CN109035247A - A kind of abnormal power equipment identifying system - Google Patents
A kind of abnormal power equipment identifying system Download PDFInfo
- Publication number
- CN109035247A CN109035247A CN201811014409.3A CN201811014409A CN109035247A CN 109035247 A CN109035247 A CN 109035247A CN 201811014409 A CN201811014409 A CN 201811014409A CN 109035247 A CN109035247 A CN 109035247A
- Authority
- CN
- China
- Prior art keywords
- power equipment
- image
- corresponding power
- module
- mobile terminal
- 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.)
- Withdrawn
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000001105 regulatory effect Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 9
- 238000001514 detection method Methods 0.000 abstract description 5
- 230000005856 abnormality Effects 0.000 abstract description 2
- 238000002834 transmittance Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 5
- 238000000034 method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of abnormal power equipment identifying system, which includes: Image Acquisition terminal, processor and mobile terminal.Image Acquisition terminal is set near corresponding power equipment, for obtaining corresponding power equipment image；Processor, for handling the power equipment image of acquisition, and the judgement result for generating corresponding power equipment safety state is sent to mobile terminal；Mobile terminal, for correspondingly being shown according to judgement result.The present invention overcomes artificial detection power equipment whether Yi Chang drawback, image recognition processing is carried out by the corresponding power equipment image acquired to Image Acquisition terminal, it is whether abnormal that power equipment in power equipment image can be automatically identified, and staff is reminded by mobile terminal, the precision and accuracy to the identification of power equipment abnormality detection are improved, the objectivity, real-time and accuracy of monitoring are also improved.
Description
Technical field
The present invention relates to electric device maintenance fields, and in particular to a kind of abnormal power equipment identifying system.
Background technique
With the continuous expansion of China's electric power networks scale, the safe and reliable operation of the power equipments such as substation is heavy to closing
It wants, and the operating status of power equipment is to determine one of the key factor of its safe and stable operation.
A kind of monitoring side that picture control is power equipment operating status is carried out to power equipment by video monitoring system
Formula.Existing video monitoring system only has video monitoring function and recording function, cannot carry out intelligentized master to monitoring objective
Dynamic discriminance analysis needs operator's moment observation analysis image, virtually increases only by a large amount of image transmitting to dispatching terminal
The work load of operator is added；Meanwhile the subjectivity of human eye fatigable weakness and artificial judgment, it has seriously affected electric power and has set
Standby monitoring running state the degree of automation further increases；In addition, the operating status of many high-tension apparatuses is difficult to be converted into electricity
Signal, the influence in signal conversion and transmission process vulnerable to strong-electromagnetic field；The operating parameter of important equipment needs real-time monitoring,
It is difficult to meet requirement of real-time using manual patrol, and the sense of responsibility of floor manager, working attitude and mental status seriously affect
The result of detection；Moreover, human eye is difficult to differentiate the grey scale change of fine image, it is difficult to which objective judgement power equipment whether there is
It is abnormal.
Summary of the invention
In view of the above-mentioned problems, the present invention provides a kind of abnormal power equipment identifying system.
The purpose of the present invention is realized using following technical scheme:
A kind of abnormal power equipment identifying system, the system include: Image Acquisition terminal, processor and mobile terminal.
Described image acquisition terminal is set near corresponding power equipment, for obtaining corresponding power equipment image；Institute
Processor is stated, for handling the power equipment image of acquisition, and generates the judgement of corresponding power equipment safety state
As a result it is sent to the mobile terminal；The mobile terminal, for correspondingly being shown according to the judgement result.
The invention has the benefit that the present invention overcomes artificial detection power equipment whether Yi Chang drawback, by right
The corresponding power equipment image of Image Acquisition terminal acquisition carries out image recognition processing, can automatically identify power equipment figure
Whether power equipment is abnormal as in, and reminds staff by mobile terminal, improves and identifies to power equipment abnormality detection
Precision and accuracy, also improve the objectivity, real-time and accuracy of monitoring.
Detailed description of the invention
The present invention will be further described with reference to the accompanying drawings, but the embodiment in attached drawing is not constituted to any limit of the invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is structure chart of the invention；
Fig. 2 is the frame construction drawing of processor 2 of the present invention.
Appended drawing reference: Image Acquisition terminal 1；Processor 2；Mobile terminal 3；Image denoising module 4；Image enhancement module 5；
Characteristic extracting module 6；Feature recognition module 7；Security feature database 8；Memory module 9.
Specific embodiment
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of abnormal power equipment identifying system, the system includes: Image Acquisition terminal 1, processor 2 and moves
Dynamic terminal 3.
Described image acquisition terminal 1 is set near corresponding power equipment, for obtaining corresponding power equipment image；
The processor 2 for handling the power equipment image of acquisition, and generates sentencing for corresponding power equipment safety state
Determine result and is sent to the mobile terminal 3；The mobile terminal 3, for correspondingly being shown according to the judgement result.
Preferably, described image acquisition terminal 1 is CCD camera.
Preferably, the mobile terminal 3 is mobile phone or tablet computer.
Preferably, referring to fig. 2, the processor 2 includes image denoising module 4, image enhancement module 5, feature extraction mould
Block 6, feature recognition module 7, security feature database 8 and memory module 9.
Described image denoises module 4, for removing the random noise in corresponding power equipment image；Described image
Enhance module 5, for carrying out enhancing processing to the power equipment image after denoising；The characteristic extracting module 6 is used for from enhancing
The feature vector of corresponding power equipment image is extracted in power equipment image afterwards；The security feature database 8, for depositing
Store up the security feature vector of trained corresponding power equipment image；The feature recognition module 7 is used for the feature
The feature vector that extraction module obtains and the security feature vector of the corresponding power equipment in the security feature database 8 into
Whether abnormal row matching judges corresponding power equipment, and generates and determine that result is sent to the mobile terminal 3 accordingly；Institute
Memory module 9 is stated, for storing the power equipment image of the acquisition of described image acquisition terminal 1.
Preferably, the random noise in the corresponding power equipment image of removal, specifically:
(1) K layers of wavelet decomposition are carried out to corresponding power equipment image using wavelet transformation, obtains one group of wavelet systems
Number s={ s1,s2…sN, N is wavelet coefficient number；
(2) wavelet coefficient s is handled using threshold value, wherein thresholding functions are as follows:
In formula, s is the wavelet coefficient before denoising, and s ' is the wavelet coefficient after denoising, T1It is upper threshold value, T2It is threshold value
Lower limit value, and T1、T2Meet T1=α T2, 0 < α < 1；M is regulatory factor, and m > 1, sgn (f) are sign function, when f is positive
When number, 1 is taken, when being negative, takes 0；
(3) s ' is reconstructed using wavelet inverse transformation, the power equipment image after being denoised.
It, can be effectively to containing the utility model has the advantages that handle noise-containing power equipment image using thresholding functions
The power equipment image of noise is filtered；According to T1、T2With the absolute difference of wavelet coefficient s, select at different threshold function tables
Wavelet coefficient is managed, the noise of power equipment image can be adaptively removed, retains the effective information of power equipment image；It is practical
Noise there are many containing in acquired image, and by adjusting the size of regulatory factor m, adjustable threshold handles the wave of function
Shape makes it possible to remove the noise in power equipment image to the maximum extent.
Preferably, in the above-described embodiment, the bottom threshold value of kth layer wavelet coefficient is calculated using following formula:
In formula, T2,kIt is the bottom threshold value of kth layer wavelet coefficient, K is the Decomposition order of wavelet transformation, and k=1,
2 ..., k ..., K, σNFor the estimate variance of N number of wavelet coefficient, N is wavelet coefficient number, σkFor the estimation of kth layer wavelet coefficient
Variance, DkFor the number of kth layer wavelet coefficient, σr,kEstimate variance for noise-free signal r in kth layer, γ1、γ2、γ3For power
Repeated factor, and meet γ1+γ2+γ3=1.
The utility model has the advantages that calculating separately the bottom threshold value of different decomposition layer using above-mentioned algorithm, and then each point will be obtained
The bottom threshold value for solving layer substitutes into thresholding functions, completes the denoising to power equipment image, which realizes
Automatic adjusument to bottom threshold value and upper threshold value can be selected according to the actual conditions of each decomposition layer of wavelet transformation
Different bottom threshold values and bottom threshold value complete the denoising process to power equipment image, avoid setting fixed threshold band
The noise wavelet coefficients come are retained, and to still remain much noise in the image after denoising, are also avoided simultaneously
Useful wavelet coefficient is treated as into noise information, and makes the target after denoising too smooth, detailed information is had lost, improves
The accuracy of denoising, be conducive to it is subsequent to power equipment whether Yi Chang accurate judgement.
Preferably, the power equipment image after described pair of denoising carries out enhancing processing, specifically:
(1) formula is utilizedPower equipment image after denoising is inverted, whereinFor denoising after power equipment image reverse image,For the power equipment image after denoising, C is image RGB
Any one Color Channel in color model；
(2) the global atmosphere light and transmittance values of the reverse image are sought respectively, in which:
The formula of global atmosphere light are as follows:
AC=[A0 A0 A0]T
In formula, Y (x) is the luminance graph in reverse image at pixel x,It is respectively anti-
Turn the channel R in image at pixel x, the channel G, channel B value, A0For initial global atmosphere light；ACFor initial global atmosphere light
In the matrix that tri- channels RGB are constituted, C is the channel R, the channel G, one of in channel B；
The formula of transmittance values are as follows:
In formula, t (x) is transmittance values, and ω is customized adjusting parameter, and Ω (x) is the neighbour centered on pixel x
Domain, y are the pixels in pixel x neighborhood,For the value of the C-channel in reverse image at pixel y；
(3) the global atmosphere light and transmissivity that acquire are substituted into following pattern function, the field after being restored
Scape light image, wherein the pattern function are as follows:
In formula,For scene light image；
(4) formula is utilizedBy scene light imageIt is inverted, is obtained
As enhanced power equipment image.
The utility model has the advantages that the power equipment image after denoising is inverted using above-mentioned algorithm, reverse image is obtained, into
And reverse image is handled, obtain scene light image, the algorithm can reduce in power equipment image due to light, mist,
The influence to acquisition power equipment image definition such as dust, edge feature and the details that can highlight power equipment image are special
Sign also can more reflect the color letter of power equipment image so that the visual effect of enhanced power equipment image is truer
Breath and its texture information, in order to subsequent extraction and identification to target signature to be identified in power equipment image, and the algorithm
Simply, processing speed is fast, also extends the service life of the system.
Preferably, transmittance values t (x) is modified using following formula, obtains revised transmittance values, revised
The calculation formula of radiance rate value t ' (x) are as follows:
The utility model has the advantages that being modified using above formula to obtained transmittance values t (x), transmittance values t ' (x) can not only have
Effect increases the detailed information of corresponding power equipment image and is also able to maintain the spatial continuity of transmissivity, so that after restoring
Scene image has more smooth visual effect.
Preferably, the feature vector that characteristic extracting module is obtained with it is corresponding in the security feature database
The security feature vector of power equipment is matched, and whether abnormal judges corresponding power equipment, and generates corresponding judgement knot
Fruit is sent to the mobile terminal, specifically: the feature vector for obtaining the characteristic extracting moduleWith trained institute
State the security feature vector of the corresponding power equipment in security feature databaseIt is matched, if described eigenvector
With the security feature vectorMeetThen the power equipment is without exception, otherwise determines power equipment exception,
Output determine as a result, and the judgement result is sent to the mobile terminal, whereinThe characteristic extracting module obtains
The feature vector of corresponding power equipment,For power equipment corresponding in the security feature database security feature to
Amount, δ are the customized similarity factor
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although explaining in detail referring to preferred embodiment to the present invention, those skilled in the art are answered
Work as understanding, it can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of abnormal power equipment identifying system, characterized in that include: Image Acquisition terminal, processor and mobile terminal；
Described image acquisition terminal is set near corresponding power equipment, for obtaining corresponding power equipment image；
The processor for handling the power equipment image of acquisition, and generates corresponding power equipment safety state
Judgement result be sent to the mobile terminal；
The mobile terminal, for correspondingly being shown according to the judgement result.
2. abnormal power equipment identifying system according to claim 1, characterized in that described image acquisition terminal is CCD
Video camera.
3. abnormal power equipment identifying system according to claim 1, characterized in that the mobile terminal is mobile phone or puts down
Plate computer.
4. abnormal power equipment identifying system according to claim 2, characterized in that the processor includes image denoising
Module, image enhancement module, characteristic extracting module, feature recognition module, security feature database and memory module；
Described image denoises module, for removing the random noise in corresponding power equipment image；
Described image enhances module, for carrying out enhancing processing to the power equipment image after denoising；
The characteristic extracting module, for extracting the feature of corresponding power equipment image from enhanced power equipment image
Vector；
The security feature database, for storing the security feature vector of trained corresponding power equipment image；
The feature recognition module, feature vector and the security feature database for obtaining the characteristic extracting module
In the security feature vector of corresponding power equipment matched, whether abnormal judge corresponding power equipment, and generate phase
The judgement result answered is sent to the mobile terminal；
The memory module, for storing the power equipment image of described image acquisition terminal acquisition.
5. abnormal power equipment identifying system according to claim 4, characterized in that the corresponding electric power of removal
Random noise in equipment image, specifically:
(1) K layers of wavelet decomposition are carried out to corresponding power equipment image using wavelet transformation, obtains one group of wavelet coefficient s
={ s1, s2…sN, N is wavelet coefficient number；
(2) wavelet coefficient s is handled using threshold value, wherein thresholding functions are as follows:
In formula, s is the wavelet coefficient before denoising, and s ' is the wavelet coefficient after denoising, T1It is upper threshold value, T2It is bottom threshold
Value, and T1、T2Meet T1=α T2, 0 < α < 1；M is regulatory factor, and m > 1, sgn (f) they are sign function, when f is positive number,
1 is taken, when being negative, takes 0；
(3) s ' is reconstructed using wavelet inverse transformation, the power equipment image after being denoised.
6. abnormal power equipment identifying system according to claim 5, characterized in that described to obtain characteristic extracting module
Feature vector matched with the security feature vector of the corresponding power equipment in the security feature database, judge phase
Whether the power equipment answered is abnormal, and generates corresponding judgement result and be sent to the mobile terminal, specifically: by the feature
The feature vector that extraction module obtainsWith the peace of the corresponding power equipment in the trained security feature database
Full feature vectorIt is matched, if described eigenvectorWith the security feature vectorMeetThen should
Power equipment is without exception, otherwise determines power equipment exception, and output determines as a result, and the judgement result is sent to the shifting
Dynamic terminal, whereinFor the feature vector for the corresponding power equipment that the characteristic extracting module obtains,For the Special safety
The security feature vector of corresponding power equipment in database is levied, δ is the customized similarity factor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014409.3A CN109035247A (en) | 2018-08-31 | 2018-08-31 | A kind of abnormal power equipment identifying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811014409.3A CN109035247A (en) | 2018-08-31 | 2018-08-31 | A kind of abnormal power equipment identifying system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109035247A true CN109035247A (en) | 2018-12-18 |
Family
ID=64622730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811014409.3A Withdrawn CN109035247A (en) | 2018-08-31 | 2018-08-31 | A kind of abnormal power equipment identifying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109035247A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651925A (en) * | 2020-12-04 | 2021-04-13 | 合肥阳光智维科技有限公司 | Diagnosis method and device of photovoltaic module |
| CN112712111A (en) * | 2020-12-23 | 2021-04-27 | 南方电网深圳数字电网研究院有限公司 | Device state detection method, electronic device, and storage medium |
-
2018
- 2018-08-31 CN CN201811014409.3A patent/CN109035247A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112651925A (en) * | 2020-12-04 | 2021-04-13 | 合肥阳光智维科技有限公司 | Diagnosis method and device of photovoltaic module |
| CN112712111A (en) * | 2020-12-23 | 2021-04-27 | 南方电网深圳数字电网研究院有限公司 | Device state detection method, electronic device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xie et al. | Image de-noising algorithm based on Gaussian mixture model and adaptive threshold modeling | |
| CN110163818A (en) | A kind of low illumination level video image enhancement for maritime affairs unmanned plane | |
| CN103729842B (en) | Based on the fabric defect detection method of partial statistics characteristic and overall significance analysis | |
| CN108510496B (en) | Fuzzy detection method for SVD (singular value decomposition) based on image DCT (discrete cosine transformation) domain | |
| CN104268519B (en) | Image recognition terminal and its recognition methods based on pattern match | |
| CN110599507B (en) | Tomato identification and positioning method and system | |
| CN109934221B (en) | Attention mechanism-based automatic analysis, identification and monitoring method and system for power equipment | |
| CN110097522B (en) | Single outdoor image defogging method based on multi-scale convolution neural network | |
| CN108268832A (en) | Electric operating monitoring method, device, storage medium and computer equipment | |
| CN109670398A (en) | Pig image analysis method and pig image analysis equipment | |
| CN111144337B (en) | Fire detection method and device and terminal equipment | |
| CN110334660A (en) | A kind of forest fire monitoring method based on machine vision under the conditions of greasy weather | |
| CN109117855A (en) | Abnormal power equipment image identification system | |
| CN109035247A (en) | A kind of abnormal power equipment identifying system | |
| CN110033487A (en) | Vegetables and fruits collecting method is blocked based on depth association perception algorithm | |
| Mei et al. | Single image dehazing using dark channel fusion and haze density weight | |
| CN108154496A (en) | A kind of power equipment appearance suitable for electric operating robot changes recognition methods | |
| CN113327263B (en) | Image vision-based fish school activity monitoring method | |
| Chen et al. | Improve transmission by designing filters for image dehazing | |
| Wang et al. | Single-image dehazing using color attenuation prior based on haze-lines | |
| CN109713745B (en) | A kind of intelligent charge detection circuit | |
| CN112418112A (en) | Orchard disease and pest monitoring and early warning method and system | |
| CN109146834A (en) | Car damage identification method and device, computer readable storage medium, terminal | |
| Balcilar et al. | Extracting vehicle density from background estimation using Kalman filter | |
| Yang et al. | Cherry recognition based on color channel transform |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181218 |
|
| WW01 | Invention patent application withdrawn after publication |