CN112305388B - On-line monitoring and diagnosing method for insulation partial discharge faults of generator stator winding - Google Patents
On-line monitoring and diagnosing method for insulation partial discharge faults of generator stator winding Download PDFInfo
- Publication number
- CN112305388B CN112305388B CN202011197314.7A CN202011197314A CN112305388B CN 112305388 B CN112305388 B CN 112305388B CN 202011197314 A CN202011197314 A CN 202011197314A CN 112305388 B CN112305388 B CN 112305388B
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- data
- sample
- insulation
- model
- 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
- 238000009413 insulation Methods 0.000 title claims abstract description 54
- 238000012544 monitoring process Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000004804 winding Methods 0.000 title claims abstract description 18
- 238000003745 diagnosis Methods 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000006243 chemical reaction Methods 0.000 claims abstract description 8
- 238000003384 imaging method Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000002265 prevention Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 2
- 238000002372 labelling Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 10
- 238000001514 detection method Methods 0.000 description 8
- 238000007405 data analysis Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000011900 installation process Methods 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 238000009421 internal insulation Methods 0.000 description 1
- 230000016507 interphase Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009736 wetting 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
- G01R31/1263—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
-
- 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
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/72—Testing of electric windings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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 an online monitoring and diagnosing method for insulation partial discharge faults of a generator stator winding, which comprises the following steps: partial discharge online monitoring data conversion and partial discharge data imaging representation; establishing an insulation partial discharge characteristic database; modeling and training a diagnosis model; and (5) model application. The invention provides objective data support for manual diagnosis, reduces the threshold required by manual diagnosis experience, and has great application value and popularization significance in the current large environment for state maintenance.
Description
Technical Field
The invention relates to the field of generators, in particular to an online monitoring and diagnosing method for insulation partial discharge faults of a generator stator winding.
Background
The stator winding of the core component of the hydraulic generator exchanges energy through the electromagnetic induction principle, and the stator winding is required to bear the action of continuously changing mechanical force, electric field and heat in the working process, and the insulation performance and service life of the stator winding are also slowly changed. The stator winding insulation can cause different small insulation defects such as internal insulation gaps, gap burrs caused by winding end binding, too small inter-phase distance, closer distance between a secondary lead and a winding end, corona in a wire rod groove, end corona, surface dirt, insulation wetting and the like on the inside or the surface of the stator winding insulation of the generator due to different production and manufacturing processes, different used insulation materials, site installation process differences and the like, so that the insulation always has partial discharge in the running state of the generator. In general, different defects are superimposed on each other, and only one defect rarely exists, so that partial discharge is different from machine to machine when superimposed on each other.
The partial discharge spectrum of the defect characterization is more pronounced as the development of certain defects worsens with increasing operational life. By detecting partial discharges of the stator insulation of the hydro-generator and diagnosing the presence of major defects in the insulation, it is necessary to monitor the development of defects and to control them during maintenance.
The existing partial discharge on-line monitoring of the hydraulic generator mainly collects partial discharge signals in insulation through a sensor, and has no diagnosis capability through software record storage, statistics and graphic display, and fault identification and diagnosis still need to be identified through experience by a professional, but the partial discharge signals are complex in data, large in fluctuation and have no corresponding fault map, so that manual diagnosis is difficult.
Disclosure of Invention
In order to overcome the defects that the existing hydraulic generator insulation partial discharge online detection device only detects recorded data and has no analysis and diagnosis capability, the partial discharge data is complex, and the manual diagnosis and analysis are difficult. On the basis of the existing generator insulation partial discharge on-line detection data, the invention adopts a big data analysis method, combines deep learning, builds model training, is applied to analysis and diagnosis of the existing partial discharge on-line detection data, determines faults existing in generator insulation, and provides an on-line monitoring and diagnosis method for generator stator winding insulation partial discharge faults.
The invention supplements the defect that the existing generator insulation partial discharge online detection system only detects recorded data and has no analysis and diagnosis capability, also provides objective data support for manual diagnosis, simplifies manual analysis and reduces the threshold required by manual diagnosis experience.
The technical scheme of the invention is as follows:
an on-line monitoring and diagnosing method for insulation partial discharge faults of a stator winding of a generator comprises the following steps:
step (1), partial discharge on-line monitoring data conversion and partial discharge data imaging representation
Deriving partial discharge original data from a partial discharge online monitoring system, extracting a sample positive partial discharge amplitude value, a positive partial discharge phase and a positive partial discharge quantity data set d1 from the partial discharge original data one by one, combining the data d1 and d2 into a partial discharge sample original data set with positive and negative partial discharge amplitude values, positive and negative partial discharge phases and positive and negative partial discharge quantity;
converting the original sample data set into a gray level diagram, and drawing a 50HZ positive brown wave curve under the same coordinate of the gray level diagram to obtain a partial discharge sample image;
step (2), establishing an insulation partial discharge characteristic database
The method comprises the steps of leading out partial discharge original data from a partial discharge online monitoring system, extracting sample acquisition time, sample number, measurement state, station and generator information from the partial discharge original data one by one to form sample information data, extracting positive and negative discharge quantity Qm and positive and negative discharge quantity NQN from the sample one by one to form sample partial discharge comprehensive data; labeling generator insulation faults according to the sequence of 0-9 to form a sample fault code table, and adding the generator insulation fault codes corresponding to the partial discharge samples one by one according to the sample sequence to form sample label data;
packaging the sample information data, the sample partial discharge comprehensive data, the partial discharge original data and the sample label data to form an insulation partial discharge characteristic data set, and continuously collecting new samples according to different insulation states of the generator to form an insulation partial discharge characteristic database;
step (3), modeling and training of diagnostic models
Establishing a deep learning model A through a convolutional neural network, inputting partial discharge original data and sample tag data in an insulation partial discharge characteristic database into the model A, and performing learning training on the model;
model a training: sampling a multi-classification loss function, adopting a self-adaptive learning rate optimization algorithm, monitoring index accuracy, and obtaining a model parameter A.h5 through multi-round and multi-batch learning training;
step (4) model application
And (3) inputting sample original data of unknown faults into a well-learned model A, and outputting fault type percentage probability of the samples after calculation of the model A and parameters A.h5.
Further, in step (1), the gray scale image uses the phase 0 to 360 degrees as the x-axis coordinate and the amplitude-30 to 30 as the y-axis coordinate, the x-axis position of the gray scale image pixel point represents the phase of the discharge, the y-axis position of the gray scale image pixel point represents the amplitude value of the discharge, and the color depth of the pixel point value represents the discharge quantity.
In the step (3), a model A is specifically a partial discharge data image diagnosis and identification model constructed through a convolutional neural network.
Further, in the step (3), when the model a is built, 30×100×1 image data is input into the model, 2 times of convolution calculation are performed in the network, the number of convolution kernels with the size of 3X3 at the 1 st time is 32, the number of convolution kernels with the size of 3X3 at the 2 nd time is 64, and the parameters of 4 overfitting prevention probability layers are all 0.25; the structure is input, convolution, probability, pooling, conversion, probability, full connection, probability, output in sequence.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention establishes a partial discharge on-line monitoring data conversion and partial discharge data imaging representation method, completely reserves partial discharge characteristic information contained in a partial discharge sample, and provides an analysis basis for partial discharge big data analysis.
The invention builds model training by adopting a big data analysis method on the basis of the existing partial discharge on-line detection data of the generator insulation, and is applied to the analysis and diagnosis of the existing partial discharge on-line detection data to determine the faults of the generator insulation. The invention supplements the defect that the existing generator insulation partial discharge online detection system only detects recorded data and has no analysis and diagnosis capability, also provides objective data support for manual diagnosis, and reduces the threshold required by manual diagnosis experience. Has great application value and popularization significance in the current large environment for state maintenance.
2. The invention can be changed along with the development of the insulation fault of the on-site generator, and a new characteristic sample is added, so that the characteristic database sample versatility is facilitated, and a rich sample library is established.
3. The model is built through the deep learning convolutional neural network, and the model is trained through the imaging partial discharge data, so that the model can be retrained along with the updating of the characteristic database in use, and the type and accuracy of fault identification are improved.
4. The invention supplements the defect that the existing generator insulation partial discharge online detection system only detects recorded data and has no analysis and diagnosis capability, also provides objective data support for manual diagnosis, simplifies manual analysis and reduces the threshold required by manual diagnosis experience.
Drawings
Fig. 1 is a partial discharge data image, where the x-axis position of a gray-scale pixel point represents the phase of the discharge, the y-axis position of the gray-scale pixel point represents the magnitude of the discharge, and the color depth of the pixel point represents the discharge quantity.
Fig. 2 is a diagram of a model a.
Fig. 3 is a model training result, wherein the upper graph is a training process accuracy improvement curve, and the lower graph is a training process loss reduction curve.
FIG. 4 shows the input samples and the output diagnostic results after model diagnosis according to the embodiment.
Detailed Description
The following description of the embodiments will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. Based on the embodiments, all other embodiments that may be obtained by a person of ordinary skill in the art without making any inventive effort are within the scope of the present invention.
Unless otherwise defined, technical or scientific terms used in the embodiments of the present application should be given a general meaning as understood by one of ordinary skill in the art. The terms "first," "second," and the like, as used in this embodiment, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. "upper", "lower", "left", "right", "transverse", and "vertical", etc. are used only with respect to the orientation of the components in the drawings, these directional terms are relative terms, which are used for descriptive and clarity with respect thereto and which may vary accordingly with respect to the orientation in which the components are disposed in the drawings.
The embodiment adopts python3.7 programming language and keras deep learning library to construct a model, train and apply the model.
The on-line monitoring and diagnosing method for the insulation partial discharge faults of the stator winding of the generator comprises the following steps:
step (1), partial discharge on-line monitoring data conversion and partial discharge data imaging representation
And (3) deriving a partial discharge data file from the partial discharge online monitoring system, extracting a sample positive partial discharge amplitude value, a positive partial discharge phase and a positive partial discharge quantity data set d1 from the partial discharge online monitoring system one by one, merging the data d1 and d2 into a partial discharge sample original data set with positive and negative partial discharge amplitude values, positive and negative partial discharge phases and positive and negative partial discharge quantity, wherein the data set is a complete data file with new amplitude value, phase and quantity representations, and is shown as sample original data c in partial discharge characteristic data in table 1.
TABLE 1 partial discharge characteristic dataset
Table 1 is a partial discharge data sample collected by the generator insulation on-line monitoring device, wherein sample information data a comprises collection time, sample number, measurement state, station and generator phase; sample tag data b representing a coded series of sample fault types; sample original data c, partial discharge characteristic data extracted from partial discharge on-line monitoring system data, wherein a 30 x 100 matrix of data form comprises discharge amplitude, quantity and phase information; the sample partial discharge comprehensive data d comprises partial discharge amplitude value + -Qm and quantity + -NQN data, namely the maximum discharge amplitude value calculated by the system and the total discharge quantity.
And converting the sample original data c into a gray level image with the phase 0 to 360 degrees as an x-axis coordinate and the amplitude-30 to 30 as a y-axis coordinate, wherein the x-axis position of a gray level image pixel point represents the phase of discharge, the y-axis position of the gray level image pixel point represents the amplitude value of discharge, the color depth of the pixel point represents the discharge quantity, and a 50HZ positive brown wave curve is drawn under the same coordinate of the gray level image to obtain the partial discharge data image shown in fig. 1.
Step (2), establishing an insulation partial discharge characteristic database
The sample information data a in the partial discharge characteristic data shown in table 1 is composed of the sample acquisition time, sample number, measurement state, station and generator information extracted from the data file one by one.
The positive and negative Qm and the positive and negative NQN data are extracted from the data file one by one to form the sample partial discharge comprehensive data d in the partial discharge characteristic data shown in the table 1. And (3) marking generator insulation faults according to the sequence of 0-9 to form a fault code table, and adding the generator insulation fault codes corresponding to the partial discharge samples one by one according to the sample sequence to form sample tag data b in the partial discharge characteristic data shown in the table 1.
And packaging the a, b, c, d data to form an insulation partial discharge characteristic data set, and continuously collecting new samples according to different insulation states of the generator and adding the new samples to form an insulation partial discharge characteristic database.
And (3) modeling and training a diagnosis model.
And (3) establishing a model A according to the structural parameters shown in fig. 2, converting tag data b shown in table 1 into onehot codes b1, and inputting b1 and c data sets into the model A.
In fig. 2, the structure is input, convolution, probability, pooling, conversion, probability, full connection, probability, output in order. The model inputs 30X 100X 1 image data, 2 times of convolution calculation are carried out in the network, the 1 st time of convolution kernel size is 3X3, the number of convolution kernels is 32, the 2 nd time of convolution kernel size is 3X3, the number of convolution kernels is 64, and the 4 overfitting prevention probability layer parameters are all 0.25.
Model training, loss function: multiple class loss function (category_cross-sentropy), optimizer: an adaptive learning rate optimization algorithm (adam), monitoring the index: accuracy (accuracy), 100 samples per batch were trained for 30 cycles. The training results are shown in FIG. 3 to obtain a model A and a parameter file A.h5.
Currently 3 types of fault type data output are used as 3 classification probabilities.
Step (4) model application
And (3) inputting sample original data of unknown faults into a well-learned model A, and outputting fault type percentage probability of the samples after calculation of the model A and parameters A.h5.
The embodiment is aimed at diagnosing faults of a hydraulic generator of a certain power plant, and specifically comprises the following steps:
the method comprises the steps of inputting 1100 on-line monitoring data samples of severe corona of a low-resistance corona prevention section of a notch at the end part of a generator bar of a certain power plant, 980 on-line monitoring data samples with severe interference data, 2400 on-line monitoring data samples with corona and insulation abnormality data, training a model, wherein the training result is shown in fig. 3, and testing ID in an on-line monitoring device: an 8917 sample, the c-form data extracted by the method of this example was input to the model diagnosis result as shown in fig. 4.
The results were as follows: 8917. predicting fault types, namely corona and insulation abnormality; notch low corona resistance probability 0.000000028; 0.000005493 data anomaly probability; corona and insulation anomaly probability 0.999994516.
While the invention has been described and illustrated in considerable detail, it should be understood that modifications and equivalents to the above-described embodiments will become apparent to those skilled in the art, and that such modifications and improvements may be made without departing from the spirit of the invention.
Claims (4)
1. An on-line monitoring and diagnosing method for insulation partial discharge faults of a stator winding of a generator is characterized by comprising the following steps of: the method comprises the following steps:
step (1), partial discharge on-line monitoring data conversion and partial discharge data imaging representation
Deriving partial discharge original data from a partial discharge online monitoring system, extracting a sample positive partial discharge amplitude value, a positive partial discharge phase and a positive partial discharge quantity data set d1 from the partial discharge original data one by one, combining the data d1 and d2 into a partial discharge sample original data set with positive and negative partial discharge amplitude values, positive and negative partial discharge phases and positive and negative partial discharge quantity;
converting the original sample data set into a gray level diagram, and drawing a 50HZ positive brown wave curve under the same coordinate of the gray level diagram to obtain a partial discharge sample image;
step (2), establishing an insulation partial discharge characteristic database
The method comprises the steps of leading out partial discharge original data from a partial discharge online monitoring system, extracting sample acquisition time, sample number, measurement state, station and generator information from the partial discharge original data one by one to form sample information data, extracting positive and negative discharge quantity Qm and positive and negative discharge quantity NQN from the sample one by one to form sample partial discharge comprehensive data; labeling generator insulation faults according to the sequence of 0-9 to form a sample fault code table, and adding the generator insulation fault codes corresponding to the partial discharge samples one by one according to the sample sequence to form sample label data;
packaging the sample information data, the sample partial discharge comprehensive data, the partial discharge original data and the sample label data to form an insulation partial discharge characteristic data set, and continuously collecting new samples according to different insulation states of the generator to form an insulation partial discharge characteristic database;
step (3), modeling and training of diagnostic models
Establishing a deep learning model A through a convolutional neural network, inputting partial discharge original data and sample tag data in an insulation partial discharge characteristic database into the model A, and performing learning training on the model;
model a training: sampling a multi-classification loss function, adopting a self-adaptive learning rate optimization algorithm, monitoring index accuracy, and obtaining a model parameter A.h5 through multi-round and multi-batch learning training;
step (4) model application
And (3) inputting sample original data of unknown faults into a well-learned model A, and outputting fault type percentage probability of the samples after calculation of the model A and parameters A.h5.
2. The on-line monitoring and diagnosing method for insulation partial discharge faults of stator windings of a generator according to claim 1, characterized in that: in the step (1), the gray scale image takes the phase 0 to 360 degrees as the x-axis coordinate and the amplitude-30 to 30 as the y-axis coordinate, the x-axis position of the gray scale image pixel point represents the phase of the discharge, the y-axis position of the gray scale image pixel point represents the amplitude value of the discharge, and the color depth of the pixel point represents the discharge quantity.
3. The on-line monitoring and diagnosing method for insulation partial discharge faults of stator windings of a generator according to claim 1, characterized in that: in the step (3), a model A is specifically a partial discharge data image diagnosis and identification model constructed through a convolutional neural network.
4. The method for on-line monitoring and diagnosing insulation partial discharge faults of stator windings of a generator according to claim 3, comprising the steps of: in the step (3), when a model A is established, 30X 100X 1 image data are input into the model, 2 times of convolution calculation are carried out in a network, the number of convolution kernels with the size of 3X3 at the 1 st time is 32, the number of convolution kernels with the size of 3X3 at the 2 nd time is 64, and the parameters of 4 overfitting prevention probability layers are all 0.25; the structure is input, convolution, probability, pooling, conversion, probability, full connection, probability, output in sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011197314.7A CN112305388B (en) | 2020-10-30 | 2020-10-30 | On-line monitoring and diagnosing method for insulation partial discharge faults of generator stator winding |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011197314.7A CN112305388B (en) | 2020-10-30 | 2020-10-30 | On-line monitoring and diagnosing method for insulation partial discharge faults of generator stator winding |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112305388A CN112305388A (en) | 2021-02-02 |
| CN112305388B true CN112305388B (en) | 2024-03-08 |
Family
ID=74333372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011197314.7A Active CN112305388B (en) | 2020-10-30 | 2020-10-30 | On-line monitoring and diagnosing method for insulation partial discharge faults of generator stator winding |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112305388B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113933660A (en) * | 2021-08-31 | 2022-01-14 | 华能澜沧江水电股份有限公司 | Generator insulation fault degradation monitoring method based on partial discharge characteristics |
| CN113945848B (en) * | 2021-10-15 | 2023-12-22 | 哈尔滨电机厂有限责任公司 | Method for determining flashover discharge path of generator stator winding |
| CN115343617B (en) * | 2022-09-22 | 2023-01-10 | 南通万成机电有限公司 | Partial discharge online monitoring and identification method for motor stator winding |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3543927A1 (en) * | 1985-12-12 | 1987-06-19 | Kraftwerk Union Ag | METHOD FOR PARTIAL DISCHARGE DETECTION AND Tear-off Spark Measurement in DYNAMOELECTRIC HIGH-VOLTAGE MACHINES AND DEVICE FOR ITS IMPLEMENTATION |
| US6064172A (en) * | 1997-02-11 | 2000-05-16 | Power Superconductor Applications Corporation | Method and apparatus for detection, classification and reduction of internal electrical faults in alternating current propulsion machinery using synchronous detection scheme |
| CN102323526A (en) * | 2011-08-15 | 2012-01-18 | 重庆大学 | Sensor based on the ultrasonic distribution character of big motor shelf depreciation is provided with analytical approach |
| CN105403820A (en) * | 2015-12-03 | 2016-03-16 | 三峡大学 | On-line detection method of partial discharging signal of generator stator winding |
| CN106556781A (en) * | 2016-11-10 | 2017-04-05 | 华乘电气科技（上海）股份有限公司 | Shelf depreciation defect image diagnostic method and system based on deep learning |
| CN109100627A (en) * | 2018-10-31 | 2018-12-28 | 红相股份有限公司 | A kind of power equipment partial discharges fault diagnostic method based on end-to-end mode |
| CN110514975A (en) * | 2019-10-14 | 2019-11-29 | 云南电网有限责任公司电力科学研究院 | A kind of shelf depreciation genre classification methods of GIS device |
| CN111175621A (en) * | 2020-01-07 | 2020-05-19 | 岭东核电有限公司 | Method, system and equipment for detecting insulation defects of medium-voltage and high-voltage rotating motors in nuclear power station |
| CN111458612A (en) * | 2020-05-29 | 2020-07-28 | 国网陕西省电力公司电力科学研究院 | State monitoring and defect simulation system for electrical insulation performance of oil-immersed sleeve |
| CN111562466A (en) * | 2019-12-06 | 2020-08-21 | 雅砻江流域水电开发有限公司 | Detection method for partial discharge of stator winding of large hydraulic generator |
| CN115327304A (en) * | 2022-07-14 | 2022-11-11 | 成都恒锐智科数字技术有限公司 | Transformer partial discharge type identification method and system based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019067989A (en) * | 2017-10-04 | 2019-04-25 | 株式会社日立製作所 | Diagnostic system of on-load tap changeover device, diagnostic method of on-load tap changeover device, diagnostic system of power transformer |
-
2020
- 2020-10-30 CN CN202011197314.7A patent/CN112305388B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3543927A1 (en) * | 1985-12-12 | 1987-06-19 | Kraftwerk Union Ag | METHOD FOR PARTIAL DISCHARGE DETECTION AND Tear-off Spark Measurement in DYNAMOELECTRIC HIGH-VOLTAGE MACHINES AND DEVICE FOR ITS IMPLEMENTATION |
| US6064172A (en) * | 1997-02-11 | 2000-05-16 | Power Superconductor Applications Corporation | Method and apparatus for detection, classification and reduction of internal electrical faults in alternating current propulsion machinery using synchronous detection scheme |
| CN102323526A (en) * | 2011-08-15 | 2012-01-18 | 重庆大学 | Sensor based on the ultrasonic distribution character of big motor shelf depreciation is provided with analytical approach |
| CN105403820A (en) * | 2015-12-03 | 2016-03-16 | 三峡大学 | On-line detection method of partial discharging signal of generator stator winding |
| CN106556781A (en) * | 2016-11-10 | 2017-04-05 | 华乘电气科技（上海）股份有限公司 | Shelf depreciation defect image diagnostic method and system based on deep learning |
| CN109100627A (en) * | 2018-10-31 | 2018-12-28 | 红相股份有限公司 | A kind of power equipment partial discharges fault diagnostic method based on end-to-end mode |
| CN110514975A (en) * | 2019-10-14 | 2019-11-29 | 云南电网有限责任公司电力科学研究院 | A kind of shelf depreciation genre classification methods of GIS device |
| CN111562466A (en) * | 2019-12-06 | 2020-08-21 | 雅砻江流域水电开发有限公司 | Detection method for partial discharge of stator winding of large hydraulic generator |
| CN111175621A (en) * | 2020-01-07 | 2020-05-19 | 岭东核电有限公司 | Method, system and equipment for detecting insulation defects of medium-voltage and high-voltage rotating motors in nuclear power station |
| CN111458612A (en) * | 2020-05-29 | 2020-07-28 | 国网陕西省电力公司电力科学研究院 | State monitoring and defect simulation system for electrical insulation performance of oil-immersed sleeve |
| CN115327304A (en) * | 2022-07-14 | 2022-11-11 | 成都恒锐智科数字技术有限公司 | Transformer partial discharge type identification method and system based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| Partial discharge detection for stator winding insulation of motors using artificial neural network;Chen Y-T;Advances in Mechanical Engineering;10(7);全文 * |
| 基于深度学习的水轮发电机定子绕组绝缘故障诊断;杨增杰;电力大数据;第25卷(第1期);全文 * |
| 高压电机定子绕组局部放电指纹库建立方法及放电模式识别技术研究;李传扬;中国优秀硕士学位论文全文数据库工程科技II辑(第2期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112305388A (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112305388B (en) | On-line monitoring and diagnosing method for insulation partial discharge faults of generator stator winding | |
| CN111721535B (en) | Bearing fault detection method based on convolution multi-head self-attention mechanism | |
| CN111914883B (en) | Spindle bearing state evaluation method and device based on deep fusion network | |
| CN109655259A (en) | Combined failure diagnostic method and device based on depth decoupling convolutional neural networks | |
| CN110376522B (en) | Motor fault diagnosis method of data fusion deep learning network | |
| CN109782603A (en) | The detection method and monitoring system of rotating machinery coupling fault | |
| CN113128561A (en) | Machine tool bearing fault diagnosis method | |
| CN108647786B (en) | Rotary machine on-line fault monitoring method based on deep convolution countermeasure neural network | |
| CN111340238A (en) | Fault diagnosis method, device, equipment and storage medium of industrial system | |
| CN109635928A (en) | A kind of voltage sag reason recognition methods based on deep learning Model Fusion | |
| CN107909118A (en) | A kind of power distribution network operating mode recording sorting technique based on deep neural network | |
| CN113076834B (en) | Rotating machine fault information processing method, processing system, processing terminal, and medium | |
| CN109100648A (en) | Ocean current generator impeller based on CNN-ARMA-Softmax winds failure fusion diagnosis method | |
| CN110737976A (en) | mechanical equipment health assessment method based on multi-dimensional information fusion | |
| CN106022352A (en) | Submersible piston pump fault diagnosis method based on support vector machine | |
| CN115614292B (en) | Vibration monitoring device and method for vertical water pump unit | |
| CN116593157A (en) | Complex working condition gear fault diagnosis method based on matching element learning under small sample | |
| CN115238785A (en) | Rotary machine fault diagnosis method and system based on image fusion and integrated network | |
| CN117056865B (en) | Method and device for diagnosing operation faults of machine pump equipment based on feature fusion | |
| CN114048958A (en) | Cutter wear prediction method and system based on deep convolution residual shrinkage network | |
| CN114781450B (en) | Train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN | |
| CN116644273A (en) | Fault diagnosis method and system based on interpretability multiplication convolution network | |
| CN116738367A (en) | Rolling bearing fault diagnosis method based on multi-scale map transducer | |
| CN111523557A (en) | Wind power intelligent fault diagnosis method based on big data | |
| CN114330413A (en) | Fault type identification and positioning method for traction motor bearing |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210208 Address after: 100031 A312, 3rd floor, building 6, fuxingmennei street, Xicheng District, Beijing Applicant after: HUANENG GROUP TECHNOLOGY INNOVATION CENTER Co.,Ltd. Address before: No.1, shijichengzhong Road, Kunming, Yunnan, 650214 Applicant before: HUANENG LANCANG RIVER HYDROPOWER Inc. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210226 Address after: No.1, shijichengzhong Road, Kunming, Yunnan, 650214 Applicant after: HUANENG LANCANG RIVER HYDROPOWER Inc. Applicant after: HUANENG GROUP TECHNOLOGY INNOVATION CENTER Co.,Ltd. Address before: No.1, shijichengzhong Road, Kunming, Yunnan, 650214 Applicant before: HUANENG LANCANG RIVER HYDROPOWER Inc. |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210304 Address after: No.1, shijichengzhong Road, Guandu District, Kunming City, Yunnan Province Applicant after: HUANENG LANCANG RIVER HYDROPOWER Inc. Applicant after: HUANENG GROUP TECHNOLOGY INNOVATION CENTER Co.,Ltd. Address before: No.1, shijichengzhong Road, Kunming, Yunnan, 650214 Applicant before: HUANENG LANCANG RIVER HYDROPOWER Inc. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |