CN111915572B - Adaptive gear pitting quantitative detection system and method based on deep learning - Google Patents
Adaptive gear pitting quantitative detection system and method based on deep learning Download PDFInfo
- Publication number
- CN111915572B CN111915572B CN202010671243.3A CN202010671243A CN111915572B CN 111915572 B CN111915572 B CN 111915572B CN 202010671243 A CN202010671243 A CN 202010671243A CN 111915572 B CN111915572 B CN 111915572B
- Authority
- CN
- China
- Prior art keywords
- image
- module
- gear
- pitting
- neural network
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 66
- 238000013135 deep learning Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000003044 adaptive effect Effects 0.000 title claims description 27
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 98
- 238000012549 training Methods 0.000 claims abstract description 70
- 238000011156 evaluation Methods 0.000 claims abstract description 41
- 230000007797 corrosion Effects 0.000 claims abstract description 27
- 238000005260 corrosion Methods 0.000 claims abstract description 27
- 238000007781 pre-processing Methods 0.000 claims abstract description 23
- 238000013500 data storage Methods 0.000 claims abstract description 20
- 238000010276 construction Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 46
- 238000012545 processing Methods 0.000 claims description 41
- 238000012216 screening Methods 0.000 claims description 12
- 238000011176 pooling Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 230000007547 defect Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 238000009661 fatigue test Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000003706 image smoothing Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 2
- 238000007906 compression Methods 0.000 claims description 2
- 230000002708 enhancing effect Effects 0.000 claims description 2
- 238000011158 quantitative evaluation Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 4
- 238000011002 quantification Methods 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 230000005540 biological transmission Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000009347 mechanical transmission Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/44—Analysis of texture based on statistical description of texture using image operators, e.g. filters, edge density metrics or local histograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of gear pitting detection, and discloses a self-adaptive gear pitting quantitative detection system and method based on deep learning, wherein the self-adaptive gear pitting quantitative detection system based on deep learning comprises the following components: the system comprises an image data acquisition module, an image preprocessing module, a main control module, a model construction module, a sample acquisition module, a model training module, an image recognition module, a result evaluation module, a data storage module and a display module. The invention quantitatively detects the gear pitting corrosion through the convolutional neural network model, so as to avoid the problems of subjective interference, difficult accurate quantification and the like in the traditional manual visual detection process; the method can detect the pitting corrosion of different tooth surfaces of different gears, solves the problems of low precision and poor effect of the traditional pitting corrosion detection method, classifies the pitting corrosion of gears in different forms, can accurately and effectively prevent the occurrence of gear breakage, and meets the working requirements of accurate and intelligent gear pitting corrosion quantitative evaluation and detection.
Description
Technical Field
The invention belongs to the technical field of gear pitting detection, and particularly relates to a self-adaptive gear pitting quantitative detection system and method based on deep learning.
Background
At present, gear transmission is the most widely applied transmission form in mechanical transmission, and has the advantages of more accurate transmission, high efficiency, compact structure and reliable work. The main form of gear failure is gear failure, and in order to improve and increase the service life of gear, the form of gear failure needs to be studied in depth. The failure mode of gear pitting is one of the most common failure modes of gears, and under the condition of long-term load operation, the gear falls off from the tooth surface due to stress, so that punctiform pits, namely initial pitting, appear. Initial pitting can be continuously expanded under repeated loading, so that the gear is broken, and irrecoverable loss is caused. Therefore, in order to quantitatively control the law of pitting expansion and effectively prevent tooth breakage, quantitative evaluation and detection of gear pitting are particularly important.
The conventional gear pitting detection method is mainly observed and determined by naked eyes, wherein microscopic pitting which is not easily perceived by naked eyes is needed to be further observed and determined by a microscope. Chinese patent 201910973345.8 discloses a self-adaptive gear pitting quantitative evaluation and detection device based on deep learning, which comprises a gear box platform, an integrated data acquisition system, an image processing system, a control system, a magnetic seat and a mobile platform, wherein the mobile platform consists of a sliding rail and an electric push rod. According to the analysis of the existing related technology, the traditional gear pitting detection method only carries out qualitative assessment on gear pitting, so that the method is complex in steps, low in efficiency and precision and waste of a large amount of human resources. At present, a gear pitting quantitative evaluation and detection method based on deep learning is rarely reported, and a formed product with reliable gear pitting quantitative evaluation and detection is not found in the market.
Through the above analysis, the problems and defects existing in the prior art are as follows:
(1) The traditional gear pitting detection method is mainly observed and determined by naked eyes, and is not easy to detect very tiny pitting.
(2) The traditional gear pitting detection method only carries out qualitative evaluation on gear pitting, has complex steps, low efficiency and precision and wastes a large amount of manpower resources.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a self-adaptive gear pitting quantitative detection system and method based on deep learning.
The invention discloses a self-adaptive gear pitting quantitative detection method based on deep learning, which comprises the following steps of:
acquiring high-quality tooth surface image data of a gear by using a CCD industrial camera through an image data acquisition module to obtain an image to be detected; the CCD industrial camera is placed perpendicular to the tooth surface of the gear to be detected.
And secondly, mapping the pixel points of the tooth surface image which is originally acquired by three-dimensional description into the pixel points of the one-dimensional description by using a graying unit of a preprocessing program through an image preprocessing module, so as to realize gray processing.
And thirdly, converting the image signal processed by the gray level processing unit in the second step into a binary image signal with only black and white by a binarization unit, and performing binarization processing on the image.
And step four, removing the isolated white points on the image strokes, the isolated black points outside the image strokes and the concave-convex points on the edges of the image strokes by an image smoothing unit so that the edges of the image strokes become smooth.
Step five, gray level processing, binarization processing and smoothing processing are carried out on the collected tooth surface image to obtain a meshing area binary image and a pit-like binary image; and obtaining a pit binary image according to the meshing area binary image and the pit-like binary image.
And step six, the main control module is utilized to coordinate and control the normal operation of each module of the adaptive gear pitting corrosion quantitative detection system based on the deep learning.
Step seven, constructing a convolutional neural network model for carrying out pitting detection on the gear based on deep learning by using a model construction program through a model construction module; the convolutional neural network comprises at least one convolutional layer, wherein the at least one convolutional layer comprises the steps of carrying out segmentation compression processing on a feature matrix and carrying out sparse matrix vector multiplication on a generated sparse matrix.
And step eight, collecting a large number of gear pit binary images by using sample collecting equipment through a sample collecting module to serve as sample data for convolutional neural network model training.
And step nine, carrying out unified processing on the sample data trained in the step eight to form an extraction feature matrix with consistent dimensions, carrying out enhancement processing on the extracted data feature matrix, and inputting the extraction feature matrix and the known data classification labels into the convolutional neural network model constructed in the step seven.
Step ten, training the convolutional neural network model by a model training module according to a large number of collected image samples by using a model training program to obtain a trained convolutional neural network model; the convolutional neural network model comprises an input layer, a convolutional layer, a pooling layer, a full-connection layer and an output layer which are sequentially connected.
And step eleven, inputting the preprocessed tooth surface image into a pre-trained convolutional neural network model by utilizing an image recognition program through an image recognition module to intelligently recognize the pitting state of the gear.
And step twelve, grading the pitting degree of the gear by utilizing a result evaluation program according to the recognition result of the convolutional neural network model and a preset judgment standard through a result evaluation module to obtain pitting grade data of the gear, and generating a result evaluation report.
And step thirteen, storing the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the result evaluation report by a data storage module through a storage server.
Fourteen, displaying the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the real-time data of the result evaluation report by using a display module;
in the process of carrying out coordinated control on the normal work of each module of the self-adaptive gear pitting quantitative detection system based on deep learning, the data fusion process of each module by the main control module is as follows:
the method comprises the steps of establishing a data fusion training sample from various data transmitted by an image data acquisition module, an image preprocessing module, a model construction module, a sample acquisition module, a model training module, an image recognition module, a result evaluation module and a data storage module with a main control module;
preprocessing the data fusion training sample, extracting corresponding characteristic values and characteristic average values, and subtracting the characteristic average values from the characteristic values;
according to the characteristic values and the characteristic average values, calculating a covariance matrix and simultaneously calculating corresponding characteristic values;
Sorting the characteristic values, selecting N characteristic values, extracting the largest characteristic value, and establishing a characteristic vector corresponding to the largest characteristic value;
according to the feature vector, establishing a corresponding mapping relation and performing explanation; fusing the data according to the explanation;
in the process that the data storage module stores various data by using the storage server, the process of classifying the data is as follows:
the method comprises the steps of establishing a data classification training set by collected tooth surface image data, preprocessed image data, a convolutional neural network model, training sample images, image recognition results and result evaluation reports, and establishing a similarity matrix;
the similarity matrix is subjected to matrix transformation, a Laplace matrix is established, and corresponding characteristic values are obtained;
sorting the eigenvalues, solving eigenvectors corresponding to the eigenvalues, and constructing an eigenvalue matrix;
and according to the constructed eigenvalue matrix, carrying out data classification by utilizing Kmeans.
The process for extracting the image features by using the image recognition module for inputting the preprocessed tooth surface image into the pre-trained convolutional neural network model to carry out intelligent recognition on the gear pitting state comprises the following steps:
Dividing the processed image into a plurality of small areas;
determining pixels in each small area, sorting the pixels, and selecting intermediate pixel values as correction pixels;
when the surrounding pixel value is larger than the correction pixel value, the position of the pixel point is marked as 1, otherwise, the position is 0, and the LBP value of the central pixel point of the window is obtained;
calculating a histogram of each small region, i.e., the frequency of occurrence of each number; then, carrying out normalization processing on the histogram;
after normalization is completed, the statistical histogram of each small region is connected to form a feature vector, namely the LBP texture feature vector of the whole graph.
Further, in the second step, the method for gray processing the collected tooth surface image by the graying unit includes:
(I) Acquiring the gray value of each pixel in the target tooth surface image to obtain a gray matrix;
(II) obtaining an equalization array according to the line/column gray level distribution trend in the gray level matrix;
and (III) correcting the gray matrix according to the balance array to obtain the tooth surface image after gray processing.
Further, in the eighth step, the method for collecting, by the sample collection module, a gear pit binary image as sample data includes:
(a) Simulating a gear pitting image sample by using a gear contact fatigue test through a gear box platform by using a sample image generating unit;
(b) Repeatedly acquiring a gear pitting image sample by using a CCD industrial camera which is arranged perpendicular to a gear of the gear box through a sample image acquisition unit;
(c) And comparing and screening the collected gear pitting image samples through a sample screening unit, and deleting sample images with high similarity.
Further, in step nine, the method for enhancing the extracted data features includes:
when the convolutional neural network is transmitted in the forward direction, the original convolutional kernels are modulated through dot multiplication of the hand-modulated kernels and the original convolutional kernels on each original convolutional kernel, the modulated convolutional kernels are obtained, and the original convolutional kernels are replaced by the modulated convolutional kernels for transmitting the neural network in the forward direction, so that the enhancement of the data characteristics is realized.
Further, in step ten, the method for training the convolutional neural network model by using the model training program through the model training module includes the following steps:
(1) Collecting a large number of gear pitting images and performing manual marking to identify the positions and the pitting sizes of pitting, thereby obtaining training samples for training a convolutional neural network model;
(2) The gear pitting image sample is led into a convolutional neural network model, and the convolutional neural network model is optimally trained by utilizing an optimization algorithm in combination with artificial mark information;
(3) And after the training ending condition is met, the parameters of each target detection model are saved, so that the convolutional neural network model based on deep learning is obtained.
Further, in step eleven, the method for intelligently identifying the pitting corrosion state of the gear through the convolutional neural network model comprises the following steps:
1) Dividing the preprocessed image to be detected into a plurality of images with m multiplied by m resolution by adopting a multi-target detection method;
2) Inputting the separated images into a convolutional neural network model based on deep learning, judging whether each input image has a pitting defect, and if so, giving the position of a pitting pit and the size of the pitting pit;
3) Summarizing the data information of the pitting defect and outputting the detection result of the pitting degree of the gear.
Another object of the present invention is to provide a deep learning-based adaptive gear pitting quantitative detection system to which the deep learning-based adaptive gear pitting quantitative detection method is applied, the deep learning-based adaptive gear pitting quantitative detection system comprising:
The system comprises an image data acquisition module, an image preprocessing module, a main control module, a model construction module, a sample acquisition module, a model training module, an image recognition module, a result evaluation module, a data storage module and a display module.
The image data acquisition module is connected with the main control module and is used for acquiring high-quality image data from the tooth surface of the gear through the CCD industrial camera, and the CCD industrial camera is vertically arranged with the tooth surface of the detected gear;
the image preprocessing module is connected with the main control module and is used for carrying out gray level processing, binarization processing and smoothing processing on the acquired tooth surface image through a preprocessing program to obtain a meshing area binary image and a pit-like pit binary image; obtaining a pit binary image according to the meshing area binary image and the pit-like binary image;
the main control module is connected with the image data acquisition module, the image preprocessing module, the model construction module, the sample acquisition module, the model training module, the main control module, the image recognition module, the result evaluation module, the data storage module and the display module and is used for carrying out coordination control on the normal work of each module of the adaptive gear pitting corrosion quantitative detection system based on deep learning through the main control machine;
The model construction module is connected with the main control module and used for constructing a convolutional neural network model for carrying out pitting detection on the gear based on deep learning through a model construction program;
the sample acquisition module is connected with the main control module and is used for acquiring a large number of gear pitting images through sample acquisition equipment to serve as samples for convolutional neural network model training;
the model training module is connected with the main control module and is used for training the convolutional neural network model by utilizing a large number of collected image samples through a model training program;
the image recognition module is connected with the main control module and is used for inputting the preprocessed tooth surface image into a pre-trained convolutional neural network model through an image recognition program to intelligently recognize the pitting state of the gear;
the result evaluation module is connected with the main control module and is used for grading the pitting degree of the gear according to the identification result of the convolutional neural network model and a preset evaluation standard through a result evaluation program to obtain pitting grade data of the gear and generate a result evaluation report;
the data storage module is connected with the main control module and used for storing the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the result evaluation report through the storage server;
The display module is connected with the main control module and used for displaying the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the real-time data of the result evaluation report through the display.
Further, the image preprocessing module includes:
the grey-scale unit is used for mapping the pixel points originally described in three dimensions into pixel points described in one dimension;
a binarization unit converting the image signal processed by the gray-scale unit into a binary image signal having only black and white;
an image smoothing unit for removing isolated white points on the image strokes and isolated black points outside the strokes, and concave-convex points on the edges of the strokes, so that the edges of the strokes become smooth;
the sample acquisition module includes:
the sample image generation unit is used for simulating a gear pitting image sample by utilizing a gear contact fatigue test through the gear box platform;
the sample image acquisition unit is used for repeatedly acquiring the pitting image samples of the gear through a CCD industrial camera which is arranged perpendicular to the gear of the gear box;
and the sample screening unit is used for comparing and screening the collected gear pitting image samples and deleting sample images with high similarity.
It is another object of the present invention to provide a computer program product stored on a computer readable medium, comprising a computer readable program, which when executed on an electronic device, provides a user input interface to implement the adaptive gear pitting quantitative detection method based on deep learning.
Another object of the present invention is to provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the adaptive gear pitting quantitative detection method based on deep learning.
By combining all the technical schemes, the invention has the advantages and positive effects that: according to the invention, the gear pitting corrosion is quantitatively detected based on a deep learning algorithm, so that the problems of subjective interference of detection personnel, difficulty in accurate quantification and the like in the traditional manual visual detection process are avoided; the method can detect the pitting corrosion of different tooth surfaces of different gears, provides a deep learning method for dividing and detecting the pitting corrosion images of the gears, solves the problems of low precision and poor effect of the traditional pitting corrosion detection method, completes quantitative evaluation of the pitting corrosion of the gears, classifies the pitting corrosion of the gears in different forms, can accurately and effectively prevent the occurrence of gear breakage phenomenon, and meets the working requirements of accurate and intelligent quantitative evaluation and detection of the pitting corrosion of the gears.
The invention obtains the balance array by utilizing the line/column gray level distribution trend in the gray level matrix through the image preprocessing module, and the balance array can balance the line/column gray level distribution trend in the gray level matrix, so that the gray level value distribution in the gray level matrix is balanced, the brightness of an over-dark area can be improved, the brightness of an over-bright area is reduced, and the effect of increasing the definition of a target image is realized; the characteristic matrix of the convolution layer is compressed through the constructed convolution neural network model, so that training time and memory consumption of the neural network are reduced, and further, memory consumption and zero value calculation in the calculation process are reduced.
Drawings
Fig. 1 is a flowchart of a method for quantitatively detecting pitting corrosion of an adaptive gear based on deep learning, which is provided by an embodiment of the invention.
FIG. 2 is a schematic diagram of a deep learning-based adaptive gear pitting quantitative detection system according to an embodiment of the present invention;
in the figure: 1. an image data acquisition module; 2. an image preprocessing module; 3. a main control module; 4. a model building module; 5. a sample collection module; 6. a model training module; 7. an image recognition module; 8. a result evaluation module; 9. a data storage module; 10. and a display module.
Fig. 3 is a flowchart of a method for gray processing an acquired tooth surface image by a graying unit according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for collecting a gear pit binary image as sample data by a sample collection module according to an embodiment of the present invention.
FIG. 5 is a flowchart of a method for training a convolutional neural network model using a model training program by a model training module, according to an embodiment of the present invention.
Fig. 6 is a flowchart of a method for intelligently identifying a pitting state of a gear through a convolutional neural network model according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Aiming at the problems in the prior art, the invention provides a self-adaptive gear pitting corrosion quantitative detection system and method based on deep learning, and the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the adaptive gear pitting corrosion quantitative detection method based on deep learning provided by the embodiment of the invention comprises the following steps:
S101, acquiring high-quality image data of the tooth surface of the gear by using a CCD industrial camera through an image data acquisition module, wherein the CCD industrial camera is vertically arranged with the tooth surface of the detected gear.
S102, carrying out gray level processing, binarization processing and smoothing processing on the collected tooth surface image by utilizing a preprocessing program through an image preprocessing module to obtain a meshing area binary image and a pit-like binary image; and obtaining a pit binary image according to the meshing area binary image and the pit-like binary image.
S103, the main control module is utilized to coordinate and control the normal operation of each module of the adaptive gear pitting corrosion quantitative detection system based on the deep learning.
S104, constructing a convolutional neural network model for detecting the pitting corrosion of the gear based on deep learning by using a model construction program through a model construction module.
S105, collecting a large number of gear pitting images by using a sample collecting device through a sample collecting module to serve as samples for convolutional neural network model training.
S106, training the convolutional neural network model by using a model training program through a model training module by using a large number of collected image samples.
S107, inputting the preprocessed tooth surface image into a pre-trained convolutional neural network model by an image recognition module through an image recognition program to perform intelligent recognition of the gear pitting state.
S108, grading the pitting degree of the gear by using a result evaluation program according to the recognition result of the convolutional neural network model and a preset judgment standard through a result evaluation module, and generating a result evaluation report.
S109, the data storage module is used for storing the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the result evaluation report by using the storage server.
S110, displaying the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the real-time data of the result evaluation report by a display module through a display.
In the process of carrying out coordinated control on the normal operation of each module of the self-adaptive gear pitting corrosion quantitative detection system based on deep learning, the main control module carries out the data fusion process on each module, which is as follows:
the method comprises the steps of establishing a data fusion training sample from various data transmitted by an image data acquisition module, an image preprocessing module, a model construction module, a sample acquisition module, a model training module, an image recognition module, a result evaluation module and a data storage module with a main control module;
Preprocessing the data fusion training sample, extracting corresponding characteristic values and characteristic average values, and subtracting the characteristic average values from the characteristic values;
according to the characteristic values and the characteristic average values, calculating a covariance matrix and simultaneously calculating corresponding characteristic values;
sorting the characteristic values, selecting N characteristic values, extracting the largest characteristic value, and establishing a characteristic vector corresponding to the largest characteristic value;
according to the feature vector, establishing a corresponding mapping relation and performing explanation; fusing the data according to the explanation;
in the process of storing various data by using the storage server, the data storage module provided by the invention classifies the data as follows:
the method comprises the steps of establishing a data classification training set by collected tooth surface image data, preprocessed image data, a convolutional neural network model, training sample images, image recognition results and result evaluation reports, and establishing a similarity matrix;
the similarity matrix is subjected to matrix transformation, a Laplace matrix is established, and corresponding characteristic values are obtained;
sorting the eigenvalues, solving eigenvectors corresponding to the eigenvalues, and constructing an eigenvalue matrix;
and according to the constructed eigenvalue matrix, carrying out data classification by utilizing Kmeans.
The invention provides a process for extracting image features by using an image recognition module for inputting a preprocessed tooth surface image into a pre-trained convolutional neural network model to intelligently recognize the pitting state of a gear, wherein the process comprises the following steps of:
dividing the processed image into a plurality of small areas;
determining pixels in each small area, sorting the pixels, and selecting intermediate pixel values as correction pixels;
when the surrounding pixel value is larger than the correction pixel value, the position of the pixel point is marked as 1, otherwise, the position is 0, and the LBP value of the central pixel point of the window is obtained;
calculating a histogram of each small region, i.e., the frequency of occurrence of each number; then, carrying out normalization processing on the histogram;
after normalization is completed, the statistical histogram of each small region is connected to form a feature vector, namely the LBP texture feature vector of the whole graph.
As shown in fig. 2, the adaptive gear pitting corrosion quantitative detection system based on deep learning provided by the embodiment of the invention includes: the system comprises an image data acquisition module 1, an image preprocessing module 2, a main control module 3, a model construction module 4, a sample acquisition module 5, a model training module 6, an image identification module 7, a result evaluation module 8, a data storage module 9 and a display module 10.
The image data acquisition module 1 is connected with the main control module 3 and is used for acquiring high-quality image data on the tooth surface of the gear through a CCD industrial camera, and the CCD industrial camera is vertically arranged with the tooth surface of the detected gear;
the image preprocessing module 2 is connected with the main control module 3 and is used for carrying out gray level processing, binarization processing and smoothing processing on the collected tooth surface image through a preprocessing program to obtain a meshing area binary image and a pit-like binary image; obtaining a pit binary image according to the meshing area binary image and the pit-like binary image;
the main control module 3 is connected with the image data acquisition module 1, the image preprocessing module 2, the model construction module 4, the sample acquisition module 5, the model training module 6, the image recognition module 7, the result evaluation module 8, the data storage module 9 and the display module 10 and is used for carrying out coordinated control on the normal work of each module of the adaptive gear pitting quantitative detection system based on deep learning through the main control computer;
the model construction module 4 is connected with the main control module 3 and is used for constructing a convolutional neural network model for detecting the pitting corrosion of the gear based on deep learning through a model construction program;
the sample acquisition module 5 is connected with the main control module 3 and is used for acquiring a large number of gear pitting images through sample acquisition equipment to serve as samples for convolutional neural network model training;
The model training module 6 is connected with the main control module 3 and is used for training the convolutional neural network model by using a large number of collected image samples through a model training program;
the image recognition module 7 is connected with the main control module 3 and is used for inputting the preprocessed tooth surface image into a pre-trained convolutional neural network model through an image recognition program to intelligently recognize the pitting state of the gear;
the result evaluation module 8 is connected with the main control module 3 and is used for grading the pitting degree of the gear according to the identification result of the convolutional neural network model and a preset evaluation standard through a result evaluation program to obtain pitting grade data of the gear and generate a result evaluation report;
the data storage module 9 is connected with the main control module 3 and is used for storing the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the result evaluation report through the storage server;
the display module 10 is connected with the main control module 3 and is used for displaying the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the real-time data of the result evaluation report through a display.
The image preprocessing module 2 provided by the embodiment of the invention comprises:
the graying unit 2-1 is used for mapping the pixel points originally described by three dimensions into pixel points described by one dimension;
a binarization unit 2-2 for converting the image signal processed by the gray-scale unit into a binary image signal having only black and white;
an image smoothing unit 2-3 for removing isolated white points on the image strokes and isolated black points outside the strokes, and concave-convex points of the stroke edges, so that the stroke edges become smooth.
The sample collection module 5 provided by the embodiment of the invention comprises:
a sample image generation unit 5-1 for simulating a gear pitting image sample by a gear contact fatigue test through a gear box platform;
the sample image acquisition unit 5-2 is used for repeatedly acquiring the pitting image samples of the gear through a CCD industrial camera which is arranged perpendicular to the gear of the gear box;
and the sample screening unit 5-3 is used for carrying out contrast screening on the collected gear pitting image samples and deleting sample images with high similarity.
The invention is further described below in connection with specific embodiments.
Example 1
The adaptive gear pitting quantitative detection method based on deep learning provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, as shown in fig. 3, the method for carrying out gray processing on the collected tooth surface image through the gray processing unit provided by the embodiment of the invention comprises the following steps:
S201, acquiring gray values of pixels in the target tooth surface image to obtain a gray matrix.
S202, obtaining an equalization array according to the row/column gray level distribution trend in the gray level matrix.
And S203, correcting the gray matrix according to the balance array to obtain the tooth surface image after gray processing.
Example 2
The method for quantitatively detecting the pitting corrosion of the self-adaptive gear based on the deep learning provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, as shown in fig. 4, the method for collecting the binary image of the pitting corrosion pit of the gear by the sample collecting module provided by the embodiment of the invention comprises the following steps:
s301, simulating a gear pitting image sample by a gear contact fatigue test through a sample image generating unit by utilizing a gear box platform.
S302, repeatedly acquiring a gear pitting image sample by a sample image acquisition unit through a CCD industrial camera which is perpendicular to a gear of the gear box.
S303, comparing and screening the collected gear pitting image samples through a sample screening unit, and deleting sample images with high similarity.
Example 3
The adaptive gear pitting quantitative detection method based on deep learning provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, as shown in fig. 5, the method for training a convolutional neural network model by using a model training program through a model training module provided by the embodiment of the invention comprises the following steps:
S401, collecting a large number of gear pitting images and performing manual marking to identify the positions and the pitting sizes of pitting, thereby obtaining a training sample for training a convolutional neural network model.
S402, the gear pitting image sample is led into a convolutional neural network model, and the convolutional neural network model is optimally trained by utilizing an optimization algorithm in combination with artificial mark information.
S403, after the training ending condition is met, the parameters of each target detection model are saved, and therefore the convolutional neural network model based on deep learning is obtained.
Example 4
The adaptive gear pitting quantitative detection method based on deep learning provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, as shown in fig. 6, the method for intelligently identifying the gear pitting state through a convolutional neural network model provided by the embodiment of the invention comprises the following steps:
s501, dividing the preprocessed image to be detected into a plurality of images with m multiplied by m resolution by adopting a multi-target detection method.
S502, inputting the separated images into a convolutional neural network model based on deep learning, judging whether each input image has a pitting defect, and if so, giving the position of a pitting pit and the size of the pitting pit.
And S503, summarizing the data information of the pitting defect, and outputting the detection result of the pitting degree of the gear.
Convolutional neural networks (Convolutional Neural Networks, CNN) are a type of feedforward neural network comprising convolutional computation and having a deep structure, which incorporate the ideas of both neural networks and machine learning algorithms, thus having the autonomous learning capability of machine learning and the capability of neural networks to deal with nonlinear problems. The method is widely applied to image, video, audio and text data at present, and is one of representative algorithms for deep learning.
After twenty-first century, convolutional neural networks have been developed rapidly with the advent of deep learning theory and the improvement of numerical computing devices, and have been applied largely to the fields of computer vision, natural language processing, etc., and have achieved good classification effects in some pattern recognition fields.
The convolutional neural network is similar to a common neural network in structure and comprises an input layer, an hidden layer and an output layer.
Firstly, an input layer of the convolutional neural network can process multidimensional data, and the input layer of the one-dimensional convolutional neural network receives a one-dimensional or two-dimensional array, wherein the one-dimensional array is usually time or frequency spectrum sampling; the two-dimensional array may include a plurality of channels; the input layer of the two-dimensional convolutional neural network receives a two-dimensional or three-dimensional array; the input layer of the three-dimensional convolutional neural network receives a four-dimensional array. Since gradient descent is used for learning, the input features of convolutional neural networks need to be normalized. Specifically, before the learning data is input into the convolutional neural network, the input data needs to be normalized in a channel or time/frequency dimension, and if the input data is a pixel, the original pixel values distributed in [0,255] can be normalized to a [0,1] interval.
In the hidden layer, the common structures of the convolution layer, the pooling layer and the full connection layer 3 are mainly contained. The image features are extracted through a plurality of convolution layers and pooling layers, so that the convolution layers and the pooling layers are alternately arranged, namely one convolution layer is connected with one pooling layer, one convolution layer is connected after the pooling layer, and the like. In a common construction, the main difference between convolutional neural networks and other neural networks is that convolutional neural networks have convolutional layers and pooling layers. The convolution kernels in the convolution layer contain weight coefficients, whereas the pooled layer does not, and therefore the pooled layer may not be considered a separate layer. In convolutional neural networks, there are often not only 1 convolutional layer and pooling layer, and in the case of Le Net-5, the order in which class 3 is commonly built in implicit layers is usually: input-convolution layer-pooling layer-full connection layer-output.
The output layer upstream of the convolutional neural network is usually a fully-connected layer, so that the structure and the working principle of the convolutional neural network are the same as those of the output layer of the traditional feedforward neural network. For image classification problems, the output layer outputs classification labels using a logic function or a normalized exponential function. In the object recognition problem, the output layer may be designed to output the center coordinates, size, and classification of the object. In image semantic segmentation, the output layer directly outputs the classification result of each pixel.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When used in whole or in part, is implemented in the form of a computer program product comprising one or more computer instructions. When loaded or executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
The foregoing is merely illustrative of specific embodiments of the present invention, and the scope of the invention is not limited thereto, but any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention will be apparent to those skilled in the art within the scope of the present invention.
Claims (6)
1. The adaptive gear pitting quantitative detection method based on the deep learning is characterized by comprising the following steps of:
acquiring high-quality tooth surface image data of a gear by using a CCD industrial camera through an image data acquisition module to obtain an image to be detected; the CCD industrial camera is vertically arranged with the detected tooth surface of the gear;
step two, the image preprocessing module is used for mapping the pixel points of the tooth surface image which is originally acquired by three-dimensional description into the pixel points of the one-dimensional description by using a graying unit of a preprocessing program, so that the gray processing is realized;
converting the image signal processed by the gray level unit in the second step into a binary image signal with only black and white through a binary unit, and performing binarization processing on the image;
Removing isolated white points on the image strokes, isolated black points outside the image strokes and concave-convex points on the edges of the image strokes by an image smoothing unit so that the edges of the image strokes become smooth;
step five, gray level processing, binarization processing and smoothing processing are carried out on the collected tooth surface image to obtain a meshing area binary image and a pit-like binary image; obtaining a pit binary image according to the meshing area binary image and the pit-like binary image;
step six, the main control module is utilized to coordinate and control the normal operation of each module of the self-adaptive gear pitting corrosion quantitative detection system based on the deep learning;
step seven, constructing a convolutional neural network model for carrying out pitting detection on the gear based on deep learning by using a model construction program through a model construction module; the convolutional neural network comprises at least one convolutional layer, wherein the at least one convolutional layer comprises the steps of carrying out segmentation compression processing on a feature matrix and carrying out sparse matrix vector multiplication on a generated sparse matrix;
step eight, collecting a large number of gear pit binary images by using sample collecting equipment through a sample collecting module as sample data for convolutional neural network model training;
Step nine, carrying out unified processing on the sample data trained in the step eight to form an extraction feature matrix with consistent dimensions, carrying out enhancement processing on the extraction feature matrix, and inputting the extraction feature matrix and a known data classification label into a convolutional neural network model constructed in the step seven;
step ten, training the convolutional neural network model by a model training module according to a large number of collected image samples by using a model training program to obtain a trained convolutional neural network model; the convolutional neural network model comprises an input layer, a convolutional layer, a pooling layer, a full-connection layer and an output layer which are sequentially connected;
step eleven, inputting the preprocessed tooth surface image into a pre-trained convolutional neural network model by an image recognition module through an image recognition program to intelligently recognize the pitting state of the gear;
step twelve, grading the pitting degree of the gear by utilizing a result evaluation program according to the recognition result of the convolutional neural network model and a preset judgment standard through a result evaluation module to obtain pitting grade data of the gear, and generating a result evaluation report;
step thirteen, storing the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the result evaluation report by a data storage module through a storage server;
Fourteen, displaying the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the real-time data of the result evaluation report by using a display module;
in the process of carrying out coordinated control on the normal work of each module of the self-adaptive gear pitting quantitative detection system based on deep learning, the data fusion process of each module by the main control module is as follows:
the method comprises the steps of establishing a data fusion training sample from various data transmitted by an image data acquisition module, an image preprocessing module, a model construction module, a sample acquisition module, a model training module, an image recognition module, a result evaluation module and a data storage module with a main control module;
preprocessing the data fusion training sample, extracting corresponding characteristic values and characteristic average values, and subtracting the characteristic average values from the characteristic values;
according to the characteristic values and the characteristic average values, calculating a covariance matrix and simultaneously calculating corresponding characteristic values;
sorting the characteristic values, selecting N characteristic values, extracting the largest characteristic value, and establishing a characteristic vector corresponding to the largest characteristic value;
according to the feature vector, establishing a corresponding mapping relation and performing explanation; fusing the data according to the explanation;
In the process that the data storage module stores various data by using the storage server, the process of classifying the data is as follows:
the method comprises the steps of establishing a data classification training set by collected tooth surface image data, preprocessed image data, a convolutional neural network model, training sample images, image recognition results and result evaluation reports, and establishing a similarity matrix;
the similarity matrix is subjected to matrix transformation, a Laplace matrix is established, and corresponding characteristic values are obtained;
sorting the eigenvalues, solving eigenvectors corresponding to the eigenvalues, and constructing an eigenvalue matrix;
according to the constructed eigenvalue matrix, carrying out data classification by utilizing Kmeans;
the process for extracting the image features by using the image recognition module for inputting the preprocessed tooth surface image into the pre-trained convolutional neural network model to carry out intelligent recognition on the gear pitting state comprises the following steps:
dividing the processed image into a plurality of small areas;
determining pixels in each small area, sorting the pixels, and selecting intermediate pixel values as correction pixels;
when the surrounding pixel value is larger than the correction pixel value, the position of the pixel point is marked as 1, otherwise, the position is 0, and the LBP value of the central pixel point of the window is obtained;
Calculating a histogram of each small region, i.e., the frequency of occurrence of each number; then, carrying out normalization processing on the histogram;
after normalization is completed, the statistical histogram of each small region is connected to form a feature vector, namely an LBP texture feature vector of the whole graph;
in the second step, the method for gray processing the collected tooth surface image by the graying unit comprises the following steps:
(I) Acquiring the gray value of each pixel in the target tooth surface image to obtain a gray matrix;
(II) obtaining an equalization array according to the line/column gray level distribution trend in the gray level matrix;
(III) correcting the gray matrix according to the equalization array to obtain the tooth surface image after gray processing;
in the eighth step, the method for collecting the gear pit binary image as the sample data by the sample collecting module includes:
(a) Simulating a gear pitting image sample by using a gear contact fatigue test through a gear box platform by using a sample image generating unit;
(b) Repeatedly acquiring a gear pitting image sample by using a CCD industrial camera which is arranged perpendicular to a gear of the gear box through a sample image acquisition unit;
(c) Comparing and screening the collected gear pitting image samples through a sample screening unit, and deleting sample images with high similarity;
In step nine, the method for enhancing the extracted data features includes:
when the convolutional neural network is transmitted in the forward direction, on each original convolutional kernel, the modulation of the original convolutional kernel is realized through the dot multiplication of the hand-modulated kernel and the original convolutional kernel, the modulated convolutional kernel is obtained, and the modulated convolutional kernel is used for replacing the original convolutional kernel to transmit the neural network in the forward direction, so that the enhancement of the data characteristics is realized;
in step ten, the method for training the convolutional neural network model by using the model training program through the model training module comprises the following steps:
(1) Collecting a large number of gear pitting images and performing manual marking to identify the positions and the pitting sizes of pitting, thereby obtaining training samples for training a convolutional neural network model;
(2) The gear pitting image sample is led into a convolutional neural network model, and the convolutional neural network model is optimally trained by utilizing an optimization algorithm in combination with artificial mark information;
(3) And after the training ending condition is met, the parameters of each target detection model are saved, so that the convolutional neural network model based on deep learning is obtained.
2. The adaptive gear pitting quantitative detection method based on deep learning as set forth in claim 1, wherein in step eleven, the method for intelligently identifying the gear pitting state through a convolutional neural network model comprises the following steps:
1) Dividing the preprocessed image to be detected into a plurality of images with m multiplied by m resolution by adopting a multi-target detection method;
2) Inputting the separated images into a convolutional neural network model based on deep learning, judging whether each input image has a pitting defect, and if so, giving the position of a pitting pit and the size of the pitting pit;
3) Summarizing the data information of the pitting defect and outputting the detection result of the pitting degree of the gear.
