CN118568647B - Industrial equipment fault intelligent detection method and system based on digital twin - Google Patents
Industrial equipment fault intelligent detection method and system based on digital twin Download PDFInfo
- Publication number
- CN118568647B CN118568647B CN202411046466.5A CN202411046466A CN118568647B CN 118568647 B CN118568647 B CN 118568647B CN 202411046466 A CN202411046466 A CN 202411046466A CN 118568647 B CN118568647 B CN 118568647B
- Authority
- CN
- China
- Prior art keywords
- workflow
- tested
- vibration
- cluster
- difference
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 claims abstract description 49
- 230000008859 change Effects 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 9
- 239000013598 vector Substances 0.000 claims description 52
- 230000001052 transient effect Effects 0.000 claims description 44
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 230000000694 effects Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 6
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 5
- 230000003247 decreasing effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The application relates to the technical field of data processing, in particular to an intelligent detection method and system for industrial equipment faults based on digital twinning, wherein the method comprises the following steps: obtaining vibration data, noise data and current data of each time in each historical workflow and workflow to be tested of a manipulator on industrial equipment; determining a vibration stability coefficient of a work flow to be tested; determining a vibration deviation coefficient of the workflow to be tested according to the time interval difference condition and the discrete degree in the change process of the vibration data and the current data of all moments of the workflow to be tested; determining equipment fault coefficients of the workflow to be tested according to the difference condition of noise data between the workflow to be tested and all historical workflows; and determining the fault confidence coefficient of the workflow to be tested, and carrying out fault detection on the manipulator in the industrial equipment. The application further analyzes the multidimensional data characteristics and improves the precision of mechanical arm fault detection in industrial equipment.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an intelligent detection method and system for industrial equipment faults based on digital twinning.
Background
Along with the rapid development of informatization technology, the level of intellectualization of industrial equipment is also continuously improved. However, as equipment is upgraded, the internal structure of the equipment becomes more and more complex, so that the difficulty in detecting equipment faults is gradually increased. The automatic tool changing device (tool magazine and manipulator) is one of key components of the numerical control machine tool, and the complex internal structure and the strict requirements of tool changing mean that if the manipulator fails, the tool changing will be directly failed, and even the machine tool and a workpiece to be processed may be damaged. Therefore, it is particularly important to perform real-time fault monitoring on the manipulator.
The digital twin technology can not only feed back the real running state of the manipulator in real time by constructing a virtual model completely corresponding to the physical entity, but also perform deep fault detection and analysis on the manipulator on the premise of not influencing the actual operation of the manipulator. However, even though the digital twin technology is used, the prior art still has a certain problem in performing fault detection on the manipulator. For example, although the state of the manipulator is monitored by using multidimensional data in the prior art, the characteristics of the multidimensional data and the nonlinear relation between the data are not deeply analyzed, so that the characteristic analysis is not deep enough in the processing of the manipulator which is a relatively complex industrial device, and the fault detection effect is not good.
Disclosure of Invention
In order to solve the technical problems, the intelligent detection method and the intelligent detection system for the industrial equipment faults based on digital twinning are provided to solve the existing problems.
The technical problem solving scheme of the application is to provide an intelligent detection method and system for industrial equipment faults based on digital twinning, and the method comprises the following steps:
in a first aspect, an embodiment of the present application provides an intelligent detection method for industrial equipment failure based on digital twinning, the method including the steps of:
Obtaining vibration data, noise data and current data of each time in each historical workflow and workflow to be tested of a manipulator on industrial equipment;
determining the vibration stability coefficient of the workflow to be tested according to the fluctuation difference conditions and the monotonic change trend of vibration data at different moments in the workflow to be tested;
Determining a vibration deviation coefficient of the workflow to be tested according to the time interval difference condition and the discrete degree in the change process of the vibration data and the current data of the workflow to be tested and by combining the vibration stability coefficient;
According to the difference condition of noise data between the workflow to be tested and all the historical workflows, and combining the vibration deviation coefficient, determining the equipment fault coefficient of the workflow to be tested;
And determining the fault confidence coefficient of the workflow to be tested according to the abnormal degree of the equipment fault coefficient in all the historical workflows, and carrying out fault detection on the manipulator in the industrial equipment.
Preferably, the determining the vibration stability coefficient of the workflow to be tested includes:
extracting subsequences from vibration data at all moments in a work flow to be detected by adopting a variable length subsequence clustering algorithm, and clustering the subsequences;
analyzing the discrete condition of each subsequence in each cluster in the workflow to be tested, and determining the discrete condition as the intra-cluster fluctuation index of each cluster in the workflow to be tested;
The cluster with the largest intra-cluster fluctuation index is marked as a vibration fluctuation cluster, and the cluster with the smallest intra-cluster fluctuation index is marked as a vibration stable cluster;
analyzing the change trend condition of elements in each subsequence in the vibration fluctuation cluster, and determining the monotone change difference of each subsequence in the vibration fluctuation cluster of the workflow to be tested;
the ratio of the number of the monotone change differences of all the subsequences in the vibration fluctuation cluster to the number of the subsequences is 0 is recorded as a first ratio of the vibration fluctuation cluster;
and taking the ratio of the first ratio of the vibration fluctuation cluster to the intra-cluster fluctuation index of the vibration stable cluster as the vibration stability coefficient of the work flow to be tested.
Preferably, the determining the intra-cluster fluctuation index of each cluster in the workflow to be tested includes:
Taking the sum of the discrete degree and the average value of each subsequence in each cluster in the workflow to be tested as the vibration change degree of each subsequence in each cluster in the workflow to be tested;
And determining the discrete degree of the vibration variation degree of all the subsequences in each cluster in the workflow to be tested as the intra-cluster fluctuation index of each cluster in the workflow to be tested.
Preferably, the determining the monotone variation difference of each sub-sequence in the vibration fluctuation cluster of the workflow to be tested includes:
performing first-order difference on each subsequence in the vibration fluctuation cluster of the workflow to be tested to obtain each difference subsequence;
assigning an element greater than or equal to 0 in the differential subsequence to be 1; elements less than 0 are assigned a value of-1;
The absolute value of the sum of all the elements after assignment in the differential subsequence is recorded as a first absolute value of each subsequence;
And taking the difference between the first absolute value and the length of the differential subsequence as the monotone change difference of each subsequence in the vibration fluctuation cluster of the workflow to be tested.
Preferably, the determining the vibration deviation coefficient of the workflow to be tested includes:
Aiming at current data at all moments in the working flow to be detected, obtaining a current fluctuation cluster and a current stable cluster of the working flow to be detected by adopting the same method as that of the vibration fluctuation cluster and the vibration stable cluster;
Selecting acquisition moments corresponding to maximum values of elements in each subsequence of the vibration fluctuation cluster, and sequencing according to a time sequence to form a vibration transient sequence; aiming at each subsequence of the current fluctuation cluster, a current transient sequence is obtained by adopting the same method as a vibration transient sequence;
Analyzing the difference condition between the vibration transient sequence and the current transient sequence, and determining the difference condition as the transient deviation coefficient of the workflow to be tested;
And taking the ratio of the instantaneous deviation coefficient to the vibration stability coefficient as the vibration deviation coefficient of the work flow to be tested.
Preferably, the determining as the instantaneous deviation coefficient of the workflow to be tested includes:
recording the difference between each acquisition time of the vibration transient sequence and the acquisition time of the same position in the current transient sequence as a delay effect value;
taking the discrete degree of all the delay effect values as a time difference index of the workflow to be tested;
Taking the difference between the length of the vibration transient sequence and the length of the current transient sequence as the transient frequency difference of the work flow to be tested;
And counting the number of the delay effect values which are smaller than or equal to 0, and fusing the number, the time difference index and the instantaneous frequency difference to determine the instantaneous deviation coefficient of the workflow to be detected.
Preferably, the determining the equipment failure coefficient of the workflow to be tested includes:
dividing noise data at all moments in a workflow to be tested into a plurality of noise subsequences;
calculating the variance, the mean value and the subsequence length of each noise subsequence in the workflow to be tested;
the variance, the mean value and the sequence length of all the noise subsequences are respectively formed into a noise variance vector, a noise mean value vector and a noise length vector of the workflow to be tested;
Aiming at the noise data at all moments in each historical workflow, the noise variance vector, the noise mean vector and the noise length vector of each historical workflow are obtained by adopting the same method as the noise variance vector, the noise mean vector and the noise length vector of the workflow to be tested;
performing cluster analysis on all the noise variance vectors, all the noise mean vectors and all the noise length vectors of the workflow to be tested and all the historical workflows respectively to obtain a plurality of variance clusters, a plurality of mean clusters and a plurality of length clusters respectively;
Analyzing the quantity difference between different clusters and the difference condition between noise data of the workflow to be tested and the cluster aggregation center, and determining the noise deviation coefficient of the workflow to be tested;
And fusing the vibration deviation coefficient and the noise deviation coefficient to determine the vibration deviation coefficient and the noise deviation coefficient as equipment fault coefficients of the workflow to be tested.
Preferably, the determining the noise deviation coefficient of the workflow to be tested includes:
the mean value of the differences between the noise variance vector of the workflow to be tested and the clustering center vector of each variance cluster is recorded as a first difference;
Aiming at the noise mean value vector and the noise length vector of the workflow to be tested, a second difference and a third difference of the workflow to be tested are obtained by adopting the same method as the first difference;
counting the numbers of the variance clusters, the mean clusters and the length clusters respectively, and recording the sum of differences between any two numbers as a clustering difference;
calculating the product of the average value of the number of variance clusters, the number of mean clusters and the number of length clusters and the clustering difference, and recording the product as a first product;
and fusing the first product with the average value of the first difference, the second difference and the third difference, and determining the noise deviation coefficient of the workflow to be tested.
Preferably, the determining the fault confidence of the workflow to be tested, performing fault detection on the manipulator in the industrial equipment, includes:
Aiming at vibration data, noise data and current data at all moments in each historical workflow, calculating the equipment fault coefficients of each historical workflow by adopting a method with the same equipment fault coefficients of the workflow to be tested;
Adopting an anomaly detection algorithm to the equipment fault coefficients of the to-be-detected workflow and all the historical workflows to obtain anomaly values corresponding to all the equipment fault coefficients;
if the abnormal value corresponding to the equipment fault coefficient of the workflow to be tested is the unique maximum value, the fault weight factor is a first preset value, otherwise, the fault weight factor is a second preset value, wherein the first preset value is smaller than the second preset value;
Normalizing the abnormal values corresponding to all the equipment fault coefficients, and taking the ratio of the normalized result of the abnormal value corresponding to the equipment fault coefficient of the workflow to be tested to the fault weight factor as the fault confidence coefficient of the workflow to be tested;
If the fault confidence coefficient is larger than or equal to a preset fault threshold value, the manipulator in the industrial equipment fails, otherwise, the manipulator in the industrial equipment operates normally.
In a second aspect, an embodiment of the present application further provides a digital twin-based industrial equipment fault intelligent detection system, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor executes the computer program to implement the steps of any one of the above digital twin-based industrial equipment fault intelligent detection methods.
The application has at least the following beneficial effects:
According to the fluctuation difference conditions and monotone change trends of vibration data at different moments in the working flow to be tested, the vibration stability coefficient of the working flow to be tested is determined, and the method has the advantages that the instantaneous vibration fluctuation state of the manipulator in the working process is considered to be distinguished from the vibration stability state, so that the fluctuation conditions in different states are analyzed, the vibration stability condition of the manipulator is reflected, and the possibility of the manipulator to be out of order is further described; according to the time interval difference and the discrete degree in the change process of the vibration data and the current data of all moments of the workflow to be tested, the vibration stability coefficient is combined to determine the vibration deviation coefficient of the workflow to be tested, and the method has the advantages that the fluctuation variation difference of the current data of the instantaneous change and the vibration data of the instantaneous change is considered, so that the possibility of the mechanical arm fault is evaluated; according to the difference condition of noise data between the working flow to be tested and all the historical working flows, determining the noise deviation coefficient of the working flow to be tested, and combining the vibration deviation coefficient to determine the equipment fault coefficient of the working flow to be tested; according to the abnormal degree of the equipment fault coefficient in all the historical working flows, the fault confidence coefficient of the working flow to be detected is determined, and the fault detection is carried out on the manipulator in the industrial equipment.
