CN108181562A - Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems - Google Patents
Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems Download PDFInfo
- Publication number
- CN108181562A CN108181562A CN201810049636.3A CN201810049636A CN108181562A CN 108181562 A CN108181562 A CN 108181562A CN 201810049636 A CN201810049636 A CN 201810049636A CN 108181562 A CN108181562 A CN 108181562A
- Authority
- CN
- China
- Prior art keywords
- study
- layer
- insulator
- estimation method
- cold standby
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000012212 insulator Substances 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000015556 catabolic process Effects 0.000 title claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 18
- 230000005684 electric field Effects 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 5
- VIEYMVWPECAOCY-UHFFFAOYSA-N 7-amino-4-(chloromethyl)chromen-2-one Chemical compound ClCC1=CC(=O)OC2=CC(N)=CC=C21 VIEYMVWPECAOCY-UHFFFAOYSA-N 0.000 claims abstract description 4
- 239000013598 vector Substances 0.000 claims description 36
- 230000006870 function Effects 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000032683 aging Effects 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000002405 diagnostic procedure Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000011160 research Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 4
- 230000003862 health status Effects 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims description 2
- 210000001638 cerebellum Anatomy 0.000 claims description 2
- 230000005611 electricity Effects 0.000 claims 1
- 230000001537 neural effect Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 4
- 230000002490 cerebral effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011982 device technology Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004861 thermometry Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- 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
- G01R31/1245—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 line insulators or spacers, e.g. ceramic overhead line cap insulators; of insulators in HV bushings
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Ceramic Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Relating To Insulation (AREA)
- Insulators (AREA)
Abstract
The present invention provides a kind of insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems, including MCU, the first pretreatment circuit, the second pretreatment circuit, third pretreatment circuit, electric-field sensor, leakage current sensor, temperature sensor, long-range transceiver module and remote computer;Pass through electric-field sensor, Leakage Current sensor and temperature sensor acquisition signal, denoising is carried out with Kalman filtering algorithm, the feature samples with fault message are obtained, establish insulator breakdown information training sample database, classification based training is carried out to sample by FCMAC, it is trained using BP algorithm, the weights for making network optimal and threshold value are obtained, when new message sample inputs network, can accurately judge the fault type of insulator rapidly.With reference to Kalman Algorithm and CMAC, each modified weights are few, and pace of learning is fast, has many advantages, such as certain generalization ability, improve the efficiency and accuracy rate of insulator breakdown analysis.
Description
Technical field
The invention belongs to isolator detecting fields, and in particular to a kind of insulator based on Study On Reliability Estimation Method For Cold Standby Systems
Trouble-shooter and method.
Background technology
Traditional isolator detecting method has IR thermometry, ultraviolet image method, ultrasonic Detection Method, Leakage Current method,
But these detection methods all there are of high cost, safety it is low or poor for applicability etc. the drawbacks of.With computer technology, sensing
The continuous development of device technology, machine learning have been successfully applied to the fault detect link of many industries.To the failure of insulator
Existing research is diagnosed, many researchs are only identified from some specific fault, although recognition result accuracy is high, but know
Other ability is limited, also there is it is certain the defects of.
Invention content
The object of the present invention is to provide a kind of insulator breakdown diagnostic devices based on Study On Reliability Estimation Method For Cold Standby Systems.
To achieve the above object, the present invention uses following technical scheme:It is a kind of based on Study On Reliability Estimation Method For Cold Standby Systems
Insulator breakdown diagnostic device, it is characterised in that:Locate in advance including MCU, the first pretreatment circuit, the second pretreatment circuit, third
Manage circuit, electric-field sensor, leakage current sensor, temperature sensor, long-range transceiver module and remote computer;The MCU
It is connect respectively with the first pretreatment circuit, the second pretreatment circuit, third pretreatment circuit, long-range transceiver module;Described first
Pretreatment circuit is connect with electric-field sensor;The second pretreatment circuit is connect with leakage current sensor;The third is pre-
Processing circuit is connect with temperature sensor;The long-range transceiver module is connect by wireless network with remote computer.
In an embodiment of the present invention, a human-computer interaction device is further included, the human-computer interaction device is connect with MCU.
In an embodiment of the present invention, the first pretreatment circuit, the second pretreatment circuit, third pretreatment circuit are equal
For the signal denoising processing circuit based on Kalman filtering algorithm.
The present invention also provides a kind of insulator breakdown diagnostic method based on Study On Reliability Estimation Method For Cold Standby Systems, feature exists
In:Include the following steps:Step S1:It is studied by artificial accelerated aging and live the Ageing of Insulators research, insulator is applied
Electric signal sample information in the case of adding different failures, detection corresponding, constructs insulator breakdown information training sample database, as
The training sample of neural network;Step S2:Pass through electric-field sensor, Leakage Current sensor, collection voltages signal, electric current letter
Number, denoising is carried out to the signal of acquisition with Kalman filtering algorithm, obtains the feature samples U with fault messagei1,U01,
I01, obtain the feature samples with fault message;Step S3:Insulator health shape can be reacted by being extracted from fault signature sample
The performance parameter of condition pair obtains performance characteristic vector { x1,x2,...,xm,, i=1,2 ..., m, m are Insulators Used parameter
Number, and using performance parameter vector as the input signal of Study On Reliability Estimation Method For Cold Standby Systems, use trained nerve net
Network carries out analysis classification to this group of performance parameter, judges the specific fault type of insulator.
In an embodiment of the present invention, Study On Reliability Estimation Method For Cold Standby Systems FCMAC is mainly by vector input layer, blurring
Layer, triggering strength layer, associative strength layer and five part of network output layer composition;Wherein:Vector input layer:By feature vector { x1,
x2,...,xi,...,xmIntroduce Cerebellar Model Articulation Controller network;It is blurred layer:Using Gauss π membership function, to defeated
The eigen vector entered carries out Fuzzy processing;Trigger strength layer:For calculating triggering intensity of the input to association's unit;Association is strong
Spend layer:The triggering intensity that third layer calculates will trigger the associative strength associated in unit;Output layer:To the connection of the 4th layer of triggering
Think that intensity is summed, obtain output vector.
In an embodiment of the present invention, the learning algorithm of Study On Reliability Estimation Method For Cold Standby Systems FCMAC declines BP using gradient
Algorithm, the specific steps are:Input state vector calculates the reality output of network, and and phase along neural network signal propagation direction
Output is hoped to compare, object function is calculated, if target function value is unsatisfactory for error precision, using gradient descent method to network
Weights are modified;It is trained again, calculating target function, so cycle is until meeting error requirements;If target function value
Meet error, then complete to train.
Compared with prior art, the present invention acquires failure letter using sensor technology in a manner that computer technology is combined
Sample is ceased, speed is fast, and accuracy rate is high, and data are accurate;Insulator is fallen using FCMAC networks string, crackle, filth detection point
Class compared to traditional CMAC networks, introduces fuzzy theory, is carried out when being divided to input state vector and when triggering associative strength
Fuzzy processing makes system obtain stronger real-time adjustment and self-learning capability, in addition the original advantages of CMAC, by the use of it as former
Barrier grader has a clear superiority, and the health status for judging insulator that can be more accurate, more reliable also improves insulator breakdown
The efficiency of analysis.
Description of the drawings
Fig. 1 apparatus structure block diagrams.
Fig. 2 establishes insulator breakdown information training sample database flow chart.
The overall flow figure of insulator breakdown diagnostic methods of the Fig. 3 based on Study On Reliability Estimation Method For Cold Standby Systems.
The model mapping schematic diagram of Fig. 4 Fuzzy CMACs.
Fig. 5 trains flow.
Fig. 6 diagnostic process.
Fig. 7 gradients decline the flow chart of BP algorithm.
Specific embodiment
Explanation is further explained to the present invention in the following with reference to the drawings and specific embodiments.
Referring to Fig. 1, the present invention provides a kind of insulator breakdown diagnostic device based on Study On Reliability Estimation Method For Cold Standby Systems,
It is characterized in that:Including MCU, the first pretreatment circuit, the second pretreatment circuit, third pretreatment circuit, electric-field sensor, leakage
Current sensor, temperature sensor, long-range transceiver module and remote computer;The MCU respectively with the first pretreatment circuit, the
Two pretreatment circuits, third pretreatment circuit, the connection of long-range transceiver module;The first pretreatment circuit connects with electric-field sensor
It connects;The second pretreatment circuit is connect with leakage current sensor;The third pretreatment circuit is connect with temperature sensor;
The long-range transceiver module is connect by wireless network with remote computer.It, will be from as shown in Figure 1, by designing apparatus structure
Electric-field sensor, collected signal passes to pretreatment circuit in Leakage Current sensor and temperature sensor, passes through micro-control
Unit (MCU) processing processed, on the interface of human-computer interaction, with long-range transceiver module, the mode of wireless transmission passes to signal
Remote computer.