3. A deep learning-based adaptive gear pitting quantitative detection system applying the deep learning-based adaptive gear pitting quantitative detection method according to any one of claims 1 to 2, characterized in that the deep learning-based adaptive gear pitting quantitative detection system comprises:
the image data acquisition module is connected with the main control module and is used for acquiring high-quality image data from the tooth surface of the gear through the CCD industrial camera, and the CCD industrial camera is vertically arranged with the tooth surface of the detected gear;
the image preprocessing module is connected with the main control module and is used for carrying out gray level processing, binarization processing and smoothing processing on the acquired tooth surface image through a preprocessing program to obtain a meshing area binary image and a pit-like pit binary image; obtaining a pit binary image according to the meshing area binary image and the pit-like binary image;
The main control module is connected with the image data acquisition module, the image preprocessing module, the model construction module, the sample acquisition module, the model training module, the main control module, the image recognition module, the result evaluation module, the data storage module and the display module and is used for carrying out coordination control on the normal work of each module of the adaptive gear pitting corrosion quantitative detection system based on deep learning through the main control machine;
the model construction module is connected with the main control module and used for constructing a convolutional neural network model for carrying out pitting detection on the gear based on deep learning through a model construction program;
the sample acquisition module is connected with the main control module and is used for acquiring a large number of gear pitting images through sample acquisition equipment to serve as samples for convolutional neural network model training;
the model training module is connected with the main control module and is used for training the convolutional neural network model by utilizing a large number of collected image samples through a model training program;
the image recognition module is connected with the main control module and is used for inputting the preprocessed tooth surface image into a pre-trained convolutional neural network model through an image recognition program to intelligently recognize the pitting state of the gear;
The result evaluation module is connected with the main control module and is used for grading the pitting degree of the gear according to the identification result of the convolutional neural network model and a preset evaluation standard through a result evaluation program to obtain pitting grade data of the gear and generate a result evaluation report;
the data storage module is connected with the main control module and used for storing the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the result evaluation report through the storage server;
the display module is connected with the main control module and used for displaying the collected tooth surface image data, the preprocessed image data, the convolutional neural network model, the training sample image, the image recognition result and the real-time data of the result evaluation report through the display.
4. The adaptive gear pitting quantitative detection system based on deep learning of claim 3, wherein the image preprocessing module comprises:
the grey-scale unit is used for mapping the pixel points originally described in three dimensions into pixel points described in one dimension;
a binarization unit converting the image signal processed by the gray-scale unit into a binary image signal having only black and white;
An image smoothing unit for removing isolated white points on the image strokes and isolated black points outside the strokes, and concave-convex points on the edges of the strokes, so that the edges of the strokes become smooth;
the sample acquisition module includes:
the sample image generation unit is used for simulating a gear pitting image sample by utilizing a gear contact fatigue test through the gear box platform;
sample image acquisition unit for pitting image of gear by CCD industrial camera perpendicular to gear of gear box
Repeatedly collecting an image sample;
and the sample screening unit is used for comparing and screening the collected gear pitting image samples and deleting sample images with high similarity.
5. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the deep learning based adaptive gear pitting quantitative detection method of any one of claims 1-2 when executed on an electronic device.
6. A computer readable storage medium storing instructions that when executed on a computer cause the computer to perform the deep learning-based adaptive gear pitting quantitative detection method of any one of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010671243.3A CN111915572B (en) | 2020-07-13 | 2020-07-13 | Adaptive gear pitting quantitative detection system and method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010671243.3A CN111915572B (en) | 2020-07-13 | 2020-07-13 | Adaptive gear pitting quantitative detection system and method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111915572A CN111915572A (en) | 2020-11-10 |
| CN111915572B true CN111915572B (en) | 2023-04-25 |
Family
ID=73226418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010671243.3A Active CN111915572B (en) | 2020-07-13 | 2020-07-13 | Adaptive gear pitting quantitative detection system and method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111915572B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112331322A (en) * | 2020-12-04 | 2021-02-05 | 上海蓬海涞讯数据技术有限公司 | Method, device, processor and storage medium for realizing quantitative evaluation processing aiming at special ability of hospital based on neural network |
| CN112991260A (en) * | 2021-02-03 | 2021-06-18 | 南昌航空大学 | Infrared nondestructive testing system with light and ultrasonic composite excitation |
| CN113034341B (en) * | 2021-05-25 | 2021-08-03 | 浙江双元科技股份有限公司 | Data acquisition processing circuit for Cameralink high-speed industrial camera |
| CN113288425A (en) * | 2021-05-27 | 2021-08-24 | 徐州医科大学附属医院 | Visual navigation system for guide pin in fixation of limb fracture |
| CN115049667B (en) * | 2022-08-16 | 2022-12-06 | 启东市群鹤机械设备有限公司 | Gear defect detection method |
| CN115578365B (en) * | 2022-10-26 | 2023-06-20 | 西南交通大学 | Method and equipment for detecting tooth pitch of adjacent racks of rack rail |
| CN117387517B (en) * | 2023-10-25 | 2024-03-15 | 常州佳恒新能源科技有限公司 | Digital instrument panel quality detection method and system |
| CN117474925B (en) * | 2023-12-28 | 2024-03-15 | 山东润通齿轮集团有限公司 | Gear pitting detection method and system based on machine vision |
| CN117495867B (en) * | 2024-01-03 | 2024-05-31 | 东莞市星火齿轮有限公司 | Visual detection method and system for precision of small-module gear |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853491A (en) * | 2010-04-30 | 2010-10-06 | 西安电子科技大学 | SAR (Synthetic Aperture Radar) image segmentation method based on parallel sparse spectral clustering |
| CN103810722A (en) * | 2014-02-27 | 2014-05-21 | 云南大学 | Moving target detection method combining improved LBP (Local Binary Pattern) texture and chrominance information |
| CN104318241A (en) * | 2014-09-25 | 2015-01-28 | 东莞电子科技大学电子信息工程研究院 | Local density spectral clustering similarity measurement algorithm based on Self-tuning |
| CN105426889A (en) * | 2015-11-13 | 2016-03-23 | 浙江大学 | PCA mixed feature fusion based gas-liquid two-phase flow type identification method |
| CN106845524A (en) * | 2016-12-28 | 2017-06-13 | 田欣利 | A kind of carburizing and quenching steel grinding textura epidermoidea and burn intelligent identification Method |
| CN107633296A (en) * | 2017-10-16 | 2018-01-26 | 中国电子科技集团公司第五十四研究所 | A kind of convolutional neural networks construction method |
| CN108932712A (en) * | 2018-06-22 | 2018-12-04 | 东南大学 | A kind of rotor windings quality detecting system and method |
| CN109523518A (en) * | 2018-10-24 | 2019-03-26 | 浙江工业大学 | A kind of tire X-ray defect detection method |
| CN109754442A (en) * | 2019-01-10 | 2019-05-14 | 重庆大学 | A kind of gear pitting corrosion detection system based on machine vision |
| CN109858575A (en) * | 2019-03-19 | 2019-06-07 | 苏州市爱生生物技术有限公司 | Data classification method based on convolutional neural networks |
| CN109934811A (en) * | 2019-03-08 | 2019-06-25 | 中国科学院光电技术研究所 | A kind of optical element surface defect inspection method based on deep learning |
| CN110567985A (en) * | 2019-10-14 | 2019-12-13 | 重庆大学 | Self-adaptive gear pitting quantitative evaluation and detection device based on deep learning |
| CN110660057A (en) * | 2019-11-01 | 2020-01-07 | 重庆大学 | Binocular automatic gear pitting detection device based on deep learning |
| CN110738603A (en) * | 2018-07-18 | 2020-01-31 | 中国商用飞机有限责任公司 | image gray scale processing method, device, computer equipment and storage medium |
| CN110807823A (en) * | 2019-11-13 | 2020-02-18 | 四川大学 | Image simulation generation method for dot matrix character printing effect |
| CN111127533A (en) * | 2019-12-23 | 2020-05-08 | 魏志康 | Neural network-based multi-feature fusion grinding wheel grinding performance prediction method |
| CN111260640A (en) * | 2020-01-13 | 2020-06-09 | 重庆大学 | Tree generator network gear pitting image measuring method and device based on cyclean |
-
2020
- 2020-07-13 CN CN202010671243.3A patent/CN111915572B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853491A (en) * | 2010-04-30 | 2010-10-06 | 西安电子科技大学 | SAR (Synthetic Aperture Radar) image segmentation method based on parallel sparse spectral clustering |
| CN103810722A (en) * | 2014-02-27 | 2014-05-21 | 云南大学 | Moving target detection method combining improved LBP (Local Binary Pattern) texture and chrominance information |
| CN104318241A (en) * | 2014-09-25 | 2015-01-28 | 东莞电子科技大学电子信息工程研究院 | Local density spectral clustering similarity measurement algorithm based on Self-tuning |
| CN105426889A (en) * | 2015-11-13 | 2016-03-23 | 浙江大学 | PCA mixed feature fusion based gas-liquid two-phase flow type identification method |
| CN106845524A (en) * | 2016-12-28 | 2017-06-13 | 田欣利 | A kind of carburizing and quenching steel grinding textura epidermoidea and burn intelligent identification Method |
| CN107633296A (en) * | 2017-10-16 | 2018-01-26 | 中国电子科技集团公司第五十四研究所 | A kind of convolutional neural networks construction method |
| CN108932712A (en) * | 2018-06-22 | 2018-12-04 | 东南大学 | A kind of rotor windings quality detecting system and method |
| CN110738603A (en) * | 2018-07-18 | 2020-01-31 | 中国商用飞机有限责任公司 | image gray scale processing method, device, computer equipment and storage medium |
| CN109523518A (en) * | 2018-10-24 | 2019-03-26 | 浙江工业大学 | A kind of tire X-ray defect detection method |
| CN109754442A (en) * | 2019-01-10 | 2019-05-14 | 重庆大学 | A kind of gear pitting corrosion detection system based on machine vision |
| CN109934811A (en) * | 2019-03-08 | 2019-06-25 | 中国科学院光电技术研究所 | A kind of optical element surface defect inspection method based on deep learning |
| CN109858575A (en) * | 2019-03-19 | 2019-06-07 | 苏州市爱生生物技术有限公司 | Data classification method based on convolutional neural networks |
| CN110567985A (en) * | 2019-10-14 | 2019-12-13 | 重庆大学 | Self-adaptive gear pitting quantitative evaluation and detection device based on deep learning |
| CN110660057A (en) * | 2019-11-01 | 2020-01-07 | 重庆大学 | Binocular automatic gear pitting detection device based on deep learning |
| CN110807823A (en) * | 2019-11-13 | 2020-02-18 | 四川大学 | Image simulation generation method for dot matrix character printing effect |
| CN111127533A (en) * | 2019-12-23 | 2020-05-08 | 魏志康 | Neural network-based multi-feature fusion grinding wheel grinding performance prediction method |
| CN111260640A (en) * | 2020-01-13 | 2020-06-09 | 重庆大学 | Tree generator network gear pitting image measuring method and device based on cyclean |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111915572A (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111915572B (en) | Adaptive gear pitting quantitative detection system and method based on deep learning | |
| CN111862064B (en) | Silver wire surface flaw identification method based on deep learning | |
| CN110148130B (en) | Method and device for detecting part defects | |
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN108765412B (en) | Strip steel surface defect classification method | |
| CN105678332B (en) | Converter steelmaking end point judgment method and system based on flame image CNN recognition modeling | |
| CN115082467A (en) | Building material welding surface defect detection method based on computer vision | |
| CN108564085B (en) | Method for automatically reading of pointer type instrument | |
| CN114897816B (en) | Mask R-CNN mineral particle identification and particle size detection method based on improved Mask | |
| CN111667455A (en) | AI detection method for various defects of brush | |
| CN101140216A (en) | Gas-liquid two-phase flow type recognition method based on digital graphic processing technique | |
| CN112949704B (en) | Tobacco leaf maturity state identification method and device based on image analysis | |
| CN115797354B (en) | Method for detecting appearance defects of laser welding seam | |
| CN117152161B (en) | Shaving board quality detection method and system based on image recognition | |
| CN111753794A (en) | Fruit quality classification method and device, electronic equipment and readable storage medium | |
| CN115294033A (en) | Tire belt layer difference level and misalignment defect detection method based on semantic segmentation network | |
| KR102430946B1 (en) | System and method for diagnosing small bowel preparation scale | |
| CN112766419A (en) | Image quality evaluation method and device based on multitask learning | |
| CN114065798A (en) | Visual identification method and device based on machine identification | |
| CN117372332A (en) | Fabric flaw detection method based on improved YOLOv7 model | |
| CN114820611B (en) | Artificial intelligence-based mechanical part quality evaluation method and system | |
| CN116051539A (en) | Diagnosis method for heating fault of power transformation equipment | |
| CN114898362A (en) | Mushroom image classification method based on neural network | |
| Mohammed et al. | A fuzzy system for detection and classification of textile defects to ensure the quality of fabric production. | |
| CN112767365A (en) | Flaw detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |