CN103824092A - Image classification method for monitoring state of electric transmission and transformation equipment on line - Google Patents
Image classification method for monitoring state of electric transmission and transformation equipment on line Download PDFInfo
- Publication number
- CN103824092A CN103824092A CN201410075980.1A CN201410075980A CN103824092A CN 103824092 A CN103824092 A CN 103824092A CN 201410075980 A CN201410075980 A CN 201410075980A CN 103824092 A CN103824092 A CN 103824092A
- Authority
- CN
- China
- Prior art keywords
- image
- transformation equipment
- classification
- sorter
- sample set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000009466 transformation Effects 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 238000012549 training Methods 0.000 claims abstract description 44
- 230000002159 abnormal effect Effects 0.000 claims abstract description 11
- 238000002372 labelling Methods 0.000 claims abstract description 7
- 238000002790 cross-validation Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims description 26
- 238000002156 mixing Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 3
- 238000013145 classification model Methods 0.000 abstract 3
- 230000001131 transforming effect Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides an image classification method for monitoring a state of electric transmission and transformation equipment on line. The method comprises the following steps: labeling positive and negative samples; extracting a characteristic data value, and forming an original training sample set; obtaining a classification model; performing cross validation on the classification model; classifying state images of electric transmission and transformation equipment. According to the image classification method, effective classification models can be trained aiming at cost-sensitive and class-unbalanced characteristics of state monitoring images of the electric transmission and transformation equipment, the operating state of the electric transmission and transformation equipment is effectively and automatically judged in real time through identification and classification of the state image of the equipment, abnormal equipment is rapidly and accurately found, and the effectiveness and intelligent level of inspection information processing of the electric transmission and transformation equipment are improved.
Description
Technical field
The present invention relates to a kind of sorting technique, specifically relate to a kind of image classification method for power transmission and transformation equipment state on-line monitoring.
Background technology
Along with the fast development of power construction, the continuous expansion of electrical network scale, the Problem work of grid equipment is more and more frequent.Power transmission and transforming equipment is being undertaken important duty in operation power, and the status monitoring to power transmission and transforming equipment and fault diagnosis are the bases that guarantees power network safety operation.
Equipment condition monitoring comprises on-line monitoring, offline inspection if desired and test, and all means that obtain running state data such as (as take photo by plane and infrared monitoring) that directly do not contact with operational outfit.Carry out longitudinal comparison analysis according to the characteristic quantity of equipment condition monitoring and historical results before, carry out lateral comparison with the monitoring result of same category of device, and in conjunction with offline inspection test figure over the years and operating experience etc., can whether break down to equipment, fault type, the order of severity and reason etc. are made comprehensive judgement, provide maintenance policy and method.
Take photo by plane and infrared thermal imaging as contactless Condition Monitoring Technology collecting device status image, be widely used in maintenance and the fault diagnosis of power transmission and transforming equipment, can the in the situation that of breaks in production not, find power transmission and transforming equipment fault.If adopt manual type that the image collecting is analyzed and diagnosed, its efficiency is lower and real-time is poor.Therefore, guaranteeing, under the prerequisite of correct identification fault, to adopt automatic mode to improve the real-time of image processing, be, the key issue that realizes on-line monitoring.
At present, existing many ripe machine learning algorithms are applied in image processing problem, particularly Images Classification problem.For example: target detection in land classification, video or image based on remote sensing images etc.Traditional machine learning image classification method comprises support vector machine (SVM), decision tree, multilayer neural network etc., but these methods are in the time solving classification problem, all do not consider cost-sensitive problem and class imbalance problem.The surveillance map of power transmission and transformation equipment state looks like to exist the problem of class imbalance, and the image of its normal class is far more than the image of exception class; Meanwhile, to the cost-sensitive problem also existing in the judgement of equipment state, its normal class spectral discrimination is abnormal and exception class spectral discrimination is that normal cost is different.
Summary of the invention
Look like to have the feature of cost-sensitive and class imbalance for power transmission and transformation equipment state surveillance map, the invention provides a kind of image classification method for power transmission and transformation equipment state on-line monitoring, can be for power transmission and transformation equipment state surveillance map the feature as cost-sensitive and class imbalance, train effective disaggregated model, by the recognition and classification to equipment state image, the running status of in real time effective automatic discrimination power transmission and transforming equipment, find out fast and accurately the abnormal equipment that occurs, raising power transmission and transforming equipment is patrolled and examined actual effect and the intelligent level of information processing.
In order to realize foregoing invention object, the present invention takes following technical scheme:
The invention provides a kind of image classification method for power transmission and transformation equipment state on-line monitoring, said method comprising the steps of:
Step 1: mark positive and negative class sample;
Step 2: extract characteristic data value, form original training sample set;
Step 3: obtain disaggregated model;
Step 4: disaggregated model is carried out to cross validation;
Step 5: power transmission and transformation equipment state image is carried out to real-time grading.
Positive and negative class sample image in described step 1 derives from takes photo by plane and the infrared image of patrolling and examining, and choosing the normal image labeling of display device state is positive class sample, and the image labeling of choosing display device abnormal state is anti-class sample.
In described step 2, according to the color characteristic of positive and negative class sample and texture feature extraction characteristic data value, and according to the respective classes label of mark, characteristic data value is converted into the example of corresponding classification problem, forms original training sample collection.
In described step 3, adopt tandem type sorting technique to obtain disaggregated model.
Described step 3 specifically comprises the following steps:
Step 3-1: use Integrated Algorithm at original training sample set X
1upper, train the 1st grade of sorter S
1;
Step 3-2: original training sample set X
1through the 1st grade of sorter S
1, the 1st grade of sorter S
1be defined as the positive class sample set of listing in of positive class sample Y with high confidence level
1, other samples are listed the 2nd layer of training sample set X in
1-Y
1;
Step 3-3: use Integrated Algorithm at the 2nd layer of training sample set X
1-Y
1upper, train the 2nd grade of sorter S
2;
Step 3-4: the 2nd layer of training sample set X
1-Y
1through the 2nd grade of sorter S
2, the 2nd grade of sorter S
2be defined as the positive class sample set of listing in of positive class sample Y with high confidence level
2, other samples are listed the 3rd layer of training sample set X in
2-Y
2;
Step 3-5: use Integrated Algorithm at the 3rd layer of training sample set X
2-Y
2upper, train 3rd level sorter S
3;
Step 3-6: by that analogy, train i layer sorter S
i, i layer training sample set X
i-1-Y
i-1through i level sorter S
i, divide positive class sample and anti-class sample with high confidence level, 1-i layer altogether i sorter builds generation disaggregated model.
Described step 4 comprises the following steps:
Step 4-1: original training sample set is divided into N part at random, is respectively A
1, A
2, A
3..., A
n, wherein 5<=N<=20, gets A wherein
1as test data, the mixing of other N-1 parts tests sample data as training data, according to the classification results of test data, draws classification accuracy H
1;
Step 4-2: adjust combination, get A wherein
2as test data, the mixing of other N-1 parts tests sample data as training data, according to the classification results of test data, draws classification accuracy H
2;
Step 4-3: by that analogy, adjust combination, get A wherein
nas test data, the mixing of other N-1 parts tests sample data as training data, according to the classification results of test data, draws classification accuracy H
n;
Step 4-5: 5-10 step 4-1 of circulation, to step 4-3, obtains 5N-10N classification accuracy altogether, gets obtained classification accuracy mean value, as the classification accuracy to this disaggregated model;
Step 4-6: if the classification accuracy of disaggregated model, lower than predetermined threshold value, re-executes step 2, again extract characteristic data value, set up new disaggregated model; If the classification accuracy of this disaggregated model greater than or equal to arrange threshold value time, Renewal model not, execution step 5.
In described step 5, the disaggregated model that application generates carries out real-time grading to power transmission and transformation equipment state image.
Compared with prior art, beneficial effect of the present invention is:
(1) Image Classfication Technology is applied in power transmission and transformation equipment state monitoring, by the recognition and classification to equipment routing inspection image, finds out fast abnormal state equipment, effectively improve power transmission and transforming equipment and patrol and examine the intelligent level of information processing.
(2) disaggregated model that utilizes tandem type sorting technique to train, takes into full account positive class sample image quantity much larger than anti-class sample image quantity, and based on cascade structure, positive class sample image is filtered step by step, effectively solves class imbalance problem.
(3) disaggregated model that utilizes tandem type sorting technique to train, takes into full account state normal picture different with the cost of abnormal state image recognition, in every one-level, according to mis-classification cost, adjusts the weights between cascade, solves cost-sensitive problem.
(4) disaggregated model is carried out to cross validation, draw the performance evaluation value of this disaggregated model, if disaggregated model is not up to standard, again extract characteristic item, until training obtains the outstanding disaggregated model of performance, accelerate the speed of Images Classification.
Accompanying drawing explanation
Fig. 1 is the image classification method process flow diagram for power transmission and transformation equipment state on-line monitoring in the embodiment of the present invention;
Fig. 2 adopts tandem type sorting technique to obtain disaggregated model process flow diagram in the embodiment of the present invention;
Fig. 3 is 5 times of cross-validation methods estimation flow figure to disaggregated model in the embodiment of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
The invention provides a kind of image classification method for power transmission and transformation equipment state on-line monitoring, said method comprising the steps of:
Step 1: mark positive and negative class sample;
Step 2: extract characteristic data value, form original training sample set;
Step 3: obtain disaggregated model;
Step 4: disaggregated model is carried out to 5 times of cross validations;
Step 5: power transmission and transformation equipment state image is carried out to real-time grading.
Positive and negative class sample image in described step 1 derives from takes photo by plane and the infrared image of patrolling and examining, and choosing the normal image labeling of display device state is positive class sample, and the image labeling of choosing display device abnormal state is anti-class sample.
In described step 2, according to the color characteristic of positive and negative class sample and texture feature extraction characteristic data value, and according to the respective classes label of mark, characteristic data value is converted into the example of corresponding classification problem, forms original training sample collection.
In described step 3, adopt tandem type sorting technique to obtain disaggregated model.
Build tandem type sorter, sorter not at the same level is paid close attention to different patterns, and the positive class sample image being easily identified is correctly filtered in last two-stage, and in cascade structure, sorter to the rear is responsible for paying close attention to the pattern being more difficult between difference image of how distinguishing.
Tandem type sorting technique takes into full account positive class sample image quantity much larger than anti-class sample image quantity, based on cascade structure, positive class sample image is filtered step by step, and along with progression increases, the class imbalance of positive class sample image and anti-class sample image is solved.
And it is different with the cost of abnormal state image recognition to take into full account state normal picture, in every one-level, according to mis-classification cost, the weights between output and the cascade of regularized learning algorithm device, embody the cost-sensitive of abnormal state image.
Described step 3 specifically comprises the following steps:
Step 3-1: use Integrated Algorithm at original training sample set X
1upper, train the 1st grade of sorter S
1;
Step 3-2: original training sample set X
1through the 1st grade of sorter S
1, the 1st grade of sorter S
1be defined as the positive class sample set of listing in of positive class sample Y with high confidence level
1, other samples are listed the 2nd layer of training sample set X in
1-Y
1;
Step 3-3: use Integrated Algorithm at the 2nd layer of training sample set X
1-Y
1upper, train the 2nd grade of sorter S
2;
Step 3-4: the 2nd layer of training sample set X
1-Y
1through the 2nd grade of sorter S
2, the 2nd grade of sorter S
2be defined as the positive class sample set of listing in of positive class sample Y with high confidence level
2, other samples are listed the 3rd layer of training sample set X in
2-Y
2;
Step 3-5: use Integrated Algorithm at the 3rd layer of training sample set X
2-Y
2upper, train 3rd level sorter S
3;
Step 3-6: by that analogy, train i layer sorter S
i, i layer training sample set X
i-1-Y
i-1through i level sorter S
i, divide positive class sample and anti-class sample with high confidence level, 1-i layer altogether i sorter builds generation disaggregated model.
Described step 4 comprises the following steps:
Step 4-1: original training sample set is divided into 5 parts at random, is respectively A
1, A
2, A
3, A
4, A
5, wherein 5<=N<=20, gets A wherein
1as test data, other 4 parts of mixing are tested sample data as training data, according to the classification results of test data, draw classification accuracy H
1;
Step 4-2: adjust combination, get A wherein
2as test data, other 4 parts of mixing are tested sample data as training data, according to the classification results of test data, draw classification accuracy H
2;
Step 4-3: by that analogy, adjust combination, get A wherein
5as test data, other 4 parts of mixing are tested sample data as training data, according to the classification results of test data, draw classification accuracy H
5;
Step 4-5: 5-10 step 4-1 of circulation, to step 4-3, obtains 25 classification accuracies altogether, gets obtained classification accuracy mean value, as the classification accuracy to this disaggregated model;
Step 4-6: if the classification accuracy of disaggregated model, lower than predetermined threshold value, re-executes step 2, again extract characteristic data value, set up new disaggregated model; If the classification accuracy of this disaggregated model greater than or equal to arrange threshold value time, Renewal model not, execution step 5.
In described step 5, the disaggregated model that application generates carries out real-time grading to power transmission and transformation equipment state image, if Images Classification is anti-class, corresponding power transmission and transformation equipment state is abnormal, further this equipment is diagnosed.
Finally should be noted that: above embodiment is only in order to illustrate that technical scheme of the present invention is not intended to limit, although the present invention is had been described in detail with reference to above-described embodiment, those of ordinary skill in the field are to be understood that: still can modify or be equal to replacement the specific embodiment of the present invention, and do not depart from any modification of spirit and scope of the invention or be equal to replacement, it all should be encompassed in the middle of claim scope of the present invention.
Claims (7)
1. for an image classification method for power transmission and transformation equipment state on-line monitoring, it is characterized in that: said method comprising the steps of:
Step 1: mark positive and negative class sample;
Step 2: extract characteristic data value, form original training sample set;
Step 3: obtain disaggregated model;
Step 4: disaggregated model is carried out to cross validation;
Step 5: power transmission and transformation equipment state image is carried out to real-time grading.
2. the image classification method for power transmission and transformation equipment state on-line monitoring according to claim 1, it is characterized in that: the positive and negative class sample image in described step 1 derives from takes photo by plane and the infrared image of patrolling and examining, choosing the normal image labeling of display device state is positive class sample, and the image labeling of choosing display device abnormal state is anti-class sample.
3. the image classification method for power transmission and transformation equipment state on-line monitoring according to claim 1, it is characterized in that: in described step 2, according to the color characteristic of positive and negative class sample and texture feature extraction characteristic data value, and according to the respective classes label of mark, characteristic data value is converted into the example of corresponding classification problem, forms original training sample collection.
4. the image classification method for power transmission and transformation equipment state on-line monitoring according to claim 1, is characterized in that: in described step 3, adopt tandem type sorting technique to obtain disaggregated model.
5. the image classification method for power transmission and transformation equipment state on-line monitoring according to claim 4, is characterized in that: described step 3 specifically comprises the following steps:
Step 3-1: use Integrated Algorithm at original training sample set X
1upper, train the 1st grade of sorter S
1;
Step 3-2: original training sample set X
1through the 1st grade of sorter S
1, the 1st grade of sorter S
1be defined as the positive class sample set of listing in of positive class sample Y with high confidence level
1, other samples are listed the 2nd layer of training sample set X in
1-Y
1;
Step 3-3: use Integrated Algorithm at the 2nd layer of training sample set X
1-Y
1upper, train the 2nd grade of sorter S
2;
Step 3-4: the 2nd layer of training sample set X
1-Y
1through the 2nd grade of sorter S
2, the 2nd grade of sorter S
2be defined as the positive class sample set of listing in of positive class sample Y with high confidence level
2, other samples are listed the 3rd layer of training sample set X in
2-Y
2;
Step 3-5: use Integrated Algorithm at the 3rd layer of training sample set X
2-Y
2upper, train 3rd level sorter S
3;
Step 3-6: by that analogy, train i layer sorter S
i, i layer training sample set X
i-1-Y
i-1through i level sorter S
i, divide positive class sample and anti-class sample with high confidence level, 1-i layer altogether i sorter builds generation disaggregated model.
6. the image classification method for power transmission and transformation equipment state on-line monitoring according to claim 1, is characterized in that: described step 4 comprises the following steps:
Step 4-1: original training sample set is divided into N part at random, is respectively A
1, A
2, A
3..., A
n, wherein 5<=N<=20, gets A wherein
1as test data, the mixing of other N-1 parts tests sample data as training data, according to the classification results of test data, draws classification accuracy H
1;
Step 4-2: adjust combination, get A wherein
2as test data, the mixing of other N-1 parts tests sample data as training data, according to the classification results of test data, draws classification accuracy H
2;
Step 4-3: by that analogy, adjust combination, get A wherein
nas test data, the mixing of other N-1 parts tests sample data as training data, according to the classification results of test data, draws classification accuracy H
n;
Step 4-5: 5-10 step 4-1 of circulation, to step 4-3, obtains 5N-10N classification accuracy altogether, gets obtained classification accuracy mean value, as the classification accuracy to this disaggregated model;
Step 4-6: if the classification accuracy of disaggregated model, lower than predetermined threshold value, re-executes step 2, again extract characteristic data value, set up new disaggregated model; If the classification accuracy of this disaggregated model greater than or equal to arrange threshold value time, Renewal model not, execution step 5.
7. the image classification method for power transmission and transformation equipment state on-line monitoring according to claim 1, is characterized in that: in described step 5, the disaggregated model that application generates carries out real-time grading to power transmission and transformation equipment state image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410075980.1A CN103824092A (en) | 2014-03-04 | 2014-03-04 | Image classification method for monitoring state of electric transmission and transformation equipment on line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410075980.1A CN103824092A (en) | 2014-03-04 | 2014-03-04 | Image classification method for monitoring state of electric transmission and transformation equipment on line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103824092A true CN103824092A (en) | 2014-05-28 |
Family
ID=50759144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410075980.1A Pending CN103824092A (en) | 2014-03-04 | 2014-03-04 | Image classification method for monitoring state of electric transmission and transformation equipment on line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103824092A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268570A (en) * | 2014-09-19 | 2015-01-07 | 北京理工大学 | Layering single-class ship target false alarm eliminating method based on intra-class difference |
| CN106485705A (en) * | 2016-10-08 | 2017-03-08 | 西安交通大学 | Power equipment infrared image abnormality recognition method based on support matrix machine |
| CN107862468A (en) * | 2017-11-23 | 2018-03-30 | 深圳市智物联网络有限公司 | The method and device that equipment Risk identification model is established |
| CN108171234A (en) * | 2017-12-26 | 2018-06-15 | 爱保理网（北京）科技有限公司 | A kind of operation association operation state monitoring system and method based on cross validation |
| CN110245232A (en) * | 2019-06-03 | 2019-09-17 | 网易传媒科技（北京）有限公司 | File classification method, device, medium and calculating equipment |
| CN111553497A (en) * | 2020-04-29 | 2020-08-18 | 成都新潮传媒集团有限公司 | Equipment working state detection method and device of multimedia terminal |
| CN112183303A (en) * | 2020-09-24 | 2021-01-05 | 南方电网数字电网研究院有限公司 | Transformer equipment image classification method and device, computer equipment and medium |
| CN113537528A (en) * | 2021-07-28 | 2021-10-22 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
| CN113544923A (en) * | 2019-03-07 | 2021-10-22 | Abb瑞士股份有限公司 | Device for monitoring a switchgear |
-
2014
- 2014-03-04 CN CN201410075980.1A patent/CN103824092A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268570A (en) * | 2014-09-19 | 2015-01-07 | 北京理工大学 | Layering single-class ship target false alarm eliminating method based on intra-class difference |
| CN104268570B (en) * | 2014-09-19 | 2017-10-20 | 北京理工大学 | A kind of stratification list classification Ship Target false-alarm elimination method based on difference in class |
| CN106485705A (en) * | 2016-10-08 | 2017-03-08 | 西安交通大学 | Power equipment infrared image abnormality recognition method based on support matrix machine |
| CN107862468A (en) * | 2017-11-23 | 2018-03-30 | 深圳市智物联网络有限公司 | The method and device that equipment Risk identification model is established |
| CN108171234A (en) * | 2017-12-26 | 2018-06-15 | 爱保理网（北京）科技有限公司 | A kind of operation association operation state monitoring system and method based on cross validation |
| CN108171234B (en) * | 2017-12-26 | 2021-11-02 | 爱保理网（北京）科技有限公司 | Operation complex operation state monitoring system and method based on cross validation |
| CN113544923A (en) * | 2019-03-07 | 2021-10-22 | Abb瑞士股份有限公司 | Device for monitoring a switchgear |
| CN110245232A (en) * | 2019-06-03 | 2019-09-17 | 网易传媒科技（北京）有限公司 | File classification method, device, medium and calculating equipment |
| CN110245232B (en) * | 2019-06-03 | 2022-02-18 | 网易传媒科技（北京）有限公司 | Text classification method, device, medium and computing equipment |
| CN111553497A (en) * | 2020-04-29 | 2020-08-18 | 成都新潮传媒集团有限公司 | Equipment working state detection method and device of multimedia terminal |
| CN112183303A (en) * | 2020-09-24 | 2021-01-05 | 南方电网数字电网研究院有限公司 | Transformer equipment image classification method and device, computer equipment and medium |
| CN113537528A (en) * | 2021-07-28 | 2021-10-22 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
| CN113537528B (en) * | 2021-07-28 | 2022-05-03 | 贵州电网有限责任公司 | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103824092A (en) | Image classification method for monitoring state of electric transmission and transformation equipment on line | |
| Davari et al. | Intelligent diagnosis of incipient fault in power distribution lines based on corona detection in UV-visible videos | |
| CN112380952B (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| Wang et al. | A two-stage data-driven approach for image-based wind turbine blade crack inspections | |
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| CN111444939B (en) | Small-scale equipment component detection method based on weak supervision cooperative learning in open scene of power field | |
| CN111505424A (en) | Large experimental device power equipment fault diagnosis method based on deep convolutional neural network | |
| WO2017200524A1 (en) | Deep convolutional neural networks for crack detection from image data | |
| CN105044122A (en) | Copper part surface defect visual inspection system and inspection method based on semi-supervised learning model | |
| CN106198551A (en) | Method and device for detecting defects of power transmission line | |
| CN108802041B (en) | Method for rapidly changing small sample set of screen detection | |
| CN113642474A (en) | Hazardous area personnel monitoring method based on YOLOV5 | |
| CN106951863B (en) | Method for detecting change of infrared image of substation equipment based on random forest | |
| CN111862065B (en) | Power transmission line diagnosis method and system based on multitask deep convolutional neural network | |
| CN105300528A (en) | Infrared image diagnosis method and infrared image diagnosis system for transformer station equipment | |
| CN116824517B (en) | Substation operation and maintenance safety control system based on visualization | |
| CN114022671B (en) | Intelligent cableway cable position identification method based on residual neural network | |
| CN113469950A (en) | Method for diagnosing abnormal heating defect of composite insulator based on deep learning | |
| CN105550710A (en) | Nonlinear fitting based intelligent detection method for running exception state of contact network | |
| CN111461120A (en) | Method for detecting surface defects of convolutional neural network object based on region | |
| CN110660049A (en) | Tire defect detection method based on deep learning | |
| CN117636129A (en) | Identification method of power construction supervision image | |
| CN117372723A (en) | Intelligent substation violation operation early warning system | |
| Zhang et al. | A YOLOv3 and ODIN Based State Detection Method for High-speed Railway Catenary Dropper | |
| CN117274903B (en) | Intelligent early warning device and method for electric power inspection based on intelligent AI chip |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: CHINA ELECTRIC POWER RESEARCH INSTITUTE NANJING UN Free format text: FORMER OWNER: CHINA ELECTRIC POWER RESEARCH INSTITUTE NANJING UNIVERSITY Effective date: 20140918 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20140918 Address after: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant after: State Grid Corporation of China Applicant after: China Electric Power Research Institute Applicant after: Nanjing University Applicant after: Electric Power Research Institute of State Grid Shandong Electric Power Company Address before: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant before: State Grid Corporation of China Applicant before: China Electric Power Research Institute Applicant before: Nanjing University |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160429 Address after: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant after: State Grid Corporation of China Applicant after: China Electric Power Research Institute Applicant after: State Grid Smart Grid Institute Applicant after: Nanjing University Applicant after: Electric Power Research Institute of State Grid Shandong Electric Power Company Address before: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant before: State Grid Corporation of China Applicant before: China Electric Power Research Institute Applicant before: Nanjing University Applicant before: Electric Power Research Institute of State Grid Shandong Electric Power Company |
|
| CB02 | Change of applicant information |
Address after: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant after: State Grid Corporation of China Applicant after: China Electric Power Research Institute Applicant after: GLOBAL ENERGY INTERCONNECTION RESEARCH INSTITUTE Applicant after: Nanjing University Applicant after: Electric Power Research Institute of State Grid Shandong Electric Power Company Address before: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant before: State Grid Corporation of China Applicant before: China Electric Power Research Institute Applicant before: State Grid Smart Grid Institute Applicant before: Nanjing University Applicant before: Electric Power Research Institute of State Grid Shandong Electric Power Company |
|
| COR | Change of bibliographic data | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140528 |