CN103984952B - The method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure - Google Patents
The method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure Download PDFInfo
- Publication number
- CN103984952B CN103984952B CN201410157662.XA CN201410157662A CN103984952B CN 103984952 B CN103984952 B CN 103984952B CN 201410157662 A CN201410157662 A CN 201410157662A CN 103984952 B CN103984952 B CN 103984952B
- Authority
- CN
- China
- Prior art keywords
- blade
- mrow
- msub
- primitive
- wind
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses the method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure, the method comprising the steps of one, divides blade of wind-driven generator, obtains blade primitive；Step 2: being taken pictures to blade of wind-driven generator primitive, and background is rejected；Step 3: the blade primitive result images progress obtained to step 2 is secondary to be divided into picture element, and feature extraction is carried out to primitive result images；Step 4: being trained to the SVMs used in fault diagnosis；Step 5: being diagnosed using the SVMs trained to the superficial failure species of blade of wind-driven generator primitive；Step 6: the operation Step 2: three, five is carried out to all blade primitives, until completing the superficial failure diagnosis of integrated plate blade.This method diagnostic accuracy is high.
Description
Technical field
The present invention relates to wind energy conversion system fault diagnosis field, specifically refer to send out power system wind-force based on machine vision image
The method that motor blade surface crack fault is diagnosed.
Background technology
Blade as one of wind energy conversion system fault rate highest part, because its is bulky, sensor installation difficulty, monitoring
The reasons such as equipment costliness all the time without it is a kind of can be with the fault diagnosis of field application and failure supervision meanses.Existing pneumatic equipment bladess
Fault diagnosis be mainly and pass through to the fault-signal of wind energy conversion system driving-chain supervision diagnosis pneumatic equipment bladess failure indirectly.To wind-force
The research of the fault diagnosis of machine blade has caused the attention of scientific research personnel and has carried out a variety of trial Journal of Sex Research.Including to wind-force
Machine blade surface installs the contact diagnostic methods of sensor such as vibration, stress, sound emission and carries out thermal imaging, X-ray to blade
Scanning, the noncontact method for diagnosing faults of digital picture correlation analysis.
For contact method for diagnosing faults, reached by then passing through to be monitored sensor institute installation position signal
The purpose being integrally monitored to blade, so fault location accuracy rate is relatively low, and due to the more meeting of required number of sensors
Bring cost too high and the shortcomings of difficult arrangement.Contactless method for diagnosing faults with accurately to failure carry out position but by
In its equipment price it is expensive and it is bulky be difficult to install at the scene also without being applied.
The content of the invention
Power system blade of wind-driven generator surface is split based on machine vision image it is an object of the invention to provide one kind
The method that line failure is diagnosed.
What the above-mentioned purpose of the present invention was realized by following technical solution：Based on machine vision image to power system wind
The method that power generator blade surface crack fault is diagnosed, this method comprises the following steps：
Step 1: dividing blade of wind-driven generator, blade primitive is obtained；
The detailed process of step one is as follows：First, using coating the method for colour band on blade of wind-driven generator surface to whole
Individual blade carries out region division, is divided into N number of subregion, wherein N >=1, any one subregion is referred to as blade primitive；
Step 2: being taken pictures to blade of wind-driven generator primitive, and background is rejected；
The detailed process of step 2 is as follows：Blade of wind-driven generator primitive is shot first, blade primitive is obtained
Original image；Then, original image is passed through into gray proces, gray-scale map is changed into from cromogram, obtain the gray-scale map of blade primitive
Picture；Blade primitive contours extract is carried out to gray level image by using Roberts contour extraction methods again, blade primitive is obtained
Bianry image, the bianry image Leaf primitive is white Foreground, and remainder is black background；Further, to bianry image
Morphological scale-space is carried out, the effect of preliminary denoising is reached, preliminary denoising image is obtained；And then, in preliminary denoising image, use
Bianry image connected component labeling method, twice sweep is performed to preliminary denoising image, is scanned for the first time by progressively scanning pixel,
Judge the neighbouring relations between pixel, identical connection label is assigned to the pixel for belonging to same connected region；Second of scanning
The mark repeated is eliminated, is merged and is belonged to same connected region but with the subregion of not isolabeling number, looked for by the scanning of two steps
To white 8 connected region that region area is maximum, white 8 connected region of the maximum is exactly the wind-driven generator leaf to be obtained
Piece primitive image-region；Finally, the region removed outside blade of wind-driven generator primitive image-region is scratched from original image, is reached
To the purpose for rejecting background, while the blade primitive result images of wind-driven generator can be obtained；
Step 3: the blade primitive result images progress obtained to step 2 is secondary to be divided into picture element, and to primitive
Result images carry out feature extraction；
The detailed process of step 3 is as follows：First, the blade primitive result images that step 2 is obtained are divided into multiple flat
Row quadrilateral mesh, and then pneumatic equipment bladess primitive result images are split into according to grid by picture element；Then data are used
Feature extraction algorithm is handled picture element, obtains the data characteristics of picture element.
