CN111553432A - Stator bar insulation aging degree prediction method based on image feature support vector machine - Google Patents
Stator bar insulation aging degree prediction method based on image feature support vector machine Download PDFInfo
- Publication number
- CN111553432A CN111553432A CN202010364444.9A CN202010364444A CN111553432A CN 111553432 A CN111553432 A CN 111553432A CN 202010364444 A CN202010364444 A CN 202010364444A CN 111553432 A CN111553432 A CN 111553432A
- Authority
- CN
- China
- Prior art keywords
- support vector
- vector machine
- stator bar
- insulation
- aging degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
The invention relates to the field of stator bar insulation aging degree prediction, and discloses a stator bar insulation aging degree prediction method based on an image feature support vector machine. After the atlas of the aging material is obtained, the direction gradient histogram and the local binary pattern of the atlas are calculated, and the image characteristics of the atlas are obtained. After the image features are obtained, a support vector machine model is trained, different model parameters are set, and an optimal model is obtained. And finally, testing the test data by using the trained support vector machine model, thereby realizing the prediction of the insulation aging degree of the stator bar. The method is a novel method for predicting the insulation aging degree of the stator bar, and compared with the traditional method, the method is more accurate in prediction result, higher in efficiency and great in economic value.
Description
Technical Field
The invention belongs to the field of stator bar material aging degree prediction, and particularly relates to a stator bar insulation aging degree prediction method based on an image feature support vector machine.
Background
The aging of the polymer material has become a very important problem, the actual harm is much more serious than people imagine, especially under the harsh environmental conditions, the equipment is prematurely failed, the material is greatly lost, the economic loss is great, the resource waste is caused, and even the environmental pollution is caused by the failure and decomposition of the material. However, during the processing, storage and use of the polymer materials, the polymer materials are degraded under the combined action of internal and external factors such as light, heat, water, chemical and biological erosion, and the like, and the performance is gradually reduced, so that the use value of the polymer materials is partially lost or lost.
The stator bars are important components of the generator, and the quality of the insulation state of the stator bars determines the service life of the generator to a great extent. The insulation of the stator bar mainly adopts an epoxy mica insulation system, and in the long-term operation process, the mechanical property and the dielectric property of the stator bar are gradually deteriorated and the electrical strength is reduced under the combined action of stress factors such as electricity, heat, mechanical vibration, environment and the like, so that the insulation breakdown is finally caused. Statistical results show that the main cause of generator failure is caused when the insulation is damaged. The method for observing diffraction spots, micro-morphology and the like in the insulation aging process of the stator bar plays an important role in judging the aging degree of the insulation material.
The traditional stator bar insulation aging degree evaluation method is mainly a formula method, and mainly comprises a partial discharge parameter prediction method, a D-image method and other non-electrical parameter life evaluation methods by establishing the relationship between various electrical appliance parameters such as dielectric loss factors and partial discharge amount and the residual life. The methods are complex to operate, and the evaluation results have large difference and are not accurate enough.
Disclosure of Invention
In order to predict the insulation aging degree of the stator bar, the invention aims to provide a method for predicting the insulation aging degree of the stator bar based on an image feature support vector machine.
The invention adopts the following technical scheme:
a stator bar insulation aging degree prediction method based on an image feature support vector machine comprises the following steps:
s1, carrying out thermal oxidation aging on the insulating sheet on the stator bar, and taking out a plurality of aged samples at intervals;
s2, acquiring a diffraction spot map and a micro-topography map of the aging sample;
s3, extracting the directional gradient histogram feature of the diffraction spot map of the aging sample and the local binary pattern feature of the micro-topography map;
s4, dividing the data obtained in S3 into a training set, a verification set and a test set, inputting the directional gradient histogram features and the local binary pattern features of the training set into a support vector machine, and constructing a support vector machine model;
s5, finding out the model parameter with the highest accuracy of the insulation sheet in the verification set by setting different model parameters of the support vector machine, and taking the model parameter as the final model parameter to obtain a trained support vector machine;
and S6, inputting the test set into the trained support vector machine model, predicting the aging degree of the atlas in the test set, and taking the aging degree value output by the support vector machine model as the insulation aging degree prediction value.
Preferably, in S3:
the calculation process of the histogram of directional gradients includes:
and (3) segmenting the diffraction spot spectrum of the aged sample, calculating the direction and gradient of pixels in each segmentation block, accumulating the gradients according to the direction of pixel change to obtain a directional gradient map in one segmentation block, and counting the directional gradients in all the segmentation blocks to obtain the directional gradient histogram characteristics of the image.
Preferably, in S3:
the local binary pattern feature calculation process of the micro-topography map of the aged sample comprises the following steps:
the original local binary pattern operator is defined as that in a window of 3 x 3, the central pixel of the window is used as a threshold value, the gray values of 8 adjacent pixels are compared with the central pixel, if the values of the surrounding pixels are larger than the value of the central pixel, the position of the pixel is marked as 1, otherwise, the position of the pixel is marked as 0, 8 points in the 3 x 3 neighborhood are compared to generate 8-bit binary numbers, and the 8-bit binary numbers are converted into decimal numbers to obtain the local binary pattern characteristic of the central pixel of the window.
Preferably, in S5:
the parameters that need to be set are as follows:
c: a penalty term;
kernel: a kernel function type;
degree: the order of the polynomial kernel;
gamma: a kernel function coefficient;
coef 0: individual terms in the kernel function;
mobility: whether probability estimation is enabled;
ringing: whether a heuristic shrinkage mode is adopted;
tol: the error precision of svm stopping training;
class _ weight: a category weight;
max _ iter: maximum number of iterations;
precision _ function _ shape: a decision function type;
random _ state: seed values when data is shuffled.
Preferably, in S2, observing the diffraction spot pattern of the aged sample by two-dimensional small-angle X-ray scattering; and observing the appearance information of the aged sample by using an atomic force microscope to obtain a microscopic appearance map of the aged sample, wherein the appearance information of the aged sample comprises the surface form and the interface state among different components.
Preferably, in S1, the insulation sample is peeled from the stator wire rod to obtain a single-layer or multi-layer stacked insulation sheet, the temperature of the thermo-oxidative aging is 100 ℃ to 200 ℃ for 100h to 200h, and 4 to 8 insulation sheets are taken out every 5h to 10 h.
Compared with the prior art, the invention has the following beneficial effects:
the stator bar insulation aging degree prediction method based on the image feature support vector machine analyzes by using the diffraction spot diagram and the micro-topography diagram of the insulation material, the small change of the insulation material can be clearly shown in the diffraction spot diagram and the micro-topography diagram, and the observation and research on the material micro-layer can ensure that the analysis result is more reliable. The traditional modeling technology needs to preset a plurality of mathematical model constructions for verification, and the model is only suitable for the insulation material prediction under specific conditions. The invention utilizes the method of the support vector machine to carry out modeling, the construction method is quick, excessive human intervention is not needed, and the service life of the insulating material can be conveniently predicted. The invention carries out thermo-oxidative aging on the insulating sheet on the stator bar, adopts an accelerated aging method of the insulating sample to carry out the test, can predict the aging degree of the insulating material of the stator bar in the design stage of the generator, and has good guiding function for the design of the generator. The invention adopts the direction gradient histogram characteristic and the local binary pattern characteristic to extract the characteristics of the image, the two methods count the change of the map pixel level, and the tiny change of the material on the microscopic level can be accurately captured by combining the diffraction spot pattern and the microscopic topography pattern of the insulating material. In conclusion, the method has accurate prediction results and has a good guiding function for evaluating the insulation aging degree of the stator bar.
Drawings
FIG. 1 is a flow chart of a stator bar insulation aging degree prediction method based on an image feature support vector machine.
FIG. 2 is a graph of 2D-SAXS spectra of stator bar insulation at various stages of aging for an embodiment of the present invention.
FIG. 3 is an AFM map of stator bar insulation at various stages of aging in an embodiment of the present invention.
Detailed Description
The invention is further described in detail below with reference to the drawings and the detailed description.
As shown in FIG. 1, the invention relates to a stator bar insulation aging degree prediction method based on an image feature support vector machine, which comprises the following steps:
s1: preparation of an aged sample:
stripping the insulation sample from the stator wire rod to obtain a single-layer or multi-layer stacked insulation sheet, placing the insulation sheet in a glass dish for thermo-oxidative aging, and taking out a plurality of aging samples at intervals to obtain aging samples;
s2: obtaining diffraction light spot map and micro-morphology map of stator bar insulation aging sample
Observing diffraction spots of the aged sample at different aging stages by using 2D-SAXS (two-dimensional small-angle X-ray scattering) to obtain a diffraction spot spectrum of the aged sample; observing the surface morphology of the aged samples in different aging states on a nanometer scale and the interface states among different components by using an Atomic Force Microscope (AFM) to obtain a micro-morphology map of the aged samples;
s3: extracting image characteristics of diffraction light spot map and micro-topography map
Extracting direction gradient histogram features of the diffraction light spot map and local binary pattern features of the micro-topography map;
s4: constructing support vector machine model
Dividing the data obtained in the step S3 into a training set, a verification set and a test set, inputting the directional gradient histogram characteristics and the local binary pattern characteristics of the training set into a support vector machine, and constructing a support vector machine model;
s5: by setting different model parameters of the support vector machine, finding the model parameter with the highest accuracy of the predicted insulating sheet material in the verification set atlas, and taking the model parameter as the final model parameter to obtain a trained support vector machine model S6: inputting the map features of the test set into the trained support vector machine model, and predicting the aging degree of the map in the test set.
Through the steps, the prediction of the insulation aging degree of the stator bar can be realized through the 2D-SAXS and the AFM spectrum and the establishment of a support vector machine model.
In addition to the above technical solution, in S3:
the calculation process of the histogram of directional gradients includes:
firstly, segmenting a diffraction spot map of an aging sample, calculating the direction and gradient of pixels in each segmentation block, accumulating the gradients according to the direction of pixel change to obtain a directional gradient map in one segmentation block, and counting the directional gradients in all the segmentation blocks to obtain the directional gradient histogram characteristics of an image, namely the directional gradient histogram characteristics of the image;
the calculation process of the local binary pattern characteristics of the micro-topography map of the aged sample comprises the following steps:
the original local binary pattern operator is defined as that in a window of 3 x 3, the central pixel of the window is used as a threshold value, the gray values of 8 adjacent pixels are compared with the central pixel, if the values of the peripheral pixels are larger than the value of the central pixel, the position of the pixel point is marked as 1, and if not, the position of the pixel point is 0. Thus, 8 points in the 3 × 3 neighborhood can generate 8-bit binary numbers (usually converted into decimal numbers, namely, local binary pattern codes, which are 256 in total) through comparison, and the local binary pattern value of the pixel point in the center of the window is obtained.
Preferably, S5 includes the following steps: setting different support vector machine parameters to obtain an optimal prediction model, wherein the required set parameters are as follows:
c: penalty item, float type, optional parameter, default 1.0, the larger C, i.e. the greater the penalty degree for the misclassified samples, so the higher the accuracy in the training samples, but the lower the generalization ability, i.e. the lower the classification accuracy for the test data. On the contrary, if C is reduced, some misclassified error samples in the training samples are allowed, and the generalization capability is strong. For the case where the training samples are noisy, the latter is generally adopted, and the misclassified samples in the training sample set are taken as noise.
kernel: kernel function type, str type, defaults to 'rbf'. The optional parameters are:
1) 'linear': linear kernel function
2) A poly': polynomial kernel function
3) 'rbf': radial image kernel function/Gaussian kernel
4) 'sigmod': sigmod kernel
5) 'precomputed': and (4) a kernel matrix. precomputed means that the kernel function matrix is calculated in advance, and at this time, the kernel function is not used in the algorithm to calculate the kernel matrix, but the kernel matrix given by you is directly used, and the kernel matrix needs to be n x n.
degree: the order of the polynomial kernel, int type, optional parameters, is 3 by default. This parameter is only useful for polynomial kernels and refers to the order n of the polynomial kernel, which is automatically ignored if the given kernel parameter is other kernels.
gamma: kernel coefficients, float type, optional parameters, auto by default. Effective only for 'rbf', 'poly', 'sigmod'. If gamma is auto, it represents that the value is the reciprocal of the sample feature number, i.e. 1/n _ features.
coef 0: the individual term in the kernel, float type, optional parameter, defaults to 0.0. Only for the 'poly' and 'sigmod' kernels is useful, is the parameter c therein.
Mobility: whether probability estimation, the pool type, optional parameters, default to False, must be enabled before the call of fit () and the fit () method slows down.
Ringing: and whether a heuristic shrinkage mode, a bool type and optional parameters are adopted is determined as True by default.
tol: the error precision of svm stopping training, float type, optional parameters, default to 1e ^ -3.
class _ weight: category weight, dit type or str type, optional parameters, and default to None. Each class is set with a different penalty parameter C, and if not, all classes are given C ═ 1, i.e., the parameter C indicated by the previous parameter. If the parameter 'balance' is given, the weight inversely proportional to the class frequency in the input data is automatically adjusted using the value of y.
max _ iter: the maximum number of iterations, int type, defaults to-1, indicating no restriction.
Precision _ function _ shape: the decision function type, optional parameters 'ovo' and 'ovr', is defaulted to 'ovr'. 'ovo' denotes onevsone, and 'ovr' denotes onevsrest.
random _ state: the seed value at which the data is shuffled, int type, optional parameters, default to None. A seed of a pseudo-random number generator is used for probability estimation when shuffling data.
And verifying different parameters in the verification set to obtain the optimal result of the model parameters, and using the optimal result as a trained support vector machine model.
Examples
The method for predicting the insulation aging degree of the stator bar of the support vector machine based on the image characteristics comprises the following steps:
the method comprises the following steps: preparation of aged samples
The insulation samples were stripped from the stator wire rods to obtain single or multi-layer stacked insulation sheets. The insulating sheet was cut into 1cm × 1cm samples. The samples were placed in a glass dish for thermo-oxidative aging. The aging temperature is 200 ℃, and the aging time is 200 hours. Every 10h, 4 aged samples were taken for subsequent testing.
Step two: 100 each of the 2D-SAXS spectrum and the AFM spectrum of the aged sample were obtained.
2D-SAXS (two-dimensional small-angle X-ray scattering) maps of epoxy resin aging samples at different aging stages are obtained by using 2D-SAXS. And (3) observing the surface morphology of the stator bar insulation in different aging states on a nanometer scale and the interface state between different components by using an Atomic Force Microscope (AFM).
Step three: image features of 2D-SAXS (shown in FIG. 2) and AFM spectra (shown in FIG. 3) were extracted. Taking the 2D-SAXS map with the aging time of 0 hour in the attached drawing 2 as an example, the image is partitioned, and the directional gradient histogram feature of the 2D-SAXS map and the local binary pattern feature of the AFM map are extracted.
The image is divided into 13 × 13 — 169 blocks, each block is divided into 2 × 2 — 4 cells, each cell has 8 × 8 — 64 pixels.
The gradients and directions of the pixels in the cell are then calculated, and in one cell, for each pixel, the gradients and directions define the magnitude and direction of the change in the pixel, such that there are 64 gradients and directions of the pixels in one cell, with the gradient directions of the pixels ranging from 0 to 180 degrees.
Then, 64 pixels are counted according to the gradient direction, the interval from 0 to 180 degrees is divided into 9 equal parts, the first unit at the upper left corner of the picture is counted, finally, the histogram is vectorized, and the statistics of each unit is carried out to obtain the total gradient value, wherein the gradient value result of the first unit of the gradient value of the histogram is as follows: [36,89,156,98,54,35,78,23,56]. Accumulating all unit directional gradients according to gradient directions to obtain directional gradient histogram characteristics of the map, wherein the final directional gradient histogram characteristics are as follows: [52133,94532,144323,103912,8934,68343,78345,12638].
The local binary pattern features are calculated as follows: the original local binary pattern operator is defined as that in a window of 3 x 3, the central pixel of the window is used as a threshold value, the gray values of 8 adjacent pixels are compared with the central pixel, if the values of the peripheral pixels are larger than the value of the central pixel, the position of the pixel point is marked as 1, and if not, the position of the pixel point is 0. Thus, 8 points in the 3 × 3 neighborhood can generate 8-bit binary numbers (usually converted into decimal numbers, i.e. local binary pattern codes, 256 types in total) through comparison, and then the local binary pattern value of the central pixel point of the window is obtained, and the obtained local binary pattern value is: [56,21,62,48,46,73 … 45,92 ].
Step four: after acquiring the directional gradient histogram feature and the local binary pattern feature of the map, dividing the data into a training set, a verification set and a test set, wherein the proportion is 6: 3: 1, training set 120 groups of data, validation set 60 groups of data, and test set 20 groups of data. Inputting the directional gradient histogram feature and the local binary pattern feature of the training set into a support vector machine, and constructing a support vector machine model.
Step five: by setting different model parameters of the support vector machine, the parameters of the support vector machine are set to be C1.0, kernel rbf ', gamma 20, mobility True, ringing True, tol 1e-6 and precision _ function _ shape ovr'. And finding out the model parameter with the highest accuracy of the insulation material prediction in the verification set map as the final model parameter.
Step six: inputting the map characteristics of the test set into a trained support vector machine model, predicting the aging degree of the map in the test set, selecting samples with different aging times for prediction, and accurately predicting the trained model according to model prediction results [0h,20h,30h,40h and 50h ], wherein the trained model prediction results are accurate, and the samples with different aging times are accurately predicted.
Claims (6)
1. A stator bar insulation aging degree prediction method based on an image feature support vector machine is characterized by comprising the following steps:
s1, carrying out thermal oxidation aging on the insulating sheet on the stator bar, and taking out a plurality of aged samples at intervals;
s2, acquiring a diffraction spot map and a micro-topography map of the aging sample;
s3, extracting the directional gradient histogram feature of the diffraction spot map of the aging sample and the local binary pattern feature of the micro-topography map;
s4, dividing the data obtained in S3 into a training set, a verification set and a test set, inputting the directional gradient histogram features and the local binary pattern features of the training set into a support vector machine, and constructing a support vector machine model;
s5, finding out the model parameter with the highest accuracy of the insulation sheet in the verification set by setting different model parameters of the support vector machine, and taking the model parameter as the final model parameter to obtain a trained support vector machine;
and S6, inputting the test set into the trained support vector machine model, predicting the aging degree of the atlas in the test set, and taking the aging degree value output by the support vector machine model as the insulation aging degree prediction value.
2. The image feature support vector machine-based stator bar insulation aging degree prediction method according to claim 1, characterized in that in S3:
the calculation process of the histogram of directional gradients includes:
and (3) segmenting the diffraction spot spectrum of the aged sample, calculating the direction and gradient of pixels in each segmentation block, accumulating the gradients according to the direction of pixel change to obtain a directional gradient map in one segmentation block, and counting the directional gradients in all the segmentation blocks to obtain the directional gradient histogram characteristics of the image.
3. The image feature support vector machine-based stator bar insulation aging degree prediction method according to claim 1, characterized in that in S3:
the local binary pattern feature calculation process of the micro-topography map of the aged sample comprises the following steps:
the original local binary pattern operator is defined as that in a window of 3 x 3, the central pixel of the window is used as a threshold value, the gray values of 8 adjacent pixels are compared with the central pixel, if the values of the surrounding pixels are larger than the value of the central pixel, the position of the pixel is marked as 1, otherwise, the position of the pixel is marked as 0, 8 points in the 3 x 3 neighborhood are compared to generate 8-bit binary numbers, and the 8-bit binary numbers are converted into decimal numbers to obtain the local binary pattern characteristic of the central pixel of the window.
4. The image feature support vector machine-based stator bar insulation aging degree prediction method according to claim 1, characterized in that in S5:
the parameters that need to be set are as follows:
c: a penalty term;
kernel: a kernel function type;
degree: the order of the polynomial kernel;
gamma: a kernel function coefficient;
coef 0: individual terms in the kernel function;
mobility: whether probability estimation is enabled;
ringing: whether a heuristic shrinkage mode is adopted;
tol: the error precision of svm stopping training;
class _ weight: a category weight;
max _ iter: maximum number of iterations;
precision _ function _ shape: a decision function type;
random _ state: seed values when data is shuffled.
5. The stator bar insulation aging degree prediction method based on the image feature support vector machine according to claim 1, characterized in that in S2, a diffraction spot map of an aging sample is observed by using two-dimensional small-angle X-ray scattering; and observing the appearance information of the aged sample by using an atomic force microscope to obtain a microscopic appearance map of the aged sample, wherein the appearance information of the aged sample comprises the surface form and the interface state among different components.
6. The method for predicting the insulation aging degree of the stator bar based on the image feature support vector machine as claimed in claim 1, wherein in S1, the insulation sample is peeled off from the stator bar to obtain the single-layer or multi-layer stacked insulation sheets, the temperature of the thermal oxidation aging is 100 ℃ to 200 ℃, the time is 100h to 200h totally, and 4 to 8 insulation sheets are taken out every 5h to 10 h.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010364444.9A CN111553432B (en) | 2020-04-30 | 2020-04-30 | Stator bar insulation aging degree prediction method based on image feature support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010364444.9A CN111553432B (en) | 2020-04-30 | 2020-04-30 | Stator bar insulation aging degree prediction method based on image feature support vector machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111553432A true CN111553432A (en) | 2020-08-18 |
| CN111553432B CN111553432B (en) | 2022-02-22 |
Family
ID=72007839
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010364444.9A Active CN111553432B (en) | 2020-04-30 | 2020-04-30 | Stator bar insulation aging degree prediction method based on image feature support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111553432B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112269081A (en) * | 2020-10-14 | 2021-01-26 | 西安交通大学 | Multi-factor aging stress control platform and method for stator bar of large hydraulic generator |
| CN113051713A (en) * | 2021-03-01 | 2021-06-29 | 东方电气集团科学技术研究院有限公司 | Composite material aging prediction method based on image gray level co-occurrence matrix multi-feature extraction |
| CN113569507A (en) * | 2021-09-27 | 2021-10-29 | 中国人民解放军海军工程大学 | Machine learning-based stator bar insulation aging state composite prediction method |
| CN114062232A (en) * | 2021-09-30 | 2022-02-18 | 国高材高分子材料产业创新中心有限公司 | Oven, and automatic measuring system and method for thermal-oxidative aging life of polymer material |
| CN114167221A (en) * | 2021-12-13 | 2022-03-11 | 华北电力大学（保定） | Epoxy resin insulation aging discrimination and inspection method under different voltage frequencies |
| CN115062495A (en) * | 2022-08-05 | 2022-09-16 | 深圳市联嘉祥科技股份有限公司 | Method and device for analyzing insulating property of material, electronic equipment and storage medium |
| CN117877028A (en) * | 2024-03-13 | 2024-04-12 | 浙江大学 | Motor insulation life prediction method and system based on microscopic image features |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5552222A (en) * | 1995-01-27 | 1996-09-03 | General Electric Company | Electrically conductive articles comprising insulation resistant to corona discharge-induced degradation |
| WO1998047009A2 (en) * | 1997-04-11 | 1998-10-22 | General Electric Company | Statistical pattern analysis methods of partial discharge measurments in high voltage insulation |
| CN102135593A (en) * | 2010-12-28 | 2011-07-27 | 太原理工大学 | On-line diagnosis and evaluation method of insulation state of large electric machine |
| CN104764748A (en) * | 2015-05-04 | 2015-07-08 | 成都唐源电气有限责任公司 | Method and system for positioning insulators and method and system for fault detection |
| CN105825527A (en) * | 2016-03-25 | 2016-08-03 | 华北电力大学（保定） | Surface microtopography analysis method after insulation material flashover based on fractal theory |
| CN106771765A (en) * | 2017-01-05 | 2017-05-31 | 华北电力大学（保定） | A kind of multidimensional parameter appraisal procedure of operating composite insulator degree of aging |
| CN109696605A (en) * | 2018-10-19 | 2019-04-30 | 中电华创电力技术研究有限公司 | A kind of lifetime estimation method of generator stator bar epoxy resin mica insulation |
-
2020
- 2020-04-30 CN CN202010364444.9A patent/CN111553432B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5552222A (en) * | 1995-01-27 | 1996-09-03 | General Electric Company | Electrically conductive articles comprising insulation resistant to corona discharge-induced degradation |
| WO1998047009A2 (en) * | 1997-04-11 | 1998-10-22 | General Electric Company | Statistical pattern analysis methods of partial discharge measurments in high voltage insulation |
| US6192317B1 (en) * | 1997-04-11 | 2001-02-20 | General Electric Company | Statistical pattern analysis methods of partial discharge measurements in high voltage insulation |
| CN102135593A (en) * | 2010-12-28 | 2011-07-27 | 太原理工大学 | On-line diagnosis and evaluation method of insulation state of large electric machine |
| CN104764748A (en) * | 2015-05-04 | 2015-07-08 | 成都唐源电气有限责任公司 | Method and system for positioning insulators and method and system for fault detection |
| CN105825527A (en) * | 2016-03-25 | 2016-08-03 | 华北电力大学（保定） | Surface microtopography analysis method after insulation material flashover based on fractal theory |
| CN106771765A (en) * | 2017-01-05 | 2017-05-31 | 华北电力大学（保定） | A kind of multidimensional parameter appraisal procedure of operating composite insulator degree of aging |
| CN109696605A (en) * | 2018-10-19 | 2019-04-30 | 中电华创电力技术研究有限公司 | A kind of lifetime estimation method of generator stator bar epoxy resin mica insulation |
Non-Patent Citations (4)
| Title |
|---|
| RUIHUA LI: "Multi-feature Fusion and Damage Identification of Large Generator Stator Insulation Based on Lamb Wave Detection and SVM Method", 《SENSORS》 * |
| 廖瑞金: "局部放电对油浸绝缘纸表面损伤特性研究", 《中国电机工程学报》 * |
| 张跃: "采用混合核函数支持向量机算法的大型发电机定子线棒绝缘状态评估方法", 《西安交通大学学报》 * |
| 郝艳捧: "X射线衍射法研究大电机定子绝缘的老化过程", 《电工技术学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112269081A (en) * | 2020-10-14 | 2021-01-26 | 西安交通大学 | Multi-factor aging stress control platform and method for stator bar of large hydraulic generator |
| CN113051713A (en) * | 2021-03-01 | 2021-06-29 | 东方电气集团科学技术研究院有限公司 | Composite material aging prediction method based on image gray level co-occurrence matrix multi-feature extraction |
| CN113569507A (en) * | 2021-09-27 | 2021-10-29 | 中国人民解放军海军工程大学 | Machine learning-based stator bar insulation aging state composite prediction method |
| CN114062232A (en) * | 2021-09-30 | 2022-02-18 | 国高材高分子材料产业创新中心有限公司 | Oven, and automatic measuring system and method for thermal-oxidative aging life of polymer material |
| CN114062232B (en) * | 2021-09-30 | 2024-02-02 | 国高材高分子材料产业创新中心有限公司 | Automatic measuring system and method for thermal oxidative aging life of baking oven and polymer material |
| CN114167221A (en) * | 2021-12-13 | 2022-03-11 | 华北电力大学（保定） | Epoxy resin insulation aging discrimination and inspection method under different voltage frequencies |
| CN114167221B (en) * | 2021-12-13 | 2023-06-13 | 华北电力大学（保定） | Epoxy resin insulation aging discrimination and test method under different voltage frequencies |
| CN115062495A (en) * | 2022-08-05 | 2022-09-16 | 深圳市联嘉祥科技股份有限公司 | Method and device for analyzing insulating property of material, electronic equipment and storage medium |
| CN117877028A (en) * | 2024-03-13 | 2024-04-12 | 浙江大学 | Motor insulation life prediction method and system based on microscopic image features |
| CN117877028B (en) * | 2024-03-13 | 2024-05-14 | 浙江大学 | Motor insulation life prediction method and system based on microscopic image features |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111553432B (en) | 2022-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111553432B (en) | Stator bar insulation aging degree prediction method based on image feature support vector machine | |
| CN110082136B (en) | Rotary machine fault diagnosis method based on cloud genetic algorithm optimization support vector machine | |
| CN110147760B (en) | Novel efficient electric energy quality disturbance image feature extraction and identification method | |
| CN103968937B (en) | A kind of distribution switch mechanical state diagnostic method based on EMD Sample Entropies and FCM | |
| CN111563622B (en) | Method for predicting insulation aging degree of stator bar | |
| CN111931983B (en) | Precipitation prediction method and system | |
| CN112016588B (en) | Space autocorrelation clustering method facing remote correlation mode | |
| CN113391211B (en) | Method for predicting remaining life of lithium battery under small sample condition | |
| CN110333078B (en) | Rolling bearing degradation state stage determination method | |
| CN112288147B (en) | Method for predicting insulation state of generator stator by BP-Adaboost strong predictor | |
| CN117252878B (en) | Image defect detection method of nano-imprint mold | |
| CN109670652A (en) | A kind of failure prediction method of photovoltaic module | |
| CN106570790A (en) | Wind farm output power data restoration method considering segmental characteristics of wind speed data | |
| Peng et al. | A very short term wind power prediction approach based on Multilayer Restricted Boltzmann Machine | |
| CN112746934A (en) | Method for diagnosing fan fault through self-association neural network | |
| CN115980588A (en) | Lithium ion battery health state estimation method based on self-encoder extraction features | |
| CN116243115A (en) | High-voltage cable mode identification method and device based on time sequence topology data analysis | |
| CN115291110A (en) | Electric pile aging prediction method based on characteristic parameter extraction and aging experience base construction | |
| CN113361782A (en) | Photovoltaic power generation power short-term rolling prediction method based on improved MKPLS | |
| CN113051713B (en) | Composite material aging prediction method based on image gray level co-occurrence matrix multi-feature extraction | |
| CN109508350B (en) | Method and device for sampling data | |
| CN111814961A (en) | Rainfall forecast method based on generative confrontation network | |
| CN114118592B (en) | Smart power grids power consumption end short-term energy consumption prediction system | |
| CN114123971B (en) | Photovoltaic string abnormality detection method and system based on VaDE | |
| CN117805616A (en) | Abnormal cell identification method for lithium ion energy storage 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 |