CN113504244A - New energy automobile battery flaw detection method and device - Google Patents
New energy automobile battery flaw detection method and device Download PDFInfo
- Publication number
- CN113504244A CN113504244A CN202110791491.6A CN202110791491A CN113504244A CN 113504244 A CN113504244 A CN 113504244A CN 202110791491 A CN202110791491 A CN 202110791491A CN 113504244 A CN113504244 A CN 113504244A
- Authority
- CN
- China
- Prior art keywords
- flaw detection
- automobile battery
- battery
- class
- image
- 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
Images
Classifications
-
- 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
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
-
- 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
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/888—Marking defects
-
- 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
- G01N2021/8887—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 based on image processing techniques
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biochemistry (AREA)
- Quality & Reliability (AREA)
- Textile Engineering (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses a new energy automobile battery flaw detection method and device, and relates to the technical field of computer vision. The invention comprises the following steps: collecting a large number of automobile battery pictures with different types and a plurality of angles to establish a mathematical model; the method comprises the following steps that a plurality of high-definition cameras collect photos of an automobile battery at different angles on a production line; preprocessing the acquired automobile battery image; extracting image edge information by using an edge detection operator, and determining a detection area; marking the defects in the monitored area by using a Harris corner detection method; importing the pictures marked with defects into a mathematical model for flaw detection and extraction; and calculating the defect area, determining the flaw detection grade and giving an alarm. The computer vision technology of the invention can quickly carry out multi-angle surface scanning identification on the automobile battery on the production line, carry out flaw detection treatment on the automobile battery, mark the defects in the monitoring area, calculate the area size of the defects and improve the production quality and efficiency of the automobile battery.
Description
Technical Field
The invention belongs to the technical field of computer vision, and particularly relates to a new energy automobile battery flaw detection method and device.
Background
In recent years, with the continuous improvement of the quality of life of people, automobiles gradually enter families to become transportation tools of people, and meanwhile, more and more gas is discharged to pollute the environment. Under the background of advocating green environmental protection in the environmental protection department, electric automobiles with various purposes are produced.
Most of the existing electric automobiles adopt electric energy stored in storage batteries as power energy, and mechanical faults which are difficult to find can cause output of a large number of defective products in a short time in the actual production process. Most of existing detection methods adopt manual detection, but a large number of quality testing personnel on an assembly line can only roughly observe whether the outer wall of the new energy automobile battery is damaged, deformed, leaked liquid and the like through naked eyes, and fine damage is not easy to observe, so that defective products are caused, and product quality is affected.
In order to solve the problems, the application document adopts a new energy battery quality auxiliary detection tool, applies an optical automatic detection principle to industrial production, and has great advantages in timeliness, reliability and durability compared with the traditional manual detection.
Disclosure of Invention
The invention aims to provide a new energy automobile battery flaw detection method and device, which can be used for rapidly scanning and identifying an automobile battery on a production line and carrying out flaw detection treatment on the automobile battery through a computer vision technology, and solves the problems that manual visual detection is needed in the existing product production process, and the production efficiency and the product quality are influenced.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a new energy automobile battery flaw detection method, which comprises the following steps:
step S1: collecting a large number of automobile battery pictures with different types and a plurality of angles to establish a mathematical model;
step S2: the method comprises the following steps that a plurality of high-definition cameras collect photos of an automobile battery at different angles on a production line;
step S3: preprocessing the acquired automobile battery image;
step S4: extracting image edge information by using an edge detection operator, and determining a detection area;
step S5: marking the defects in the monitored area by using a Harris corner detection method;
step S6: importing the pictures marked with defects into a mathematical model for flaw detection and extraction;
step S7: and calculating the defect area, determining the flaw detection grade and giving an alarm.
Preferably, in step S1, the collecting a plurality of different models of multiple-angle car battery pictures includes: the method comprises the following steps that qualified pictures of automobile batteries of different models are used as a positive sample for training, defect pictures of the automobile batteries of different models are used as a negative sample for training, and defect labels are marked in the negative sample pictures; the defect label includes a battery flange, a battery notch, a battery breach, a battery scratch, a battery nick, a battery trauma, and a battery dent.
Preferably, in step S2, a collection platform is set up on the production line, and when the automobile battery passes through the collection platform, after being monitored by the infrared sensor, the PLC controller sends an operation instruction to the high-definition camera to control the high-definition camera to collect an image of the automobile battery.
Preferably, the step of preprocessing the car battery image comprises:
step S31: carrying out morphological reconstruction and enhancement processing on the acquired automobile battery image;
step S32: carrying out image enhancement processing on the flaw detection image by using an index enhancement function on the flaw detection edge profile information of the reconstructed image;
step S33: after image enhancement, the flaw detection area and the background area are separated.
Preferably, in step S4, image edge information is extracted from the flaw detection area, and the extracted edge information is divided into a circular boundary and a rectangular boundary;
the circle and the radius of the surface area of the automobile battery are determined firstly by the circular boundary, and the specific formula is as follows:
in the formula (x)0,y0) As a circle center coordinate, d represents an Euclidean distance, Cim represents a point set of the outer edge of the flaw detection area, C (x, y) represents a point in the flaw detection area, and P (i, j) represents a point on the outer edge;
the rectangular boundary firstly determines the coordinates of the upper left corner and the lower right corner of the surface area of the automobile battery, and determines the rectangular boundary according to the two coordinates.
Preferably, in step S5, the Harris corner detection formula is as follows:
where E denotes an image intensity variation value energy function, u denotes a position of the window function in the horizontal direction, v denotes a displacement of the window function in the vertical direction, w (x, y) is the window function at (x, y), equivalent to one mask, I (x, y) is an image intensity at a point (x, y), and I (x + u, y + v) denotes an image intensity after the point.
Preferably, in step S6, before flaw detection extraction, coarse extraction is performed; the steps of the crude extraction are as follows: performing feature matching on the obtained feature points through Euclidean distance, performing range compression on similarity of all the matching points, and proposing matching pairs outside a pointing range, wherein most of the proposed matching pairs are wrong matching pairs; and then further purifying the matched pairs of the feature points by using an improved self-adaptive RANSAC algorithm, eliminating wrong matched pairs of the feature points, judging the matched pairs which conform to a mathematical model of the RANSAC algorithm to be correct, and judging the matched pairs which do not conform to the model to be wrong.
Preferably, in step S6, the flow of flaw detection extraction is as follows:
step S61: randomly selecting an angular point in the detection area, taking the angular point as an initial class, and taking an angular coordinate of the angular point in a polar coordinate system as a characteristic value of the class;
step S62: randomly selecting a corner point from the unclassified corner point set, if the absolute value of the difference between the angular coordinate value of the point and the initial class characteristic value is less than a threshold value AsIf so, classifying the point into an initial class, and updating the characteristic value of the initial class according to the mean value of the angle direction coordinate values of all sample points in the initial class; if the absolute value of the difference between the angular coordinate value of the point and the initial class characteristic value is larger than the threshold AsThen a new class is established based on the point according to the method of step S61;
step S63: taking out the angular points from the unclassified angular point set one by one, comparing the taken out angular points with the characteristic values of the existing classes one by one according to a step S62 classification method, and if the extracted angular points and a certain class meet classification conditions in the comparison process, immediately classifying the class and updating the characteristic values of the class; otherwise, establishing a new class;
step S64: step 4, after the angular points in all the detection areas are classified, counting the number of sample points in each class, selecting the class with the largest number of sample points and the number of the sample points being more than 2, and using A as the characteristic value of the classfRepresents; the angular coordinate in the detection area is Af-AsAnd Af+AsThe pixel points in the middle are extracted and displayed.
The invention relates to a new energy automobile battery flaw detection device, which comprises an acquisition platform and an upper computer, wherein the acquisition platform and the upper computer are erected on a production line;
the acquisition platform comprises a plurality of high-definition cameras positioned above the conveyor belt and an infrared sensor positioned on one side of the conveyor belt; the infrared sensor is connected with the input end of the PLC; the output end of the PLC is connected with the high-definition camera;
the PLC is in communication connection with the upper computer; the upper computer is internally provided with a pre-trained digital model and an image preprocessing module, an effective area extraction module, a flaw detection extraction module and a defect area calculation module which are sequentially connected.
The invention has the following beneficial effects:
according to the invention, through a computer vision technology, multi-angle surface scanning recognition is rapidly carried out on the automobile battery on the production line, flaw detection processing is carried out on the automobile battery, the defects are marked in a monitoring area, the area size of the defects is calculated, battery quality is graded according to the area size, and an alarm is sent to remind operation and maintenance personnel to maintain, so that the production quality and efficiency of the automobile battery are improved.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced 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 that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a step diagram of a new energy automobile battery flaw detection method of the invention;
fig. 2 is a schematic structural diagram of the new energy automobile battery flaw detection device of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the invention relates to a new energy automobile battery flaw detection method, which includes the following steps:
step S1: collecting a large number of automobile battery pictures with different types and a plurality of angles to establish a mathematical model;
step S2: the method comprises the following steps that a plurality of high-definition cameras collect photos of an automobile battery at different angles on a production line;
step S3: preprocessing the acquired automobile battery image;
step S4: extracting image edge information by using an edge detection operator, and determining a detection area;
step S5: marking the defects in the monitored area by using a Harris corner detection method;
step S6: importing the pictures marked with defects into a mathematical model for flaw detection and extraction;
step S7: and calculating the defect area, determining the flaw detection grade and giving an alarm.
In step S1, collecting a plurality of different models of automobile battery pictures at a plurality of angles includes: the method comprises the following steps that qualified pictures of automobile batteries of different models are used as a positive sample for training, defect pictures of the automobile batteries of different models are used as a negative sample for training, and defect labels are marked in the negative sample pictures; the defect label comprises a battery flanging, a battery notch, a battery split, a battery scratch, a battery nick, a battery wound and a battery dent; .
In step S2, a collection platform is set up on the production line, and when the automobile battery passes through the collection platform, the collection platform is monitored by the infrared sensor, and then the PLC controller sends an operation instruction to the high-definition camera to control the high-definition camera to collect images of the automobile battery.
The method for preprocessing the automobile battery image comprises the following steps of:
step S31: carrying out morphological reconstruction and enhancement processing on the acquired automobile battery image;
step S32: carrying out image enhancement processing on the flaw detection image by using an index enhancement function on the flaw detection edge profile information of the reconstructed image;
step S33: after image enhancement, the flaw detection area and the background area are separated.
In step S4, image edge information is extracted from the flaw detection area, and the extracted edge information is divided into a circular boundary and a rectangular boundary;
the circle boundary firstly determines the circle and the radius of the surface area of the automobile battery, and the specific formula is as follows:
in the formula (x)0,y0) As a circle center coordinate, d represents an Euclidean distance, Cim represents a point set of the outer edge of the flaw detection area, C (x, y) represents a point in the flaw detection area, and P (i, j) represents a point on the outer edge;
the rectangular boundary firstly determines the coordinates of the upper left corner and the lower right corner of the surface area of the automobile battery, and determines the rectangular boundary according to the two coordinates.
In step S5, the Harris corner detection formula is as follows:
where E denotes an image intensity variation value energy function, u denotes a position of the window function in the horizontal direction, v denotes a displacement of the window function in the vertical direction, w (x, y) is the window function at (x, y), equivalent to one mask, I (x, y) is an image intensity at a point (x, y), and I (x + u, y + v) denotes an image intensity after the point.
In step S6, coarse extraction is performed before flaw detection extraction; the steps of crude extraction are as follows: performing feature matching on the obtained feature points through Euclidean distance, performing range compression on similarity of all the matching points, and proposing matching pairs outside a pointing range, wherein most of the proposed matching pairs are wrong matching pairs; and then further purifying the matched pairs of the feature points by using an improved self-adaptive RANSAC algorithm, eliminating wrong matched pairs of the feature points, judging the matched pairs which conform to a mathematical model of the RANSAC algorithm to be correct, and judging the matched pairs which do not conform to the model to be wrong.
In step S6, the flow of flaw detection extraction is as follows:
step S61: randomly selecting an angular point in the detection area, taking the angular point as an initial class, and taking an angular coordinate of the angular point in a polar coordinate system as a characteristic value of the class;
step S62: randomly selecting a corner point from the unclassified corner point set, if the absolute value of the difference between the angular coordinate value of the point and the initial class characteristic value is less than a threshold value AsIf so, classifying the point into an initial class, and updating the characteristic value of the initial class according to the mean value of the angle direction coordinate values of all sample points in the initial class; if the absolute value of the difference between the angular coordinate value of the point and the initial class characteristic value is larger than the threshold AsThen a new class is established based on the point according to the method of step S61;
step S63: taking out the angular points from the unclassified angular point set one by one, comparing the taken out angular points with the characteristic values of the existing classes one by one according to a step S62 classification method, and if the extracted angular points and a certain class meet classification conditions in the comparison process, immediately classifying the class and updating the characteristic values of the class; otherwise, establishing a new class;
step S64: step 4, after the angular points in all the detection areas are classified, counting the number of sample points in each class, selecting the class with the largest number of sample points and the number of the sample points being more than 2, and using A as the characteristic value of the classfRepresents; the angular coordinate in the detection area is Af-AsAnd Af+AsThe pixel points in the middle are extracted and displayed.
Referring to fig. 2, the invention relates to a new energy vehicle battery flaw detection device, which comprises an acquisition platform and an upper computer, wherein the acquisition platform is erected on a production line;
the acquisition platform comprises a plurality of high-definition cameras positioned above the conveyor belt and an infrared sensor positioned on one side of the conveyor belt; the infrared sensor is connected with the input end of the PLC; the output end of the PLC is connected with the high-definition camera;
the PLC is in communication connection with the upper computer; the upper computer is internally provided with a pre-trained digital model and an image preprocessing module, an effective area extraction module, a flaw detection extraction module and a defect area calculation module which are connected in sequence.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, it is understood by those skilled in the art that all or part of the steps in the method for implementing the embodiments described above may be implemented by a program instructing associated hardware, and the corresponding program may be stored in a computer-readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (9)
1. The new energy automobile battery flaw detection method is characterized by comprising the following steps:
step S1: collecting a large number of automobile battery pictures with different types and a plurality of angles to establish a mathematical model;
step S2: the method comprises the following steps that a plurality of high-definition cameras collect photos of an automobile battery at different angles on a production line;
step S3: preprocessing the acquired automobile battery image;
step S4: extracting image edge information by using an edge detection operator, and determining a detection area;
step S5: marking the defects in the monitored area by using a Harris corner detection method;
step S6: importing the pictures marked with defects into a mathematical model for flaw detection and extraction;
step S7: and calculating the defect area, determining the flaw detection grade and giving an alarm.
2. The new energy automobile battery flaw detection method according to claim 1, wherein the step S1 of collecting a plurality of different models of automobile battery pictures at a plurality of angles includes: the method comprises the following steps that qualified pictures of automobile batteries of different models are used as a positive sample for training, defect pictures of the automobile batteries of different models are used as a negative sample for training, and defect labels are marked in the negative sample pictures; the defect label includes a battery flange, a battery notch, a battery breach, a battery scratch, a battery nick, a battery trauma, and a battery dent.
3. The new energy automobile battery flaw detection method according to claim 1, characterized in that in step S2, a collection platform is built on a production line, and when an automobile battery passes through the collection platform, after being monitored by an infrared sensor, a PLC controller sends an operation instruction to a high-definition camera to control the high-definition camera to perform image collection on the automobile battery.
4. The new energy automobile battery flaw detection method according to claim 1, wherein the step of preprocessing the automobile battery image comprises the following steps:
step S31: carrying out morphological reconstruction and enhancement processing on the acquired automobile battery image;
step S32: carrying out image enhancement processing on the flaw detection image by using an index enhancement function on the flaw detection edge profile information of the reconstructed image;
step S33: after image enhancement, the flaw detection area and the background area are separated.
5. The new energy automobile battery flaw detection method according to claim 1, characterized in that in step S4, image edge information is extracted from a flaw detection area, and the extracted edge information is divided into two types, namely a circular boundary and a rectangular boundary;
the circle and the radius of the surface area of the automobile battery are determined firstly by the circular boundary, and the specific formula is as follows:
in the formula (x)0,y0) As a circle center coordinate, d represents an Euclidean distance, Cim represents a point set of the outer edge of the flaw detection area, C (x, y) represents a point in the flaw detection area, and P (i, j) represents a point on the outer edge;
the rectangular boundary firstly determines the coordinates of the upper left corner and the lower right corner of the surface area of the automobile battery, and determines the rectangular boundary according to the two coordinates.
6. The new energy automobile battery flaw detection method according to claim 1, wherein in step S5, the Harris corner detection formula is as follows:
where E denotes an image intensity variation value energy function, u denotes a position of the window function in the horizontal direction, v denotes a displacement of the window function in the vertical direction, w (x, y) is the window function at (x, y), equivalent to one mask, I (x, y) is an image intensity at a point (x, y), and I (x + u, y + v) denotes an image intensity after the point.
7. The new energy automobile battery flaw detection method according to claim 1, characterized in that in step S6, before flaw detection extraction, rough extraction is performed; the steps of the crude extraction are as follows: performing feature matching on the obtained feature points through Euclidean distance, performing range compression on similarity of all the matching points, and proposing matching pairs outside a pointing range, wherein most of the proposed matching pairs are wrong matching pairs; and then further purifying the matched pairs of the feature points by using an improved self-adaptive RANSAC algorithm, eliminating wrong matched pairs of the feature points, judging the matched pairs which conform to a mathematical model of the RANSAC algorithm to be correct, and judging the matched pairs which do not conform to the model to be wrong.
8. The new energy automobile battery flaw detection method according to claim 1, wherein in the step S6, the flow of flaw detection extraction is as follows:
step S61: randomly selecting an angular point in the detection area, taking the angular point as an initial class, and taking an angular coordinate of the angular point in a polar coordinate system as a characteristic value of the class;
step S62: randomly selecting a corner point from the unclassified corner point set, if the absolute value of the difference between the angular coordinate value of the point and the initial class characteristic value is less than a threshold value AsIf so, classifying the point into an initial class, and updating the characteristic value of the initial class according to the mean value of the angle direction coordinate values of all sample points in the initial class; if the absolute value of the difference between the angular coordinate value of the point and the initial class characteristic value is larger than the threshold AsThen a new class is established based on the point according to the method of step S61;
step S63: taking out the angular points from the unclassified angular point set one by one, comparing the taken out angular points with the characteristic values of the existing classes one by one according to a step S62 classification method, and if the extracted angular points and a certain class meet classification conditions in the comparison process, immediately classifying the class and updating the characteristic values of the class; otherwise, establishing a new class;
step S64: step 4, after the angular points in all the detection areas are classified, counting the number of sample points in each class, selecting the class with the largest number of sample points and the number of the sample points being more than 2, and using A as the characteristic value of the classfRepresents; the angular coordinate in the detection area is Af-AsAnd Af+AsThe pixel points in the middle are extracted and displayed.
9. A new energy automobile battery flaw detection device is characterized by comprising an acquisition platform and an upper computer which are erected on a production line;
the acquisition platform comprises a plurality of high-definition cameras positioned above the conveyor belt and an infrared sensor positioned on one side of the conveyor belt; the infrared sensor is connected with the input end of the PLC; the output end of the PLC is connected with the high-definition camera;
the PLC is in communication connection with the upper computer; the upper computer is internally provided with a pre-trained digital model and an image preprocessing module, an effective area extraction module, a flaw detection extraction module and a defect area calculation module which are sequentially connected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791491.6A CN113504244A (en) | 2021-07-13 | 2021-07-13 | New energy automobile battery flaw detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110791491.6A CN113504244A (en) | 2021-07-13 | 2021-07-13 | New energy automobile battery flaw detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113504244A true CN113504244A (en) | 2021-10-15 |
Family
ID=78013263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110791491.6A Pending CN113504244A (en) | 2021-07-13 | 2021-07-13 | New energy automobile battery flaw detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113504244A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116148289A (en) * | 2023-04-20 | 2023-05-23 | 宁德时代新能源科技股份有限公司 | Battery defect detection method and system and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111667470A (en) * | 2020-06-05 | 2020-09-15 | 西安科技大学 | Industrial pipeline flaw detection inner wall detection method based on digital image |
| CN112017150A (en) * | 2020-04-30 | 2020-12-01 | 河南爱比特科技有限公司 | Intelligent visual detection method and equipment for surface defects of lithium ion battery pole piece |
| CN112630222A (en) * | 2020-11-24 | 2021-04-09 | 河海大学常州校区 | Mobile phone cover plate glass defect detection method based on machine vision |
| CN113030093A (en) * | 2020-12-30 | 2021-06-25 | 凌云光技术股份有限公司 | Battery diaphragm surface defect detection method and system |
-
2021
- 2021-07-13 CN CN202110791491.6A patent/CN113504244A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112017150A (en) * | 2020-04-30 | 2020-12-01 | 河南爱比特科技有限公司 | Intelligent visual detection method and equipment for surface defects of lithium ion battery pole piece |
| CN111667470A (en) * | 2020-06-05 | 2020-09-15 | 西安科技大学 | Industrial pipeline flaw detection inner wall detection method based on digital image |
| CN112630222A (en) * | 2020-11-24 | 2021-04-09 | 河海大学常州校区 | Mobile phone cover plate glass defect detection method based on machine vision |
| CN113030093A (en) * | 2020-12-30 | 2021-06-25 | 凌云光技术股份有限公司 | Battery diaphragm surface defect detection method and system |
Non-Patent Citations (2)
| Title |
|---|
| 徐建元等: "基于计算机视觉的电池表面探伤方法", 《计算机应用》 * |
| 王磊: "基于机器视觉的电池表面缺陷检测技术研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116148289A (en) * | 2023-04-20 | 2023-05-23 | 宁德时代新能源科技股份有限公司 | Battery defect detection method and system and computer readable storage medium |
| CN116148289B (en) * | 2023-04-20 | 2023-08-29 | 宁德时代新能源科技股份有限公司 | Battery defect detection method and system and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110555842A (en) | Silicon wafer image defect detection method based on anchor point set optimization | |
| CN111091544B (en) | Method for detecting breakage fault of side integrated framework of railway wagon bogie | |
| CN107782733A (en) | Image recognition the cannot-harm-detection device and method of cracks of metal surface | |
| CN113548419A (en) | Belt tearing detection method, device and system based on machine vision image recognition | |
| CN112364740B (en) | Unmanned aerial vehicle room monitoring method and system based on computer vision | |
| CN113538503B (en) | Solar panel defect detection method based on infrared image | |
| CN112529875A (en) | Photovoltaic module glass burst early warning method and system based on artificial intelligence | |
| CN110544231A (en) | lithium battery electrode surface defect detection method based on background standardization and centralized compensation algorithm | |
| CN113327255A (en) | Power transmission line inspection image processing method based on YOLOv3 detection, positioning and cutting and fine-tune | |
| CN111415339A (en) | Image defect detection method for complex texture industrial product | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN114662208B (en) | Construction visualization system and method based on Bim technology | |
| CN114092478B (en) | Anomaly detection method | |
| CN113504244A (en) | New energy automobile battery flaw detection method and device | |
| CN111951218A (en) | Lipstick quality inspection system of mixed deep learning model | |
| CN117269168B (en) | New energy automobile precision part surface defect detection device and detection method | |
| CN113989196A (en) | Vision-based earphone silica gel gasket appearance defect detection method | |
| CN113469938A (en) | Pipe gallery video analysis method and system based on embedded front-end processing server | |
| CN112001336A (en) | Pedestrian boundary crossing alarm method, device, equipment and system | |
| CN115797280A (en) | Transformer surface defect detection system based on image AI recognition algorithm | |
| CN112712055B (en) | Double-path deformable CNN coal mine gateway belt conveying foreign matter monitoring method | |
| CN113989209A (en) | Power line foreign matter detection method based on fast R-CNN | |
| CN114596439A (en) | Image-based intelligent damage assessment and check method and device for car insurance and electronic equipment | |
| CN114120175A (en) | Method for identifying foreign matters on coal conveying belt based on computer vision | |
| CN110503627A (en) | Building tear detection method, device, storage medium and computer equipment |
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: 20211015 |
|
| RJ01 | Rejection of invention patent application after publication |