In an embodiment of the present invention, a human-computer interaction device is further included, the human-computer interaction device is connect with MCU.
In an embodiment of the present invention, the first pretreatment circuit, the second pretreatment circuit, third pretreatment circuit are equal
For the signal denoising processing circuit based on Kalman filtering algorithm.
The present invention also provides a kind of insulator breakdown diagnostic method based on Study On Reliability Estimation Method For Cold Standby Systems, feature exists
In:Include the following steps:
Step S1:Establish insulator breakdown information training sample database:It is studied by artificial accelerated aging and scene is insulated
Sub- ageing research applies insulator different failures, the electric signal sample information in the case of detection is corresponding, construction insulator event
Hinder information training sample database, the training sample as neural network.In one embodiment of the invention, as shown in Fig. 2, establishing insulator
Fault message training sample database:It is studied by artificial accelerated aging and live the Ageing of Insulators research, to insulator application not
Same failure, the electric signal sample information in the case of detection is corresponding, constructs insulator breakdown information training sample database, as nerve
The training sample of network.
Step S2:By electric-field sensor, Leakage Current sensor, collection voltages signal, current signal are filtered with Kalman
Wave algorithm carries out denoising to the signal of acquisition, obtains the feature samples U with fault messagei1,U01,I01.The present invention one is real
Example is applied, as shown in figure 3, by electric-field sensor, Leakage Current sensor acquires the electric signal of insulator to be measured on the spot, including
Collection voltages signal (input voltage Ui, output voltage U0), current signal (output current I0), with Kalman filtering algorithm to adopting
The signal of collection carries out denoising, obtains the feature samples U with fault messagei1,U01,I01, extracted from fault signature sample
The performance parameter of insulator health status pair can be reacted by going out, and obtain performance characteristic vector { x1,x2,...,xm,, i=1,2 ...,
M, m are Insulators Used number of parameters, and using performance parameter vector as the input signal of Study On Reliability Estimation Method For Cold Standby Systems, are used
Trained network carries out analysis classification to this group of performance parameter, judges the specific fault type of insulator.
Step S3:The performance parameter of insulator health status can be reacted by being extracted from fault signature sample, obtain performance
Feature vector { x1,x2,...,xm,, i=1,2 ..., m, m be Insulators Used number of parameters, and performance parameter vector is made
For the input signal of Study On Reliability Estimation Method For Cold Standby Systems, this group of performance parameter is analyzed with trained neural network
The specific fault type of insulator is judged in classification.
Study On Reliability Estimation Method For Cold Standby Systems FCMAC is mainly strong by vector input layer, blurring layer, triggering strength layer, association
Spend layer and five part of network output layer composition;Wherein:Vector input layer:By feature vector { x1,x2,...,xi,...,xmIntroduce
Cerebellar Model Articulation Controller network;It is blurred layer:Using Gauss π membership function, the eigen vector of input is obscured
Change is handled;Trigger strength layer:For calculating triggering intensity of the input to association's unit;Associative strength layer:What third layer calculated
The associative strength associated in unit will be triggered by triggering intensity;Output layer:It sums, obtains to the associative strength of the 4th layer of triggering
Output vector.
