CN109470628A - Contact net insulator contamination condition detection method - Google Patents
Contact net insulator contamination condition detection method Download PDFInfo
- Publication number
- CN109470628A CN109470628A CN201811144504.5A CN201811144504A CN109470628A CN 109470628 A CN109470628 A CN 109470628A CN 201811144504 A CN201811144504 A CN 201811144504A CN 109470628 A CN109470628 A CN 109470628A
- Authority
- CN
- China
- Prior art keywords
- contact net
- insulator
- image
- condition detection
- detection method
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N17/00—Investigating resistance of materials to the weather, to corrosion, or to light
- G01N17/008—Monitoring fouling
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental & Geological Engineering (AREA)
- Environmental Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Insulators (AREA)
Abstract
The invention discloses a kind of contact net insulator contamination condition detection methods, this method passes through the technique study of simulated experiment discharge scenario of the contact net insulator under different gradation for surface pollution, and the characteristic quantity that can characterize Insulator Contaminant Discharge has been extracted by video image processing algorithm, ultraviolet image characteristic quantity and contact net insulator salt density are connected on this basis.Then the contact net filth state-detection model based on least square method supporting vector machine LSSVR is established.The invention has the benefit that the colouring information that HSI image includes is less, save operation time, and the insulator contamination Detection accuracy after IPSO optimizes is higher.
Description
Technical field
The present invention relates to contact net technical fields, and in particular to a kind of contact net insulator contamination condition detection method.
Background technique
China Railway High-speed and electrified track communication sustainable development, as the indivisible core of electric railway
Part, the safety and stability of railway contact line, reliability service are always the hot spot and Important Problems of industry research.And insulator conduct
Huge one of the critical component of dosage, operating status have huge shadow to the reliability of contact net and stable operation in contact net
It rings.Meanwhile the extensive development of Chinese industrial causes compared with havoc environment, bad weather increases, to contact net insulator
The pollution level on surface is further aggravated, and may cause safely high risks to China railways.
When insulator local environment is more severe and surface has filthy, internal field is stronger, and having larger may go out
Existing corona and arcing events.It therefore is the safe operation for realizing China railways, China develops and utilizes overhead contact line shape
State detection monitoring device (abbreviation 4C system) carries out the monitoring running state of contact net means, wherein also including exhausted to contact net
The detection of edge.
Summary of the invention
The purpose of the present invention is to provide a kind of contact net insulator contamination condition detection method, this method can comparatively fast be given
The accurate judgement of gradation for surface pollution out.
To achieve the above object, the technical scheme is that
A kind of contact net insulator contamination condition detection method, includes the following steps:
Step (1): carrying out the experiment of contact net Insulator Contaminant Discharge in the controlled environment chamber, existing using ultraviolet imager observation experiment
As studying contact net insulator difference equivalent salt deposit density ESDD, the i.e. discharge scenario under different gradation for surface pollution；
Step (2): using video with digital image processing algorithm to the electric discharge phenomena under the different gradation for surface pollution of contact net insulator
It is analyzed, extracts the characteristic quantity of characterization Insulator Contaminant Discharge, and ultraviolet image characteristic quantity and contact net insulator is attached
Salt density directly connects, to reflect the pollution level of contact net insulator；
Step (3): the contact net filth state-detection model based on least square method supporting vector machine is established, it is exhausted to realize contact net
The close detection of the salt of edge；
Step (4): punishment parameter C and nuclear parameter σ are optimized using Modified particle swarm optimization algorithm；
Step (5): parameter is inputted using filthy state-detection model using the image of monitoring system acquisition insulator are as follows: steady
Fixed/interval hot spot average area, total hot spot average area, humidity；Output parameter is the salt density value of contact net insulator.
Preferably, it in step (1), is carried out in Insulator Contaminant Discharge experiment in the controlled environment chamber, relative humidity is adjustable model
Enclose is 0.0 ~ 1.0；Artificial pollution experimental solids layer is using sodium chloride and kaolin group at experiment pollution layer；It is applied to insulator
Add constant 10 kV voltage, insulator humidity is controlled by discontinuously method that is quantitative, being spaced humidification.
Preferably, in step (2), the pre-processing of image includes: HSI color space conversion, image segmentation, image procossing
And feature extraction.
Preferably, HSI color space refers to through color, saturation degree and luminance information the image defined, is adopted by ultraviolet
The rgb space collected can be converted uniquely to the space HSI.
Preferably, image segmentation uses Maximum scatter difference Threshold segmentation.
Preferably, to using ultraviolet acquired image to carry out burn into expansion；Pass through the noise in corrosion filtering image；
By the blank lacked in expansion supplemental image, keep ultraviolet image more complete.
Preferably, difference is characterized with hot spot average area, interval hot spot average area and total hot spot average area is stablized
The characteristic parameter of pollution degree difference.
The operation principle of the present invention is that:
The present invention will be converted by ultraviolet collected RGB image to the space HSI, therefore include the luminance information of image, and
It is unrelated with the color information of image.Therefore the colouring information for including in original image can be largely reduced, storage space is saved, is improved
Arithmetic speed.
Corrosion and expansion process are carried out to the ultraviolet image of contact net insulator, the image made is more convenient for the later period
Processing and analysis.
Contact net filth state-detection model is established based on least square method supporting vector machine, solution procedure is very fast and simple
It is single.
Least square method supporting vector machine punishment parameter C and nuclear parameter σ is carried out using Modified particle swarm optimization algorithm
Optimization, avoids the blindness of artificial repeated labor, improves the applicable ability and filthy detection level judgement of model
Accuracy rate.
The invention has the benefit that this method can comparatively fast provide the accurate judgement of gradation for surface pollution.
Detailed description of the invention
Fig. 1 show the flow chart of embodiment according to the present invention use.
The ultraviolet image HSI that Fig. 2 show embodiment according to the present invention is decomposed.
Fig. 3 show the insulator arc-over ultraviolet image of embodiment according to the present invention.
Fig. 4 show the number of iterations and fitness relationship based on Modified particle swarm optimization of embodiment according to the present invention
Curve.
Specific embodiment
With reference to the accompanying drawings and examples, further description of the specific embodiments of the present invention.Following embodiment is only
For clearly illustrating technical solution of the present invention, and not intended to limit the protection scope of the present invention.
The technical solution that the present invention embodies is:
As shown in Figure 1, being contact net insulator contamination condition detection method flow chart.This method is first using experiment and video figure
The method of shape processing has obtained discharge scenario of contact net insulator under the conditions of different filthy, and has carried out to wherein characteristic quantity
It extracts.Then contact net insulator contamination detection model is established using least square method supporting vector machine, and by improving grain
The key parameter in model is optimized in subgroup optimization algorithm, finally realizes the insulator contamination etc. based on ultraviolet image
The accurate judgement of grade.
In embodiment, provide a kind of contact net insulator contamination condition detection method comprising steps of
Step (1): carrying out the experiment of contact net Insulator Contaminant Discharge in the controlled environment chamber, and research contact net insulator is different equivalent
Salt density (ESDD), the i.e. discharge scenario under different gradation for surface pollution.Ultraviolet imager observation experiment phenomenon is used in experiment；
According to " 2007-1997 contact nets in electrified railways of TB/T insulation gradation for surface pollution standard ", contact net insulator contamination etc.
Grade can be divided into three-level according to ESDD value, and wherein ESDD value is 0.01-0.1mgcm2When for remove contamination, 0.1-0.3 mgcm2When
Attach most importance to dirty, 0.3-0.35 mgcm2When be extra heavy dirt.In terms of humidity, taking experiment humidity is respectively 60% -95%, and with 5%
For fixed step size.
High-speed railway is selected often to use contact network cantilever insulator as experimental subjects in experiment.
Step (2): using video with digital image processing algorithm to the electric discharge under the different gradation for surface pollution of contact net insulator
Phenomenon is analyzed.Then the characteristic quantity of characterization Insulator Contaminant Discharge is extracted, and ultraviolet image characteristic quantity and contact net
Insulator salt density directly connects, to reflect the pollution level of contact net insulator；
Obtained ultraviolet image is subjected to HSI spatial decomposition first, wherein H represents hue information, S represents saturation infromation, I generation
Table luminance information.Digitized processing more preferably can be carried out to image using the space HSI.By ultraviolet image institute acquired image
RGB information can be converted uniquely to the space HSI, formula are as follows:
In above formula, R ≠ G or R ≠ B, B > G.
HSI spatial decomposition situation is as shown in Figure 2.
Then using thresholding method by the ultraviolet hot spot feature of the I component of ultraviolet image from gray value with background colour
It distinguishes.Thresholding method is the threshold value that target image sets a gray scale, and the pixel portion higher than the value is set as 1, is lower than the value
Pixel portion be set as 0.Facula area is defined as:
In above formula, M is the line number of bianry image matrix；N is bianry image matrix column number；B (i, j) is filtered two
It is worth image.And the selection of gray threshold is the key that image segmentation, and the method for Maximum scatter difference Threshold segmentation is used in the present invention
Carry out the determination of gray threshold.
Then contact net insulator image is handled using the method for expansion and corrosion, the image that makes that treated is more just
In the operation and analysis in later period.
Finally by the analysis of the information recorded to ultraviolet imager, as shown in figure 3, contact can be characterized by therefrom extracting
The characteristic parameter of net insulator difference gradation for surface pollution, including stablize hot spot average area；Interval hot spot average area；Total hot spot is flat
Equal area.
Step (3): establishing the contact net filth state-detection model based on least square method supporting vector machine, realizes contact net
The close detection of the salt of insulator.
Selection input parameter first are as follows: stablize hot spot average area, interval hot spot average area, hot spot average area, wet
Degree；Select output parameter for salt density value；Selection is removed contamination, weight is dirty and extra heavy dirty insulator video sample each 50, contact net, as
Training set sample；It selects to remove contamination, weight is dirty and extra heavy dirty insulator video sample each 20, contact net is as test sample collection.By institute
There is input parameter to normalize in [0,1] section.The method that normalized uses are as follows:
X in formulaminRepresent the minimum value in input parameter, xmaxRepresent the maximum value in input parameter.
Then kernel function is selected, selects radial basis function as kernel function in the present embodiment.
In above formula, K represents Radial basis kernel function；σ represents nuclear parameter.
Step (4): optimizing punishment parameter C and nuclear parameter σ using Modified particle swarm optimization algorithm, avoid according to
By the blindness of experimental selection parameter repeatedly, the applicable ability of least square method supporting vector machine regression model is improved
On the basis of traditional PS O algorithm, the random attenuation factor of particle, convergence rate β and γ parameter are introduced, and assign initial value.
The random attenuation factor of particle changes with the increase of the number of iterations；Convergence rate β, which can be characterized, improves PSO algorithm the convergence speed
Speed, and be positively correlated therewith.The iteration of α, which updates, to be indicated are as follows:
In above formula, γ represents the constant in expression formula.I.e. the α numerical value of iterative process is α in last iterative process each time
γ times of parameter values.
The algorithm is as follows to the improvement of particle position renewal process:
In above formula, best indicates the current position of particle；The globally optimal solution of gbest representing optimized object；R represent one with
Machine number；The section size of scale expression value range.
The Modified particle swarm optimization algorithm by introducing random attenuation factor, convergence rate β and γ parameter accelerates receipts
Speed is held back, ability of searching optimum is improved.
Iteration convergence curve is as shown in Figure 4.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvements and modifications can also be made, these improvements and modifications
Also it should be regarded as protection scope of the present invention.
Claims (7)
1. a kind of contact net insulator contamination condition detection method, which comprises the steps of:
Step (1): carrying out the experiment of contact net Insulator Contaminant Discharge in the controlled environment chamber, existing using ultraviolet imager observation experiment
As studying contact net insulator difference equivalent salt deposit density ESDD, the i.e. discharge scenario under different gradation for surface pollution；
Step (2): using video with digital image processing algorithm to the electric discharge phenomena under the different gradation for surface pollution of contact net insulator
It is analyzed, extracts the characteristic quantity of characterization Insulator Contaminant Discharge, and ultraviolet image characteristic quantity and contact net insulator is attached
Salt density directly connects, to reflect the pollution level of contact net insulator；
Step (3): the contact net filth state-detection model based on least square method supporting vector machine is established, it is exhausted to realize contact net
The close detection of the salt of edge；
Step (4): punishment parameter C and nuclear parameter σ are optimized using Modified particle swarm optimization algorithm；
Step (5): parameter is inputted using filthy state-detection model using the image of monitoring system acquisition insulator are as follows: steady
Fixed/interval hot spot average area, total hot spot average area, humidity；Output parameter is the salt density value of contact net insulator.
2. contact net insulator contamination condition detection method according to claim 1, which is characterized in that
In step (1), Insulator Contaminant Discharge experiment in the controlled environment chamber in carry out, adjustable relative humidity range, be 0.0 ~
1.0；Artificial pollution experimental solids layer is using sodium chloride and kaolin group at experiment pollution layer；Apply constant 10 to insulator
KV voltage controls insulator humidity by discontinuously method that is quantitative, being spaced humidification.
3. contact net insulator contamination condition detection method according to claim 2, which is characterized in that
In step (2), the pre-processing of image includes: HSI color space conversion, image segmentation, image procossing and feature extraction.
4. contact net insulator contamination condition detection method according to claim 3, which is characterized in that
HSI color space refers to through color, saturation degree and luminance information the image defined, empty by ultraviolet collected RGB
Between can uniquely convert to the space HSI.
5. contact net insulator contamination condition detection method according to claim 4, which is characterized in that
Image segmentation uses Maximum scatter difference Threshold segmentation.
6. contact net insulator contamination condition detection method according to claim 5, which is characterized in that
To using ultraviolet acquired image to carry out burn into expansion；Pass through the noise in corrosion filtering image；It is supplemented by expansion
The blank lacked in image keeps ultraviolet image more complete.
7. contact net insulator contamination condition detection method according to claim 6, which is characterized in that
Different pollution degree differences are characterized with hot spot average area, interval hot spot average area and total hot spot average area is stablized
Characteristic parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811144504.5A CN109470628A (en) | 2018-09-29 | 2018-09-29 | Contact net insulator contamination condition detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811144504.5A CN109470628A (en) | 2018-09-29 | 2018-09-29 | Contact net insulator contamination condition detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109470628A true CN109470628A (en) | 2019-03-15 |
Family
ID=65664514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811144504.5A Pending CN109470628A (en) | 2018-09-29 | 2018-09-29 | Contact net insulator contamination condition detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109470628A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114113947A (en) * | 2021-11-30 | 2022-03-01 | 国网辽宁省电力有限公司铁岭供电公司 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1081375A2 (en) * | 1999-09-02 | 2001-03-07 | Ngk Spark Plug Co., Ltd. | Method of detecting spark plug fouling and ignition system having means for carrying out the same |
| WO2007067626A2 (en) * | 2005-12-06 | 2007-06-14 | Eisenmann Corporation | Wet electrostatic liquid film oxidizing reactor apparatus and method for removal of nox, sox, mercury, acid droplets, heavy metals and ash particles from a moving gas |
| CN101598692A (en) * | 2008-06-02 | 2009-12-09 | 邱雪 | A kind of external insulation pollution of electric transmission and transformation equipment degree measuring method, system and device |
| CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Visible image based insulator detection method and device thereof |
| CN203732603U (en) * | 2013-12-12 | 2014-07-23 | 国家电网公司 | Insulator pollution flashover alarm system |
| CN103940824A (en) * | 2014-04-29 | 2014-07-23 | 长春工程学院 | Air electric transmission line insulator detecting method |
| KR20140100638A (en) * | 2013-02-06 | 2014-08-18 | 주식회사 케이씨씨 | Liquid Silicone Rubber Composition for Insulator |
| CN104280072A (en) * | 2014-10-21 | 2015-01-14 | 华北电力大学（保定） | Insulator dirt detecting method and device |
| DE102014003093B3 (en) * | 2014-03-01 | 2015-03-19 | Thomas Warscheid | Method and apparatus for indicating mold growth in an environment to be monitored |
| CN104483326A (en) * | 2014-12-19 | 2015-04-01 | 长春工程学院 | High-voltage wire insulator defect detection method and high-voltage wire insulator defect detection system based on deep belief network |
| CN105004972A (en) * | 2015-06-25 | 2015-10-28 | 华北电力大学（保定） | Porcelain insulator insulation state evaluation method based on solar-blind ultraviolet imaging image feature |
| CN105445283A (en) * | 2016-02-01 | 2016-03-30 | 成都通甲优博科技有限责任公司 | Detection method for filthy conditions of insulator images |
| CN106124942A (en) * | 2016-06-27 | 2016-11-16 | 华北电力大学（保定） | A kind of based on infrared and ultraviolet image method zero resistance insulator detection method |
| CN106124949A (en) * | 2016-08-30 | 2016-11-16 | 国网山东省电力公司济南供电公司 | A kind of based on thermal infrared imaging technology to insulator breakdown on-line monitoring method |
| CN106596579A (en) * | 2016-11-15 | 2017-04-26 | 同济大学 | Insulator contamination condition detection method based on multispectral image information fusion |
| CN106682774A (en) * | 2016-12-23 | 2017-05-17 | 中国铁路总公司 | Contact net insulator pollution flashover prediction method |
| CN106770070B (en) * | 2016-11-11 | 2018-01-16 | 清华大学深圳研究生院 | A kind of insulator surface equivalent salt density measuring method and device |
| CN108197396A (en) * | 2018-01-09 | 2018-06-22 | 国网福建省电力有限公司 | A kind of high voltage isolator superheat state Forecasting Methodology based on PSO-SVM |
-
2018
- 2018-09-29 CN CN201811144504.5A patent/CN109470628A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1081375A2 (en) * | 1999-09-02 | 2001-03-07 | Ngk Spark Plug Co., Ltd. | Method of detecting spark plug fouling and ignition system having means for carrying out the same |
| WO2007067626A2 (en) * | 2005-12-06 | 2007-06-14 | Eisenmann Corporation | Wet electrostatic liquid film oxidizing reactor apparatus and method for removal of nox, sox, mercury, acid droplets, heavy metals and ash particles from a moving gas |
| CN101598692A (en) * | 2008-06-02 | 2009-12-09 | 邱雪 | A kind of external insulation pollution of electric transmission and transformation equipment degree measuring method, system and device |
| KR20140100638A (en) * | 2013-02-06 | 2014-08-18 | 주식회사 케이씨씨 | Liquid Silicone Rubber Composition for Insulator |
| CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Visible image based insulator detection method and device thereof |
| CN203732603U (en) * | 2013-12-12 | 2014-07-23 | 国家电网公司 | Insulator pollution flashover alarm system |
| DE102014003093B3 (en) * | 2014-03-01 | 2015-03-19 | Thomas Warscheid | Method and apparatus for indicating mold growth in an environment to be monitored |
| CN103940824A (en) * | 2014-04-29 | 2014-07-23 | 长春工程学院 | Air electric transmission line insulator detecting method |
| CN104280072A (en) * | 2014-10-21 | 2015-01-14 | 华北电力大学（保定） | Insulator dirt detecting method and device |
| CN104483326A (en) * | 2014-12-19 | 2015-04-01 | 长春工程学院 | High-voltage wire insulator defect detection method and high-voltage wire insulator defect detection system based on deep belief network |
| CN105004972A (en) * | 2015-06-25 | 2015-10-28 | 华北电力大学（保定） | Porcelain insulator insulation state evaluation method based on solar-blind ultraviolet imaging image feature |
| CN105445283A (en) * | 2016-02-01 | 2016-03-30 | 成都通甲优博科技有限责任公司 | Detection method for filthy conditions of insulator images |
| CN106124942A (en) * | 2016-06-27 | 2016-11-16 | 华北电力大学（保定） | A kind of based on infrared and ultraviolet image method zero resistance insulator detection method |
| CN106124949A (en) * | 2016-08-30 | 2016-11-16 | 国网山东省电力公司济南供电公司 | A kind of based on thermal infrared imaging technology to insulator breakdown on-line monitoring method |
| CN106770070B (en) * | 2016-11-11 | 2018-01-16 | 清华大学深圳研究生院 | A kind of insulator surface equivalent salt density measuring method and device |
| CN106596579A (en) * | 2016-11-15 | 2017-04-26 | 同济大学 | Insulator contamination condition detection method based on multispectral image information fusion |
| CN106682774A (en) * | 2016-12-23 | 2017-05-17 | 中国铁路总公司 | Contact net insulator pollution flashover prediction method |
| CN108197396A (en) * | 2018-01-09 | 2018-06-22 | 国网福建省电力有限公司 | A kind of high voltage isolator superheat state Forecasting Methodology based on PSO-SVM |
Non-Patent Citations (5)
| Title |
|---|
| 曾建潮: "二阶微粒群算法", 《计算机研究与发展》 * |
| 王喜宾: "《基于优化支持向量机的个性化推荐研究》", 30 June 2017 * |
| 胡建秀: "二阶振荡微粒群算法", 《系统仿真学报》 * |
| 赵乃刚: "自适应二阶震荡粒子群算法", 《电子技术与软件工程》 * |
| 金立军: "基于紫外成像技术的接触网绝缘子污秽状态检测", 《高电压技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114113947A (en) * | 2021-11-30 | 2022-03-01 | 国网辽宁省电力有限公司铁岭供电公司 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105004972B (en) | Porcelain insulator Condition assessment of insulation method based on day blind ultraviolet imagery characteristics of image | |
| CN109389180A (en) | A power equipment image-recognizing method and inspection robot based on deep learning | |
| CN106680285B (en) | Method for recognizing insulator contamination state based on infrared image assisted visible light image | |
| CN113486865B (en) | Power transmission line suspended foreign object target detection method based on deep learning | |
| CN106407928B (en) | Transformer composite insulator casing monitoring method and system based on raindrop identification | |
| CN106375345A (en) | Malware domain name detection method and system based on periodic detection | |
| CN103940824B (en) | A kind of aerial electric transmission line isolator detection method | |
| CN106934418B (en) | Insulator infrared diagnosis method based on convolution recursive network | |
| CN105445283A (en) | Detection method for filthy conditions of insulator images | |
| CN106054032A (en) | Non-contact measurement method for surface discharge pulse peak of high-voltage insulator | |
| CN111864896A (en) | Power load monitoring method and system | |
| CN103323460A (en) | Visible image based insulator detection method and device thereof | |
| CN107679495A (en) | A kind of detection method of transmission line of electricity periphery activity engineering truck | |
| CN110110732B (en) | Intelligent inspection method for catering kitchen | |
| CN108092989B (en) | DDoS attack detection method based on intelligent bee colony algorithm | |
| CN109470628A (en) | Contact net insulator contamination condition detection method | |
| CN107833211A (en) | Zero resistance insulator automatic testing method and device based on infrared image | |
| CN108596196B (en) | Pollution state evaluation method based on insulator image feature dictionary | |
| CN110059076A (en) | A kind of Mishap Database semi-automation method for building up of power transmission and transformation line equipment | |
| CN111798405B (en) | Deep learning-based fault diagnosis method for casing infrared image | |
| CN110163855B (en) | Color image quality evaluation method based on multi-path deep convolutional neural network | |
| CN111161236A (en) | Method, device, medium and equipment for detecting hydrophobicity of composite insulator | |
| Liu et al. | Insulator contamination diagnosis method based on deep learning convolutional neural network | |
| CN114897918B (en) | Artificial intelligence-based photovoltaic cleaning robot brush power adjustment method and system | |
| CN113744179A (en) | Hardware defect detection method on power transmission and distribution line |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190315 |
|
| RJ01 | Rejection of invention patent application after publication |