Drawings
The intelligent detection method for the faults of the industrial equipment based on digital twin is further described in detail below with reference to the accompanying drawings.
FIG. 1 is a flow chart of steps of an intelligent detection method for industrial equipment faults based on digital twinning;
FIG. 2 is a flow chart of steps of a method for obtaining vibration stability coefficients of a workflow to be tested according to the present application;
FIG. 3 is a flow chart of steps of a method for obtaining vibration deviation coefficients of a workflow to be tested according to the present application;
Fig. 4 is a schematic diagram of noise data of a workflow to be tested according to the present application.
Detailed Description
In order to make the purposes, technical schemes and advantages of the application more clear, the intelligent detection method and system for the faults of the industrial equipment based on digital twinning, which are provided by the application, are further described in detail below with reference to the accompanying drawings and the implementation examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
Referring to fig. 1, a flowchart of steps of a digital twin-based intelligent detection method for industrial equipment faults is shown, which includes the following steps:
Step 1, vibration data, noise data and current data of each time in each historical workflow and workflow to be tested of a manipulator of industrial equipment are obtained.
Through carrying out fault detection to the manipulator of industrial equipment, the working process of manipulator tool changing can divide into "grab", "pull", "change", "plug" four flows, with the manipulator from grabbing beginning, to the flow of tool changing end record as a work flow, gather the operation data of current manipulator work, the acquisition process is: placing an acceleration sensor at a mechanical hand pushing shaft to acquire vibration data of the mechanical hand; according to the requirement of noise monitoring, a noise detector is placed at a position d meters away from the manipulator to acquire noise data; the method comprises the steps of obtaining current of each joint of a manipulator through a servo system in each joint of the manipulator, taking the average value of the current of all joints at the same moment as current data of the manipulator, recording the current working flow as a working flow to be tested, collecting vibration data, noise data and current data of all moments of the working flow to be tested at a time interval of T, collecting historical operation data of the historical working flow of the manipulator for T times from a database, including vibration data, noise data and current data of all moments of the historical working flow for T times, and carrying out normalization processing on all obtained data.
Preferably, in this embodiment, a noise detector is placed 1 meter away from the manipulator to obtain noise data, the collection time interval is 0.01s, and vibration data, noise data and current data of all moments of the 100 times of historical workflow are collected.
So far, vibration data, noise data and current data of each time in each historical workflow and workflow to be tested of the manipulator of the industrial equipment are obtained.
And step 2, determining the vibration stability coefficient of the work flow to be tested according to the fluctuation difference conditions and the monotone change trend of the vibration data at different moments in the work flow to be tested.
Through analysis of the manipulator work flow, the vibration characteristics of the manipulator are found to have transience at certain moments, and the vibration data of the manipulator are instantaneously increased at the moments of grabbing, pulling, replacing and inserting to reach a very high amplitude value, and then the vibration data is rapidly decreased; and outside the instant moment, the vibration data of the manipulator is stable and the fluctuation is small. There are two obvious wave trends in the vibration data at all times, namely a rapid wave trend and a steady wave trend.
Based on the analysis, the fluctuation trend of the vibration data is analyzed, and the rapid fluctuation trend is distinguished from the stable fluctuation trend, specifically:
Extracting subsequences from vibration data at all moments in a work flow to be detected by adopting a Variable-length subsequence clustering (Variable-Length Subsequence Clustering) algorithm, and clustering the subsequences;
Preferably, in this embodiment, the minimum length of the subsequence is set to 5, the maximum length of the subsequence is set to 30, and the number of clusters is set to 2 in the variable-length subsequence clustering algorithm, which is a known technique and will not be described herein.
Taking the sum of the discrete degree and the mean value of each subsequence in each cluster in the workflow to be tested as the vibration change degree of each subsequence in each cluster in the workflow to be tested;
Determining the discrete degree of the vibration variation degree of all subsequences in each cluster in the workflow to be tested as the intra-cluster fluctuation index of each cluster in the workflow to be tested;
The cluster with the largest intra-cluster fluctuation index is marked as a vibration fluctuation cluster, and the cluster with the smallest intra-cluster fluctuation index is marked as a vibration stable cluster;
preferably, in this embodiment, the degree of dispersion is measured by variance, and as other embodiments, the practitioner may use other methods in the prior art, for example, standard deviation, coefficient of variation, etc., which is not particularly limited in this embodiment.
It should be noted that, since the peak vibration data of the transient state is significantly higher than the vibration data in the steady state, and the plurality of transient peak vibration data are not consistent and show decreasing trend, the fluctuation difference between each sub-sequence corresponding to the transient moment and each sub-sequence corresponding to the steady state is significantly increased, so that the larger the intra-cluster fluctuation index is, the more likely the corresponding transient state in the cluster is to rapidly fluctuate.
Further, if the manipulator does not fail, the vibration data fluctuation degree of each sub-sequence in the vibration stable cluster is more consistent, and each sub-sequence in the vibration fluctuation cluster has a decreasing trend. If the mechanical arm has fault behaviors, and if vibration data caused by faults are clustered into vibration stable clusters in whole or in part, the fluctuation degree of the data of each sub-sequence in the vibration stable clusters is not consistent any more, the fluctuation degree difference of each sub-sequence is larger, and therefore the intra-cluster fluctuation index of the vibration stable clusters is larger; if vibration data caused by faults are clustered into vibration fluctuation clusters in whole or in part, the descending degree of each subsequence in the vibration fluctuation clusters is not consistent, so that monotonic change difference is constructed by analyzing the descending degree of the subsequence in the vibration fluctuation clusters, specifically:
performing first-order difference on each subsequence in the vibration fluctuation cluster of the workflow to be tested to obtain each difference subsequence;
assigning an element greater than or equal to 0 in the differential subsequence to be 1; elements less than 0 are assigned a value of-1;
The absolute value of the sum of all the elements after assignment in the differential subsequence is recorded as a first absolute value of each subsequence;
Taking the difference between the first absolute value and the length of the differential subsequence as the monotone change difference of each subsequence in the vibration fluctuation cluster of the workflow to be tested;
Preferably, in this embodiment, the absolute value of the difference between the first absolute value and the length of the differential sub-sequence is used as the monotonic variation difference of each sub-sequence in the vibration fluctuation cluster of the workflow to be tested.
If the monotonous variation difference is 0, the corresponding subsequence is monotonically described; the larger the monotonous change difference is, the worse the monotonous degree of the corresponding sub-sequence is.
Further, based on the fluctuation index in the vibration stable cluster and the monotonic variation difference of each subsequence in the vibration fluctuation cluster, the vibration stability coefficient of the work flow to be tested is determined so as to reflect the vibration stability condition of the manipulator in the current working process, and the method specifically comprises the following steps:
the ratio of the number of the monotone change differences of all the subsequences in the vibration fluctuation cluster to the number of the subsequences in the vibration fluctuation cluster is 0 is recorded as a first ratio of the vibration fluctuation cluster;
Taking the ratio of the first ratio of the vibration fluctuation cluster to the intra-cluster fluctuation index of the vibration stable cluster as a vibration stability coefficient of the work flow to be tested;
Further, a step flowchart of the method for obtaining the vibration stability coefficient of the workflow to be tested provided in the embodiment of the present application is shown in fig. 2.
If the manipulator does not fail, the data fluctuation degree of each subsequence in the vibration stable cluster is more consistent, and the intra-cluster fluctuation index is smaller; meanwhile, all subsequences in the vibration fluctuation cluster have a strictly decreasing trend, so that the monotone difference of all subsequences is 0, the first ratio of the vibration fluctuation cluster reaches the maximum value of 1, and the vibration stability coefficient is larger. If a fault occurs, no matter which cluster the vibration data caused by the fault are clustered into, the difference of the data trend can be caused, the intra-cluster fluctuation index of the vibration stable cluster can be caused to be larger, the first ratio of the vibration fluctuation cluster is smaller, the vibration stability coefficient is smaller, and the smaller the vibration stability coefficient is, the greater the possibility of the mechanical arm in the industrial equipment to be broken down is indicated.
So far, the vibration stability coefficient of the work flow to be tested is obtained.
And step 3, determining the vibration deviation coefficient of the workflow to be tested according to the time interval difference condition and the discrete degree in the change process of the vibration data and the current data of all moments of the workflow to be tested and combining the vibration stability coefficient.
In the manipulator's workflow, when the manipulator performs a task, such as a "grab" operation, the servo motor is required to generate enough torque to overcome resistance or move the load, at which time the current in the servo motor may significantly surge, then rapidly decline and eventually fluctuate smoothly. When the current is instantaneously increased, the manipulator starts to perform the next operation, which causes the vibration data to also be instantaneously increased in a short time, so that the instant when the current data is increased and the instant when the vibration data is increased have a certain time delay. Therefore, the time delay condition of the current data and the vibration data is analyzed, and the instantaneous deviation coefficient is determined according to the consistent degree of delay time corresponding to the current increase and the vibration increase so as to reflect the possibility of the fault of the manipulator, specifically:
Aiming at current data at all moments in the working flow to be detected, obtaining a current fluctuation cluster and a current stable cluster of the working flow to be detected by adopting the same method as that of the vibration fluctuation cluster and the vibration stable cluster;
Selecting acquisition moments corresponding to maximum values of elements in each subsequence of the vibration fluctuation cluster, and sequencing according to a time sequence to form a vibration transient sequence; aiming at each subsequence of the current fluctuation cluster, a current transient sequence is obtained by adopting the same method as a vibration transient sequence;
Taking the difference value between each acquisition time of the vibration transient sequence and the acquisition time of the same position in the current transient sequence as a delay effect value of each serial number;
in the present embodiment, it is assumed that the maximum values of the elements in each sub-sequence of the vibration fluctuation cluster are respectively The corresponding acquisition time is respectivelyConstitutes a vibration transient sequenceWherein, the method comprises the steps of, wherein,，，，The maximum values of the elements in each subsequence of the same current fluctuation cluster are respectivelyThe corresponding acquisition time is respectivelyComposing a current transient sequenceWherein, the method comprises the steps of, wherein,，，，Will be，，，As a delayed effect value.
If the vibration transient sequence and the current transient sequence are not identical in length, the end of the sequence having a short length is filled with a 0 value.
Taking the discrete degree of all the delay effect values as a time difference index of the workflow to be tested;
Taking the difference between the length of the vibration transient sequence and the length of the current transient sequence as the transient frequency difference of the work flow to be tested;
Counting the number of the delay effect values which are less than or equal to 0, and fusing the number, the time difference index and the instantaneous frequency difference to determine an instantaneous deviation coefficient of the workflow to be detected;
It is to be understood that the fusion specific relationship may be an addition relationship, a multiplication relationship, or the like, and the specific relationship is determined according to an actual scene, which is not particularly limited in this embodiment.
Preferably, in this embodiment, the variance of all the delay effect values is used as a time difference index of the workflow to be tested, and the absolute value of the difference between the length of the vibration transient sequence and the length of the current transient sequence is used as the transient frequency difference of the workflow to be tested; and secondly, taking the sum of the number, the time difference index and the instantaneous frequency difference as an instantaneous deviation coefficient of the workflow to be tested.
It should be noted that, if the manipulator does not fail, the vibration is normal vibration in the workflow, and before the vibration, the current is significantly increased, and at the same time, the time interval between each current data increase and the vibration data increase is relatively consistent, which means that the possibility that the manipulator is still in a normal running state is greater. Therefore, if the difference of the instantaneous times is smaller, the current data is increased and the frequency of the vibration data is increased more consistent; the smaller the time difference index, the more consistent the time interval between each current transient increase and vibration transient increase; if the delay effect value is less than or equal to 0, indicating that the instantaneous increasing moment of the vibration data is after the instantaneous increasing moment of the current; the smaller the resulting instantaneous deviation factor, the less likely the manipulator will fail. If the instantaneous frequency difference is larger, the time difference index is larger, which means that the number of the delay effect values is smaller than or equal to 0 is larger, and the characteristic change difference between the vibration data and the current data of the manipulator is larger, so that the probability of the manipulator to be broken down is larger.
Further, based on the vibration stability coefficient and the instantaneous deviation coefficient, analyzing the deviation degree of the vibration characteristic change of the manipulator in the industrial equipment, and determining the vibration deviation coefficient, specifically:
taking the ratio of the instantaneous deviation coefficient to the vibration stability coefficient as the vibration deviation coefficient of the work flow to be tested;
the smaller the vibration stability coefficient is, the greater the transient deviation coefficient is, the greater the possibility of changing the vibration characteristics of the manipulator is, and the greater the vibration deviation coefficient is, the greater the possibility of the manipulator being out of order is.
Further, a flowchart of steps of the method for obtaining the vibration deviation coefficient of the workflow to be tested according to the embodiment of the present application is shown in fig. 3.
Thus, the vibration deviation coefficient of the work flow to be measured is obtained.
And step 4, determining a noise deviation coefficient of the workflow to be tested according to the difference condition of noise data between the workflow to be tested and all the historical workflows, and determining an equipment fault coefficient of the workflow to be tested by combining the vibration deviation coefficient.
By analyzing the noise characteristics of the manipulator, it is found that the noise data of the manipulator is usually changed in a stepwise manner in different operation stages of the manipulator, and a relatively obvious difference is shown in the noise data of all times of the whole manipulator, but the noise data is relatively stable in different stages, and the noise data is shown in fig. 4, wherein the abscissa is time, and the ordinate is noise data.
Based on the analysis, the noise data of different stages are divided to analyze the noise difference, specifically:
dividing noise data at all moments in a workflow to be tested into a plurality of noise subsequences;
Preferably, in this embodiment, a BG (Bernaola Galvan) sequence division algorithm is used for division, where the BG sequence division algorithm is a known technology and is not described herein, and as other embodiments, an operator may use other methods in the prior art, for example, a mutation point detection method for division, which is not limited in particular in this embodiment.
Calculating the variance, the mean value and the subsequence length of each noise subsequence in the workflow to be tested;
the variance, the mean value and the sequence length of all the noise subsequences are respectively formed into a noise variance vector, a noise mean value vector and a noise length vector of the workflow to be tested;
Aiming at the noise data at all moments in each historical workflow, the noise variance vector, the noise mean vector and the noise length vector of each historical workflow are obtained by adopting the same method as the noise variance vector, the noise mean vector and the noise length vector of the workflow to be tested;
performing cluster analysis on all the noise variance vectors, all the noise mean vectors and all the noise length vectors of the workflow to be tested and all the historical workflows respectively to obtain a plurality of variance clusters, a plurality of mean clusters and a plurality of length clusters respectively;
the mean value of the differences between the noise variance vector of the workflow to be tested and the clustering center vector of each variance cluster is recorded as a first difference;
Aiming at the noise mean value vector and the noise length vector of the workflow to be tested, a second difference and a third difference of the workflow to be tested are obtained by adopting the same method as the first difference;
Preferably, in this embodiment, a DPC density clustering algorithm is used to perform cluster analysis, and the number of clusters is obtained by a cross-validation method, where the DPC density clustering algorithm and the cross-validation method are known techniques and are not described herein again; and taking the mean value of Euclidean distances between the noise variance vector of the workflow to be tested and the clustering center vector of each variance cluster as a first difference of the workflow to be tested.
It may be understood that, in this embodiment, the DPC density clustering algorithm is used to perform cluster analysis, the euclidean distance is used to measure the difference between the two vectors, and as other embodiments, the implementer may use other methods in the prior art, for example, hierarchical clustering algorithm, DBSCAN clustering algorithm, and use the difference between the DTW distance and cosine similarity metric vectors to perform clustering, which is not limited in particular.
Further, the deviation condition of the noise data of the work flow to be detected relative to the noise data of the historical flow is analyzed, and a noise deviation coefficient is determined so as to further reflect the fault possibility of the manipulator, specifically:
counting the numbers of all the variance clusters, the mean clusters and the length clusters respectively, and recording the sum of differences between any two numbers as a clustering difference;
calculating the product of the average value of the number of variance clusters, the number of mean clusters and the number of length clusters and the clustering difference, and recording the product as a first product;
Fusing the first product with the average value of the first difference, the second difference and the third difference to determine a noise deviation coefficient of the workflow to be tested;
Preferably, in this embodiment, an absolute value of a difference between the number of variance clusters and the number of mean clusters is calculated and recorded as a first difference; calculating the absolute value of the difference value between the number of the variance clusters and the number of the length clusters, and recording the absolute value as a second difference value; calculating the absolute value of the difference value between the number of the length clusters and the number of the mean value clusters, marking the absolute value as a third difference value, and taking the mean value of the first difference value, the second difference value and the third difference value as a clustering difference value; and taking the sum of the first product and the average value of the first difference, the second difference and the third difference as a noise deviation coefficient of the workflow to be tested.
In this embodiment, the method for calculating the noise deviation coefficient of the workflow to be measured includes: wherein, the method comprises the steps of, wherein, For the noise figure of deviation of the workflow to be measured,For the number of all variance clusters,For the number of all mean clusters,For the number of clusters of all lengths,In the first difference of the first difference,In the case of the second difference,Is the third difference in whichFor the amount of the cluster difference,Is the first product.
It should be noted that, if the manipulator does not fail, the noise data collected in each historical workflow is more consistent, and the noise intensity under different stages, the noise duration of each stage and the noise fluctuation degree in each stage are more consistent, so after the clustering operation, the number of variance clusters, mean clusters and length clusters should be consistent, and the first difference, the second difference and the third difference are smaller, so the clustering difference should be 0, the second mean value is smaller, and the noise deviation coefficient is smaller. If a fault occurs, the difference between the noise data and the previous noise data is larger, the difference among the numbers of variance clusters, mean clusters and length clusters is caused, at the moment, the clustering difference becomes larger, and the first mean is larger; meanwhile, the second average value is larger because of the difference from the previous data, so that the larger the noise deviation coefficient is, the greater the possibility of the mechanical arm fault is.
Further, based on the vibration deviation coefficient and the noise deviation coefficient, analyzing the equipment fault coefficient of the workflow to be tested, specifically:
Fusing the vibration deviation coefficient and the noise deviation coefficient to determine an equipment fault coefficient of the workflow to be tested;
preferably, in this embodiment, the product of the vibration deviation coefficient and the noise deviation coefficient is used as the equipment failure coefficient of the workflow to be tested.
The larger the noise deviation coefficient of the workflow to be tested is, the larger the difference between the noise data in the current operation data and the past historical operation data is, and the larger the vibration deviation coefficient is, the larger the possibility that the vibration characteristic of the manipulator changes in the current operation data is, so that the larger the equipment failure coefficient is, the larger the possibility that the manipulator fails is.
So far, the equipment fault coefficient of the workflow to be tested is obtained.
And step 5, determining the fault confidence level of the work flow to be detected according to the abnormality degree of the equipment fault coefficient in all the historical work flows, and carrying out fault detection on the manipulator in the industrial equipment.
Further, based on the equipment fault coefficient, detecting the operation state of the manipulator in the industrial equipment, specifically:
Aiming at vibration data, noise data and current data at all moments in each historical workflow, calculating the equipment fault coefficients of each historical workflow by adopting a method with the same equipment fault coefficients of the workflow to be tested;
Adopting an anomaly detection algorithm to the equipment fault coefficients of the to-be-detected workflow and all the historical workflows to obtain anomaly values corresponding to all the equipment fault coefficients;
Preferably, in this embodiment, an LOF anomaly detection algorithm is used for anomaly detection, where the LOF anomaly detection algorithm is a well-known technique and is not described herein, and as other embodiments, an implementer may use other methods in the prior art, such as an isolated forest, etc., and this embodiment is not limited in particular.
If the abnormal value corresponding to the equipment failure coefficient of the workflow to be tested is the unique maximum value, the failure weight factor is a first preset value, and if the abnormal value corresponding to the equipment failure coefficient of the workflow to be tested is not the unique maximum value, the failure weight factor is a second preset value, wherein the first preset value is smaller than the second preset value;
preferably, in this embodiment, the first preset value is 1, the second preset value is 10, and as another embodiment, the practitioner can set the first preset value according to the actual situation.
It should be noted that, if the abnormal value corresponding to the equipment failure coefficient of the workflow to be tested is the only maximum value among all abnormal values, the abnormal degree of the manipulator is very large, and if the abnormal value corresponding to the equipment failure coefficient of the workflow to be tested is not the only maximum value, the equipment failure coefficient of the workflow to be tested is not abnormal in the historical data, and the possibility of occurrence of the abnormality is very small.
Normalizing the abnormal values corresponding to all the equipment fault coefficients, and taking the ratio of the normalized result of the abnormal value corresponding to the equipment fault coefficient of the workflow to be tested to the fault weight factor as the fault confidence coefficient of the workflow to be tested;
If the fault confidence coefficient is larger than or equal to a preset fault threshold value, the mechanical arm in the industrial equipment is in fault, maintenance and processing are needed in time, and if the fault confidence coefficient is smaller than the preset fault threshold value, the mechanical arm in the industrial equipment is in normal running state, so that fault detection of the mechanical arm is realized.
Preferably, in this embodiment, the preset failure threshold value is 0.5, and as another implementation manner, the implementation person can set the failure threshold value by himself.
And establishing a geometric model of the manipulator according to the design drawing and specification of the manipulator, and constructing a digital twin model through operation data of each historical workflow of the manipulator. And constructing a fault detection system in the digital twin model, detecting the operation data of the manipulator through the digital twin model after the operation data of the workflow to be detected of the manipulator is obtained, updating the digital twin model if the operation data of the workflow to be detected is not abnormal, and uploading the operation data of the workflow to be detected to a database. The actual running state of the manipulator can be received, detected and reflected in real time through the digital twin model, and the real-time state monitoring of the manipulator is realized. Meanwhile, through the historical operation data stored by the digital twin model, the difference of the operation data between the workflow to be tested and the historical workflow can be analyzed, so that more accurate fault detection is realized, and a more accurate maintenance strategy is formulated according to the detection result.
Based on the same inventive concept as the above method, the embodiment of the application further provides a digital twin-based industrial equipment fault intelligent detection system, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to realize the steps of any one of the above digital twin-based industrial equipment fault intelligent detection methods.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or sub-steps of other steps.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the application. It should be noted that, for those skilled in the art, several variations and modifications can be made without departing from the spirit of the present application, and therefore, any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present application fall within the protection scope of the technical solution of the present application.