In one embodiment of the invention, as shown in figure 4, structure Study On Reliability Estimation Method For Cold Standby Systems (FCMAC):Fuzzy cerebellum mould
Type neural network is mainly by vector input layer, blurring layer, triggering five part group of strength layer, associative strength layer and network output layer
Into.It is specific as follows:
(1) first layer is vector input layer:By feature vector { x1,x2,...,xi,...,xmCMAC networks are introduced, it is defeated
Entering output relation is:
Input node:Each component of performance characteristic vector
Output node:
(2) second layer is blurring layer:Using Gauss π membership function, the eigen vector of input is carried out at blurring
Reason, it is assumed that quantify to each input vector, divide h block, then input xiCorresponding j-th piece of membership is:
I=1,2 in formula ..., m;J=1,2 ..., h.And δijCenter and the width of Gaussian function are represented respectively.Second
Layer input/output relation be:
Input node:
Output node:
(3) third layer is triggering strength layer, for calculating triggering intensity of the input to association's unit, it is assumed that each input
Vector quantified, be divided into h block, then on all input vectors corresponding piece constitute hmA hypercube;Each
Hypercube is corresponding with the 4th layer of association's unit, and corresponding associative strength is store in each association's unit;It is assumed that
HypercubeBy blockComposition, then its intensity of activation to association's unit is:
In formula, pk=1,2 ..., h, " * " product operation represent minimizing operation;
Third layer input/output relation is:
Input node:
Output node:
(4) the 4th layers are associative strength layer, and the triggering intensity that third layer calculates is strong by the association triggered in association's unit
Degree, input/output relation are:
Input node:
Output node:
In formula, q=1,2 ..., n;N is the classification number of classification;Represent the associative strength in association's unit.
(5) layer 5 is output layer, sums to the associative strength of the 4th layer of triggering, obtains output vector, is inputted
Output relation is:
Input node:
Output node:
In formula, q=1,2 ..., n;Y represents the output of network.
As shown in figure 5, by electric-field sensor, the sample (voltage signal, current signal) of Leakage Current sensor acquisition,
Denoising is carried out to the sample signal of acquisition with Kalman filtering algorithm, with insulator breakdown information training sample database to structure
FCMAC networks be trained;Its training effect is judged, until meeting effect requirements, i.e. training terminates.
As shown in fig. 6, new message sample is input in trained FCMAC networks, judged with FCMAC networks
Insulator breakdown type.
In an embodiment of the present invention, the learning algorithm of Study On Reliability Estimation Method For Cold Standby Systems FCMAC declines BP using gradient
Algorithm, the specific steps are:Input state vector calculates the reality output of network, and and phase along neural network signal propagation direction
Output is hoped to compare, object function is calculated, if target function value is unsatisfactory for error precision, using gradient descent method to network
Weights are modified;It is trained again, calculating target function, so cycle is until meeting error requirements;If target function value
Meet error, then complete to train.
In an embodiment of the present invention, as shown in Figure 7:The learning algorithm of FCMAC:BP algorithm is declined using gradient
Object function:
In formula:D (k) represents desired output, and y (k) represents reality output.
Network weight is modified using gradient descent method:
It is above-mentioned to construct FCMAC networks, with the insulator breakdown information training sample database of structure, network is trained,
Optimizing, obtain can accurate recognition be out of order the network of type.For carrying out event to the electric signal of the insulator to be measured acquired on the spot
Hinder type identification.
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
During with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (6)
1. a kind of insulator breakdown diagnostic device based on Study On Reliability Estimation Method For Cold Standby Systems, it is characterised in that:Including MCU,
One pretreatment circuit, the second pretreatment circuit, third pretreatment circuit, electric-field sensor, leakage current sensor, temperature sensing
Device, long-range transceiver module and remote computer;The MCU is pre- with the first pretreatment circuit, the second pretreatment circuit, third respectively
Processing circuit, the connection of long-range transceiver module;The first pretreatment circuit is connect with electric-field sensor;The second pretreatment electricity
Road is connect with leakage current sensor;The third pretreatment circuit is connect with temperature sensor;The long-range transceiver module leads to
Wireless network is crossed to connect with remote computer.
2. the insulator breakdown diagnostic device according to claim 1 based on Study On Reliability Estimation Method For Cold Standby Systems, feature
It is:A human-computer interaction device is further included, the human-computer interaction device is connect with MCU.
3. the insulator breakdown diagnostic device according to claim 1 based on Study On Reliability Estimation Method For Cold Standby Systems, feature
It is:The first pretreatment circuit, the second pretreatment circuit, third pretreatment circuit are based on Kalman filtering algorithm
Signal denoising processing circuit.
4. a kind of insulator breakdown diagnostic method based on Study On Reliability Estimation Method For Cold Standby Systems, it is characterised in that:Including following step
Suddenly:
Step S1:It is studied and live the Ageing of Insulators research, insulator is applied different former by artificial accelerated aging
Barrier, the electric signal sample information in the case of detection is corresponding, constructs insulator breakdown information training sample database, as neural network
Training sample;Step S2:By electric-field sensor, Leakage Current sensor, collection voltages signal, current signal use Kalman
Filtering algorithm carries out denoising to the signal of acquisition, obtains the feature samples U with fault messagei1,U01,I01, carried
The feature samples of fault message;
Step S3:The performance parameter of insulator health status pair can be reacted by being extracted from fault signature sample, obtain performance spy
Levy vector { x1,x2,...,xm, i=1,2 ..., m, m be Insulators Used number of parameters, and using performance parameter vector as
The input signal of Study On Reliability Estimation Method For Cold Standby Systems carries out this group of performance parameter analysis point with trained neural network
Class judges the specific fault type of insulator.
5. the insulator breakdown diagnostic method according to claim 4 based on Study On Reliability Estimation Method For Cold Standby Systems, feature
It is:Study On Reliability Estimation Method For Cold Standby Systems FCMAC is mainly by vector input layer, blurring layer, triggering strength layer, associative strength layer
It is formed with five part of network output layer;Wherein:Vector input layer:By feature vector { x1,x2,...,xi,...,xmIntroduce cerebellum
Model Neural CMAC networks;It is blurred layer:Using Gauss π membership function, the eigen vector of input is carried out at blurring
Reason;Trigger strength layer:For calculating triggering intensity of the input to association's unit;Associative strength layer:The triggering that third layer calculates
Intensity will trigger the associative strength associated in unit;Output layer:It sums, is exported to the associative strength of the 4th layer of triggering
Vector.
6. the insulator breakdown diagnostic method according to claim 4 based on Study On Reliability Estimation Method For Cold Standby Systems, feature
It is:The learning algorithm of Study On Reliability Estimation Method For Cold Standby Systems FCMAC declines BP algorithm using gradient, the specific steps are:Input shape
State vector calculates the reality output of network along neural network signal propagation direction, and is compared with desired output, calculates mesh
Scalar functions if target function value is unsatisfactory for error precision, are modified network weight using gradient descent method;It carries out again
Training, calculating target function, so cycle is until meeting error requirements;If target function value meets error, complete to train.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810049636.3A CN108181562A (en) | 2018-01-18 | 2018-01-18 | Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810049636.3A CN108181562A (en) | 2018-01-18 | 2018-01-18 | Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108181562A true CN108181562A (en) | 2018-06-19 |
Family
ID=62550933
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810049636.3A Pending CN108181562A (en) | 2018-01-18 | 2018-01-18 | Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108181562A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109116150A (en) * | 2018-08-03 | 2019-01-01 | 福州大学 | A kind of converters method for diagnosing faults based on Cerebellar Model Articulation Controller |
CN109142989A (en) * | 2018-06-14 | 2019-01-04 | 中国电力科学研究院有限公司 | Super UHV transmission line composite insulator live-working safety appraisal procedure |
CN109919936A (en) * | 2019-03-13 | 2019-06-21 | 国网重庆市电力公司电力科学研究院 | A kind of analysis method, device and the equipment of composite insulator operating status |
CN111539442A (en) * | 2019-11-25 | 2020-08-14 | 福州大学 | Processing method and processing system for power electronic abnormal data |
CN111914732A (en) * | 2020-07-28 | 2020-11-10 | 北京交通大学 | Insulation fault diagnosis method, device, equipment and computer readable storage medium |
CN112288153A (en) * | 2020-10-22 | 2021-01-29 | 福州大学 | Automatic optimization method for initial value weight of cerebellum model neural network fault diagnoser |
CN112504522A (en) * | 2020-11-27 | 2021-03-16 | 武汉大学 | Micro-pressure sensor based on brain-like calculation |
CN113252218A (en) * | 2021-05-12 | 2021-08-13 | 太原理工大学 | Insulator surface stress prediction method and prediction device |
EP3913383A1 (en) * | 2020-05-22 | 2021-11-24 | Rohde & Schwarz GmbH & Co. KG | Method and system for detecting anomalies in a spectrogram, spectrum or signal |
CN113759868A (en) * | 2021-08-16 | 2021-12-07 | 浙江运达风电股份有限公司 | Industrial Ethernet fault prediction method based on neural network |
CN114114052A (en) * | 2021-11-25 | 2022-03-01 | 福州大学 | Method for rapidly estimating SOH and SOC of battery based on shock response characteristic |
CN114611636A (en) * | 2022-05-11 | 2022-06-10 | 深圳市三江电气有限公司 | Method for realizing measured value analysis by fusing information of various sensors |
CN116148600A (en) * | 2023-04-20 | 2023-05-23 | 清华大学 | Method, device and equipment for correcting stress application line fault positioning model of aero-engine |
CN117517907A (en) * | 2024-01-04 | 2024-02-06 | 山东思极科技有限公司 | Insulation state monitoring method and system for transformer substation capacitive equipment |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103823165A (en) * | 2014-02-26 | 2014-05-28 | 国家电网公司 | Insulator pollution flashover pre-warning method and system based on leakage currents |
CN105116273A (en) * | 2015-08-26 | 2015-12-02 | 芜湖市凯鑫避雷器有限责任公司 | Insulator on-line monitoring system |
CN105158628A (en) * | 2015-08-26 | 2015-12-16 | 芜湖市凯鑫避雷器有限责任公司 | Power transmission line insulator pollution online monitoring system |
CN207817139U (en) * | 2018-01-18 | 2018-09-04 | 福州大学 | Insulator breakdown diagnostic device based on Study On Reliability Estimation Method For Cold Standby Systems |
-
2018
- 2018-01-18 CN CN201810049636.3A patent/CN108181562A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103823165A (en) * | 2014-02-26 | 2014-05-28 | 国家电网公司 | Insulator pollution flashover pre-warning method and system based on leakage currents |
CN105116273A (en) * | 2015-08-26 | 2015-12-02 | 芜湖市凯鑫避雷器有限责任公司 | Insulator on-line monitoring system |
CN105158628A (en) * | 2015-08-26 | 2015-12-16 | 芜湖市凯鑫避雷器有限责任公司 | Power transmission line insulator pollution online monitoring system |
CN207817139U (en) * | 2018-01-18 | 2018-09-04 | 福州大学 | Insulator breakdown diagnostic device based on Study On Reliability Estimation Method For Cold Standby Systems |
Non-Patent Citations (4)
Title |
---|
关盈 等: "一种模糊小脑模型神经网络及其仿真研究", vol. 28, no. 1, pages 70 - 73 * |
孙开林 等: "基于FCMAC的鲁棒自适应迭代学习控制算法", 《计算机系统应用》, vol. 20, no. 11 * |
孙祎 等: "模糊CMAC及其在机器人轨迹跟踪控制中的应用", 《控制理论与应用》, vol. 23, no. 1 * |
张冠军 等: "高压绝缘子远程在线检测诊断系统的初步研究", pages 7 - 9 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109142989B (en) * | 2018-06-14 | 2021-07-13 | 中国电力科学研究院有限公司 | Live-line work safety assessment method for composite insulator of ultra-high voltage transmission line |
CN109142989A (en) * | 2018-06-14 | 2019-01-04 | 中国电力科学研究院有限公司 | Super UHV transmission line composite insulator live-working safety appraisal procedure |
CN109116150A (en) * | 2018-08-03 | 2019-01-01 | 福州大学 | A kind of converters method for diagnosing faults based on Cerebellar Model Articulation Controller |
CN109919936A (en) * | 2019-03-13 | 2019-06-21 | 国网重庆市电力公司电力科学研究院 | A kind of analysis method, device and the equipment of composite insulator operating status |
CN109919936B (en) * | 2019-03-13 | 2023-05-30 | 国网重庆市电力公司电力科学研究院 | Method, device and equipment for analyzing running state of composite insulator |
CN111539442A (en) * | 2019-11-25 | 2020-08-14 | 福州大学 | Processing method and processing system for power electronic abnormal data |
EP3913383A1 (en) * | 2020-05-22 | 2021-11-24 | Rohde & Schwarz GmbH & Co. KG | Method and system for detecting anomalies in a spectrogram, spectrum or signal |
CN111914732A (en) * | 2020-07-28 | 2020-11-10 | 北京交通大学 | Insulation fault diagnosis method, device, equipment and computer readable storage medium |
CN112288153B (en) * | 2020-10-22 | 2022-06-14 | 福州大学 | Automatic optimization method for initial value weight of cerebellum model neural network fault diagnoser |
CN112288153A (en) * | 2020-10-22 | 2021-01-29 | 福州大学 | Automatic optimization method for initial value weight of cerebellum model neural network fault diagnoser |
CN112504522A (en) * | 2020-11-27 | 2021-03-16 | 武汉大学 | Micro-pressure sensor based on brain-like calculation |
CN113252218A (en) * | 2021-05-12 | 2021-08-13 | 太原理工大学 | Insulator surface stress prediction method and prediction device |
CN113252218B (en) * | 2021-05-12 | 2023-11-17 | 国网山西省电力公司电力科学研究院 | Insulator surface stress prediction method and prediction device |
CN113759868A (en) * | 2021-08-16 | 2021-12-07 | 浙江运达风电股份有限公司 | Industrial Ethernet fault prediction method based on neural network |
CN113759868B (en) * | 2021-08-16 | 2023-05-02 | 浙江运达风电股份有限公司 | Industrial Ethernet fault prediction method based on neural network |
CN114114052A (en) * | 2021-11-25 | 2022-03-01 | 福州大学 | Method for rapidly estimating SOH and SOC of battery based on shock response characteristic |
CN114611636A (en) * | 2022-05-11 | 2022-06-10 | 深圳市三江电气有限公司 | Method for realizing measured value analysis by fusing information of various sensors |
CN116148600A (en) * | 2023-04-20 | 2023-05-23 | 清华大学 | Method, device and equipment for correcting stress application line fault positioning model of aero-engine |
CN117517907A (en) * | 2024-01-04 | 2024-02-06 | 山东思极科技有限公司 | Insulation state monitoring method and system for transformer substation capacitive equipment |
CN117517907B (en) * | 2024-01-04 | 2024-03-22 | 山东思极科技有限公司 | Insulation state monitoring method and system for transformer substation capacitive equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108181562A (en) | Insulator breakdown diagnostic device and method based on Study On Reliability Estimation Method For Cold Standby Systems | |
CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
CN102122133B (en) | Self-adaption wavelet neural network abnormity detection and fault diagnosis classification system and method | |
EP3723046B1 (en) | Target tracking method and device | |
CN103838229B (en) | Diagnosis method and device of electric car | |
CN108447078A (en) | The interference of view-based access control model conspicuousness perceives track algorithm | |
CN104809722A (en) | Electrical device fault diagnosis method based on infrared thermography | |
CN111353450B (en) | Target recognition system and method based on heterogeneous electromagnetic perception information fusion | |
CN110163075A (en) | A kind of multi-information fusion method for diagnosing faults based on Weight Training | |
CN116934304B (en) | Intelligent power distribution room equipment operation maintenance management system and method thereof | |
CN111046840B (en) | Personnel safety monitoring method and system based on artificial intelligence in pollution remediation environment | |
CN108257365B (en) | Industrial alarm design method based on global uncertainty evidence dynamic fusion | |
CN110516742A (en) | A kind of distribution terminal fault distinguishing method and system based on Combination neural network model | |
CN111060779B (en) | Power grid partition fault diagnosis method and system based on probabilistic neural network | |
CN115204302A (en) | Unmanned aerial vehicle small sample fault diagnosis system and method | |
CN202119467U (en) | Self-adaptive wavelet neural network categorizing system of anomaly detection and fault diagnosis | |
Liao et al. | A channel-spatial-temporal attention-based network for vibration-based damage detection | |
CN108764541B (en) | Wind energy prediction method combining space characteristic and error processing | |
CN115980560A (en) | CNN-GRU-based high-voltage circuit breaker mechanical fault diagnosis system, method and equipment | |
CN114048546A (en) | Graph convolution network and unsupervised domain self-adaptive prediction method for residual service life of aircraft engine | |
CN113358993A (en) | Online fault diagnosis method and system for multi-level converter IGBT | |
CN117156442A (en) | Cloud data security protection method and system based on 5G network | |
CN113033624A (en) | Industrial image fault diagnosis method based on federal learning | |
CN115510950A (en) | Aircraft telemetry data anomaly detection method and system based on time convolution network | |
CN106301610A (en) | The adaptive failure detection of a kind of superhet and diagnostic method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180619 |
|
RJ01 | Rejection of invention patent application after publication |