CN114814491A - Cable on-line monitoring system fault diagnosis method based on wireless communication - Google Patents
Cable on-line monitoring system fault diagnosis method based on wireless communication Download PDFInfo
- Publication number
- CN114814491A CN114814491A CN202210418804.8A CN202210418804A CN114814491A CN 114814491 A CN114814491 A CN 114814491A CN 202210418804 A CN202210418804 A CN 202210418804A CN 114814491 A CN114814491 A CN 114814491A
- Authority
- CN
- China
- Prior art keywords
- data
- pulse
- cable
- time
- monitoring system
- 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.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 title claims abstract description 26
- 238000004891 communication Methods 0.000 title claims abstract description 19
- 238000005070 sampling Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 230000008447 perception Effects 0.000 abstract 1
- 238000009413 insulation Methods 0.000 description 6
- 229920003020 cross-linked polyethylene Polymers 0.000 description 4
- 239000004703 cross-linked polyethylene Substances 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Testing Relating To Insulation (AREA)
- Monitoring And Testing Of Transmission In General (AREA)
Abstract
The invention discloses a fault diagnosis method of a cable on-line monitoring system based on wireless communication, which comprises the following steps: (1) collecting data of a perception layer; (2) carrying out real-time preprocessing on the acquired data signals and extracting pulses; if the number of the extracted pulses is smaller than a preset pulse number threshold value, sending data information obtained by performing fixed sampling point downsampling on the preprocessed data to a data processing center of a system server, otherwise, sending pulse data information to the data processing center; (3) and the data processing center of the system server carries out fault diagnosis according to the received data information. The invention realizes real-time preprocessing of data and respectively calculates the data preprocessing and data diagnosis at the sensor end and the server end, can realize high-frequency acquisition of the cable, saves the memory space, simultaneously ensures the transmission efficiency of the data and the integrity of pulse signals, reduces the communication pressure of an online system, and simultaneously improves the accuracy of fault characteristics of the online monitoring system of the cable.
Description
Technical Field
The invention belongs to the technical field of power equipment insulation state monitoring, and particularly relates to a fault diagnosis method of a cable online monitoring system based on wireless communication.
Background
The partial discharges are referred to as partial discharges, in which the insulation of the electrical apparatus is subjected to a strong electric field and the discharges occur locally. Partial discharge of some weak parts in the insulation under the action of high electric field is a common problem, and insulation deterioration and even breakdown can be caused under certain conditions. The power cable has been widely used due to the advantages of small floor space, safe and reliable power supply, small electromagnetic interference to the surrounding environment and the like, and has been used for hundreds of years. In the use process of the power cable, the power cable is gradually aged due to the actions of electromagnetism, heat, machinery, chemistry and the like, so that destructive faults are generated. Early cables mainly have body faults, overload faults are more frequent recently, and the faults of the cable terminal and the middle joint are the main reasons of the cable faults. Monitoring the cable state is an important means for preventing the occurrence of cable faults. The traditional power cable preventive test needs power failure detection, low test voltage and long test period, belongs to off-line detection, and can not meet the requirements of uninterrupted power production and supply. The research on the online monitoring technology of the power cable state, the real-time display of the cable running state and the guarantee of safe and reliable power supply have become the development trend of power systems of various countries. The technology of cable insulation monitoring and fault diagnosis has been researched since the sixties and seventies of the twentieth century abroad, and China starts to develop later in this respect but develops faster in recent years. Due to the characteristics of easy laying, simple and convenient operation and maintenance, high temperature resistance, excellent insulating property and the like, a cross-linked polyethylene (XLPE) cable is widely applied to a power distribution network to gradually replace an oil paper insulated cable and an overhead line, and power failure accidents caused by the problems of insulation damage of the XLPE cable and a cable joint and the like are increased. XPLE cable is laid underground with forms such as direct-burried, calandria, tunnel mostly, has increased the difficulty of judging whether cable operating condition is normal, consequently, how to judge the insulating degradation state of cable through various detection means fast effectively has important realistic meaning.
The cable on-line monitoring can well monitor the equipment in real time for a long time, find out equipment faults in time and ensure the normal operation of the equipment. However, because the high-frequency sensor has a high sampling rate and a large data volume, and is influenced by the storage space of the sensor end and the communication pressure, the sampling data can be subjected to snapshot processing in a conventional mode, so that some useful characteristics of the original signal can be lost, and the fault diagnosis rate is reduced.
Disclosure of Invention
In order to overcome the problems, the invention provides a fault diagnosis method of a cable online monitoring system based on wireless communication, which calculates data preprocessing and data diagnosis at a sensor end and a server end respectively, thereby ensuring the transmission efficiency of data, ensuring the integrity of pulse signals, reducing the communication pressure of the online system and improving the fault characteristic accuracy of the cable online monitoring system. The method provides high guiding significance for the development of a cable-based on-line monitoring system, and is suitable for on-line monitoring of cables in different environments.
The technical scheme of the invention is as follows:
a fault diagnosis method of a cable on-line monitoring system based on wireless communication comprises the following steps:
(1) sensing layer data acquisition, namely acquiring data signals of the cable by adopting an HFCT sensor;
(2) carrying out real-time preprocessing on the acquired data signals and extracting pulses; if the number of the extracted pulses is smaller than a preset pulse number threshold value, sending data information obtained by performing fixed sampling point down-sampling on the preprocessed data to a data processing center of a system server, otherwise sending the extracted pulse data information to the data processing center of the system server;
(3) and the data processing center of the system server carries out fault diagnosis according to the received data information:
if the received pulse data information is pulse data information, a PRPD graph and a TF spectrogram are drawn, time-frequency S conversion is carried out on the pulse, then a characteristic value is obtained through calculation, and then further diagnosis of the discharge type is carried out; otherwise, the data processing center outputs the normal fault type and does not carry out further fault type diagnosis.
The invention further explains that in the step (2), the collected data signals are preprocessed in real time and pulses are extracted, and the steps are as follows:
firstly, performing real-time noise removal on signals through a Deslauriers-Dubuc (5,3) wavelet, collecting and processing the signals at the same time, only storing the preprocessed data, and selecting the size of a real-time preprocessed data window for 20 mu s;
and after data is preprocessed, sliding window pulse extraction is simultaneously carried out, and the amplitude, the initial phase and the pulse equivalent time frequency value of each pulse are recorded for the extracted pulses.
The length (duration) of each pre-processing of the cable signal is 1 s.
Further, the size of the sliding window is 1 μ s, and each pulse length is 5 μ s.
The invention further illustrates that the fixed sample point is 3600 (i.e. from every 1s of raw data to 3600 fixed samples), and the maximum amplitude value is recorded for the fixed sample point.
The invention further explains that the PRPD graph is a PRPD two-dimensional gray scale graph generated by pulse phase, pulse amplitude and pulse frequency; and drawing the TF spectrogram into a two-dimensional scatter diagram by using the pulse equivalent time-frequency value. The pulse S is transformed into a pulse time-frequency distribution map.
The invention further explains that the characteristic value of the PRPD two-dimensional gray scale image is obtained by a sparse coding algorithm, and the method specifically comprises the following steps: the method comprises the steps of normalizing a PRPD two-dimensional gray scale image into 512 × 256 pixels, randomly selecting 3000 picture blocks with the size of 16 × 16 for each picture to obtain a data set with the size of 256 × 3000, and acquiring a feature vector set F of the data set based on a sparse coding algorithm 1 (ii) a The sparse coding algorithm adopts Gabor to initialize a basis function, and selects kurtosis as a measurement criterion of sparsity.
The invention further explains that the time-frequency S transformation of the pulse is to select S transformation to calculate characteristic values of all pulse time-frequency transformation, and specifically comprises the following steps: sparse matrix decomposition is carried out on the amplitude matrix after pulse S transformation to obtain a base matrix W ═ W 1 ,w 2 ,…,w r And coefficient matrix H ═ H (H) 1 ,h 2 ,…,h r ) T Where { w i } i =1,... r and h i } i R is a frequency domain basis vector and a corresponding time domain basis vector, and a feature vector set F can be obtained based on the frequency domain basis vector and the time domain basis vector 2 。
The invention further discloses that the characteristic value of the TF spectrogram is subjected to fast Fourier transform to calculate pulse equivalent time and equivalent frequency points and carry out data normalization to obtain a characteristic vector set F 3 。
The invention further provides that the obtained feature vector set (F) is subjected to 1 、F 2 、F 3 ) And (4) performing feature dimension reduction and optimization, and performing fault type diagnosis on the optimized features by learning through an extreme learning machine.