Claims (7)
1. The intelligent detection method for the industrial equipment faults based on digital twinning is characterized by comprising the following steps of:
Obtaining vibration data, noise data and current data of each time in each historical workflow and workflow to be tested of a manipulator on industrial equipment;
determining the vibration stability coefficient of the workflow to be tested according to the fluctuation difference conditions and the monotonic change trend of vibration data at different moments in the workflow to be tested;
Determining a vibration deviation coefficient of the workflow to be tested according to the time interval difference condition and the discrete degree in the change process of the vibration data and the current data of the workflow to be tested and by combining the vibration stability coefficient;
According to the difference condition of noise data between the workflow to be tested and all the historical workflows, and combining the vibration deviation coefficient, determining the equipment fault coefficient of the workflow to be tested;
Determining the fault confidence coefficient of the workflow to be tested according to the abnormal degree of the equipment fault coefficient in all the historical workflows, and performing fault detection on the manipulator in the industrial equipment;
the determining the vibration stability coefficient of the workflow to be tested comprises the following steps:
extracting subsequences from vibration data at all moments in a work flow to be detected by adopting a variable length subsequence clustering algorithm, and clustering the subsequences;
analyzing the discrete condition of each subsequence in each cluster in the workflow to be tested, and determining the discrete condition as the intra-cluster fluctuation index of each cluster in the workflow to be tested;
The cluster with the largest intra-cluster fluctuation index is marked as a vibration fluctuation cluster, and the cluster with the smallest intra-cluster fluctuation index is marked as a vibration stable cluster;
analyzing the change trend condition of elements in each subsequence in the vibration fluctuation cluster, and determining the monotone change difference of each subsequence in the vibration fluctuation cluster of the workflow to be tested;
the ratio of the number of the monotone change differences of all the subsequences in the vibration fluctuation cluster to the number of the subsequences is 0 is recorded as a first ratio of the vibration fluctuation cluster;
Taking the ratio of the first ratio of the vibration fluctuation cluster to the intra-cluster fluctuation index of the vibration stable cluster as a vibration stability coefficient of the work flow to be tested;
The determining the vibration deviation coefficient of the workflow to be tested comprises the following steps:
Aiming at current data at all moments in the working flow to be detected, obtaining a current fluctuation cluster and a current stable cluster of the working flow to be detected by adopting the same method as that of the vibration fluctuation cluster and the vibration stable cluster;
Selecting acquisition moments corresponding to maximum values of elements in each subsequence of the vibration fluctuation cluster, and sequencing according to a time sequence to form a vibration transient sequence; aiming at each subsequence of the current fluctuation cluster, a current transient sequence is obtained by adopting the same method as a vibration transient sequence;
Analyzing the difference condition between the vibration transient sequence and the current transient sequence, and determining the difference condition as the transient deviation coefficient of the workflow to be tested;
taking the ratio of the instantaneous deviation coefficient to the vibration stability coefficient as the vibration deviation coefficient of the work flow to be tested;
the determining the equipment fault coefficient of the workflow to be tested comprises the following steps:
dividing noise data at all moments in a workflow to be tested into a plurality of noise subsequences;
calculating the variance, the mean value and the subsequence length of each noise subsequence in the workflow to be tested;
the variance, the mean value and the sequence length of all the noise subsequences are respectively formed into a noise variance vector, a noise mean value vector and a noise length vector of the workflow to be tested;
Aiming at the noise data at all moments in each historical workflow, the noise variance vector, the noise mean vector and the noise length vector of each historical workflow are obtained by adopting the same method as the noise variance vector, the noise mean vector and the noise length vector of the workflow to be tested;
performing cluster analysis on all the noise variance vectors, all the noise mean vectors and all the noise length vectors of the workflow to be tested and all the historical workflows respectively to obtain a plurality of variance clusters, a plurality of mean clusters and a plurality of length clusters respectively;
Analyzing the quantity difference between different clusters and the difference condition between noise data of the workflow to be tested and the cluster aggregation center, and determining the noise deviation coefficient of the workflow to be tested;
And fusing the vibration deviation coefficient and the noise deviation coefficient to determine the vibration deviation coefficient and the noise deviation coefficient as equipment fault coefficients of the workflow to be tested.
2. The intelligent detection method for industrial equipment failure based on digital twinning according to claim 1, wherein the determining as the intra-cluster fluctuation index of each cluster in the workflow to be tested comprises:
Taking the sum of the discrete degree and the average value of each subsequence in each cluster in the workflow to be tested as the vibration change degree of each subsequence in each cluster in the workflow to be tested;
And determining the discrete degree of the vibration variation degree of all the subsequences in each cluster in the workflow to be tested as the intra-cluster fluctuation index of each cluster in the workflow to be tested.
3. The intelligent detection method for industrial equipment faults based on digital twinning according to claim 1, wherein the determining the monotone variation difference of each sub-sequence in the vibration fluctuation cluster of the workflow to be detected comprises:
performing first-order difference on each subsequence in the vibration fluctuation cluster of the workflow to be tested to obtain each difference subsequence;
assigning an element greater than or equal to 0 in the differential subsequence to be 1; elements less than 0 are assigned a value of-1;
The absolute value of the sum of all the elements after assignment in the differential subsequence is recorded as a first absolute value of each subsequence;
And taking the difference between the first absolute value and the length of the differential subsequence as the monotone change difference of each subsequence in the vibration fluctuation cluster of the workflow to be tested.
4. The intelligent detection method for industrial equipment faults based on digital twinning according to claim 1, wherein the determining is an instantaneous deviation coefficient of a workflow to be detected comprises:
recording the difference between each acquisition time of the vibration transient sequence and the acquisition time of the same position in the current transient sequence as a delay effect value;
taking the discrete degree of all the delay effect values as a time difference index of the workflow to be tested;
Taking the difference between the length of the vibration transient sequence and the length of the current transient sequence as the transient frequency difference of the work flow to be tested;
And counting the number of the delay effect values which are smaller than or equal to 0, and fusing the number, the time difference index and the instantaneous frequency difference to determine the instantaneous deviation coefficient of the workflow to be detected.
5. The intelligent detection method for industrial equipment faults based on digital twinning according to claim 1, wherein the determining a noise deviation coefficient of a workflow to be detected comprises:
the mean value of the differences between the noise variance vector of the workflow to be tested and the clustering center vector of each variance cluster is recorded as a first difference;
Aiming at the noise mean value vector and the noise length vector of the workflow to be tested, a second difference and a third difference of the workflow to be tested are obtained by adopting the same method as the first difference;
counting the numbers of the variance clusters, the mean clusters and the length clusters respectively, and recording the sum of differences between any two numbers as a clustering difference;
calculating the product of the average value of the number of variance clusters, the number of mean clusters and the number of length clusters and the clustering difference, and recording the product as a first product;
and fusing the first product with the average value of the first difference, the second difference and the third difference, and determining the noise deviation coefficient of the workflow to be tested.
6. The intelligent detection method for faults of industrial equipment based on digital twinning according to claim 1, wherein the determining the fault confidence of the workflow to be detected, performing fault detection on a manipulator in the industrial equipment, comprises:
Aiming at vibration data, noise data and current data at all moments in each historical workflow, calculating the equipment fault coefficients of each historical workflow by adopting a method with the same equipment fault coefficients of the workflow to be tested;
Adopting an anomaly detection algorithm to the equipment fault coefficients of the to-be-detected workflow and all the historical workflows to obtain anomaly values corresponding to all the equipment fault coefficients;
if the abnormal value corresponding to the equipment fault coefficient of the workflow to be tested is the unique maximum value, the fault weight factor is a first preset value, otherwise, the fault weight factor is a second preset value, wherein the first preset value is smaller than the second preset value;
Normalizing the abnormal values corresponding to all the equipment fault coefficients, and taking the ratio of the normalized result of the abnormal value corresponding to the equipment fault coefficient of the workflow to be tested to the fault weight factor as the fault confidence coefficient of the workflow to be tested;
If the fault confidence coefficient is larger than or equal to a preset fault threshold value, the manipulator in the industrial equipment fails, otherwise, the manipulator in the industrial equipment operates normally.
7. A digital twin based industrial equipment fault intelligent detection system comprising a memory, a processor and a computer program stored in the memory and running on the processor, characterized in that the processor implements the steps of the digital twin based industrial equipment fault intelligent detection method according to any of claims 1-6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411046466.5A CN118568647B (en) | 2024-08-01 | 2024-08-01 | Industrial equipment fault intelligent detection method and system based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411046466.5A CN118568647B (en) | 2024-08-01 | 2024-08-01 | Industrial equipment fault intelligent detection method and system based on digital twin |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118568647A CN118568647A (en) | 2024-08-30 |
| CN118568647B true CN118568647B (en) | 2024-10-25 |
Family
ID=92478731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411046466.5A Active CN118568647B (en) | 2024-08-01 | 2024-08-01 | Industrial equipment fault intelligent detection method and system based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118568647B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118898043B (en) * | 2024-09-30 | 2024-12-13 | 乌海正泰世平电器有限公司 | Fault on-line detection and analysis method for switch equipment |
| CN118965043B (en) * | 2024-10-17 | 2025-01-24 | 青岛华尊机械股份有限公司 | A textile machine working fault state monitoring system and fault data analysis method |
| CN119010362B (en) * | 2024-10-21 | 2024-12-27 | 德力西集团弘宇防爆科技有限公司 | Intelligent explosion-proof power distribution device integrating wireless transmission function |
| CN119228220A (en) * | 2024-11-28 | 2024-12-31 | 深圳市金恒辉装饰工程有限公司 | A method and system for intelligent control of building material product quality detection |
| CN119268929B (en) * | 2024-12-11 | 2025-03-14 | 固耐重工（苏州）有限公司 | Crankshaft dynamic balance test data analysis method and system |
| CN119620622B (en) * | 2025-02-13 | 2025-05-06 | 浙江万胜智能科技股份有限公司 | Flow industrial energy consumption optimization system and method based on neural network |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114859845A (en) * | 2022-06-09 | 2022-08-05 | 中用科技有限公司 | Intelligent industrial data management system based on internet-of-things controller |
| CN117648587A (en) * | 2024-01-29 | 2024-03-05 | 深圳市爱宝科技有限公司 | Motor locked rotor high-sensitivity detection method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024022588A1 (en) * | 2022-07-28 | 2024-02-01 | Eaton Intelligent Power Limited | Self learning fault detection for electrical motors |
| CN117668757A (en) * | 2023-12-08 | 2024-03-08 | 长三角集成电路工业应用技术创新中心 | Fan equipment fault identification method, device, equipment and storage medium |
| CN117791876A (en) * | 2024-02-23 | 2024-03-29 | 国网甘肃省电力公司白银供电公司 | Substation equipment operation status monitoring method and abnormality management and control system |
| CN117892066B (en) * | 2024-03-14 | 2024-05-28 | 杭州银湖电气设备有限公司 | Vibration noise data processing method for magnetic control reactor |
| CN117951456B (en) * | 2024-03-26 | 2024-05-28 | 佛山市星际云数字科技有限公司 | Equipment state intelligent monitoring system based on digital twinning |
| CN118130070B (en) * | 2024-04-03 | 2024-07-30 | 上海辉度智能系统有限公司 | Escalator fault prediction diagnosis method, device and system |
-
2024
- 2024-08-01 CN CN202411046466.5A patent/CN118568647B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114859845A (en) * | 2022-06-09 | 2022-08-05 | 中用科技有限公司 | Intelligent industrial data management system based on internet-of-things controller |
| CN117648587A (en) * | 2024-01-29 | 2024-03-05 | 深圳市爱宝科技有限公司 | Motor locked rotor high-sensitivity detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118568647A (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118568647B (en) | Industrial equipment fault intelligent detection method and system based on digital twin | |
| CN118094449B (en) | Intelligent production monitoring method, system and device based on industrial Internet | |
| CA2634328C (en) | Method and system for trend detection and analysis | |
| CN111931834B (en) | Anomaly detection method, equipment and storage medium for aluminum profile extrusion process flow data based on isolated forest algorithm | |
| CN118478239B (en) | Intelligent control method and system for tool magazine of vertical numerical control machine tool | |
| CN117556366B (en) | Data abnormality detection system and method based on data screening | |
| CN113579851A (en) | Non-stationary drilling process monitoring method based on adaptive segmented PCA | |
| CN119105422B (en) | Production line abnormal data processing method and system based on digital twinning | |
| CN117129904B (en) | Industrial power supply rapid switching monitoring method based on data analysis | |
| CN117454283A (en) | State evaluation method for wind turbine generator operation detection data | |
| CN119204455A (en) | Multi-dimensional adjustable potential evaluation method of virtual power plant based on integrated intelligent model | |
| CN119475194A (en) | Air compressor operating status monitoring data processing method and system | |
| CN118501720B (en) | Lithium battery abnormality detection system based on big data analysis | |
| CN118365251B (en) | A chemical material storage management system based on the Internet of Things | |
| CN119889686A (en) | Nursing physical examination data intelligent analysis and management method | |
| CN117850403B (en) | Dynamic detection method for initiating and controlling system | |
| CN119045441A (en) | Processing optimization method and system for scene self-adaptive connector | |
| CN112621381A (en) | Intelligent health state evaluation method and device for machine tool feeding system | |
| CN114548177A (en) | Equipment health assessment method, system and equipment | |
| CN119960383B (en) | Numerical control machine tool running state monitoring method and system for processing hardware | |
| CN119807713B (en) | Station electric equipment steady-state feature extraction system based on load perception | |
| CN118979873B (en) | Mining water pump anomaly monitoring and early warning system | |
| CN117931897B (en) | Temperature data operation monitoring method for heating device | |
| CN119990543B (en) | Intelligent maintenance system and method for electric actuator based on fault prediction | |
| CN115854490B (en) | Analysis method and system for dehumidifier state monitoring |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |