CN110411580B - Diagnosis method and diagnosis system for heating defects of electric equipment - Google Patents
Diagnosis method and diagnosis system for heating defects of electric equipment Download PDFInfo
- Publication number
- CN110411580B CN110411580B CN201910717499.0A CN201910717499A CN110411580B CN 110411580 B CN110411580 B CN 110411580B CN 201910717499 A CN201910717499 A CN 201910717499A CN 110411580 B CN110411580 B CN 110411580B
- Authority
- CN
- China
- Prior art keywords
- defect
- data
- heating
- infrared
- power equipment
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 156
- 238000010438 heat treatment Methods 0.000 title claims abstract description 101
- 238000003745 diagnosis Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000003384 imaging method Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims abstract description 10
- 238000012360 testing method Methods 0.000 claims abstract description 8
- 238000001931 thermography Methods 0.000 claims abstract description 8
- 238000001514 detection method Methods 0.000 claims description 45
- 238000012795 verification Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000020169 heat generation Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009529 body temperature measurement Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/10—Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a diagnosis method and a diagnosis system for heating defects of electric equipment, wherein the diagnosis method comprises the following steps: extracting infrared temperature data corresponding to various heating defects of the power equipment from historical field test data; preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power equipment; the defect data at least comprises an infrared thermal imaging graph, an infrared dot matrix temperature graph, a visible light imaging graph and a key measuring point temperature mark of the power equipment; training a deep convolutional neural network by using the defect data of the power equipment and the heating defect type label to obtain a heating defect diagnosis model; the input data of the heating defect model is defect data of the electric power equipment, the output data is a heating defect diagnosis result of the electric power equipment, and the diagnosis result comprises whether a heating defect exists and the type of the heating defect; and acquiring defect data of the power equipment to be diagnosed and inputting the defect data into the heating defect diagnosis model to obtain a heating defect diagnosis result.
Description
Technical Field
The invention belongs to the technical field of infrared live detection of electrical equipment, and particularly relates to a method and a system for diagnosing heating defects of electrical equipment.
Background
With the continuous development of the state maintenance work of the power equipment, the infrared temperature measurement is increasingly applied to the daily maintenance of the power equipment as an important means for detecting the state of the power equipment. At present most infrared detection work still relies on fortune dimension personnel to pass through electrified detecting instrument and accomplishes, relies on personnel to carry out electrified detection alone and has following problem effectively to solve in the operation process of reality:
1. most infrared detection devices do not have a data diagnosis function, and detection personnel need to analyze and judge data automatically in the detection process. The infrared detection data amount is large, a large amount of time is consumed for manual analysis and judgment, and the detection efficiency is seriously influenced. And the voltage heating type heating fault diagnosis usually needs long-term experience accumulation to be accurate, has higher requirement on the professional skills of detection personnel, and is not beneficial to the development of infrared charged detection work on the power grid base.
2. The diagnosis function of the partial infrared detection device cannot meet the requirement of field practical application. In field application, because the expression forms of the heating defect types of the power equipment are complex and various, and a large amount of interference exists, the diagnosis function of the detection device is difficult to accurately identify the heating defect types, misjudgment can be generated in the use process, and misguidance is caused to the judgment of charged detection personnel and subsequent maintenance strategies.
Disclosure of Invention
The invention aims to provide a method and a system for diagnosing heating defects of electric equipment.
In one aspect, a method for diagnosing a heating defect of an electrical device includes the following steps:
step S1: extracting infrared temperature data corresponding to various heating defects of the power equipment from historical field test data;
step S2: preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power equipment;
the defect data at least comprises an infrared thermal imaging graph, an infrared dot matrix temperature graph, a visible light imaging graph and a key measuring point temperature mark of the power equipment;
step S3: training a deep convolutional neural network by using the defect data of the power equipment and the heating defect type label in the step S2 to obtain a heating defect diagnosis model;
the input data of the heating defect diagnosis model is defect data of the electric power equipment, and the output data is a heating defect diagnosis result of the electric power equipment, wherein the diagnosis result comprises whether a heating defect exists and the type of the heating defect;
step S4: acquiring infrared temperature data of the power equipment to be diagnosed, and preprocessing the infrared temperature data to obtain defect data;
step S5: the defect data of step S4 is input to the heat generation defect diagnosis model of step S3 to obtain a heat generation defect diagnosis result.
Further preferably, the defect data of the power equipment and the heat defect type labels acquired in step S2 are divided according to a preset ratio to obtain a training set and a verification set, each sample in the training set and the verification set corresponds to a group of defect data of the power equipment and a heat defect type label, wherein the heat defect diagnosis model in step S3 is obtained by using a training deep convolutional neural network of the training set, and the training process is as follows:
s31: inputting the defect data of the samples in the training set into a deep convolution neural network as input data;
s32: in the forward propagation process, input graphic data are subjected to convolution and pooling of multilayer convolution layers, feature vectors are extracted, and the feature vectors are transmitted into a full-link layer to obtain a classification recognition result;
s33: obtaining a heating defect diagnosis result according to the classification identification result, comparing the heating defect diagnosis result with an expected value, and if the heating defect diagnosis result does not accord with the expected value, executing S34 to perform a back propagation process;
if the defect diagnosis result is consistent with the defect diagnosis result, inputting the defect diagnosis result;
s34: calculating the error between the heating defect diagnosis result and the expected value, judging whether the error is smaller than the expected error, and outputting a deep convolution neural network if the error is smaller than the expected error; otherwise, the errors of the full connection layer, the down sampling layer and the convolution layer are calculated in sequence according to the errors, the weight of each layer is updated based on the errors of each layer respectively to obtain an updated deep convolutional neural network, and the step S31 is returned.
Preferably, the trained deep convolutional neural network is verified by using defect data of the verification centralized power equipment, and the process is as follows:
firstly, inputting defect data of each sample in a verification set into a trained deep convolutional neural network to obtain a heating diagnosis result of the power equipment;
then, identifying whether the heating diagnosis result is correct or not based on the heating defect type label corresponding to the sample to obtain the accuracy of the verification set;
and finally, adjusting the model parameters according to the accuracy to obtain a heating defect diagnosis model.
Further preferably, the step S2 of preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power device is as follows:
s21: constructing a power transformation equipment target tree according to an actual scene where the power equipment is located, equipment types and equipment components;
s22: classifying the collected infrared temperature data according to a target tree of the power transformation equipment;
s23: pre-dividing an infrared video image and extracting a target area according to the imaging characteristics of power transformation equipment in different microclimate environments;
s24: smoothing the extracted area by using a filtering algorithm to generate an infrared thermal imaging graph, an infrared dot matrix temperature graph, a visible light imaging graph and a key measuring point temperature mark of the equipment to be analyzed.
Further preferably, the infrared temperature data in step S1 is collected by using infrared sensors, where the infrared sensors include a handheld infrared thermal imager, a dot matrix infrared temperature sensor, and a non-contact infrared thermometer.
On the other hand, the diagnosis system based on the method provided by the invention comprises an infrared sensor, an infrared charged detection device and a cloud platform which are sequentially connected;
the infrared sensor is used for acquiring infrared temperature data corresponding to various heating defects of the power equipment;
the infrared electrified detection device comprises a data acquisition module, a data comprehensive processing module and a data communication module, wherein the data acquisition module acquires infrared temperature data from an infrared sensor, and the data comprehensive processing module is used for preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power equipment;
the cloud platform is used for constructing a heating defect diagnosis model, diagnosing heating defects of the power equipment in real time by using the heating defect diagnosis model, transmitting a diagnosis result to the infrared electrified detection device, and receiving the diagnosis result by the infrared electrified detection device through the data communication module.
Preferably, the infrared sensor is in wired or wireless connection with the infrared live detection device, and the infrared live detection device is connected with the cloud platform through a 4G communication network.
Advantageous effects
1. According to the invention, the heating defect diagnosis model is obtained by utilizing the deep convolution neural network training model, so that the reliability of the heating defect diagnosis result of the power equipment is improved, the heating defect diagnosis automation of the power equipment is realized, the technical requirements on field live detection personnel can be effectively reduced, the detection personnel can complete infrared live detection and diagnosis without accumulating related experience, and the popularization of the infrared live detection work at the basic level is facilitated.
2. The invention realizes real-time diagnosis by using the heating defect diagnosis model, can greatly improve the infrared live detection efficiency and effectively improve the real-time performance of field data diagnosis.
3. The invention simultaneously utilizes infrared thermal imaging graph, infrared lattice temperature graph, visible light imaging graph and key measuring point temperature mark, and the data are closely related to the heating defect.
Drawings
FIG. 1 is a schematic diagram of an architecture of a system for diagnosing a thermal defect of an electrical device according to the present invention;
FIG. 2 is a schematic diagram of a diagnostic flow process based on the diagnostic system provided by the present invention;
fig. 3 is a schematic flow chart of a method for diagnosing a heating defect of an electrical device according to the present invention.
Detailed Description
The present invention will be further described with reference to the following examples.
As shown in fig. 1, the system for diagnosing heating defects of electrical equipment provided by the present invention includes an infrared sensor, an infrared charged detection device, and a cloud platform, which are connected in sequence. The infrared sensor is wirelessly or wiredly connected with the infrared electrified detection device, and the infrared electrified detection device is in communication connection with the cloud platform through a 4G network.
In this embodiment, the infrared sensor includes a handheld infrared thermal imager, a dot matrix infrared temperature sensor, and a non-contact infrared thermometer.
In this embodiment, the infrared live detection device includes a data acquisition module, a data comprehensive processing module, a data communication module, a data display module, and a data storage module. The data acquisition module acquires infrared temperature data from the infrared sensor. And the data comprehensive processing module is used for preprocessing the infrared temperature data to obtain defect data of the power equipment. The defect data comprises an infrared thermal imaging graph, an infrared dot matrix temperature graph, a visible light imaging graph and a key measuring point temperature mark of the power equipment.
The data storage module is used for storing defect data and diagnosis results fed back by the cloud platform, and the data display module is used for displaying the diagnosis results or displaying other critical information.
As shown in fig. 2, the cloud platform is configured to construct a heating defect diagnosis model by using the method for diagnosing a heating defect of an electrical device according to the present invention, and diagnose defect data acquired in real time to obtain a diagnosis result. And finally, the diagnosis result is transmitted to the infrared live-line detection device through the data communication module, so that field live-line detection personnel can master the detection result and the equipment running state at the first time, the live-line detection personnel do not need to carry out data diagnosis, the requirement of the field infrared live-line detection on the skills of the personnel is reduced, and the field work efficiency can be effectively improved.
As shown in fig. 3, the method for diagnosing a heating defect of an electrical device according to the present invention includes the following steps:
step S1: and extracting infrared temperature data corresponding to various heating defects of the power equipment from historical field test data. Wherein, the infrared temperature data corresponding to various heating defects are extracted from the accumulated field test data.
Step S2: and preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power equipment. In this embodiment, the acquired defect data of the power equipment is divided by 80%, 10% and 10% to obtain a training set, a verification set and a test set corresponding to the heating defect type label. Each sample in the training set, the verification set and the test set corresponds to a group of defect data and a heating defect type label of the power equipment. Training set data is used for training the deep convolution neural network, and verification machine data is used for adjusting the network after training of the training set and performing overfitting adjustment. And the test set data is used for judging the quality of the obtained heating defect diagnosis model. In other possible embodiments, the above-mentioned sets may be divided in other proportions, and only the training set or only the training set and the validation set may exist. The present invention is not particularly limited in this regard.
The process of preprocessing the infrared temperature data comprises the following steps:
s21: constructing a power transformation equipment target tree according to an actual scene where the power equipment is located, equipment types and equipment components;
s22: classifying the collected infrared temperature data according to a target tree of the power transformation equipment;
s23: pre-dividing an infrared video image and extracting a target area according to the imaging characteristics of power transformation equipment in different microclimate environments;
s24: smoothing the extracted area by using a filtering algorithm to generate an infrared thermal imaging graph, an infrared dot matrix temperature graph, a visible light imaging graph and a key measuring point temperature mark of the equipment to be analyzed.
Step S3: training a deep convolutional neural network by using the defect data of the power equipment and the heating defect type label in the step S2 to obtain a heating defect diagnosis model;
the input data of the heating defect diagnosis model is defect data of the electric power equipment, and the output data is a heating defect diagnosis result of the electric power equipment, wherein the diagnosis result comprises whether a heating defect exists and the type of the heating defect. The generation process of the heating defect diagnosis model in this embodiment includes two major parts, namely, training the deep convolutional neural network by using the training set, and then adjusting the trained neural network by using the validation set to obtain the heating defect diagnosis model. In other possible embodiments, if only the training set exists, the training set may be used to train and obtain the heat defect diagnosis model.
Wherein the training process is as follows:
s31: inputting the defect data of the samples in the training set into a deep convolution neural network as input data;
s32: in the forward propagation process, input graphic data are subjected to convolution and pooling of multilayer convolution layers, feature vectors are extracted, and the feature vectors are transmitted into a full-link layer to obtain a classification recognition result;
s33: obtaining a heating defect diagnosis result according to the classification identification result, comparing the heating defect diagnosis result with an expected value, and if the heating defect diagnosis result does not accord with the expected value, executing S34 to perform a back propagation process;
if the detected data is consistent with the defect detection result, outputting a defect diagnosis result;
s34: calculating the error between the heating defect diagnosis result and the expected value, judging whether the error is smaller than the expected error, and outputting a deep convolution neural network if the error is smaller than the expected error; otherwise, the errors of the full connection layer, the down sampling layer and the convolution layer are calculated in sequence according to the errors, the weight of each layer is updated based on the errors of each layer respectively to obtain an updated deep convolutional neural network, and the step S31 is returned.
After the deep convolutional neural network is trained by using the data of the training set, the deep convolutional neural network is verified by using the data in the verification set, and the process is as follows:
s35: inputting the defect data of each sample in the verification set into the trained deep convolutional neural network to obtain a heating diagnosis result of the power equipment;
s36: identifying whether the heating diagnosis result is correct or not based on the heating defect type label corresponding to the sample to obtain the accuracy of the verification set;
s37: and adjusting the model parameters according to the accuracy to obtain a heating defect diagnosis model.
Step S4: acquiring infrared temperature data of the power equipment to be diagnosed, and preprocessing the infrared temperature data to obtain defect data;
step S5: the defect data of step S4 is input to the heat generation defect diagnosis model of step S3 to obtain a heat generation defect diagnosis result.
By the method, the heating defect diagnosis result can be obtained in real time and transmitted to the infrared live detection device, so that live detection personnel can provide judgment basis in time, and the field live detection personnel can master the detection result and the equipment running state at the first time.
It should be emphasized that the examples described herein are illustrative and not restrictive, and thus the invention is not to be limited to the examples described herein, but rather to other embodiments that may be devised by those skilled in the art based on the teachings herein, and that various modifications, alterations, and substitutions are possible without departing from the spirit and scope of the present invention.
Claims (5)
1. A method for diagnosing a heating defect of an electric power device is characterized in that: the method comprises the following steps:
step S1: extracting infrared temperature data corresponding to various heating defects of the power equipment from historical field test data;
step S2: preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power equipment;
the defect data at least comprises an infrared thermal imaging graph, an infrared dot matrix temperature graph, a visible light imaging graph and a key measuring point temperature mark of the power equipment;
step S3: training a deep convolutional neural network by using the defect data of the power equipment and the heating defect type label in the step S2 to obtain a heating defect diagnosis model;
the input data of the heating defect diagnosis model is defect data of the electric power equipment, and the output data is a heating defect diagnosis result of the electric power equipment, wherein the diagnosis result comprises whether a heating defect exists and the type of the heating defect;
step S4: acquiring infrared temperature data of the power equipment to be diagnosed, and preprocessing the infrared temperature data to obtain defect data;
step S5: inputting the defect data of the step S4 into the heat defect diagnosis model of the step S3 to obtain the heat defect diagnosis result
The defect data of the power equipment and the heating defect type labels acquired in the step S2 are divided according to a preset proportion to obtain a training set and a verification set, each sample in the training set and the verification set corresponds to a group of defect data of the power equipment and a heating defect type label, wherein the heating defect diagnosis model in the step S3 is obtained by using a training deep convolutional neural network of the training set, and the training process is as follows:
s31: inputting the defect data of the samples in the training set into a deep convolution neural network as input data;
s32: in the forward propagation process, input graphic data are subjected to convolution and pooling of multilayer convolution layers, feature vectors are extracted, and the feature vectors are transmitted into a full-link layer to obtain a classification recognition result;
s33: obtaining a heating defect diagnosis result according to the classification identification result, comparing the heating defect diagnosis result with an expected value, and if the heating defect diagnosis result does not accord with the expected value, executing S34 to perform a back propagation process;
if the detected data is consistent with the defect detection result, outputting a defect diagnosis result;
s34: calculating the error between the heating defect diagnosis result and the expected value, judging whether the error is smaller than the expected error, and outputting a deep convolution neural network if the error is smaller than the expected error; otherwise, the errors of the full connection layer, the down sampling layer and the convolution layer are calculated in sequence according to the errors, the weight of each layer is updated based on the errors of each layer respectively to obtain an updated deep convolution neural network, and the step S31 is returned;
the trained deep convolutional neural network is verified by utilizing defect data of the verification centralized power equipment, and the process is as follows:
s35: inputting the defect data of each sample in the verification set into the trained deep convolutional neural network to obtain a heating diagnosis result of the power equipment;
s36: identifying whether the heating diagnosis result is correct or not based on the heating defect type label corresponding to the sample to obtain the accuracy of the verification set;
s37: and adjusting the model parameters according to the accuracy to obtain a heating defect diagnosis model.
2. The method of claim 1, wherein: the process of preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power equipment in the step S2 is as follows:
s21: constructing a power transformation equipment target tree according to an actual scene where the power equipment is located, equipment types and equipment components;
s22: classifying the collected infrared temperature data according to a target tree of the power transformation equipment;
s23: pre-dividing an infrared video image and extracting a target area according to the imaging characteristics of power transformation equipment in different microclimate environments;
s24: smoothing the extracted area by using a filtering algorithm to generate an infrared thermal imaging graph, an infrared dot matrix temperature graph, a visible light imaging graph and a key measuring point temperature mark of the equipment to be analyzed.
3. The method of claim 1, wherein: the infrared temperature data in step S1 is acquired by using an infrared sensor, where the infrared sensor includes a handheld infrared thermal imager, a dot-matrix infrared temperature sensor, and a non-contact infrared thermometer.
4. A diagnostic system based on the method of any one of claims 1 to 3, wherein: the system comprises an infrared sensor, an infrared electrified detection device and a cloud platform which are connected in sequence;
the infrared sensor is used for acquiring infrared temperature data corresponding to various heating defects of the power equipment;
the infrared electrified detection device comprises a data acquisition module, a data comprehensive processing module and a data communication module, wherein the data acquisition module acquires infrared temperature data from an infrared sensor, and the data comprehensive processing module is used for preprocessing the infrared temperature data to obtain defect data corresponding to various heating defects of the power equipment;
the cloud platform is used for constructing a heating defect diagnosis model, performing heating defect diagnosis on the power equipment in real time by using the heating defect diagnosis model, and transmitting a diagnosis result to the infrared charged detection device, and the infrared charged detection device receives the diagnosis result through the data communication module;
data comprehensive processing module the data comprehensive processing module.
5. The diagnostic system of claim 4, wherein: the infrared sensor is connected with the infrared live detection device in a wired or wireless mode, and the infrared live detection device is connected with the cloud platform through a 4G communication network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717499.0A CN110411580B (en) | 2019-08-05 | 2019-08-05 | Diagnosis method and diagnosis system for heating defects of electric equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717499.0A CN110411580B (en) | 2019-08-05 | 2019-08-05 | Diagnosis method and diagnosis system for heating defects of electric equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110411580A CN110411580A (en) | 2019-11-05 |
| CN110411580B true CN110411580B (en) | 2021-03-16 |
Family
ID=68365859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910717499.0A Active CN110411580B (en) | 2019-08-05 | 2019-08-05 | Diagnosis method and diagnosis system for heating defects of electric equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110411580B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110907038A (en) * | 2019-11-07 | 2020-03-24 | 武汉多谱多勒科技有限公司 | Power equipment infrared thermal imaging monitoring system based on artificial intelligence |
| CN111121971B (en) * | 2019-12-18 | 2021-09-03 | 广西电网有限责任公司电力科学研究院 | Method for judging fault type through surface temperature change of high-voltage switch cabinet |
| CN113686031B (en) * | 2020-05-19 | 2022-06-24 | 山东大学 | Loop heat pipe solar liquid level pattern recognition method based on machine learning |
| CN111929542B (en) * | 2020-07-03 | 2023-05-26 | 北京国网富达科技发展有限责任公司 | Power equipment diagnosis method and system |
| CN112698615A (en) * | 2020-11-10 | 2021-04-23 | 四川省东宇信息技术有限责任公司 | Equipment fault feedback system based on cloud platform |
| CN113310580A (en) * | 2021-05-28 | 2021-08-27 | 国网江苏省电力有限公司电力科学研究院 | Infrared diagnosis method and system for substation equipment |
| CN114241727A (en) * | 2021-11-26 | 2022-03-25 | 国网新疆电力有限公司巴州供电公司 | Intelligent diagnosis early warning system, method and device for power transformation equipment |
| CN116247824B (en) * | 2023-03-30 | 2023-11-17 | 国网河南省电力公司安阳供电公司 | Control method and system for power equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7202794B2 (en) * | 2004-07-20 | 2007-04-10 | General Monitors, Inc. | Flame detection system |
| CN103617469B (en) * | 2013-12-18 | 2016-09-14 | 重庆大学 | Power system device failure prediction method and system |
| CN108564565A (en) * | 2018-03-12 | 2018-09-21 | 华南理工大学 | A kind of power equipment infrared image multi-target orientation method based on deep learning |
| CN109783560A (en) * | 2019-01-16 | 2019-05-21 | 江苏圣通电力新能源科技有限公司 | The detection method of status of electric power based on deep learning multiple features fusion |
-
2019
- 2019-08-05 CN CN201910717499.0A patent/CN110411580B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110411580A (en) | 2019-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110411580B (en) | Diagnosis method and diagnosis system for heating defects of electric equipment | |
| CN110598736B (en) | Power equipment infrared image fault positioning, identifying and predicting method | |
| CN103901072B (en) | Method for diagnosing equipment overheating defects by utilizing infrared spectrum analysis | |
| CN109800697B (en) | Transformer target detection and appearance defect identification method based on VGG-net style migration | |
| CN103439342B (en) | Based on the Infrared Non-destructive Testing method of thermal map temporal aspect | |
| CN104913797A (en) | Pointer type instrument number reading and recognition method and system | |
| CN112669305B (en) | Metal surface rust resistance test bench and rust resistance evaluation method | |
| CN110412431A (en) | A kind of diagnostic method and diagnostic system of the shelf depreciation defect type of power equipment | |
| RU2007103326A (en) | METHOD OF REPAIR AND MAINTENANCE AND APPLICABLE IN THE METHOD OF HARDWARE-SOFTWARE COMPLEX FOR DIAGNOSTICS AND SYSTEM FOR CONTROL OF QUALITY OF REPAIR AND MAINTENANCE | |
| CN109374631A (en) | A kind of tunnel state evaluating method | |
| CN111753877B (en) | Product quality detection method based on deep neural network migration learning | |
| CN116308958A (en) | Carbon emission online detection and early warning system and method based on mobile terminal | |
| CN115327270A (en) | Transformer small sample fault diagnosis system based on data-model driving | |
| CN116629627A (en) | Intelligent detection system of power transmission on-line monitoring device | |
| CN116552306B (en) | Monitoring system and method for direct current pile | |
| CN107316131A (en) | A kind of electric power meter mounting process quality detecting system based on image recognition | |
| CN114662619B (en) | Bridge monitoring system based on multi-source data fusion | |
| CN116933626A (en) | Data monitoring method and device based on digital twinning | |
| CN115953436A (en) | Intelligent assessment early warning method and system for pregnant pet behavior | |
| CN116399462A (en) | Digital visual cable temperature sensing early warning method and system | |
| TWM595226U (en) | Intelligent detection equipment for power equipment failure | |
| CN109592525A (en) | Elevator frequency converter fault diagnosis system and method | |
| CN113033845B (en) | Construction method and device for power transmission resource co-construction and sharing | |
| CN115841446A (en) | Rapid detection system and method for fault risk of solar heat collection field | |
| CN113358750A (en) | Boundary element method-based electrical equipment acoustic imaging method and system |
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 |