharge signal source based on the feature information of the plurality of partial discharge signals.

Fig. 4 is the structural diagram of the partial discharge detection device shown in another exemplary embodiment of the present application, as shown in Fig. 4, the partial discharge detection device is composed of sensor unit (AE, UHF, HFCT), preprocessing module (comprising analog-to-digital conversion , filter amplification, sparse decomposition, feature extraction), data analysis module (including noise reduction, pattern recognition, intelligent information fusion), judgment and application module (to realize fault detection, fault location, intelligent operation and maintenance). When users need to detect partial discharge signals in power equipment such as transformers, switch cabinets, and power cables, they only need to arrange sensors in advance and connect them to the transmission network. When the terminal receives the transmitted partial discharge signals, it analyzes the signals for data. According to the address bit information, it is first judged which electrical equipment the PD source comes from, and on this basis, the specific location and PD type are judged through intelligent information fusion.

A partial discharge detection device of the present application obtains partial discharge signals from various sensors, wherein the various sensors are set at different positions of electrical equipment that generate partial discharge; The discharge signal source is positioned to obtain the position of the partial discharge signal source; and the type of the partial discharge signal source is determined based on the feature information of multiple partial discharge signals. This application locates the partial discharge signal source by fusing the arrival time difference of multiple sensor signals, and determines the type of local signal source by fusing the characteristic information of multiple sensor signals, so that the advantages of multiple sensors can be used to monitor partial discharge signal, the monitoring effect is better.

It should be noted that the partial discharge detection device provided by the above embodiment and the partial discharge detection method provided by the above embodiment belong to the same idea, and the specific way of performing operations of each module and unit has been carried out in the method embodiment Detailed description will not be repeated here. In practical application of the partial discharge detection method provided by the above-mentioned embodiment, the above-mentioned function allocation can be completed by different functional modules according to the needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all the above-described Or some functions, which are not limited here.

The embodiment of the present application also provides an electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are processed by the one or more When the device is executed, the electronic device is made to implement the partial discharge detection method provided in each of the foregoing embodiments.

Fig. 5 shows a schematic structural diagram of a computer system suitable for implementing the electronic device of the embodiment of the present application. It should be noted that the computer system 500 of the electronic device shown in FIG. 5 is only an example, and should not limit the functions and scope of use of this embodiment of the present application.

As shown in FIG. 5, a computer system 500 includes a central processing unit (Central Processing Unit, CPU) 501, which can be stored in a program in a read-only memory (Read-Only Memory, ROM) 502 or loaded from a storage part 508 to a random Various appropriate actions and processes are performed by accessing programs in the memory (Random Access Memory, RAM) 503, for example, performing the methods described in the above-mentioned embodiments. In RAM 505, various programs and data necessary for system operation are also stored. The CPU 501 , ROM 502 , and RAM 503 are connected to each other through a bus 504 . An input/output (Input/Output, I/O) interface 505 is also connected to the bus 504 .

The following components are connected to the I/O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (Cathode Ray Tube, CRT), a liquid crystal display (Liquid Crystal Display, LCD), etc., and a speaker ; a storage section 508 including a hard disk or the like; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I/O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 510 as necessary so that a computer program read therefrom is installed into the storage section 508 as necessary.

In particular, according to the embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 509 and/or installed from removable media 511 . When this computer program is executed by a central processing unit (CPU) 501, various functions defined in the system of the present application are performed.

It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash memory, optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any suitable The combination. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program thereon. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . A computer program embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Wherein, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or part of the code includes one or more executable instruction. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block in the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a A combination of dedicated hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or by hardware, and the described units may also be set in a processor. Wherein, the names of these units do not constitute a limitation of the unit itself under certain circumstances.

Another aspect of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is made to execute the partial discharge detection method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being assembled into the electronic device.

Another aspect of the present application also provides a computer program product or computer program, the computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the partial discharge detection method provided in each of the foregoing embodiments.

The above-mentioned embodiments are only illustrative to illustrate the principles and effects of the present application, but not to limit the present application. Any person familiar with the technology can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical ideas disclosed in this application shall still be covered by the claims of this application.

Claims (10)

1. A partial discharge detection method, comprising:

acquiring partial discharge signals from a plurality of sensors, wherein the plurality of sensors are arranged at different positions of electrical equipment generating partial discharge;

positioning the partial discharge signal sources based on the arrival time differences of the partial discharge signals to obtain the positions of the partial discharge signal sources; and determining the type of the partial discharge signal source based on the characteristic information of the plurality of partial discharge signals.

2. The partial discharge detection method according to claim 1, wherein the electrical device is a cable, the plurality of sensors includes a plurality of HFCT sensors and a plurality of UHF sensors, wherein locating the partial discharge signal source based on arrival time differences of the plurality of partial discharge signals includes:

determining a time difference in which the plurality of HFCT sensors receive corresponding partial discharge signals;

determining distances of the plurality of HFCT sensors from the partial discharge signal source based on time differences in which the plurality of HFCT sensors receive corresponding partial discharge signals; determining a position interval of the partial discharge signal source based on the distances between the plurality of HFCT sensors and the partial discharge signal source;

Determining a time difference of receiving corresponding partial discharge signals by a plurality of UHF sensors in the position interval;

and determining the distances between the plurality of UHF sensors in the position interval and the partial discharge signal source based on the time difference of receiving the corresponding partial discharge signals by the plurality of UHF sensors in the position interval, and determining the position of the partial discharge signal source based on the distances between the plurality of UHF sensors in the position interval and the partial discharge signal source.

3. The partial discharge detection method according to claim 2, wherein the method for determining the position of the partial discharge signal source based on the distances of the plurality of sensors from the partial discharge signal source comprises:

establishing a plurality of circles by taking the distance between each HFCT sensor or UHF sensor and the partial discharge signal source as a radius and taking the corresponding sensor as a circle center;

and determining intersection points of the circles, and taking the intersection points as the positions of the partial discharge signal sources or the position intervals of the partial discharge signal sources.

4. The partial discharge detection method according to claim 2, wherein determining the time differences in which the plurality of UHF sensors of the location interval receive the corresponding partial discharge signals comprises:

Extracting characteristic parameters of partial discharge signals of a plurality of UHF sensors in the position interval;

normalizing the characteristic parameters of partial discharge signals of a plurality of UHF sensors in the position interval;

establishing a cross-correlation function of the partial discharge signals based on the normalized characteristic parameters;

and determining peak positions of the partial discharge signals based on the cross correlation function, and determining time differences of the partial discharge signals received by the UHF sensors based on the peak positions of the partial discharge signals.

5. The partial discharge detection method according to claim 1, wherein the electrical device is a switch cabinet or a transformer, the plurality of sensors includes a UHF sensor and an AE sensor, wherein positioning the partial discharge signal source based on the arrival time differences of the plurality of partial discharge signals includes:

determining a time difference of partial discharge signals received by the UHF sensor and the AE sensor;

determining the distances between the UHF sensor and the AE sensor and the partial discharge signal source based on the time difference that the UHF sensor and the AE sensor receive the partial discharge signals;

inputting the time of receiving partial discharge signals by the UHF sensor and the AE sensor, the distance between the UHF sensor and a partial discharge signal source and the distance between the AE sensor and the partial discharge signal source into a pre-established neural network model to obtain the relative positions of the UHF sensor, the AE sensor and the partial discharge signal source;

And determining the absolute position of the partial discharge signal source based on the coordinate information of the UHF sensor, the coordinate information of the AE sensor and the relative position.

6. The partial discharge detection method of claim 5, further comprising establishing a neural network model by:

acquiring training data and labels of the training data, wherein the time difference of receiving partial discharge signals by a plurality of sensors of the training data and the distance between the plurality of sensors and a partial discharge signal source are the relative positions of the sensors and the partial discharge signal source;

and training the BP neural network based on the training data and the label of the training data to obtain a neural network model.

7. The partial discharge detection method according to claim 1, wherein determining the type of the partial discharge signal source based on the characteristic information of the plurality of partial discharge signals includes:

determining multiple fault types of the partial discharge signal source and probability of each fault type based on the characteristic information of the multiple partial discharge signals and a pre-established Bayesian probability model, wherein the Bayesian probability model is established based on the characteristic information of the multiple fault types and is used for representing expected occurrence probability of each fault type in the overall fault and the characteristic information corresponding to each fault type;

Establishing a trust function based on the probability of each fault type;

converting the trust function into DS evidence, and combining the DS evidence to obtain the confidence degree of each fault type;

and judging the type of the partial discharge signal source based on the confidence of each fault type.

8. A partial discharge detection device, characterized by comprising:

an acquisition module for acquiring partial discharge signals from a plurality of sensors, wherein the plurality of sensors are arranged at different positions of an electrical device generating partial discharge;

the detection module is used for positioning the local discharge signal sources based on the arrival time differences of the partial discharge signals to obtain the positions of the local discharge signal sources; and determining the type of the partial discharge signal source based on the characteristic information of the plurality of partial discharge signals.

9. An electronic device, the electronic device comprising:

one or more processors;

storage means for storing one or more programs which, when executed by the one or more processors, cause the electronic device to implement the partial discharge detection method of any one of claims 1 to 7.

10. A computer-readable storage medium, having stored thereon a computer program which, when executed by a processor of a computer, causes the computer to perform the partial discharge detection method of any one of claims 1 to 7.