F 1 Carrying out sparse coding on the PRPD picture to obtain a feature basis vector; f 2 Respectively calculating the sharpness, the moment characteristics, the information entropy, the average value and the standard deviation based on the frequency domain basis, and calculating the derivative square sum based on the time domain basis vector; f 3 Is the pulse equivalent time-frequency central point (T) i ,F i ) And i is the number of pulse clusters.
The invention has the advantages that:
according to the invention, data preprocessing and data diagnosis are respectively calculated at the sensor end and the server end, so that the transmission efficiency of data is ensured, the integrity of pulse signals is also ensured, the fault characteristic accuracy and the fault diagnosis rate are improved, the memory space is saved, the resources required by communication are reduced, the stability of data transmission is improved, and the cost is reduced; the method provides high guiding significance for the development of a cable-based on-line monitoring system, and is suitable for on-line monitoring of cables in different environments. .
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the figures and the specific embodiments.
Example 1:
a fault diagnosis method for a cable online monitoring system based on wireless communication, as shown in fig. 1, includes the following steps:
(1) sensing layer data acquisition, namely acquiring data signals of the cable by adopting an HFCT sensor;
(2) carrying out real-time preprocessing on the acquired data signals and extracting pulses; if the number of the extracted pulses is smaller than a preset pulse number threshold value, sending data information obtained by performing fixed sampling point down-sampling on the preprocessed data to a data processing center of a system server, otherwise sending the extracted pulse data information to the data processing center of the system server;
(3) and the data processing center of the system server carries out fault diagnosis according to the received data information:
if the received pulse data information is pulse data information, drawing a PRPD graph and a TF spectrogram, calculating to obtain a characteristic value after performing time-frequency S conversion on the pulse, and then performing further diagnosis on the discharge type; otherwise, the data processing center outputs the normal fault type and does not carry out further fault type diagnosis.
Example 2:
a fault diagnosis method of a cable on-line monitoring system based on wireless communication comprises the following steps:
(1) acquiring data signals of the cable by using an HFCT sensor;
(2.1) acquiring a data signal with a proper length;
(2.2) performing real-time noise removal on the signals through a Deslauriers-Dubuc (5,3) wavelet, collecting and processing the signals simultaneously, only storing the preprocessed data, and selecting the size of a real-time preprocessed data window for 20 microseconds;
(2.3) preprocessing the data, simultaneously extracting sliding window pulses, and recording pulse information such as amplitude, initial phase, pulse equivalent time frequency value and the like of each pulse for the extracted pulses;
if the number of the extracted pulses is smaller than a preset pulse number threshold value, sending data information obtained by performing fixed sampling point down-sampling on the preprocessed data to a data processing center of a system server, otherwise sending the extracted pulse data information to the data processing center of the system server;
(3) and the data processing center of the system server carries out fault diagnosis according to the received data information:
if the received pulse data information is pulse data information, drawing a PRPD graph and a TF spectrogram, calculating to obtain a characteristic value after performing time-frequency S conversion on the pulse, and then performing further diagnosis on the discharge type; otherwise, the data processing center outputs the normal fault type and does not carry out further fault type diagnosis.
In one embodiment of the invention, the length (duration) of each preprocessed cable signal is 1 s.
In one embodiment of the invention, the size of the sliding window is 1 μ s, and each pulse length is 5 μ s.
In one embodiment of the invention, the fixed sample point is 3600 and the maximum amplitude is recorded for the fixed sample point.
Example 3:
a fault diagnosis method of a cable on-line monitoring system based on wireless communication comprises the following steps:
(1) acquiring data signals of the cable by using an HFCT sensor;
(2.1) acquiring a data signal with a proper length;
(2.2) removing real-time noise of the signals through a Deslauriers-Dubuc (5,3) wavelet, collecting and processing the signals at the same time, only storing the preprocessed data, and selecting the size of a real-time preprocessed data window for 20 mus;
(2.3) preprocessing the data, simultaneously extracting sliding window pulses, and recording pulse information such as amplitude, initial phase, pulse equivalent time frequency value and the like of each pulse for the extracted pulses;
if the number of the extracted pulses is smaller than a preset pulse number threshold value, sending data information obtained by performing fixed sampling point down-sampling on the preprocessed data to a data processing center of a system server, otherwise sending the extracted pulse data information to the data processing center of the system server;
(3) and the data processing center of the system server carries out fault diagnosis according to the received data information:
if the received pulse data information is pulse data information, drawing a PRPD graph and a TF spectrogram, calculating to obtain a characteristic value after performing time-frequency S conversion on the pulse, and then performing further diagnosis on the discharge type; otherwise, the data processing center outputs the normal fault type and does not carry out further fault type diagnosis.
The PRPD image is a PRPD two-dimensional gray scale image generated by pulse phase, pulse amplitude and pulse frequency; and drawing the TF spectrogram into a two-dimensional scatter diagram by using the pulse equivalent time-frequency value. The pulse S is transformed into a pulse time-frequency distribution map.
Further, the characteristic value of the PRPD two-dimensional gray scale image is obtained through a sparse coding algorithm, which specifically comprises: the method comprises the steps of normalizing a PRPD two-dimensional gray scale image into 512 × 256 pixels, randomly selecting 3000 picture blocks with the size of 16 × 16 for each picture to obtain a data set with the size of 256 × 3000, and acquiring a feature vector set F of the data set based on a sparse coding algorithm 1 (ii) a The sparse coding algorithm adopts Gabor to initialize a basis function, and selects kurtosis as a measurement criterion of sparsity.
In one embodiment of the present invention, the sparse coding algorithm objective function is defined as:
wherein,to representA mathematical expectation of (d); (x, y) represents pixel gray scale values; x (X, y) represents input picture data; s is a random coefficient matrix, S i Is a vector in the S matrix; a is a characteristic basis matrix, a i Is the vector in A; lambda [ alpha ] 1 ,λ 2 Is a normal constant and is a constant value,a scale constant that is a variance of the random sparse matrix; wherein λ 1 ,λ 2 In this example, 0.5, 0.05 was selected.
Further, the performing time-frequency S transform on the pulse is to select S transform to calculate a characteristic value for all pulse time-frequency transforms, and specifically includes: sparse matrix decomposition is carried out on the amplitude matrix after pulse S transformation to obtain a base matrix W ═ W 1 ,w 2 ,…,w r And coefficient matrix H ═ H (H) 1 ,h 2 ,…,h r ) T Where { w i } i=1,...r And { h i } i=1,...r A feature vector set F is obtained for the frequency domain basis vectors and the corresponding time domain basis vectors based on the frequency domain basis vectors and the time domain basis vectors 2 Including sharpness, moment features, entropy, mean and standard deviation calculated based on frequency domain bases, and derivative sum of squares calculated based on time domain bases.
Further, the characteristic value of the TF spectrogram is subjected to fast Fourier transform to calculate pulse equivalent time and equivalent frequency points and data normalization to obtain a characteristic vector set F 3 。
Further, the obtained feature vector set (F) is subjected to 1 、F 2 、F 3 ) And (4) performing feature dimension reduction optimization, and performing fault type diagnosis on the optimized features by learning through an extreme learning machine.
It should be understood that the above-described embodiments are merely examples for clearly illustrating the present invention and are not intended to limit the practice of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description; this is not necessary, nor exhaustive, of all embodiments; and obvious variations or modifications of the invention may be made without departing from the scope of the invention.
Claims (9)
1. A fault diagnosis method of a cable on-line monitoring system based on wireless communication is characterized by comprising the following steps:
(1) sensing layer data acquisition, namely acquiring data signals of the cable by adopting an HFCT sensor;
(2) carrying out real-time preprocessing on the acquired data signals and extracting pulses; if the number of the extracted pulses is smaller than a preset pulse number threshold value, sending data information obtained by performing fixed sampling point down-sampling on the preprocessed data to a data processing center of a system server, otherwise sending the extracted pulse data information to the data processing center of the system server;
(3) and the data processing center of the system server carries out fault diagnosis according to the received data information:
if the received pulse data information is pulse data information, drawing a PRPD graph and a TF spectrogram, calculating to obtain a characteristic value after performing time-frequency S conversion on the pulse, and then performing further diagnosis on the discharge type; otherwise, the data processing center outputs the normal fault type and does not carry out further fault type diagnosis.
2. The method for diagnosing the fault of the cable online monitoring system based on the wireless communication as claimed in claim 1, wherein in the step (2), the collected data signals are preprocessed in real time and pulses are extracted, specifically:
firstly, performing real-time noise removal on signals through a Deslauriers-Dubuc (5,3) wavelet, collecting and processing the signals at the same time, only storing the preprocessed data, and selecting the size of a real-time preprocessed data window for 20 mu s;
and after data is preprocessed, sliding window pulse extraction is simultaneously carried out, and the amplitude, the initial phase and the pulse equivalent time frequency value of each pulse are recorded for the extracted pulses.
3. The method as claimed in claim 2, wherein the sliding window has a size of 1 μ s, and each pulse has a length of 5 μ s.
4. The method as claimed in claim 2, wherein the fixed sampling point is 3600, and the maximum amplitude value is recorded for the fixed sampling point.
5. The fault diagnosis method for the cable online monitoring system based on wireless communication as claimed in claim 2, wherein the PRPD graph is a PRPD two-dimensional gray scale graph generated by pulse phase, pulse amplitude and pulse frequency; and drawing the TF spectrogram into a two-dimensional scatter diagram by using the pulse equivalent time-frequency value.
6. The cable online monitoring system fault diagnosis method based on wireless communication of claim 5, wherein the characteristic value of the PRPD two-dimensional gray scale map is obtained by a sparse coding algorithm, specifically:
the method comprises the steps of normalizing a PRPD two-dimensional gray scale image into 512 × 256 pixels, randomly selecting 3000 picture blocks with the size of 16 × 16 for each picture to obtain a data set with the size of 256 × 3000, and acquiring a feature vector set F of the data set based on a sparse coding algorithm 1 (ii) a The sparse coding algorithm adopts Gabor to initialize a basis function, and selects kurtosis as a measurement criterion of sparsity.
7. The method for diagnosing the fault of the cable online monitoring system based on the wireless communication as claimed in claim 6, wherein the performing the time-frequency S transformation on the pulse is selecting S transformation to calculate the characteristic value for all the pulse time-frequency transformation, and specifically comprises:
carrying out sparse matrix decomposition on the amplitude matrix after the pulse S transformation to obtain a basis matrix and a coefficient matrix, and obtaining a feature vector set F based on the frequency domain basis vector and the time domain basis vector 2 。
8. The fault diagnosis method for cable online monitoring system based on wireless communication as claimed in claim 7, wherein the feature value of the TF spectrogram is subjected to fast Fourier transform to calculate pulse equivalent time and equivalent frequency points and data normalization to obtain a feature vector set F 3 。
9. The method according to claim 8, wherein the feature vector set (F) is obtained 1 、F 2 、F 3 ) Performing characteristic dimension reduction optimization, and performing optimizationThe characteristic of the method adopts an extreme learning machine to learn and carry out fault type diagnosis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210418804.8A CN114814491B (en) | 2022-04-20 | 2022-04-20 | Cable on-line monitoring system fault diagnosis method based on wireless communication |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210418804.8A CN114814491B (en) | 2022-04-20 | 2022-04-20 | Cable on-line monitoring system fault diagnosis method based on wireless communication |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114814491A true CN114814491A (en) | 2022-07-29 |
CN114814491B CN114814491B (en) | 2024-09-06 |
Family
ID=82504719
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210418804.8A Active CN114814491B (en) | 2022-04-20 | 2022-04-20 | Cable on-line monitoring system fault diagnosis method based on wireless communication |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114814491B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20100048650A (en) * | 2008-10-31 | 2010-05-11 | 엘에스전선 주식회사 | Power apparatus defect detection method and system improved noise removal function |
CN110056640A (en) * | 2019-04-12 | 2019-07-26 | 苏芯物联技术(南京)有限公司 | Speed reducer wireless malfunction diagnostic method based on acceleration signal and edge calculations |
CN113805018A (en) * | 2021-09-15 | 2021-12-17 | 陕西省地方电力(集团)有限公司 | Intelligent identification method for partial discharge fault type of 10kV cable of power distribution network |
CN114280427A (en) * | 2020-09-28 | 2022-04-05 | 上海金艺检测技术有限公司 | Local discharge distributed monitoring and early warning method based on ground electric waves of switch cabinet |
-
2022
- 2022-04-20 CN CN202210418804.8A patent/CN114814491B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20100048650A (en) * | 2008-10-31 | 2010-05-11 | 엘에스전선 주식회사 | Power apparatus defect detection method and system improved noise removal function |
CN110056640A (en) * | 2019-04-12 | 2019-07-26 | 苏芯物联技术(南京)有限公司 | Speed reducer wireless malfunction diagnostic method based on acceleration signal and edge calculations |
CN114280427A (en) * | 2020-09-28 | 2022-04-05 | 上海金艺检测技术有限公司 | Local discharge distributed monitoring and early warning method based on ground electric waves of switch cabinet |
CN113805018A (en) * | 2021-09-15 | 2021-12-17 | 陕西省地方电力(集团)有限公司 | Intelligent identification method for partial discharge fault type of 10kV cable of power distribution network |
Also Published As
Publication number | Publication date |
---|---|
CN114814491B (en) | 2024-09-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109342909B (en) | SLLE-based cable accessory partial discharge mode identification method | |
CN109102508B (en) | Method for identifying insulation defects of alternating current cable based on partial discharge image characteristics | |
CN112069930A (en) | Vibration signal processing method and device for improving GIS equipment fault diagnosis accuracy | |
CN103018629A (en) | Method for analyzing power system fault recording data based on Marla algorithm | |
CN110988635A (en) | High-low voltage electrical equipment insulation online detection loop, system and method | |
CN117390408B (en) | Power transformer operation fault detection method and system | |
CN110161351B (en) | Transformer winding fault test system and diagnosis method under oscillatory wave | |
CN115575863A (en) | OLTC (on-line test) voiceprint signal identification method based on phase space trajectory diagram principle | |
CN117269751B (en) | GIS isolating switch switching position confirmation method | |
CN114814491A (en) | Cable on-line monitoring system fault diagnosis method based on wireless communication | |
CN113671037A (en) | Post insulator vibration acoustic signal processing method | |
Liu et al. | Bearing performance degradation assessment using linear discriminant analysis and coupled HMM | |
CN114779028B (en) | Generator partial discharge online monitoring device and monitoring method | |
CN116338391A (en) | Insulator state detection method and device, electronic equipment and medium | |
CN110994802A (en) | Method and device for monitoring running state of power transmission conductor | |
CN111025095B (en) | XLPE cable terminal insulation reliability intelligent and rapid assessment method | |
Potnuru et al. | Image processing and machine learning applied for condition monitoring of 11-kV power distribution line insulators using curvelet and LTP features | |
CN110632482B (en) | Evaluation method for insulation aging state of EPR cable based on Gaussian pyramid | |
Lewin et al. | A feature based method for partial discharge source classification | |
Wang et al. | A Denoising Method for Cable Partial Discharge Signals Based on Image Information Entropy and Multivariate Variational Mode Decomposition | |
CN118348371A (en) | Partial discharge monitoring method and device and power distribution network monitoring system | |
CN117849560B (en) | Valve side sleeve insulation monitoring method and system combining end screen voltage and partial discharge | |
CN112001326B (en) | Vibration fingerprint-based high-voltage switch equipment fault diagnosis and prediction method and system | |
Bangle | Feature Extraction of Cable Partial Discharge Signal based on DT-CWT_Hankel_SVD | |
Zhu et al. | Research on image recognition technology of overhead transmission line damage |
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 |