CN114047195A - New energy battery cap defect detection method and system - Google Patents
New energy battery cap defect detection method and system Download PDFInfo
- Publication number
- CN114047195A CN114047195A CN202111333918.4A CN202111333918A CN114047195A CN 114047195 A CN114047195 A CN 114047195A CN 202111333918 A CN202111333918 A CN 202111333918A CN 114047195 A CN114047195 A CN 114047195A
- Authority
- CN
- China
- Prior art keywords
- battery cap
- detection device
- battery
- control system
- caps
- 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 129
- 230000007547 defect Effects 0.000 title claims abstract description 65
- 238000003466 welding Methods 0.000 claims abstract description 67
- 238000005070 sampling Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000000926 separation method Methods 0.000 claims description 5
- 238000004880 explosion Methods 0.000 claims description 3
- 230000035515 penetration Effects 0.000 claims description 3
- 238000011109 contamination Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 12
- 238000007689 inspection Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 7
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 6
- 210000000887 face Anatomy 0.000 description 6
- 229910052744 lithium Inorganic materials 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004026 adhesive bonding Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
-
- 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
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
Landscapes
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Sealing Battery Cases Or Jackets (AREA)
Abstract
The invention discloses a defect detection method for new energy battery caps, which comprises the steps of arranging the battery caps on a charging tray according to sequence requirements and posture requirements, and then transferring the battery caps to a conveying belt; the conveying belt conveys the battery caps to sequentially pass through the first detection device, the position changing machine, the second detection device and the sorting machine; the battery cap moves to a first detection device in a mode that an arc welding surface faces upwards, the first detection device photographs and samples the arc welding surface of the battery cap and sends data to a main control system; the positioner overturns the battery cap by 180 degrees so that the spot welding surface of the battery cap faces upwards; the second detection device takes a picture of the welding surface of the battery cap for sampling and sends data to the master control system; the master control system judges the state of the battery cap according to the identification model in the master control system and sends the identification result to the sorting machine; and the sorting machine sorts the battery caps according to the recognition result. Meanwhile, a corresponding system is arranged, and the invention adopts a double-station detection mode, thereby ensuring that each camera can acquire workpiece defect data and ensuring the accuracy of the data.
Description
Technical Field
The invention relates to the technical field of detection equipment, in particular to a new energy battery cap defect detection method and system.
Background
At present, the domestic monthly yield of new energy 18650 batteries reaches more than twenty billion, and a battery cap is a core component of a lithium battery, so that the battery cap not only plays a role in stabilizing and conducting electricity, but also is a sealing component of the battery, plays an important role in protecting the internal structure of the battery and ensuring the safe use of the battery. The battery cap needs to be subjected to the working procedures of blanking, press fitting, welding and gluing from the raw material to the finished product, and the probability of the generated defects is higher, so that the quality inspection work must be carried out before the battery cap leaves a factory.
However, the automation level of the quality inspection link of the battery cap is low, the defects of welding, appearance, assembly and the like are mainly detected by manual inspection, the inspection strength is high, and the false inspection rate is high. At present, some defects can realize automatic detection, but the fundamental problem cannot be solved, and a large amount of manual work is still required to be invested to carry out quality inspection work.
The technology applied to the detection system which is mature in the market at present is a picture comparison technology, a judgment result is generated through simple gray scale and threshold calculation, the method has high detection accuracy on the existence of characteristics (namely missing parts and wrong parts), but the requirements of characteristics which need fuzzy judgment and classification such as wrong welding, partial welding, infirm welding and the like cannot be met, or the false detection rate in the practical process is high, and robot exchange cannot be achieved.
And new AI image recognition technology, this kind of technique set up the detection station after every process, have not only increased the earlier stage input of enterprise, also can improve the maintenance cost in later stage simultaneously, also can cause certain influence to production. In addition, the performance is unstable at present in a research and development stage, comprehensive evaluation and classification of product defects cannot be realized after a detection station is placed in each process, development and analysis of data related to the overall production condition are not facilitated, and meaningful decision judgment bases cannot be provided.
Chinese patent application with publication number CN211292617U discloses a lithium battery cap defect visual inspection system, and this application realizes automatic feeding and discharging operation at the lithium battery cap in the testing process, has reduced single lithium battery cap appearance defect and has detected required time, has increased substantially the detection efficiency of lithium cell on the whole, can accomplish the detection work of lithium battery cap fast, has improved detection efficiency. But still does not solve the above problems.
Disclosure of Invention
The invention is based on the technical problems to be solved: a set of complete battery cap defect detection method and system is set up, and detection accuracy is improved.
In order to solve the technical problems, the invention provides the following technical scheme:
a new energy battery cap defect detection method comprises the following steps:
s1, after arranging the battery caps on the charging tray according to the sequence requirement and the posture requirement, transferring the battery caps to a conveyer belt;
s2, conveying the battery caps by the conveying belt to pass through the first detection device, the position changing machine, the second detection device and the sorting machine in sequence;
s3, moving the battery cap to a first detection device in an arc welding surface upward mode, taking pictures and sampling on the arc welding surface of the battery cap by the first detection device, and sending data to a main control system;
s4, the battery cap is turned over by 180 degrees through the positioner, so that the spot welding surface of the battery cap faces upwards;
s5, taking pictures and sampling of the electric welding surface and the side surface of the battery cap by the second detection device, and sending data to the main control system;
s6, the master control system receives the data of the step S3 and the step S5, judges the state of the battery cap according to the identification model in the data and sends the identification result to the sorting machine;
and S7, classifying the battery caps by the classifier according to the recognition result of the step S6.
The advantages are that: the invention adopts the assembly line type double stations to realize the detection of the spot welding surface, the arc welding surface and the side surface of the battery cap, and then the defect classification treatment is finally carried out in a centralized way in the system. The double-station detection mode can ensure that each camera can directly acquire workpiece defect data and ensure the accuracy of the data.
Preferably, the method further comprises the following steps:
and S8, manually and periodically screening the classified battery caps, and updating the identification model of the main control system according to the screening result.
Preferably, the method further comprises the following steps:
and S9, the main control system uploads the judgment result to the database.
Preferably, the sorting machine adopts a secondary sorting mechanism for screening;
the first-stage classification comprises good products, arc welding defects, assembly defects, rubber ring defects and spot welding defects according to process defects;
the second classification includes: the arc welding defects comprise missing welding, insufficient welding, spot explosion and welding deviation; the assembly defects are divided into material mixing and reverse assembly; the rubber ring defects comprise ring damage, ring cracks and ring gaps; the spot welding defects are classified into missing welding, penetration welding, spot deviation and spot contamination.
Preferably, the automatic material loading device comprises a material loading plate, a conveying belt, a first detection device, a position changing machine, a second detection device, a sorting machine and a main control system;
the feeding tray is used for transferring the battery caps to the conveying belt after the battery caps are arranged according to the sequence requirement and the posture requirement;
the conveying belt is used for conveying the battery caps to sequentially pass through the first detection device, the positioner, the second detection device and the sorting machine;
the first detection device is used for photographing and sampling the arc welding surface of the battery cap and sending data to the main control system;
the positioner is used for overturning the battery cap by 180 degrees so that the spot welding surface of the battery cap faces upwards;
the second detection device is used for photographing and sampling the welding surface of the battery cap and sending data to the master control system;
the main control system is used for receiving the data of the first detection device and the second detection device, judging the state of the battery cap according to the identification model and sending the identification result to the sorting machine;
and the sorting machine is used for sorting the battery caps according to the recognition result of the master control system.
The advantages are that: the detection system is highly integrated, can finish all defect detection classification on a special machine, and completely replaces manual detection.
Preferably, an encoder is provided on the conveyor belt for recording the real-time position of each battery cap entering the detection system.
Preferably, the first detection means comprises a first top camera and a first light source;
the first top camera is arranged above the conveying belt and is positioned right above the battery cap to be detected by the first detection device; the first light source is disposed at a side of the first top camera.
Preferably, the second detection device comprises a second top camera, a plurality of side cameras and a second light source;
the second top camera is arranged above the conveying belt and is positioned right above the battery cap to be detected by the second detection device, and the plurality of side cameras are uniformly arranged around the periphery of the battery cap to be detected; the second light source is arranged above the side of the battery cap to be tested.
Preferably, three side cameras are uniformly arranged around the periphery of the battery cap at 120-degree included angles, and the included angles between the axes of the cameras and the horizontal plane are 40 degrees.
Preferably, a box for containing the battery cap is arranged behind the sorting machine.
Compared with the prior art, the invention has the beneficial effects that:
(1) the invention adopts the assembly line type double stations to realize the detection of the spot welding surface, the arc welding surface and the side surface of the battery cap, and then the defect classification treatment is finally carried out in a centralized way in the system. The double-station detection mode can ensure that each camera can directly acquire workpiece defect data and ensure the accuracy of the data.
(2) The detection system is highly integrated, can finish all defect detection classification on a special machine, and completely replaces manual detection.
(3) The detection efficiency of the invention is greatly improved, the detection system can detect 21 products per second on average, and skilled detection personnel in the industry can complete the detection of 3 products per second on average. I.e. the efficiency of the present detection system is 7 times higher than that of manual detection.
(4) The detection accuracy is greatly improved. The image recognition technology based on deep learning can accurately distinguish the tiny flaw points which are difficult to recognize by human eyes, and reduces the phenomena of missing detection and false detection. When the detection system is initially put into use, the accuracy can reach 95%, and the accuracy can be continuously improved to be close to 100% along with the increase of the use time; the accuracy of manual detection is generally only 80%, and meanwhile, the method is easily influenced by subjective factors such as the production quality and manpower in the previous process.
(5) The verification identification model of the system is dynamically updated. And each detected battery cap product picture and judgment result data thereof are uploaded to a database, the result is automatically screened and classified within a set threshold range, rechecking is carried out manually at regular intervals, and the defect inspection and identification model is updated according to the rechecking result, so that the detection and identification model can be continuously updated and upgraded along with the advance of production.
(6) The invention can provide powerful technology and data support for improving the quality of the battery cap by arranging and analyzing a large amount of inspection data, and provides direction and basis for production process control, product design improvement and the like.
Drawings
FIG. 1 is a schematic flow chart of the system as a whole according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a battery cap according to an embodiment of the present invention.
Detailed Description
In order to facilitate the understanding of the technical solutions of the present invention for those skilled in the art, the technical solutions of the present invention will be further described with reference to the drawings attached to the specification.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Referring to fig. 1, the embodiment discloses a new energy battery cap defect detection system, which comprises a feeding tray 1, a conveying belt 7, a first detection device 2, a positioner 3, a second detection device 4, a sorting machine 5, a material box 6 and a main control system;
referring to fig. 2, the battery cap 8 has two faces to be detected, an arc welding face 81 and a welding face.
After the battery caps 8 which are not needed to be disorderly are arranged according to the sequence requirement and the posture requirement by the feeding tray 1 through continuous vibration, the battery caps 8 are transferred to the conveying belt 7, and the arc welding surfaces 81 of the battery caps 8 output by the feeding tray 1 are upward in the embodiment.
The first detection device 2 comprises a first top camera 21 and a first light source 22; the first top camera 21 is arranged above the conveyer belt 7 and is positioned right above the battery cap 8 to be detected by the first detection device 2; the first light source 22 is disposed at a side of the first top camera 21. When the battery cap 8 with the upward arc welding surface 81 is conveyed into the imaging area of the first top camera 21 at a certain speed, the light source uniformly irradiates the surface of the battery cap 8 from the periphery of the battery cap 8 at a certain angle, so that light reflection is avoided, the first top camera 21 takes a picture, a picture meeting the characteristic recognition requirement is obtained, and the data is transmitted to the main control system for analysis and judgment.
After the battery cap 8 is photographed by the first detection device 2, the battery cap is conveyed to the position changing machine 3 by a conveying belt.
The positioner 3 turns over the battery cap 8 by 180 degrees so that the spot welding surface 82 of the battery cap 8 faces upward. The reversed battery cap 8 is conveyed to the second detecting device 4 to detect the spot welding surface 82 of the battery cap 8.
The second detection device 4 includes a second top camera 41, a plurality of side cameras 42, and a second light source 43;
the second top camera 41 is arranged above the conveyer belt 7 and is positioned right above the battery cap 8 to be detected by the second detection device 4, and the plurality of side cameras 42 are uniformly arranged around the periphery of the battery cap 8 to be detected; the second light source 43 is disposed above the side of the battery cap 8 to be tested. In this embodiment, three side cameras 42 are uniformly arranged around the periphery of the battery cap 8 at 120 ° included angles, and the included angle between the axis of the camera and the horizontal plane is 40 °. Therefore, a better photographing effect is obtained, the misjudgment rate is reduced, and the accuracy of the system is ensured.
When the battery cap 8 with the upward spot welding surface 82 is conveyed to the imaging area of the second top camera 41 and the side camera 42, the light source uniformly irradiates the surface of the battery cap 8 from the periphery of the battery cap 8 at a certain angle to ensure that the light cannot reflect, the second top camera 41 and the side camera 42 take pictures to obtain pictures meeting the feature recognition requirements, and the pictures are transmitted to the main control system for analysis and judgment.
The main control system judges the state of the battery cap 8 based on the recognition model and the data comparison, and simultaneously transmits the recognition result to the sorter 5.
The separator 5 adopts a secondary separation mechanism for screening. The first-stage classification is divided into good products, arc welding defects, assembly defects, rubber ring defects, spot welding defects and the like according to process defects. The following major categories can be further subdivided: the arc welding defects comprise missing welding, insufficient welding, spot explosion, welding deviation and the like; the assembly defects comprise material mixing, reverse assembly and the like; the rubber ring defects comprise ring damage, ring cracks, ring gaps and the like; the spot welding defects include missing welding, penetration welding, spot deviation, spot dirt and the like. While each classified outlet is provided with a magazine 6 for storage.
The sorting machine 5 adopts the two-stage sorting mechanism, so that the ordered storage of each battery cap 8 during sorting is ensured, and the stability of the system is improved. The problem that the separation structure is complex and the requirement on the action frequency of a separation actuator is too high to influence the reliability and the stability of a mechanism when the fine separation is directly started is avoided.
An encoder is provided on the conveyor belt 7 for recording the real time position of each battery cap 8 entering the detection system. The real-time position of the battery cap 8 in the detection system, the collected picture, the identification result and other information are correspondingly associated one by one. Therefore, the flow direction of the battery cap 8 in the whole detection process can be monitored, and the product quality can be better controlled.
The detection system is highly integrated, can finish all defect detection classification on a special machine, and completely replaces manual detection.
The detection efficiency of the detection system is greatly improved. The detection system can detect 21 products per second on average, and the detection personnel skilled in the industry can complete the detection of 3 products per second on average. The efficiency of the intelligent detection system is 7 times that of the manual detection.
The detection system adopts a production line type double station to realize the detection of the arc welding surface 81, the spot welding surface 82 and the side surface of the battery cap 8, and then the defect classification treatment is finally carried out in the system in a centralized way. The double-station detection mode can ensure that each camera can directly acquire workpiece defect data, ensure the data accuracy and cannot be influenced by the environment. At present, the workpiece is generally placed on a glass objective table and is simultaneously collected by an upper camera and a lower camera, so that the lower camera collects photo data through glass, and the accuracy of defect detection is influenced by impurities and attachments on the glass.
The embodiment also provides a method for detecting the defects of the new energy battery cap 8, which comprises the following steps:
and S1, after the battery caps 8 are arranged on the feeding tray 1 according to the sequence requirement and the posture requirement, the battery caps are transferred to the conveying belt 7.
S2, the battery cap 8 is conveyed by the conveying belt 7 to pass through the first detection device 2, the positioner 3, the second detection device 4 and the sorting machine 5 in sequence.
And S3, moving the battery cap 8 to the first detection device 2 in a mode that the arc welding surface 81 faces upwards, taking pictures of the arc welding surface 81 of the battery cap 8 by the first detection device 2, sampling, and sending data to a main control system.
S4, the positioner 3 overturns the battery cap 8 for 180 degrees, so that the spot welding surface 82 of the battery cap 8 faces upwards.
S5, the second detection device 4 takes pictures of the electric welding surface and the side surface of the battery cap 8 for sampling, and sends data to the main control system.
S6, the main control system receives the data of steps S3 and S5, judges the state of the battery cap 8 according to the recognition model therein and transmits the recognition result to the sorter 5.
S7, the sorter 5 sorts the battery caps 8 according to the recognition result of step S6.
And S8, manually and periodically screening the classified battery caps 8, and updating the identification model of the main control system according to the screening result.
And S9, the main control system uploads the judgment result to the database.
The system is based on the image recognition technology of deep learning, can accurately distinguish the tiny flaw points which are difficult to be recognized by human eyes, and reduces the phenomena of missing detection and false detection. When the detection system is initially put into use, the accuracy can reach 95%, and the accuracy can be continuously improved to be close to 100% along with the increase of the use time; the accuracy of manual detection is generally only 80%, and meanwhile, the method is easily influenced by subjective factors such as the production quality and manpower in the previous process. The defect identification detection model of the system has an updating mechanism. And each detected battery cap 8 product picture and judgment result data thereof are uploaded to a database, the result in a set threshold range can be automatically screened and classified, manual recheck is carried out regularly, and the defect detection model is updated according to the recheck result. By the method, the accuracy and precision of the recognition model can be guaranteed to be higher and higher.
Meanwhile, by arranging and analyzing a large amount of inspection data, powerful technology and data support can be provided for improving the quality of the battery cap 8, and directions and bases are provided for production process control, product design improvement and the like.
The system detection process and the enterprise production process are independent from each other, and mutual influence cannot be generated; the product detection is not influenced by the improvement of the production process, the replacement of production equipment and the like; the debugging and upgrading of product inspection can not influence the production of enterprises.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.
The above-mentioned embodiments only represent embodiments of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the concept of the present invention, and these embodiments are all within the protection scope of the present invention.
Claims (10)
1. A new energy battery cap defect detection method is characterized by comprising the following steps: the method comprises the following steps:
s1, after the battery caps (8) are arranged on the feeding tray (1) according to the sequence requirement and the posture requirement, the battery caps are transferred to a conveying belt (7);
s2, conveying the battery caps (8) through the conveying belt (7) to sequentially pass through the first detection device (2), the position changing machine (3), the second detection device (4) and the sorting machine (5);
s3, the battery cap (8) moves to the first detection device (2) in a mode that the arc welding surface (81) faces upwards, the first detection device (2) takes pictures and samples of the arc welding surface (81) of the battery cap (8), and data are sent to the master control system;
s4, the battery cap (8) is turned over by 180 degrees through the positioner (3), so that the spot welding surface (82) of the battery cap (8) faces upwards;
s5, the second detection device (4) takes pictures and samples of the electric welding surface of the battery cap (8), and sends data to the master control system;
s6, the master control system receives the data of the step S3 and the step S5, judges the state of the battery cap (8) according to the identification model in the data and sends the identification result to the separator (5);
s7, the sorter (5) sorts the battery caps (8) according to the recognition result of the step S6.
2. The new energy battery cap defect detection method according to claim 1, characterized in that: further comprising:
and S8, manually and periodically screening the classified battery caps (8), and updating the identification model of the main control system according to the screening result.
3. The new energy battery cap defect detection method according to claim 1, characterized in that: also comprises the following steps:
and S9, the main control system uploads the judgment result to the database.
4. The new energy battery cap defect detection system of claim 1, wherein: the separator (5) adopts a secondary separation mechanism to carry out screening;
the first-stage classification comprises good products, arc welding defects, assembly defects, rubber ring defects and spot welding defects according to process defects;
the second classification includes: the arc welding defects comprise missing welding, insufficient welding, spot explosion and welding deviation; the assembly defects are divided into material mixing and reverse assembly; the rubber ring defects comprise ring damage, ring cracks and ring gaps; the spot welding defects are classified into missing welding, penetration welding, spot deviation and spot contamination.
5. A system applying the new energy battery cap defect detection method of any one of claims 1 to 4, wherein: the automatic sorting machine comprises a feeding disc (1), a conveying belt (7), a first detection device (2), a position changing machine (3), a second detection device (4), a sorting machine (5) and a master control system;
the feeding tray (1) is used for arranging the battery caps (8) according to the sequence requirement and the posture requirement and then transferring the battery caps into the conveying belt (7);
the conveying belt (7) is used for conveying the battery caps (8) to sequentially pass through the first detection device (2), the positioner (3), the second detection device (4) and the sorting machine (5);
the first detection device (2) is used for photographing and sampling an arc welding surface (81) of the battery cap (8) and sending data to the master control system;
the positioner (3) is used for overturning the battery cap (8) for 180 degrees, so that the spot welding surface (82) of the battery cap (8) faces upwards;
the second detection device (4) is used for photographing and sampling the electric welding surface of the battery cap (8) and sending data to the main control system;
the main control system is used for receiving data of the first detection device (2) and the second detection device (4), judging the state of the battery cap (8) according to the identification model and sending the identification result to the sorting machine (5);
and the sorting machine (5) is used for sorting the battery caps (8) according to the recognition result of the main control system.
6. The new energy battery cap defect detection system of claim 5, wherein: an encoder is arranged on the conveyor belt (7) and is used for recording the real-time position of each battery cap (8) entering the detection system.
7. The new energy battery cap defect detection system of claim 5, wherein:
the first detection device (2) comprises a first top camera (21) and a first light source (22);
the first top camera (21) is arranged above the conveying belt (7) and is positioned right above the battery cap (8) to be detected by the first detection device (2); the first light source (22) is disposed at a side of the first top camera (21).
8. The new energy battery cap defect detection system of claim 5, wherein:
the second detection device (4) comprises a second top camera (41), a plurality of side cameras (42) and a second light source (43);
the second top camera (41) is arranged above the conveying belt (7) and is positioned right above the battery cap (8) to be detected by the second detection device (4), and the plurality of side cameras (42) are uniformly arranged around the periphery of the battery cap (8) to be detected; the second light source (43) is arranged above the side of the battery cap (8) to be tested.
9. The new energy battery cap defect detection system of claim 8, wherein:
three side cameras (42) are uniformly arranged around the periphery of the battery cap (8) in an included angle of 120 degrees, and the included angle between the axis of each camera and the horizontal plane is 40 degrees.
10. The new energy battery cap defect detection system of claim 5, wherein: a material box (6) for containing a battery cap (8) is arranged behind the separator (5).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111333918.4A CN114047195A (en) | 2021-11-11 | 2021-11-11 | New energy battery cap defect detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111333918.4A CN114047195A (en) | 2021-11-11 | 2021-11-11 | New energy battery cap defect detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114047195A true CN114047195A (en) | 2022-02-15 |
Family
ID=80208368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111333918.4A Pending CN114047195A (en) | 2021-11-11 | 2021-11-11 | New energy battery cap defect detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114047195A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897889A (en) * | 2022-06-27 | 2022-08-12 | 浙江旭派动力科技有限公司 | Automatic full-inspection method and system for spot welding of battery pack |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10194585A (en) * | 1997-01-14 | 1998-07-28 | Mitsubishi Paper Mills Ltd | Automatic sorting device of lithografic sheet |
| JP2003276831A (en) * | 2002-03-25 | 2003-10-02 | Maxell Hokuriku Seiki Kk | Inner/outer surface inspection device of cylindrical article and inspection method |
| CN102253048A (en) * | 2011-04-29 | 2011-11-23 | 惠州市钧悦科技有限公司 | Machine vision detection method and system for detection of various products |
| CN102284431A (en) * | 2011-04-28 | 2011-12-21 | 河南科技大学 | On-line detection grading device for lithium ion battery pole piece and method thereof |
| CN104792788A (en) * | 2015-03-18 | 2015-07-22 | 浙江野马电池有限公司 | Gluing visual detection method and device |
| CN106706654A (en) * | 2017-02-28 | 2017-05-24 | 武汉易视维科技有限公司 | Quality visual detection system for plastic bottles |
| CN106944351A (en) * | 2017-05-03 | 2017-07-14 | 王红燕 | A kind of automatic sorting device of machine components |
| CN107516308A (en) * | 2017-07-06 | 2017-12-26 | 佛山科学技术学院 | A kind of battery cap front visible detection method |
| CN206871947U (en) * | 2017-06-08 | 2018-01-12 | 佛山科学技术学院 | A kind of product quality vision detection system |
| CN107670996A (en) * | 2017-09-18 | 2018-02-09 | 扬州和信食品有限公司 | A kind of agricultural product multistage automatic fraction collector |
| CN107716346A (en) * | 2017-10-30 | 2018-02-23 | 上海燕龙基再生资源利用有限公司 | Multistage cullet light selects sorting system and its control method |
| CN208140593U (en) * | 2018-05-16 | 2018-11-23 | 苏州卡塔姆机器人科技有限公司 | A kind of quality assessment equipment of the carborundum line of view-based access control model |
| CN109190712A (en) * | 2018-09-21 | 2019-01-11 | 福州大学 | A kind of line walking image automatic classification system of taking photo by plane based on deep learning |
| CN109211921A (en) * | 2018-09-19 | 2019-01-15 | 惠勇 | A kind of precision hardware detection device |
| WO2020103324A1 (en) * | 2018-11-20 | 2020-05-28 | 深圳市维图视技术有限公司 | On-line mask detection system and method |
| CN212540167U (en) * | 2020-07-15 | 2021-02-12 | 南通宁远自动化科技有限公司 | Burr detection device of lithium battery pole piece |
| CN113205499A (en) * | 2021-04-30 | 2021-08-03 | 聚时科技(上海)有限公司 | Bearing defect modular detection device and method based on machine vision |
| CN113610749A (en) * | 2021-04-21 | 2021-11-05 | 北京智慧空间科技有限责任公司 | Fan blade defect detection method based on neural network |
-
2021
- 2021-11-11 CN CN202111333918.4A patent/CN114047195A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10194585A (en) * | 1997-01-14 | 1998-07-28 | Mitsubishi Paper Mills Ltd | Automatic sorting device of lithografic sheet |
| JP2003276831A (en) * | 2002-03-25 | 2003-10-02 | Maxell Hokuriku Seiki Kk | Inner/outer surface inspection device of cylindrical article and inspection method |
| CN102284431A (en) * | 2011-04-28 | 2011-12-21 | 河南科技大学 | On-line detection grading device for lithium ion battery pole piece and method thereof |
| CN102253048A (en) * | 2011-04-29 | 2011-11-23 | 惠州市钧悦科技有限公司 | Machine vision detection method and system for detection of various products |
| CN104792788A (en) * | 2015-03-18 | 2015-07-22 | 浙江野马电池有限公司 | Gluing visual detection method and device |
| CN106706654A (en) * | 2017-02-28 | 2017-05-24 | 武汉易视维科技有限公司 | Quality visual detection system for plastic bottles |
| CN106944351A (en) * | 2017-05-03 | 2017-07-14 | 王红燕 | A kind of automatic sorting device of machine components |
| CN206871947U (en) * | 2017-06-08 | 2018-01-12 | 佛山科学技术学院 | A kind of product quality vision detection system |
| CN107516308A (en) * | 2017-07-06 | 2017-12-26 | 佛山科学技术学院 | A kind of battery cap front visible detection method |
| CN107670996A (en) * | 2017-09-18 | 2018-02-09 | 扬州和信食品有限公司 | A kind of agricultural product multistage automatic fraction collector |
| CN107716346A (en) * | 2017-10-30 | 2018-02-23 | 上海燕龙基再生资源利用有限公司 | Multistage cullet light selects sorting system and its control method |
| CN208140593U (en) * | 2018-05-16 | 2018-11-23 | 苏州卡塔姆机器人科技有限公司 | A kind of quality assessment equipment of the carborundum line of view-based access control model |
| CN109211921A (en) * | 2018-09-19 | 2019-01-15 | 惠勇 | A kind of precision hardware detection device |
| CN109190712A (en) * | 2018-09-21 | 2019-01-11 | 福州大学 | A kind of line walking image automatic classification system of taking photo by plane based on deep learning |
| WO2020103324A1 (en) * | 2018-11-20 | 2020-05-28 | 深圳市维图视技术有限公司 | On-line mask detection system and method |
| CN212540167U (en) * | 2020-07-15 | 2021-02-12 | 南通宁远自动化科技有限公司 | Burr detection device of lithium battery pole piece |
| CN113610749A (en) * | 2021-04-21 | 2021-11-05 | 北京智慧空间科技有限责任公司 | Fan blade defect detection method based on neural network |
| CN113205499A (en) * | 2021-04-30 | 2021-08-03 | 聚时科技(上海)有限公司 | Bearing defect modular detection device and method based on machine vision |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114897889A (en) * | 2022-06-27 | 2022-08-12 | 浙江旭派动力科技有限公司 | Automatic full-inspection method and system for spot welding of battery pack |
| CN114897889B (en) * | 2022-06-27 | 2023-01-31 | 浙江旭派动力科技有限公司 | Automatic full-inspection method and system for spot welding of battery pack |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11213860B2 (en) | Automatic magnetic core sorting system based on machine vision | |
| CN109772724B (en) | Flexible detection and analysis system for major surface and internal defects of castings | |
| CN107344173B (en) | A kind of electrodes of lithium-ion batteries defect detecting system and its detection method | |
| CN103808732B (en) | Capacitive detection system based on machine vision and method | |
| CN210022894U (en) | Double SCARA battery defect detector | |
| CN103785627A (en) | On-line lithium battery pole piece surface defect detection sorting system and method | |
| CN104634790A (en) | Capsule detection method and high-speed fully-automatic detection device | |
| CN207254770U (en) | Gearbox cover cap swinging cross intelligence sorting unit | |
| CN204564599U (en) | A kind of glass tube outward appearance automatic detection system | |
| CN108333188A (en) | A kind of online apparent visual detection device of battery pole piece | |
| CN204564598U (en) | Glass tube sorting unit and glass tube outward appearance automatic detection system | |
| CN203778357U (en) | Online detecting sorting system for surface defects of lithium battery pole piece | |
| CN106353336A (en) | Lens coating automatic detection system | |
| CN212301356U (en) | Wheel hub welding seam visual detection device | |
| CN201702119U (en) | Gear apparent defect automatic optical picking machine | |
| CN114047195A (en) | New energy battery cap defect detection method and system | |
| WO2023197918A1 (en) | Glove sorting apparatus and method based on visual inspection | |
| CN109759755A (en) | AI intelligent process anomalous identification processing system and solar cell chip bonding machine | |
| CN114029237A (en) | Real-time sorting system and method for surface defects of aluminum profiles | |
| CN114529510B (en) | Automatic detection and classification method for cathode copper on-line quality | |
| CN110044921A (en) | Lithium battery open defect detection system and method | |
| CN106964562B (en) | A kind of online quality intelligent of industrial digital metaplasia production detects sorting unit | |
| CN112657869A (en) | Nut sorting equipment based on vision and sorting method thereof | |
| CN107214108A (en) | A kind of Efficient intelligent produces and processes the method for work of system | |
| CN217165388U (en) | Unqualified glove classifying screen device |
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 |