Step 4: being trained to the SVMs used in fault diagnosis；
The detailed process of step 4 is as follows：It assign the picture element data characteristics obtained in step 3 as training data；So
Afterwards, SVMs is trained using training data, obtains the SVMs trained；Supporting vector in the step 4
The training of machine uses standard algorithm of support vector machine, and specific training step is as follows：
(1) training set T={ (x are set1,y1),(x2,y2),…(xl,yl)}∈(X,Y)l
Wherein xi∈X∈RP, yi∈ Y={ -1,1 }, i=1 ... l;
xiThe vector constituted for the data characteristics of picture element；If xiThere are blade cracks on corresponding picture element, then
yiFor 1, otherwise yiFor -1.
(2) optimization problem is solved（1.1）, obtain optimal solution：
αi>=0, i=1 ..., l.
Wherein αiIt is multiplier corresponding with each training data for the intermediate variable of introducing.
(3) α is selected*Positive component, calculate
Wherein b*It is classification thresholds for the intermediate variable of introducing.
(4) linear optimal Optimal Separating Hyperplane is constructed, decision function is drawn：
Step 5: being examined using the SVMs trained the superficial failure species of blade of wind-driven generator primitive
It is disconnected；
The detailed process of step 5 is as follows：The picture element data that blade of wind-driven generator primitive is obtained through step 3 are special
Levy and be followed successively by the decision function that variable x substitutes into step 4 acquisition, the generator blade primitive is judged by the value of decision function
With the presence or absence of face crack failure, represent there are blade cracks if being 1 if the value of decision function, if the value of decision function is -1
Represent that blade cracks are not present；
Step 6: the operation Step 2: three, five is carried out to all blade primitives, until completing the table of integrated plate blade
Face fault diagnosis.
Above-mentioned formula is quoted：Zhang Xuegong are on Statistical Learning Theory and SVMs [J] automation journals .2000
(01) formula in, is prior art.
In the present invention, in the step 3, it is to use to be based on dual-tree complex wavelet that data characteristics processing is carried out to picture element
The picture feature extraction method of analysis.
In the present invention, in the step 3, data characteristics processing is carried out to picture element to be used based on manifold learning
Image data method of descent.
In the present invention, in the step 3, data characteristics processing is carried out to picture element to be used based on improvement manifold
Practise the image data method of descent of algorithm.
In summary, this patent provides a kind of blade of wind-driven generator superficial failure diagnosis side based on computer vision
Method；First, blade of wind-driven generator is divided, blade primitive is obtained.Then, pneumatic equipment bladess primitive is taken pictures, and background is entered
Row is rejected.And then, it is secondary to the progress of blade primitive result images to be divided into picture element, and picture element position is recorded to piecemeal
Put.Further, feature extraction is carried out to picture element.Further, the characteristic of a part of picture element is taken as instruction
Practice data to be trained SVMs.Finally, using the SVMs trained come to whole pneumatic equipment bladess whether
There is face crack failure to be judged, and supervise the development of its failure.
Compared with prior art, this patent is exercised supervision and diagnosed to pneumatic equipment bladess failure using image acquiring apparatus.
Carried for blade background complexity, blade fault location difficulty, the blade fault type classification difficulty in blade fault monitor procedure
Solution is gone out.Designed by rejecting flow, blade fault positioning flow and blade classification process to blade background.
This patent can effectively reject the complicated background of blade, remove the influence produced by complex background is recognized to leaf image.Adopt
Positioning is carried out to pneumatic equipment bladess failure with colour band and anchor point can effectively supervise the growth of failure.
Brief description of the drawings
The present invention is described in further detail with reference to the accompanying drawings and detailed description.
Fig. 1 is the overall flow schematic diagram of diagnostic method of the present invention；
Fig. 2 is that diagnostic method Leaf image background of the present invention rejects flow；
Fig. 3 is picture element extraction flow in diagnostic method of the present invention.
Embodiment
The present invention is described in detail with reference to the accompanying drawings and examples.
The invention provides one kind based on machine vision image to power system blade of wind-driven generator face crack failure
The method diagnosed, this method comprises the following steps：
Step 1: dividing blade of wind-driven generator, blade primitive is obtained；
In embodiments of the present invention, it is used in pneumatic equipment bladess surface and coats the method for colour band and leaf area is drawn
Point, in order to the extraction to monitor area.This is due to nearly hundred meters of large scale wind power machine single blade length, therefore single capture can not
The IMAQ to whole blade can be completed.Divided by colour band, blade is integrally carried out region division into 20 sub-regions, appointed
A sub-regions of anticipating are referred to as blade primitive, then adjust camera angle and make it that the overwhelming majority in blade photograph region is a certain area
Domain, the effect scanned to whole blade is just can reach by converting camera angle.Can also be overall by blade according to actual needs
Region division is carried out into N number of subregion, wherein N >=1.
Step 2: being taken pictures to blade of wind-driven generator primitive, and background is rejected；
In embodiments of the present invention, appropriate shooting angle is chosen first and intensity of illumination is clapped pneumatic equipment bladess
Take the photograph.Wherein, appropriate shooting angle and intensity of illumination are obtained by experiment.Shooting angle is with normal angle at 0~75 °, and illumination is strong
The information of image can be retained substantially by spending the image obtained in 90~1300LUX, will not be produced by illumination variation is produced
Degenerate or grow in raw fault zone, it can be ensured that fault picture is readily identified and extracts.
Further, original image is converted into gray-scale map, then by using Roberts contour extraction methods and morphology
Processing method obtains the binary map of image.Roberts contour extraction methods ask for image by the gradient of image pixel gray level
Edge variation, and then detect the profile of blade.Morphological scale-space method include expansion, corrosion and its be used in combination open fortune
Calculate and closed operation, can effectively suppress the noise of image, while ensureing that the profile of wind energy conversion system image keeps constant.
And then bianry image is carried out to obtain the two-value denoising image of image after Morphological scale-space, find in image region most
Part where big part is blade, then takes out the bianry image that other parts obtain blade, is eventually found original graph
It is that white part can extract the image of whole blade primitive in correspondence blade bianry image as in, reaches and reject background
Purpose, obtains blade primitive result images.
First, original image passes through gray proces, and gray-scale map is changed into from cromogram；Then, with Roberts operators to wind
Power machine primitive image carries out contours extract, obtains the binary map of wind energy conversion system picture, pneumatic equipment bladess are white Foreground, remainder
For black background；Further, Morphological scale-space is carried out to binary map, the effect of preliminary denoising can be reached；And then, preliminary
In the image of denoising, maximum white 8 connected region of region area is found, is exactly the pneumatic equipment bladess elementary area of gained；Most
Afterwards, the region removed outside pneumatic equipment bladess primitive is scratched from artwork, it is possible to obtain complete pneumatic equipment bladess primitive result
Image.It is also prior art to find maximum white 8 connected region of region area.
Wherein, find maximum white 8 connected region of region area and use bianry image connected component labeling method, two steps
Method, i.e., perform twice sweep to preliminary denoising image：Scanning for the first time judges adjacent between pixel by progressively scanning pixel
Relation, identical connection label is assigned to the pixel for belonging to same connected region.Second of scanning eliminates the mark repeated, merges
Belong to same connected region but with the subregion of not isolabeling number.
Step 3: secondary to the progress of blade primitive result images be divided into picture element, and feature is carried out to picture element
Extract；
First, it is secondary to the progress of blade primitive result images to be divided into picture element；Because large-scale blade surface can be produced
Radian, it is in embodiments of the present invention, artificial again in blade primitive result images to make a mark a little, pass through mark point and region
Four angle points can divide region is secondary, can be approximately considered at grade inside these grids.Utilize mark point
Leaf area is split, leaf area is divided into multiple parallelogram mesh, and then according to grid wind energy conversion system leaf
Picture is divided into picture element, to reach the purpose of refinement monitor area, and trouble location can be positioned.
First, the pneumatic equipment bladess of colour band will be coated, after the processing of step one, blade primitive result images are obtained；
Then, blade primitive result images are split using mark point, blade and blade piece primitive is divided into multiple grids；Finally,
Pneumatic equipment bladess primitive result images are split into according to grid by subregion, wind energy conversion system picture element has just been obtained, recorded simultaneously
Position after piecemeal, can reach what the fault category and failure that monitor whole blade grew by monitoring failure mode and failure
Purpose.
Further, feature extraction is carried out to wind energy conversion system picture element；In embodiments of the present invention, picture element storehouse is adopted
Picture element is handled with a variety of data characteristics extraction algorithms, data characteristics is obtained and extracts result.
Specifically, there are following 3 kinds of data characteristics extraction algorithms：
1st, extracted based on the picture feature that dual-tree complex wavelet is analyzed：
First, two-dimensional decomposition is carried out to image using dual-tree complex wavelet；Then, from energy, entropy, the moment of inertia, related
Average and standard deviation are extracted to the textural characteristics of image as 8 dimensional features, are used as the standard of characteristics of image.
Dual-tree complex wavelet refer to using two wavelet trees carry out analyzing and processing cause algorithm have approximate translation invariance with
Each opposite sex of decomposition coefficient correspondence and direction.The result that dual-tree complex wavelet image is decomposed can be more relative to discrete wavelet analysis
Plus retain the details of primary signal, reduce local distortion.
2nd, the image data dimensionality reduction based on manifold learning：
Manifold learning recovers low dimensional manifold structure in referring to the data sampled from dimensional Euclidean Space, while obtaining corresponding
Embedded mapping, to realize yojan, dimensionality reduction or the visualization of data.Chosen in the embodiment of the present invention in popular learning method
LLE methods are used as data processing method.
LLE algorithms can be attributed to three steps:(1) the k Neighbor Points each put are found in high dimensional data sample；（2）By
The Neighbor Points of each sample point calculate the partial reconstruction weight matrix of the sample point；（3）Weighed by the partial reconstruction of the sample point
Value matrix and its Neighbor Points calculate the output valve of the sample point.
Specific in the embodiment of the present invention, two and three dimensions are carried out to database intra vane fault picture data using LLE
The data obtained after dimensionality reduction, the result obtained as Data Dimensionality Reduction.
3rd, based on the image data dimensionality reduction for improving manifold learning arithmetic：
First, initial data is divided into by n classes by fuzzy clustering, and then obtains each class cluster centre and the fuzzy person in servitude of individual
Category degree.
Then, select what the sample near every class center was clustered as General Neural Network according to the result of fuzzy clustering
Training sample.General Neural Network is trained using training data.The General Neural Network prediction module neural network forecast trained
The output sequence of all input sample data.
Further, it is n classes sample data X to be divided according to neural network forecast output sequence Y, then obtains all samples in every class
This average value meani（I=1,2 ..., n）, obtain all sample X to center prop up apart from ecenti（I=1,2 ..., n）, from distance
M minimum sample of matrix chosen distance sets its corresponding network inputs as i as one group.N × m has so been obtained again
Group network training data, its input data is initial data, and output data is category feature data.Sample class number is obtained,
Center of a sample and the number per class sample.
Finally, by obtained sample class number, center of a sample, number and characteristic per class sample, LLE algorithms pair
Data carry out dimension-reduction treatment, obtain data characteristics and extract result.
Step 4: being trained to the SVMs used in fault diagnosis；
First, it assign the part in the picture element data characteristics obtained in step 3 as training data；Then, use
Training data is to SVMs.
SVMs is the statistical theory based on research and its learning law under finite sample.The purpose is to find one
Individual higher-dimension hyperplane is classified to sample data, and the hyperplane for wanting to make two class sample intervals maximum builds for plane
Principle.
In embodiments of the present invention, using standard algorithm of support vector machine, its training step is as follows：
(1) training set T={ (x are set1,y1),(x2,y2),…(xl,yl)}∈(X,Y)l
Wherein xi∈X∈RP, yi∈ Y={ -1,1 }, i=1 ... l;
xiThe vector constituted for the data characteristics of picture element；If xiThere are blade cracks on corresponding picture element, then
yiFor 1, otherwise yiFor -1.
(2) optimization problem is solved（1.1）, obtain optimal solution：
αi>=0, i=1 ..., l.
Wherein αiIt is multiplier corresponding with each training data for the intermediate variable of introducing.
(3) α is selected*Positive component, calculate
Wherein b*It is classification thresholds for the intermediate variable of introducing.
(4) linear optimal Optimal Separating Hyperplane is constructed, decision function is drawn：
Step 5: whether being deposited to the surface of blade of wind-driven generator primitive using the SVMs trained in step 4
Diagnosed in crack fault.
Specific diagnostic method is as follows：
The picture element data characteristics that blade of wind-driven generator primitive is obtained through step 3 be followed successively by x substitute into support to
Decision function in amount machine, judges that the generator blade primitive whether there is face crack failure by the value of decision function.Decision-making letter
Several values is 1 or -1, wherein 1 is has a blade cracks, -1 be in the absence of.And then by the corresponding decision-making letter of which picture element
Several values is 1, can determine whether the position of face crack.
Failure for differentiation can divide fault level, and breakdown judge result is stored into the fault data table such as database
It is interior.Database is monitored by wind energy conversion system failure disposal module, if fault data table, which is produced, updates meeting according to different events
Barrier grade is operated to hardware, including alarm, chain shutdown etc., and historical record is carried out to the operation made.
Step 6: the operation Step 2: three, five is carried out to all blade primitives, until completing the table of integrated plate blade
Face fault diagnosis.
First, blade of wind-driven generator is divided, blade primitive is obtained；Then, pneumatic equipment bladess are taken pictures, and background is entered
Row is rejected.And then, it is secondary to the progress of blade primitive result images to be divided into picture element, and picture element position is recorded to piecemeal
Put.Further, feature extraction is carried out to picture element.To picture element database using dual-tree complex wavelet processing, manifold
A variety of data characteristics extraction algorithms processing images such as habit processing, the popular study processing of improvement, and take the spy of a part of picture element
Data are levied to be trained SVMs as training data.Finally, using the SVMs trained come to wind energy conversion system
Blade is judged with the presence or absence of face crack failure, and supervises the development of its failure.
In summary, this patent provides a kind of blade of wind-driven generator superficial failure diagnosis side based on computer vision
Method：First, blade of wind-driven generator is divided, blade primitive is obtained.Then, pneumatic equipment bladess primitive is taken pictures, and background is entered
Row is rejected.And then, it is secondary to the progress of blade primitive result images to be divided into picture element, and picture element position is recorded to piecemeal
Put.Further, feature extraction is carried out to picture element.Further, the characteristic of a part of picture element is taken as instruction
Practice data to be trained SVMs.Finally, using the SVMs trained come to whole pneumatic equipment bladess whether
There is face crack failure to be judged, and supervise the development of its failure.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations, the above
The explanation of embodiment is only intended to help and understands technical scheme；For those of ordinary skill in the art, according to this
In place of the thought of invention, change in specific embodiments and applications, should be included in protection scope of the present invention it
It is interior.
Claims (4)
1. the method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure, the party
Method comprises the following steps：
Step 1: dividing blade of wind-driven generator, blade primitive is obtained；
The detailed process of step one is as follows：First, using coating the method for colour band on blade of wind-driven generator surface to whole leaf
Piece carries out region division, is divided into N number of subregion, wherein N >=1, any one subregion is referred to as blade primitive；
Step 2: being taken pictures to blade of wind-driven generator primitive, and background is rejected；
The detailed process of step 2 is as follows：Blade of wind-driven generator primitive is shot first, the original of blade primitive is obtained
Image；Then, original image is passed through into gray proces, gray-scale map is changed into from cromogram, obtain the gray level image of blade primitive；Again
Blade primitive contours extract is carried out to gray level image by using Roberts contour extraction methods, the two-value of blade primitive is obtained
Image, the bianry image Leaf primitive is white Foreground, and remainder is black background；Further, bianry image is carried out
Morphological scale-space, reaches the effect of preliminary denoising, obtains preliminary denoising image；And then, in preliminary denoising image, using two-value
Image connectivity zone marker method, twice sweep is performed to preliminary denoising image, and scanning for the first time is judged by progressively scanning pixel
Neighbouring relations between pixel, identical connection label is assigned to the pixel for belonging to same connected region；Second of scanning is eliminated
The mark repeated, merges and belongs to same connected region but with the subregion of not isolabeling number, area is found by the scanning of two steps
Maximum white 8 connected region of domain area, white 8 connected region of the maximum is exactly the blade of wind-driven generator base to be obtained
First image-region；Finally, the region removed outside blade of wind-driven generator primitive image-region is scratched from original image, reaches and picks
Except the purpose of background, while the blade primitive result images of wind-driven generator can be obtained；
Step 3: the blade primitive result images progress obtained to step 2 is secondary to be divided into picture element, and to primitive result
Image carries out feature extraction；
The detailed process of step 3 is as follows：First, the blade primitive result images that step 2 is obtained are divided into multiple parallel four
Side shape grid, and then pneumatic equipment bladess primitive result images are split into according to grid by picture element；Then data characteristics is used
Extraction algorithm is handled picture element, obtains the data characteristics of picture element；
Step 4: being trained to the SVMs used in fault diagnosis；
The detailed process of step 4 is as follows：It assign the picture element data characteristics obtained in step 3 as training data；Then, adopt
SVMs is trained with training data, the SVMs trained is obtained；
The training of SVMs uses standard algorithm of support vector machine in the step 4, and specific training step is as follows：
(1) training set T={ (x are set1,y1),(x2,y2),…(xl,yl)}∈(X,Y)l
Wherein xi∈X∈RP, yi∈ Y={ -1,1 }, i=1 ... l；
xiThe vector constituted for the data characteristics of picture element；If xiThere are blade cracks on corresponding picture element, then yiFor
1, otherwise yiFor -1
(2) optimization problem (1.1) is solved, optimal solution is obtained：
<mrow>
<mtable>
<mtr>
<mtd>
<munder>
<mi>min</mi>
<mi>&alpha;</mi>
</munder>
</mtd>
<mtd>
<mrow>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<msub>
<mi>y</mi>
<mi>j</mi>
</msub>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<msub>
<mi>&alpha;</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>-</mo>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>s</mi>
<mo>.</mo>
<mi>t</mi>
<mo>.</mo>
</mrow>
</mtd>
<mtd>
<mrow>
<munderover>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mn>0</mn>
<mo>,</mo>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow></mrow>
</mtd>
<mtd>
<mrow>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>&GreaterEqual;</mo>
<mn>0</mn>
<mo>,</mo>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<mi>l</mi>
<mo>.</mo>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1.1</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein αiIt is multiplier corresponding with each training data for the intermediate variable of introducing；
(3) α is selected*Positive component, calculate
<mrow>
<msup>
<mi>b</mi>
<mo>*</mo>
</msup>
<mo>=</mo>
<msub>
<mi>y</mi>
<mi>j</mi>
</msub>
<mo>-</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<msubsup>
<mi>&alpha;</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein b*It is classification thresholds for the intermediate variable of introducing；
(4) linear optimal Optimal Separating Hyperplane is constructed, decision function is drawn：
<mrow>
<mi>f</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>sgn</mi>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<msubsup>
<mi>a</mi>
<mi>i</mi>
<mo>*</mo>
</msubsup>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<mrow>
<mi>x</mi>
<mo>&CenterDot;</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
</mrow>
<mo>)</mo>
</mrow>
<mo>+</mo>
<msup>
<mi>b</mi>
<mo>*</mo>
</msup>
<mo>)</mo>
</mrow>
<mo>;</mo>
</mrow>
Step 5: being diagnosed using the SVMs trained to the superficial failure species of blade of wind-driven generator primitive；
The detailed process of step 5 is as follows：The picture element data characteristics that blade of wind-driven generator primitive is obtained through step 3 according to
It is secondary to substitute into the decision function that step 4 is obtained as variable x, the generator blade primitive is judged by the value of decision function whether
There is face crack failure, represent there are blade cracks if being 1 if the value of decision function, represented if being -1 if the value of decision function
In the absence of blade cracks；
Step 6: the operation Step 2: three, five is carried out to all blade primitives, until completing the surface event of integrated plate blade
Barrier diagnosis.
2. the machine vision image according to claim 1 that is based on is to power system blade of wind-driven generator face crack failure
The method diagnosed, it is characterised in that：In the step 3, data characteristics processing is carried out to picture element to be used based on double
The picture feature extraction method of tree complex wavelet analysis.
3. the machine vision image according to claim 1 that is based on is to power system blade of wind-driven generator face crack failure
The method diagnosed, it is characterised in that：In the step 3, data characteristics processing is carried out to picture element to be used based on stream
The image data method of descent of shape study.
4. the machine vision image according to claim 1 that is based on is to power system blade of wind-driven generator face crack failure
The method diagnosed, it is characterised in that：In the step 3, it is to use to be based on changing that data characteristics processing is carried out to picture element
Enter the image data method of descent of manifold learning arithmetic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410157662.XA CN103984952B (en) | 2014-04-18 | 2014-04-18 | The method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410157662.XA CN103984952B (en) | 2014-04-18 | 2014-04-18 | The method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103984952A CN103984952A (en) | 2014-08-13 |
| CN103984952B true CN103984952B (en) | 2017-09-22 |
Family
ID=51276914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410157662.XA Active CN103984952B (en) | 2014-04-18 | 2014-04-18 | The method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103984952B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104865269A (en) * | 2015-04-13 | 2015-08-26 | 华北理工大学 | Wind turbine blade fault diagnosis method |
| CN106778723B (en) * | 2016-11-28 | 2017-09-26 | 华中科技大学 | A kind of pneumatic equipment bladess surface image extracting method in complex background environment |
| CN107587983A (en) * | 2017-09-01 | 2018-01-16 | 天津科技大学 | Novel wind motor blade state monitors and fault early warning system |
| CN108459027A (en) * | 2018-03-21 | 2018-08-28 | 华北电力大学 | A kind of blade of wind-driven generator detection method of surface flaw based on image procossing |
| CN108956655B (en) * | 2018-07-06 | 2019-12-20 | 西安交通大学 | Digital ray detection partitioning method for high-temperature blades of gas turbine with unknown model |
| CN110688906B (en) * | 2019-08-31 | 2023-07-18 | 深圳市广宁股份有限公司 | Intelligent detection method of wind power equipment and related products |
| CN111413404A (en) * | 2020-03-27 | 2020-07-14 | 天津大学 | Blade crack online measurement method based on blade tip timing and support vector machine principle |
| CN111426459A (en) * | 2020-04-13 | 2020-07-17 | 天津大学 | Blade crack online measurement method based on blade tip timing and naive Bayes algorithm |
| WO2022157303A1 (en) | 2021-01-21 | 2022-07-28 | Eolotec Gmbh | Method and device for detecting and monitoring a structural change of structural components of wind turbines |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6983065B1 (en) * | 2001-12-28 | 2006-01-03 | Cognex Technology And Investment Corporation | Method for extracting features from an image using oriented filters |
| CN102136074A (en) * | 2011-03-03 | 2011-07-27 | 浙江农林大学 | Man-machine interface (MMI) based wood image texture analyzing and identifying method |
| CN102829735A (en) * | 2012-08-31 | 2012-12-19 | 哈尔滨工业大学 | Machine vision based detection method of defect of geometrical shape of back surface of E type magnet |
| CN103198322A (en) * | 2013-01-18 | 2013-07-10 | 江南大学 | Magnetic tile surface defect feature extraction and defect classification method based on machine vision |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040150815A1 (en) * | 2003-02-05 | 2004-08-05 | Applied Vision Company, Llc | Flaw detection in objects and surfaces |
-
2014
- 2014-04-18 CN CN201410157662.XA patent/CN103984952B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6983065B1 (en) * | 2001-12-28 | 2006-01-03 | Cognex Technology And Investment Corporation | Method for extracting features from an image using oriented filters |
| CN102136074A (en) * | 2011-03-03 | 2011-07-27 | 浙江农林大学 | Man-machine interface (MMI) based wood image texture analyzing and identifying method |
| CN102829735A (en) * | 2012-08-31 | 2012-12-19 | 哈尔滨工业大学 | Machine vision based detection method of defect of geometrical shape of back surface of E type magnet |
| CN103198322A (en) * | 2013-01-18 | 2013-07-10 | 江南大学 | Magnetic tile surface defect feature extraction and defect classification method based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103984952A (en) | 2014-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103984952B (en) | The method diagnosed based on machine vision image to power system blade of wind-driven generator face crack failure | |
| CN103982378B (en) | Method for diagnosing surface icing faults of wind power generator blade of power system based on machine visual images | |
| CN109118479B (en) | Capsule network-based insulator defect identification and positioning device and method | |
| CN107016405B (en) | A kind of pest image classification method based on classification prediction convolutional neural networks | |
| CN110264448B (en) | Insulator fault detection method based on machine vision | |
| CN109117858B (en) | Method and device for monitoring icing of wind driven generator blade | |
| CN112233073A (en) | Real-time detection method for infrared thermal imaging abnormity of power transformation equipment | |
| CN109359697A (en) | Graph image recognition methods and inspection system used in a kind of power equipment inspection | |
| CN104865269A (en) | Wind turbine blade fault diagnosis method | |
| CN109886937B (en) | Insulator defect detection method based on super-pixel segmentation image recognition | |
| CN111080691A (en) | Infrared hot spot detection method and device for photovoltaic module | |
| CN110223266A (en) | A kind of Railway wheelset tread damage method for diagnosing faults based on depth convolutional neural networks | |
| CN111178177A (en) | Cucumber disease identification method based on convolutional neural network | |
| CN112258490A (en) | Low-emissivity coating intelligent damage detection method based on optical and infrared image fusion | |
| Haidari et al. | Deep learning-based model for fault classification in solar modules using infrared images | |
| CN103984956B (en) | The method diagnosed based on machine vision image to power system blade of wind-driven generator surface pitting failure | |
| CN109886932A (en) | Gear ring of wheel speed sensor detection method of surface flaw based on SVM | |
| CN111402249B (en) | Image evolution analysis method based on deep learning | |
| CN115908354A (en) | Photovoltaic panel defect detection method based on double-scale strategy and improved YOLOV5 network | |
| CN115620084A (en) | Method for diagnosing faults of photovoltaic module based on intelligent routing inspection of unmanned aerial vehicle | |
| CN110009601A (en) | Large-Scale Equipment irregular contour detection method of surface flaw based on HOG | |
| CN114841957A (en) | Steel plate surface defect detection method based on deep learning | |
| CN113674225A (en) | Power equipment fault detection method based on convolutional neural network | |
| Zhang et al. | Fabric defect detection based on visual saliency map and SVM | |
| CN116309493A (en) | Method and system for detecting defects of textile products |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 510080 water Donggang 8, Dongfeng East Road, Yuexiu District, Guangzhou, Guangdong. Co-patentee after: Huazhong University of Science and Technology Patentee after: ELECTRIC POWER RESEARCH INSTITUTE, GUANGDONG POWER GRID CO., LTD. Address before: 510080 dongdongdong Road, dongdongdong Road, Guangzhou, Guangdong Province, No. 8 Co-patentee before: Huazhong University of Science and Technology Patentee before: Electrical Power Research Institute of Guangdong Power Grid Corporation |
|
| CP03 | Change of name, title or address |