CN111260626A - Workpiece wear detection method and system based on deep learning - Google Patents
Workpiece wear detection method and system based on deep learning Download PDFInfo
- Publication number
- CN111260626A CN111260626A CN202010042386.8A CN202010042386A CN111260626A CN 111260626 A CN111260626 A CN 111260626A CN 202010042386 A CN202010042386 A CN 202010042386A CN 111260626 A CN111260626 A CN 111260626A
- Authority
- CN
- China
- Prior art keywords
- workpiece
- image
- wear
- feature set
- sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 78
- 238000013135 deep learning Methods 0.000 title claims abstract description 26
- 230000007547 defect Effects 0.000 claims abstract description 54
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 42
- 238000005299 abrasion Methods 0.000 claims abstract description 38
- 238000013528 artificial neural network Methods 0.000 claims abstract description 37
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 27
- 238000002372 labelling Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 9
- 230000002146 bilateral effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 239000000853 adhesive Substances 0.000 claims description 6
- 230000001070 adhesive effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012360 testing method 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- 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
- G06T2207/20024—Filtering details
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of fault diagnosis, in particular to a workpiece abrasion detection method and a workpiece abrasion detection system based on deep learning, wherein the method comprises the following steps: firstly, obtaining sample images of a sample workpiece in various wear states; then marking the surface defect type and the defect area of the sample image to generate an image feature set of the sample workpiece; inputting the image feature set into a MaskR-CNN neural network for training to generate a workpiece abrasion detection model; and inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection, and identifying the defect type of the workpiece to be detected. The invention also correspondingly provides a workpiece abrasion detection system based on deep learning, and the invention can realize automatic detection of workpiece abrasion, improve the detection efficiency of the workpiece state and save the labor cost.
Description
Technical Field
The invention relates to the technical field of fault diagnosis, in particular to a workpiece abrasion detection method and system based on deep learning.
Background
The workpiece state monitoring technology has very important significance in automatic production, and the cutter abrasion detection technology based on the workpiece surface image is a very key technology in the automatic production and is one of the main means for reducing the manufacturing cost, reducing the environmental hazard and ensuring the normal and efficient operation of a manufacturing system and the product quality. The cutter wear state monitoring system lays a foundation for the modernization, automation and flexibility of a manufacturing system.
In order to improve the detection efficiency of the workpiece state and save the labor cost, a method for detecting the workpiece surface is urgently needed to be researched to realize the automatic detection of the workpiece abrasion.
Disclosure of Invention
In order to solve the problems, the invention provides a workpiece wear detection method and a workpiece wear detection system based on deep learning, which can realize automatic diagnosis of gear faults.
In order to achieve the purpose, the invention provides the following technical scheme:
in one aspect, a workpiece wear detection method based on deep learning is provided, including:
acquiring sample images of a sample workpiece in various wear states;
marking the surface defect type and the defect area of the sample image to generate an image feature set of the sample workpiece;
inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model;
and inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection, and identifying the defect type of the workpiece to be detected.
Further, the surface defect types include: abrasive wear, adhesive wear, surface fatigue wear, corrosive wear, and fretting wear.
Further, the step of labeling the surface defect type and the defect area of the sample image to generate an image feature set of the sample workpiece further includes:
carrying out size normalization processing on the sample image to generate a normalized image;
rejecting noise contained in the normalized image using bilateral filtering;
the normalized image is rotated 90 ° in a counter-clockwise direction and randomly scaled and cropped to enhance the data of the image feature set.
Further, the step of inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model comprises the following steps:
extracting a defect area in the image feature set as a labeling frame;
inputting the image feature set into a Mask R-CNN neural network for training to obtain a result frame of the surface defect;
calculating the deviation between the result frame and the labeling frame by adopting a multitask loss function, wherein the multitask loss function comprises a classification loss function and a regression loss function, and when the deviation is lower than a set threshold value, training of a Mask R-CNN neural network is completed;
and taking the Mask R-CNN neural network after the training as a workpiece abrasion detection model.
In another aspect, a workpiece wear detection system based on deep learning is provided, including:
the sample image acquisition module is used for acquiring sample images of the sample workpiece in various wear states;
the feature set generation module is used for marking the surface defect type and the defect area of the sample image and generating an image feature set of the sample workpiece;
the model training module is used for inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model;
and the defect detection module is used for inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection and identifying the defect type of the workpiece to be detected.
Further, the surface defect types include: abrasive wear, adhesive wear, surface fatigue wear, corrosive wear, and fretting wear.
Further, the feature set generation module is further configured to:
carrying out size normalization processing on the sample image to generate a normalized image;
rejecting noise contained in the normalized image using bilateral filtering;
the normalized image is rotated 90 ° in a counter-clockwise direction and randomly scaled and cropped to enhance the data of the image feature set.
Further, the model training module is further configured to:
extracting a defect area in the image feature set as a labeling frame;
inputting the image feature set into a Mask R-CNN neural network for training to obtain a result frame of the surface defect;
calculating the deviation between the result frame and the labeling frame by adopting a multitask loss function, wherein the multitask loss function comprises a classification loss function and a regression loss function, and when the deviation is lower than a set threshold value, training of a Mask R-CNN neural network is completed;
and taking the Mask R-CNN neural network after the training as a workpiece abrasion detection model.
The invention has the beneficial effects that: the invention discloses a workpiece wear detection method and a system based on deep learning, wherein the method comprises the following steps: firstly, obtaining sample images of a sample workpiece in various wear states; then marking the surface defect type and the defect area of the sample image to generate an image feature set of the sample workpiece; inputting the image feature set into a MaskR-CNN neural network for training to generate a workpiece abrasion detection model; and inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection, and identifying the defect type of the workpiece to be detected. The invention further correspondingly provides a workpiece wear detection system based on deep learning. The invention can realize automatic detection of workpiece abrasion, improves the detection efficiency of the workpiece state and saves the labor cost.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of a method for detecting wear of a workpiece based on deep learning according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating step S200 according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating step S300 according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a workpiece wear detection system based on deep learning according to an embodiment of the present invention.
Detailed Description
The conception, specific structure and technical effects of the present disclosure will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, aspects and effects of the present disclosure. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Referring to fig. 1, fig. 1 shows a method for detecting wear of a workpiece based on deep learning, which includes the following steps:
and S100, acquiring sample images of the sample workpiece in various wear states.
In an exemplary embodiment, the surface defect types include: abrasive wear, adhesive wear, surface fatigue wear, corrosive wear, and fretting wear, the sample image being a surface image of a sample workpiece.
And S200, marking the surface defect type and the defect area of the sample image to generate an image feature set of the sample workpiece.
In this embodiment, the yolo _ mark image detection labeling tool can be used to label the position and type of the known target image, and the minimum bounding rectangle of the defect in the sample image can be labeled as the defect region.
And S300, inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model.
And S400, inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection, and identifying the defect type of the workpiece to be detected.
The Mask R-CNN neural network adopted in this embodiment is a general object instance segmentation framework (object segmentation), and not only can detect objects in an image, but also can give a high-quality segmentation result to each object, and is expanded based on the fast R-CNN neural network, and a new branch for predicting an object Mask (object Mask) is added to a bounding box retrieval branch in parallel. Specifically, for each candidate region, the Faster R-CNN has two outputs, one is the category label and the other is the rectangular box coordinate information. The Mask R-CNN target detection is to add a third branch for outputting an object Mask on the basis of fast R-CNN to segment an object. The Mask R-CNN target detection adopts two steps, wherein the first step is to extract a candidate region, the second step is to parallel to the prediction category and coordinate information, the Mask R-CNN outputs a binary Mask for each candidate region while outputting the category and frame offset, and the Mask is used for key point detection, wherein the Mask is used for generating a high-quality segmentation Mask for each example.
In the embodiment, sample images of a sample workpiece in various wear states are obtained; marking the surface defect type and the defect area of the sample image to generate an image feature set of the sample workpiece, wherein the type is limited, and the embodiment adopts a pre-marking mode to facilitate subsequent rapid model training; inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model; and inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection, and identifying the defect type of the workpiece to be detected. The invention also correspondingly provides a workpiece abrasion detection system based on deep learning, and the workpiece abrasion detection model is obtained by classifying and labeling the characteristic images of workpiece abrasion and adopting a Mask R-CNN neural network for training, so that the automatic detection of the workpiece abrasion can be realized, the workpiece state detection efficiency is improved, and the labor cost is saved.
Referring to fig. 2, in a modified embodiment, the step S200 further includes:
step S210, carrying out size normalization processing on the sample image to generate a normalized image;
step S220, noise contained in the normalized image is removed by using bilateral filtering;
and S230, rotating the normalized image by 90 degrees along the counterclockwise direction, and randomly scaling and cutting the normalized image to enhance the data of the image feature set.
The bilateral filter adopted in this embodiment is a filter capable of preserving edges and removing noise, and is also a weighted average filter, and unlike gaussian filtering, its filter kernel is composed of two functions, one of which is a filter coefficient determined by geometric spatial distance, and the other is a filter coefficient determined by pixel difference. The benefits of using bilateral filtering are: in a flat area of an image, the pixel value change is very small, the corresponding pixel range domain weight is close to 1, and the spatial domain weight plays a main role at the moment, namely Gaussian blur is performed; in the edge area of the image, the pixel value is greatly changed, and the pixel range area weight is increased, so that the information of the edge is maintained.
Referring to fig. 3, in a preferred embodiment, the step S300 includes:
and S310, extracting the defect area in the image feature set as a labeling frame.
And S320, inputting the image feature set into a Mask R-CNN neural network for training to obtain a result frame of the surface defect.
And S330, calculating the deviation between the result frame and the labeling frame by adopting a multitask loss function, and finishing the training of the Mask R-CNN neural network when the deviation is lower than a set threshold value.
Wherein the multitasking loss function comprises a classification loss function and a regression loss function.
And step S340, taking the Mask R-CNN neural network after the training as a workpiece abrasion detection model.
In the embodiment, a result frame obtained by training the Mask R-CNN neural network is compared with a marking frame serving as a test standard, the Mask R-CNN neural network is iterated according to the deviation of the result frame and the marking frame, when a set threshold is met, the training of the Mask R-CNN neural network is completed, the training times of the Mask R-CNN neural network can be controlled, and a workpiece abrasion detection model with high accuracy is obtained. Wherein, the set threshold value for comparing with the deviation can be manually set, and in order to ensure the accuracy of the training result, the set threshold value is not more than 10%.
In this embodiment, the step of training the Mask R-CNN neural network is as follows:
(1) inputting the image feature set into a pre-trained Res Net network to obtain a corresponding feature map;
(2) setting a plurality of ROI (region of interest) for each point in the feature map so as to obtain a plurality of candidate ROIs;
(3) sending the candidate ROI into an RPN network to perform binary classification (divided into foreground or background) and BB regression, and filtering out a part of candidate ROI;
(4) performing ROI Align operation on the remaining ROIs (namely, firstly, corresponding the pixels of the original image and the feature image, and then, corresponding the feature image and the fixed features);
(5) these ROIs were classified (N-class classification), BB regression, and MASK generation (FCN operation within each ROI).
Referring to fig. 4, an embodiment of the present invention further provides a deep learning based workpiece wear detection system, including:
the sample image acquisition module 100 is used for acquiring sample images of sample workpieces in various wear states;
the feature set generating module 200 is configured to label the surface defect type and the defect area of the sample image, and generate an image feature set of the sample workpiece;
the model training module 300 is used for inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model;
and the defect detection module 400 is used for inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection and identifying the defect type of the workpiece to be detected.
In a preferred embodiment, the surface defect types include: abrasive wear, adhesive wear, surface fatigue wear, corrosive wear, and fretting wear.
In a preferred embodiment, the feature set generation module 200 is further configured to:
carrying out size normalization processing on the sample image to generate a normalized image;
rejecting noise contained in the normalized image using bilateral filtering;
the normalized image is rotated 90 ° in a counter-clockwise direction and randomly scaled and cropped to enhance the data of the image feature set.
In a preferred embodiment, the model training module 300 is further configured to:
extracting a defect area in the image feature set as a labeling frame;
inputting the image feature set into a Mask R-CNN neural network for training to obtain a result frame of the surface defect;
calculating the deviation between the result frame and the labeling frame by adopting a multitask loss function, wherein the multitask loss function comprises a classification loss function and a regression loss function, and when the deviation is lower than a set threshold value, training of a Mask R-CNN neural network is completed;
and taking the Mask R-CNN neural network after the training as a workpiece abrasion detection model.
It can be seen that the contents in the foregoing method embodiments are all applicable to this system embodiment, the functions specifically implemented by this system embodiment are the same as those in the foregoing method embodiment, and the advantageous effects achieved by this system embodiment are also the same as those achieved by the foregoing method embodiment.
Through the above description of the embodiments, it is clear to those skilled in the art that the method of the above embodiments may be implemented by software, and the embedded software is loaded into a processor, so as to effectively utilize data acquired by various sensors to perform workpiece wear detection based on deep learning. Based on this understanding, the technical solutions of the present invention may be embodied in the form of software products, which essentially or partially contribute to the prior art.
The Processor may be a Central-Processing Unit (CPU), other general-purpose Processor, a Digital Signal Processor (DSP), an Application-Specific-Integrated-Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center of the one type of deep learning based workpiece wear detection system, with various interfaces and lines connecting the various parts of the overall deep learning based workpiece wear detection system.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the deep learning based workpiece wear detection system by running or executing the computer programs and/or modules stored in the memory and invoking the data stored in the memory. The memory may primarily include a program storage area and a data storage area, which may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart-Media-Card (SMC), a Secure-Digital (SD) Card, a Flash-memory Card (Flash-Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
While the present disclosure has been described in considerable detail and with particular reference to a few illustrative embodiments thereof, it is not intended to be limited to any such details or embodiments or any particular embodiments, but it is to be construed with references to the appended claims so as to provide a broad, possibly open interpretation of such claims in view of the prior art, and to effectively encompass the intended scope of the disclosure. Furthermore, the foregoing describes the disclosure in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the disclosure, not presently foreseen, may nonetheless represent equivalent modifications thereto.
Claims (8)
1. A workpiece wear detection method based on deep learning is characterized by comprising the following steps:
acquiring sample images of a sample workpiece in various wear states;
marking the surface defect type and the defect area of the sample image to generate an image feature set of the sample workpiece;
inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model;
and inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection, and identifying the defect type of the workpiece to be detected.
2. The method of claim 1, wherein the surface defect types comprise: abrasive wear, adhesive wear, surface fatigue wear, corrosive wear, and fretting wear.
3. The method for detecting workpiece wear based on deep learning of claim 2, wherein the step of labeling the surface defect type and defect region of the sample image to generate the image feature set of the sample workpiece further comprises:
carrying out size normalization processing on the sample image to generate a normalized image;
rejecting noise contained in the normalized image using bilateral filtering;
the normalized image is rotated 90 ° in a counter-clockwise direction and randomly scaled and cropped to enhance the data of the image feature set.
4. The workpiece wear detection method based on deep learning of claim 3, wherein the image feature set is input to a Mask R-CNN neural network for training to generate a workpiece wear detection model, and the method comprises:
extracting a defect area in the image feature set as a labeling frame;
inputting the image feature set into a MaskR-CNN neural network for training to obtain a result frame of the surface defect;
calculating the deviation between the result frame and the labeling frame by adopting a multitask loss function, wherein the multitask loss function comprises a classification loss function and a regression loss function, and when the deviation is lower than a set threshold value, training of the MaskR-CNN neural network is completed;
and taking the Mask R-CNN neural network after the training as a workpiece abrasion detection model.
5. A workpiece wear detection system based on deep learning, comprising:
the sample image acquisition module is used for acquiring sample images of the sample workpiece in various wear states;
the feature set generation module is used for marking the surface defect type and the defect area of the sample image and generating an image feature set of the sample workpiece;
the model training module is used for inputting the image feature set into a Mask R-CNN neural network for training to generate a workpiece abrasion detection model;
and the defect detection module is used for inputting the image of the workpiece to be detected into the workpiece abrasion detection model for automatic detection and identifying the defect type of the workpiece to be detected.
6. The deep learning based workpiece wear detection system of claim 5, wherein the surface defect types comprise: abrasive wear, adhesive wear, surface fatigue wear, corrosive wear, and fretting wear.
7. The deep learning based workpiece wear detection system of claim 6, wherein the feature set generation module is further configured to:
carrying out size normalization processing on the sample image to generate a normalized image;
rejecting noise contained in the normalized image using bilateral filtering;
the normalized image is rotated 90 ° in a counter-clockwise direction and randomly scaled and cropped to enhance the data of the image feature set.
8. The deep learning based workpiece wear detection system of claim 7, wherein the model training module is further configured to:
extracting a defect area in the image feature set as a labeling frame;
inputting the image feature set into a Mask R-CNN neural network for training to obtain a result frame of the surface defect;
calculating the deviation between the result frame and the labeling frame by adopting a multitask loss function, wherein the multitask loss function comprises a classification loss function and a regression loss function, and when the deviation is lower than a set threshold value, training of a Mask R-CNN neural network is completed;
and taking the Mask R-CNN neural network after the training as a workpiece abrasion detection model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010042386.8A CN111260626A (en) | 2020-01-15 | 2020-01-15 | Workpiece wear detection method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010042386.8A CN111260626A (en) | 2020-01-15 | 2020-01-15 | Workpiece wear detection method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111260626A true CN111260626A (en) | 2020-06-09 |
Family
ID=70953133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010042386.8A Pending CN111260626A (en) | 2020-01-15 | 2020-01-15 | Workpiece wear detection method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260626A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465787A (en) * | 2020-12-03 | 2021-03-09 | 天津大学 | Digital micromirror highlight defect detection method based on deep learning |
| CN112485259A (en) * | 2020-11-13 | 2021-03-12 | 湖南交通工程学院 | Strong-self-adaptive metal surface intelligent defect visual detection equipment and detection method |
| CN112733882A (en) * | 2020-12-22 | 2021-04-30 | 郑州金惠计算机系统工程有限公司 | Cylinder sleeve surface defect detection method, system and equipment based on deep learning |
| CN112884717A (en) * | 2021-01-29 | 2021-06-01 | 东莞市牛犇智能科技有限公司 | System and method for real-time workpiece surface detection and tool life prediction |
| CN113096067A (en) * | 2021-03-04 | 2021-07-09 | 深圳市道通科技股份有限公司 | Method and system for determining surface wear of workpiece |
| CN114646563A (en) * | 2022-05-23 | 2022-06-21 | 河南银金达新材料股份有限公司 | Method for detecting surface abrasion resistance of polyester film with metal coating |
| CN116091445A (en) * | 2023-01-05 | 2023-05-09 | 中国长江电力股份有限公司 | Ship lift gear and gear surface damage identification method based on deep learning |
| CN116993679A (en) * | 2023-06-30 | 2023-11-03 | 芜湖合德传动科技有限公司 | Method for detecting belt abrasion of telescopic machine based on target detection |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711474A (en) * | 2018-12-24 | 2019-05-03 | 中山大学 | A kind of aluminium material surface defects detection algorithm based on deep learning |
| CN110310262A (en) * | 2019-06-19 | 2019-10-08 | 上海理工大学 | A kind of method, apparatus and system for detection wheel tyre defect |
-
2020
- 2020-01-15 CN CN202010042386.8A patent/CN111260626A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711474A (en) * | 2018-12-24 | 2019-05-03 | 中山大学 | A kind of aluminium material surface defects detection algorithm based on deep learning |
| CN110310262A (en) * | 2019-06-19 | 2019-10-08 | 上海理工大学 | A kind of method, apparatus and system for detection wheel tyre defect |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112485259A (en) * | 2020-11-13 | 2021-03-12 | 湖南交通工程学院 | Strong-self-adaptive metal surface intelligent defect visual detection equipment and detection method |
| CN112465787A (en) * | 2020-12-03 | 2021-03-09 | 天津大学 | Digital micromirror highlight defect detection method based on deep learning |
| CN112733882A (en) * | 2020-12-22 | 2021-04-30 | 郑州金惠计算机系统工程有限公司 | Cylinder sleeve surface defect detection method, system and equipment based on deep learning |
| CN112884717A (en) * | 2021-01-29 | 2021-06-01 | 东莞市牛犇智能科技有限公司 | System and method for real-time workpiece surface detection and tool life prediction |
| CN113096067A (en) * | 2021-03-04 | 2021-07-09 | 深圳市道通科技股份有限公司 | Method and system for determining surface wear of workpiece |
| CN113096067B (en) * | 2021-03-04 | 2022-10-11 | 深圳市道通科技股份有限公司 | Method and system for determining surface wear of workpiece |
| CN114646563A (en) * | 2022-05-23 | 2022-06-21 | 河南银金达新材料股份有限公司 | Method for detecting surface abrasion resistance of polyester film with metal coating |
| CN116091445A (en) * | 2023-01-05 | 2023-05-09 | 中国长江电力股份有限公司 | Ship lift gear and gear surface damage identification method based on deep learning |
| CN116091445B (en) * | 2023-01-05 | 2024-01-02 | 中国长江电力股份有限公司 | Ship lift gear and gear surface damage identification method based on deep learning |
| CN116993679A (en) * | 2023-06-30 | 2023-11-03 | 芜湖合德传动科技有限公司 | Method for detecting belt abrasion of telescopic machine based on target detection |
| CN116993679B (en) * | 2023-06-30 | 2024-04-30 | 芜湖合德传动科技有限公司 | Method for detecting belt abrasion of telescopic machine based on target detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260626A (en) | Workpiece wear detection method and system based on deep learning | |
| CN110826416B (en) | Bathroom ceramic surface defect detection method and device based on deep learning | |
| US20210374940A1 (en) | Product defect detection method, device and system | |
| Shumin et al. | AdaBoost learning for fabric defect detection based on HOG and SVM | |
| CN109598287B (en) | Appearance flaw detection method for resisting network sample generation based on deep convolution generation | |
| US20180268257A1 (en) | Surface defect detection | |
| CN111932489A (en) | Weld defect detection method, system, storage medium, computer device and terminal | |
| CN110599544B (en) | Workpiece positioning method and device based on machine vision | |
| CN109671078B (en) | Method and device for detecting product surface image abnormity | |
| CN106651825A (en) | Workpiece positioning and identification method based on image segmentation | |
| CN111145209A (en) | Medical image segmentation method, device, equipment and storage medium | |
| CN108647706B (en) | Article identification classification and flaw detection method based on machine vision | |
| Mera et al. | Automatic visual inspection: An approach with multi-instance learning | |
| CN111179263B (en) | Industrial image surface defect detection model, method, system and device | |
| CN112614062A (en) | Bacterial colony counting method and device and computer storage medium | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| Jian et al. | Imbalanced defect classification for mobile phone screen glass using multifractal features and a new sampling method | |
| CN113112485A (en) | Belt conveyor deviation detection method, system, equipment and medium based on image processing | |
| CN114926441A (en) | Defect detection method and system for machining and molding injection molding part | |
| CN111814852A (en) | Image detection method, image detection device, electronic equipment and computer-readable storage medium | |
| CN110276759B (en) | Mobile phone screen bad line defect diagnosis method based on machine vision | |
| Mishchenko et al. | Model-based chart image classification | |
| CN111680680B (en) | Target code positioning method and device, electronic equipment and storage medium | |
| CN116503382B (en) | Method and system for detecting scratch defects of display screen | |
| CN112669300A (en) | Defect detection method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200609 |
|
| RJ01 | Rejection of invention patent application after publication |