Gluing detection method, system and device, electronic equipment and storage medium

Abstract

The invention provides a gluing detection method, system and device, electronic equipment and a storage medium, and relates to the technical field of batteries. According to the method, a water cooling plate image of a battery cell is obtained, pixel coordinate information of each adhesive tape on a water cooling plate in the water cooling plate image is detected, then quality detection is performed on each adhesive tape according to the pixel coordinate information, and a detection result is obtained. As the obtained pixel coordinate information of each adhesive tape in the scheme can perform more detailed feedback on the gluing quality of the adhesive tape, the gluing quality of each adhesive tape is detected according to the pixel coordinate information, the accuracy is higher, and misjudgment can be effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and more specifically, to a method, system, device, electronic device, and storage medium for detecting glue coating. Background Art

[0002] During the manufacturing process of power battery modules, a new direct water cooling process technology is used. This requires automated visual inspection of the glue applied to the water cooling plate to ensure consistency in glue quality and production efficiency. However, the current inspection method generally captures the image to be inspected and then compares it with a standard image to determine the quality of the glue. However, there are many uncertainties in the glue application process, such as the splashing of hot melt adhesive. This may cause the images of some qualified glued products to differ significantly from the standard images, thus affecting the glue application inspection results and increasing the error rate. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a glue coating detection method, system, device, electronic device and storage medium to improve the problem of high misjudgment rate in existing glue coating detection methods.

[0004] In a first aspect, an embodiment of the present application provides a method for detecting glue coating, the method comprising:

[0005] Get the water cooling plate image of the battery cell;

[0006] Detecting pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image;

[0007] The quality of each rubber strip is tested according to the pixel coordinate information to obtain a test result.

[0008] In the above implementation process, by obtaining the water-cooling plate image of the battery cell, the pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image is detected, and then the quality of each rubber strip is detected according to the pixel coordinate information to obtain the detection result. Since the pixel coordinate information of each rubber strip obtained in this scheme can provide more detailed feedback on the gluing quality of the rubber strip, the gluing quality of each rubber strip is detected according to the pixel coordinate information, which is more accurate and can effectively reduce misjudgment.

[0009] Optionally, detecting pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image includes:

[0010] Extracting the glue shape contour of each glue strip on the water-cooling plate in the water-cooling plate image;

[0011] Determining the vertical coordinate of each rubber strip according to the rubber profile, wherein the pixel coordinate information of each rubber strip includes the vertical coordinate;

[0012] The performing quality inspection on each rubber strip according to the pixel coordinate information to obtain the inspection result includes:

[0013] The quality of each rubber strip is inspected according to the vertical coordinate to obtain a rubber breakage inspection result.

[0014] In the above implementation process, when performing glue break detection, the vertical coordinate of each glue strip is obtained as the pixel coordinate information of the glue strip, which can reflect the vertical position of each glue strip in the image, so as to accurately determine whether the glue is broken. For example, if it is a broken glue strip, then the difference in its vertical position will not be large.

[0015] Optionally, performing quality inspection on each rubber strip according to the vertical coordinate to obtain a rubber breakage inspection result includes:

[0016] Determine the longitudinal spacing between two adjacent rubber strips according to the longitudinal coordinates corresponding to each rubber strip;

[0017] If the longitudinal distance between two adjacent rubber strips is less than the set distance, the rubber break detection result is determined to include the two adjacent rubber strips being broken rubber strips.

[0018] In the above implementation process, if the longitudinal spacing is less than the set spacing, the two rubber strips are considered to be broken rubber strips, because if the two rubber strips formed after the break are approximately at the same horizontal position, the longitudinal spacing should be smaller, so this can accurately determine whether the rubber strips are broken.

[0019] Optionally, performing quality inspection on each rubber strip according to the vertical coordinate to obtain a rubber breakage inspection result includes:

[0020] identifying the number of rubber strips on the water cooling plate in the water cooling plate image according to the rubber-shaped contour;

[0021] Determine the longitudinal spacing between two adjacent rubber strips according to the longitudinal coordinates corresponding to each rubber strip;

[0022] If the longitudinal spacing between two adjacent rubber strips is greater than or equal to the set spacing and the number of the rubber strips is the set number, then the rubber break detection result is determined to include the two adjacent rubber strips being non-broken rubber strips.

[0023] In the above implementation process, if there is glue breakage, the number of glue strips will increase, and the glue breakage can be accurately detected by combining the number of glue strips. If there is insufficient glue application and glue breakage, the number of glue strips remains unchanged, and the glue breakage can be accurately detected by combining the longitudinal spacing.

[0024] Optionally, detecting pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image includes:

[0025] Extracting the glue shape contour of each glue strip on the water-cooling plate in the water-cooling plate image;

[0026] Extracting coordinate information of each pixel point on the rubber-shaped outline, wherein the pixel coordinate information of each rubber strip includes coordinate information of each pixel point on the rubber-shaped outline of the rubber strip;

[0027] The performing quality inspection on each rubber strip according to the pixel coordinate information to obtain the inspection result includes:

[0028] According to the coordinate information of each pixel point on the glue profile, a glue width detection result and / or a glue strip position detection result is obtained.

[0029] In the above implementation process, since the coordinate information obtained is the coordinate information of each pixel point on the rubber contour, it can reflect the coordinates of the boundary line of the rubber strip. Therefore, the rubber width of the rubber strip can be accurately measured according to the coordinates of these boundary lines and the position of the rubber strip can be detected.

[0030] Optionally, obtaining the glue width detection result according to the coordinate information of each pixel point on the glue shape contour includes:

[0031] According to a pre-defined adhesive width detection area, each adhesive strip is cut within the adhesive width detection area to obtain a portion of the adhesive strip corresponding to each adhesive strip;

[0032] Obtaining coordinate information of pixel points of the upper and lower contours of the portion of the rubber strip from coordinate information of each pixel point on the rubber-shaped contour;

[0033] According to the coordinate information of the pixel points of the upper and lower contours, it is determined that the glue width detection result includes the glue width of the partial glue strip, and the glue width of the partial glue strip is the glue width of the corresponding glue strip.

[0034] In the above implementation process, in order to avoid the problem of inconsistent testing standards caused by testing the glue width of different glue strips at different positions, which affects the subsequent quality inspection results, a glue width detection area is set up, and part of the glue strips of each glue strip are intercepted in the glue width detection area, so that the glue width of part of the glue strips can be detected in the same glue width detection area, thereby improving the accuracy of glue width detection.

[0035] Optionally, the glue width detection area is a plurality of detection areas at different positions, and the step of intercepting each glue strip within the glue width detection area according to the pre-defined glue width detection area to obtain a partial glue strip corresponding to each glue strip includes:

[0036] According to a plurality of pre-defined adhesive width detection areas, each adhesive strip is cut within each adhesive width detection area to obtain a portion of the adhesive strip corresponding to each adhesive strip;

[0037] The glue width of the partial glue strip includes the glue width at the location of each glue width detection area.

[0038] In the above implementation process, the glue width of each glue strip is detected in the glue width detection area at different positions, so that the glue width of each glue strip at different positions can be obtained, which can better detect the glue coating quality.

[0039] Optionally, determining the adhesive width of the portion of the adhesive strip according to the coordinate information of the pixel points of the upper and lower contours includes:

[0040] Determining the coordinate information of the midpoint of the upper contour according to the coordinate information of the pixel points of the upper contour, and determining the coordinate information of the midpoint of the lower contour according to the coordinate information of the pixel points of the lower contour;

[0041] The glue width of the portion of the glue strip is determined according to the coordinate information of the midpoint of the upper contour and the coordinate information of the midpoint of the lower contour.

[0042] In the above implementation process, the glue width is determined by obtaining the coordinate information of the midpoints of the upper and lower contours, so that the obtained glue width can better reflect the glue width of the glue strip, thereby achieving accurate detection of the glue width.

[0043] Optionally, obtaining the adhesive strip position detection result according to the coordinate information of each pixel point on the adhesive strip contour includes:

[0044] According to a pre-defined adhesive width detection area, each adhesive strip is cut within the adhesive width detection area to obtain a portion of the adhesive strip corresponding to each adhesive strip;

[0045] Determining coordinate information of the portion of the rubber strip according to coordinate information of each pixel point on the rubber-shaped contour;

[0046] According to the coordinate information of the partial rubber strips corresponding to each rubber strip, the rubber strip position detection result is determined to include the position information of each rubber strip, and the position information includes the distance between each rubber strip and / or the distance between each rubber strip and the edge of the image detection area.

[0047] In the above implementation process, the coordinate information of the intercepted portion of the rubber strip is obtained within the rubber width detection area to determine the position of the entire rubber strip, thereby accurately obtaining the position information of the rubber strip.

[0048] Optionally, determining the coordinate information of the portion of the rubber strip according to the coordinate information of each pixel point on the rubber strip outline includes:

[0049] Obtaining coordinate information of pixel points of an upper contour and coordinate information of pixel points of a lower contour in the portion of the rubber strip from coordinate information of each pixel point on the rubber strip contour;

[0050] Determining the coordinate information of the midpoint of the upper contour according to the coordinate information of the pixel points of the upper contour, and determining the coordinate information of the midpoint of the lower contour according to the coordinate information of the pixel points of the lower contour;

[0051] The coordinate information of the midpoint of the upper contour and the midpoint of the lower contour is used to determine the coordinate information of the midpoint of the connecting line segment between the midpoints of the two contours. The coordinate information of the midpoint of the connecting line segment is the coordinate information of the portion of the rubber strip.

[0052] In the above implementation process, the midpoint of the connecting line segment between the midpoints of the upper and lower contours is used as the coordinate information of the rubber strip, which can better reflect the position of each rubber strip and improve the accuracy of its position detection.

[0053] Optionally, the glue width detection area is a plurality of detection areas at different positions, and the step of intercepting each glue strip within the glue width detection area according to the pre-defined glue width detection area to obtain a partial glue strip corresponding to each glue strip includes:

[0054] According to a plurality of pre-defined adhesive width detection areas, each adhesive strip is cut within each adhesive width detection area to obtain a portion of the adhesive strip corresponding to each adhesive strip;

[0055] The coordinate information of each rubber strip includes the coordinate information of each rubber strip at the position of each rubber strip in each rubber width detection area.

[0056] In the above implementation process, the position accuracy of the rubber strip is detected at the locations where the multiple rubber width detection areas are located, so that a more comprehensive detection can be achieved and the accuracy of the position accuracy detection can be improved.

[0057] Optionally, detecting pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image includes:

[0058] Identify each rubber strip on the water-cooling plate in the water-cooling plate image to obtain a rubber strip that meets a set condition;

[0059] Detect pixel coordinate information of the rubber strip that meets the set conditions in the water-cooling plate image.

[0060] In the above implementation process, by identifying each rubber strip, the rubber strips that meet the set conditions are obtained, and the rubber strips that meet the set conditions are subsequently subjected to glue coating quality inspection. In this way, the rubber strips that do not meet the set conditions can be filtered out first to reduce the impact of these rubber strips on the glue coating quality inspection results.

[0061] Optionally, identifying each rubber strip on the water-cooling plate in the water-cooling plate image to obtain a rubber strip that meets a set condition includes:

[0062] Extracting the glue shape outline of the glue strip on the water-cooling plate from the water-cooling plate image;

[0063] The rubber strip formed by the rubber-shaped contour is identified according to set conditions to obtain a rubber strip that meets the set conditions.

[0064] In the above implementation process, the rubber strip is identified by extracting the rubber shape contour, which can identify some small rubber strip particles and improve the accuracy of rubber strip identification.

[0065] Optionally, identifying the rubber strip formed by the rubber-shaped contour according to set conditions to obtain the rubber strip that meets the set conditions includes:

[0066] Performing a morphological closing operation on the colloidal contour to obtain a colloidal contour with a closed contour;

[0067] Filter out the rubber strips whose width is less than the set value and whose rubber contours extend to the edge of the image detection area;

[0068] The remaining rubber-shaped contours after filtering are filled to obtain the rubber strips formed after filling, wherein the rubber strips that meet the set conditions include the rubber strips after filling.

[0069] In the above implementation process, some tiny rubber strip particles can be filtered through the above method, thereby filtering out misidentified rubber strips to reduce the impact of these rubber strips on subsequent glue coating quality detection.

[0070] Optionally, after obtaining the glue strips formed after filling, the method further includes:

[0071] Performing morphological corrosion operations on each rubber strip formed after filling to obtain separated rubber strips;

[0072] Filter the separated rubber strips whose length is less than the set value;

[0073] A morphological expansion operation is performed on the rubber strips remaining after filtration to obtain the finally separated rubber strips, wherein the rubber strips that meet the set conditions include the finally separated rubber strips.

[0074] In the above implementation process, the adhesive strip particles that are adhered to normal adhesive strips can be filtered out in the above manner, thereby filtering out misidentified adhesive strips to reduce the impact of these adhesive strips on subsequent adhesive coating quality detection.

[0075] Optionally, extracting the contour of the rubber strip on the water-cooling plate in the water-cooling plate image includes:

[0076] Performing binarization processing on the water cooling plate image using a binarization processing function to obtain a binarized water cooling plate image;

[0077] The glue shape contour of the glue strip on the water cooling plate in the water cooling plate image is extracted according to the contour lines formed in the binarized water cooling plate image.

[0078] In the above implementation process, since the binarization processing function in LabVIEW software can better process images with "dark in the middle and bright on both sides", the binarized image obtained through its processing can more clearly obtain the contour lines of the rubber strip.

[0079] Optionally, the method further includes:

[0080] A shielded detection area is set at the location where the two rubber strips are stuck in the water-cooling plate image. The shielded detection area indicates the area where the rubber strips are not identified. This can prevent the problem of the rubber strips being stuck at both ends during the gluing process, which can cause the rubber strips to be difficult to separate properly. Setting up the shielded detection area allows the rubber strips to be separated at the sticking point.

[0081] Optionally, performing quality inspection on each adhesive strip according to the pixel coordinate information to obtain the inspection result includes:

[0082] Perform glue break detection on each glue strip according to the pixel coordinate information to obtain a glue break detection result;

[0083] If the glue break detection result is not glue break, glue width detection and / or glue strip position detection are continued for each glue strip to obtain corresponding glue width detection results and / or glue strip position detection results.

[0084] In the above implementation process, since the glue break detection is faster, the glue break detection is performed first, and the remaining items are tested only when the test result is qualified, which can improve the detection efficiency.

[0085] In a second aspect, an embodiment of the present application provides a glue coating detection system, the glue coating detection system comprising:

[0086] An image collector, used to capture images of the water cooling plate of the battery cell;

[0087] A logic control device, used to control the transport equipment to transport the water-cooling plate of the battery cell to a set position so that the image collector can capture an image of the water-cooling plate;

[0088] The host computer is used to receive the water-cooling plate image transmitted by the image collector, and use the water-cooling plate image to execute the glue coating detection method provided by the first aspect.

[0089] Optionally, the logic control device is further configured to change the detection signal to a set state after receiving a preparation signal sent by the transport device, wherein the preparation signal is sent by the transport device after the transport device transports the water-cooled plate to a set position;

[0090] The host computer is further configured to read the state of the detection signal of the logic control device at a set time interval, and send an image acquisition signal to the image collector after determining that the detection signal has changed to a set state;

[0091] The image collector is further configured to collect a water-cooling plate image of the water-cooling plate according to the image collection signal.

[0092] Optionally, the host computer is further configured to determine whether the rubber strips on the water-cooling plate are qualified based on the test results; if unqualified, control the logic control device to output an alarm prompt.

[0093] In a third aspect, an embodiment of the present application provides a glue coating detection device, the device comprising:

[0094] An image acquisition module, used to acquire images of the water cooling plate of the battery cell;

[0095] An information acquisition module, configured to detect pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image;

[0096] The detection module is used to perform quality detection on each rubber strip according to the pixel coordinate information to obtain a detection result.

[0097] In a fourth aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of the method provided in the first aspect above are executed.

[0098] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are executed.

[0099] Other features and advantages of the present application will be described in the following description and, in part, will become apparent from the description or be understood by practicing the embodiments of the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0100] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0101] Figure 1 A structural block diagram of a glue coating detection system provided in an embodiment of the present application;

[0102] Figure 2 A schematic diagram of the deployment of various devices in a glue coating detection system provided in an embodiment of the present application;

[0103] Figure 3 A flow chart of a method for detecting glue coating provided in an embodiment of the present application;

[0104] FIG4( a ) is a schematic diagram of a binarized image obtained by using the binarization processing method provided in the present application according to an embodiment of the present application;

[0105] FIG4( b ) is a schematic diagram of a binarized image obtained by a binarization processing method provided by a conventional solution according to an embodiment of the present application;

[0106] FIG4( c ) is a schematic diagram of an extracted gel profile provided in an embodiment of the present application;

[0107] FIG5( a ) is a schematic diagram of setting a glue width detection area in an image according to an embodiment of the present application;

[0108] FIG5( b ) is a schematic diagram of a portion of a rubber strip cut within a rubber width detection area provided in an embodiment of the present application;

[0109] Figure 6 A schematic diagram of obtaining the coordinates of a rubber strip by cutting off part of the rubber strip provided in an embodiment of the present application;

[0110] Figure 7 A schematic diagram of an image obtained by performing a closing operation followed by a filling operation according to an embodiment of the present application;

[0111] Figure 8 A schematic diagram of an image obtained by performing an erosion-then-diffusion process according to an embodiment of the present application;

[0112] Figure 9 A schematic diagram of the distribution of detection areas in an image provided in an embodiment of the present application;

[0113] Figure 10 A structural block diagram of a glue coating detection device provided in an embodiment of the present application;

[0114] Figure 11 A schematic structural diagram of an electronic device for executing a glue coating detection method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0115] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application.

[0116] It should be noted that the terms "system" and "network" in the embodiments of the present invention are used interchangeably. "Multiple" refers to two or more. In view of this, in the embodiments of the present invention, "multiple" can also be understood as "at least two." "And / or" describes the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the related objects are in an "or" relationship.

[0117] In order to detect the quality of glue coating on the water-cooling plate of the battery, the existing solution generally collects the image of the water-cooling plate and then compares it with the standard image to determine the quality of the glue coating. However, this detection method is limited by uncertainties in the glue coating process (such as the sputtering of hot melt glue, the glue coating equipment continuously coating glue to ensure the glue coating rate, causing the two glue strips to stick together at both ends, etc.). As a result, even if some qualified glue coating products are obtained, the images obtained will be significantly different from the standard images, affecting the detection results and having a high misjudgment rate.

[0118] Therefore, the present application provides another glue coating detection method with a different inventive concept. The method obtains the water-cooling plate image of the battery cell, detects the pixel coordinate information of each glue strip on the water-cooling plate in the water-cooling plate image, and then performs quality inspection on each glue strip based on the pixel coordinate information to obtain the inspection result. Since the pixel coordinate information of each glue strip obtained in this scheme can provide more detailed feedback on the gluing quality of the glue strip, the gluing quality of each glue strip is detected based on the pixel coordinate information, which is more accurate and can effectively reduce misjudgment.

[0119] In order to facilitate the understanding of the glue coating detection method provided by this application, the glue coating detection system provided by this application is first introduced. Figure 1 As shown, the glue coating detection system 100 includes:

[0120] An image collector 110 is used to collect images of the water cooling plate of the battery cell;

[0121] The logic control device 120 is used to control the transport device to transport the water-cooling plate of the battery cell to a set position so that the image collector can capture the image of the water-cooling plate;

[0122] The host computer 130 is used to receive the water-cooling plate image transmitted by the image collector 110, and use the water-cooling plate image to execute the glue detection method provided in the subsequent embodiments. The specific implementation process of the glue detection method will be introduced in detail in the following embodiments and will not be described in detail here.

[0123] In the above implementation process, the water-cooling plate is moved through the logic control device, the water-cooling plate image is collected through the image collector, and then transmitted to the host computer for inspection. Through the cooperation of various devices, the glue coating quality on a large number of water-cooling plates can be quickly and efficiently inspected, and the inspection efficiency is higher.

[0124] In some embodiments, for ease of understanding, please refer to Figure 2 , Figure 2 This diagram illustrates the deployment of various devices within the glue coating inspection system 100. The image acquisition unit 110 includes a camera and a light source. The camera captures images of the cooling plate, while the light source emits light to facilitate clear image capture. The camera and light source are mounted in fixed locations, allowing the camera to capture images of a fixed area at a time.

[0125] The handling equipment may refer to a robot. After the water-cooling plate is coated with glue, the robot will carry the water-cooling plate to a fixed area. In the process of carrying the water-cooling plate to the fixed area, the robot can adjust the up, down, left, and right position coordinates of the water-cooling plate so that the water-cooling plate is located in the fixed area. In this way, the position of the water-cooling plate will not shift during each inspection. In other words, each water-cooling plate inspected is within a fixed area, and the camera captures images of the water-cooling plate in the fixed area, thereby reducing the detection error caused by position offset. In addition, each time the water-cooling plate is placed in a fixed area for image capture, the host computer 130 does not need to perform visual image positioning of the water-cooling plate in the water-cooling plate image, and the host computer 130 can concentrate its main resources on the quality inspection of the glue strip, which simplifies the difficulty of developing the inspection software and reduces the misjudgment caused by the visual positioning failing to reach the image baseline.

[0126] Host computer 130 is a computer connected to logic control device 120 (PLC) via a network cable. Logic control device 120 is also connected to the handling equipment via a network cable. The computer is installed with visual inspection software (LabVIEW in this solution), which is used to perform quality inspection on the rubber strips in the water-cooling plate image. This allows logic control device 120 to communicate with host computer 130 using TCP communication technology, enabling stable and automated signal connection with host computer 130. This eliminates the hardware cost and subsequent maintenance of a dedicated PCI communication card required by older software technologies.

[0127] After the glue coating machine finishes coating the water-cooling plate, it will send a notification signal to the transporting device to notify the transporting device to grab the water-cooling plate. After receiving the notification signal, the transporting device grabs the water-cooling plate from the glue coating area and transports the water-cooling plate to a fixed area, that is, to the fixed area under the camera and light source. After transporting to the fixed area, the transporting device sends a ready signal to the logic control device 120 to notify the logic control device 120 that it is ready for testing.

[0128] In some embodiments, the logic control device 120 is further configured to change the detection signal to a set state upon receiving a ready signal from the transport device. The ready signal is sent by the transport device after the transport device has transported the water cooling plate to a set position (i.e., a fixed area). For example, upon receiving the ready signal, the logic control device 120 changes the detection signal state to 1, i.e., the set state is 1.

[0129] The host computer 130 is further configured to read the state of the detection signal from the logic control device 120 at set time intervals and, upon determining that the detection signal has changed to the set state, send an image acquisition signal to the image acquisition device 110. For example, the host computer 130 cyclically reads the detection signal from the logic control device 120 at set time intervals (e.g., 50 milliseconds) to determine whether it is 1. If the detection signal changes to 1, the host computer 130 controls the image acquisition device 110 to acquire an image.

[0130] After receiving the image acquisition signal, the image acquisition device 110 acquires the water-cooling plate image of the water-cooling plate, and sends the acquired water-cooling plate image to the host computer 130 for detection.

[0131] Optionally, the host computer 130 performs a quality inspection on the rubber strip on the water-cooling plate in the water-cooling plate image, and determines whether the quality is qualified after the inspection. If the inspection result determines that the quality is qualified and is OK (good product), the OK signal and the inspection completion signal in the logic control device 120 are set to 1. Alternatively, an OK signal and a inspection completion signal of 1 are sent to the logic control device 120, and then the detection reset signal of the logic control device 120 is waited for.

[0132] Alternatively, if the host computer 130 determines that the test result is unqualified (NG (defective product)), it can control the logic control device 120 to output an alarm prompt, wait for the staff to manually review the process, and set the NG signal in the logic control device 120 to 1, or send a NG signal of 1 to the logic control device 120. If the staff finds that it is qualified after manual review, they click the OK button provided on the display interface of the host computer, and the host computer 130 sets the OK signal in the logic control device 120 to 1. If the staff finds that it is unqualified after manual review, they click the NG button, and the NG signal is still set to 1. Then, the test completion signal is set to 1, or a test completion signal of 1 is sent to the logic control device 120.

[0133] After determining that the OK signal or NG signal is set to 1 and the detection completion signal is also set to 1, or receiving the OK signal or NG signal and the detection completion signal, the logic control device 120 notifies the handling equipment to perform the next action (such as moving the water cooling plate from the fixed area) and sets the detection reset signal to 1, or sends a detection reset signal of 1 to the upper computer 130.

[0134] After receiving the detection reset signal of 1, the host computer 130 sets the OK signal, NG signal and detection completion signal to 0, and then performs the next cycle to read whether the status of the detection signal in the logic control device 120 is 1. If it is 1, the above process continues.

[0135] In the above implementation process, through the coordinated cooperation between the logic control device, the host computer and the image collector, the glue coating quality of each water-cooling plate is efficiently detected in sequence.

[0136] The following is a detailed description of the specific process of the host computer performing quality inspection on the rubber strips on the water cooling plate in the water cooling plate image. Figure 3 , Figure 3 This is a flow chart of a method for detecting glue coating provided in an embodiment of the present application. The method is executed by the above-mentioned host computer and includes the following steps:

[0137] Step S210: Acquire an image of the water cooling plate of the battery cell.

[0138] The host computer can obtain the water-cooling plate image from the image collector in the above embodiment, or receive the water-cooling plate image actively sent by the image collector, or read the internally stored water-cooling plate image, etc., which is obtained by photographing the water-cooling plate in a fixed area by the image collector. For the specific image acquisition process, please refer to the relevant description in the above embodiment, which will not be repeated here.

[0139] Step S220: detecting pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image.

[0140] The water-cooling plate image includes multiple rubber strips coated on the water-cooling plate. According to the process requirements, a certain number of rubber strips, such as 3, are generally coated on the water-cooling plate. In order to detect the gluing quality of these rubber strips, the pixel coordinate information of each rubber strip in the water-cooling plate image is detected in this application. The pixel coordinate information represents the position information of each rubber strip in the water-cooling plate image, such as the relative position information between each rubber strip, etc. Based on this information, the gluing quality of each rubber strip can be comprehensively detected.

[0141] Step S230: performing quality inspection on each rubber strip according to the pixel coordinate information to obtain inspection results.

[0142] In this application, each adhesive strip can be tested for glue breakage, glue width, and glue strip position accuracy based on pixel coordinate information. The test results obtained can include at least one of the following: glue breakage detection results, glue width detection results, and glue strip position accuracy detection results. By testing this information, a more comprehensive test of the adhesive strip's coating quality can be effectively achieved.

[0143] As shown in Table 1 below, this application includes 28 test items in Table 1, where number 1 is for glue break detection, numbers 2 to 10 are for detecting the glue width of the rubber strip, and numbers 11 to 28 are for detecting the position of the rubber strip. It is understood that the test items shown in Table 1 are only examples. In actual applications, the specific test items can be flexibly set according to actual conditions.

[0144] Table 1

[0145]

[0146]

[0147] During inspection, an image detection area is set in the water-cooling plate image, and the host computer performs quality inspection on the rubber strip within this image detection area. Since the image collector captures the water-cooling plate image within a fixed area each time, and the water-cooling plate is always placed in a fixed position, the area where the rubber strip is located on the water-cooling plate in the captured water-cooling plate image is generally within this image detection area. Therefore, once this image detection area is defined, it remains fixed. In this way, after receiving the water-cooling plate image, the host computer can directly add such an image detection area to the water-cooling plate image, and this image detection area can be used for subsequent position detection.

[0148] In the above implementation process, by obtaining the water-cooling plate image of the battery cell, the pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image is detected, and then the quality of each rubber strip is detected according to the pixel coordinate information to obtain the detection result. Since the pixel coordinate information of each rubber strip obtained in this scheme can provide more detailed feedback on the gluing quality of the rubber strip, the gluing quality of each rubber strip is detected according to the pixel coordinate information, which is more accurate and can effectively reduce misjudgment.

[0149] The following is a detailed introduction to the specific detection implementation methods of each detection item.

[0150] (1) Glue break detection.

[0151] The above-mentioned detection of the pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image includes: extracting the rubber shape outline of each rubber strip on the water-cooling plate in the water-cooling plate image, and then determining the vertical coordinate of each rubber strip based on the rubber shape outline, wherein the pixel coordinate information of each rubber strip includes the vertical coordinate, and then the quality of each rubber strip can be inspected based on the vertical coordinate to obtain the rubber break detection result.

[0152] Optionally, an industrial camera can be used for image acquisition in the present application. Since the captured water-cooling plate image may have a "bright center and dark sides" effect, in order to accurately extract the glue contour, the visual inspection software in the present application can be software written in LabVIEW language, i.e., LabVIEW software. LabVIEW software has better development speed, hardware compatibility, and detection stability. The software has a built-in fixed binarization processing function, so the water-cooling plate image can be binarized using its built-in binarization processing function to obtain a binarized water-cooling plate image, and then the glue contour of the glue strip on the water-cooling plate in the water-cooling plate image can be extracted based on the contour lines formed in the binarized water-cooling plate image.

[0153] Figure 4(a) shows the implementation of the binarization algorithm using this solution. Figure 4(b) shows the implementation using a conventional manual grayscale thresholding algorithm. Figure 4(c) shows the implementation of the contour lines extracted from the binarized image using this solution. It can be seen that the binarized image extracted using the LabVIEW binarization function in this solution is more effective than the binary image obtained using the conventional solution. The binarized water cooling plate image obtained using this solution can more accurately extract the contours of each rubber strip. For example, the binarized image in Figure 4(a) clearly and accurately extracts the contours of each rubber strip. In Figure 4(c), the contours of three rubber strips can be extracted, and the vertical coordinate of each contour can be obtained.

[0154] To obtain the vertical coordinate, the "LabelToROI" function provided by LabVIEW software can be used to convert the rubber strip into a "region of interest" of the rubber contour. The "region of interest" data contains the coordinate information of the rubber contour and the XY coordinate information of each pixel on the rubber contour.

[0155] The coordinate information of the shape outline may refer to the coordinate information of the circumscribed rectangle of the shape outline, or may refer to the coordinate information of any pixel point on the shape outline, or may refer to the coordinate information of a pixel point at a specific position.

[0156] If the coordinate information of the rubber strip refers to the coordinate information of the circumscribed rectangle of the rubber strip's outline, the circumscribed rectangle of the rubber strip's outline can be obtained first. This can be achieved using existing image processing algorithms. The coordinate information of the circumscribed rectangle can refer to the vertical coordinate of any vertex of the circumscribed rectangle, such as the vertical coordinate of the top left position. In this way, the vertical coordinates of all three rubber strips refer to the vertical coordinate of the top left position of the circumscribed rectangle of their rubber strips.

[0157] If the coordinate information of the rubber strip refers to the coordinate information of any pixel point on the rubber-shaped contour or the coordinate information of the pixel point at a specific position, then for each rubber strip, the vertical coordinate of the pixel point at the corresponding position can be obtained, such as obtaining the vertical coordinate of a pixel point in its upper contour or lower contour, such as obtaining the vertical coordinate of the midpoint of the upper contour in the rubber-shaped contour of each rubber strip, or obtaining the vertical coordinate of the midpoint of the lower contour in the rubber-shaped contour of each rubber strip.

[0158] In the above implementation process, when performing glue break detection, the vertical coordinate of each glue strip is obtained as the pixel coordinate information of the glue strip, which can reflect the vertical position of each glue strip in the image, so as to accurately determine whether the glue is broken. For example, if it is a broken glue strip, then the difference in its vertical position will not be large.

[0159] On the basis of the above embodiment, after obtaining the vertical coordinate of each rubber strip, when performing rubber break detection, the longitudinal spacing between two adjacent rubber strips can be determined according to the vertical coordinate corresponding to each rubber strip. If the longitudinal spacing between two adjacent rubber strips is less than the set spacing, it is determined that the rubber break detection result includes two adjacent rubber strips as broken rubber strips, indicating that the rubber break detection result is unqualified.

[0160] In this method, the strips can be sorted by their vertical coordinates, for example, from largest to smallest. This will determine the strips arranged from top to bottom in the cold plate image, making it easier to identify which strips are adjacent. The vertical coordinates of two adjacent strips are then subtracted, and the resulting difference is used as the vertical spacing between the two adjacent strips. According to the requirements of the gluing process, if the rubber strips are of qualified quality, the longitudinal spacing between two adjacent rubber strips should be within the specified range. For example, if the longitudinal spacing is specified to be within 100 pixels, the set spacing can be set to 100. Therefore, if the longitudinal spacing between two adjacent rubber strips is less than the set spacing, the two adjacent rubber strips are determined to be broken rubber strips. This is because if a rubber strip is broken, two rubber profiles will be extracted for the broken rubber strip when the rubber profile is extracted. This is actually formed after a rubber strip is broken. Therefore, the upper or lower profiles on the two rubber profiles, or the vertical coordinates of the vertices of their circumscribed rectangles should not be much different, or should have the same vertical coordinates. Therefore, by judging the longitudinal spacing between the two adjacent rubber strips, it is possible to accurately determine whether it is a broken rubber strip.

[0161] In some other embodiments, the distribution of the vertical coordinates of each rubber strip can also be judged to detect the rubber breakage, for example, whether it is an arithmetic distribution. If not, it is considered that there is a rubber strip that is broken.

[0162] It can be understood that if the longitudinal spacing between two adjacent rubber strips is greater than or equal to the set spacing, the two adjacent rubber strips can be considered as non-broken rubber strips, indicating that the breakage detection result is qualified.

[0163] In the above implementation process, if the longitudinal spacing is less than the set spacing, the two rubber strips are considered to be broken rubber strips, because if the two rubber strips formed after the break are approximately at the same horizontal position, the longitudinal spacing should be smaller, so this can accurately determine whether the rubber strips are broken.

[0164] In other embodiments, in order to improve the accuracy of glue break detection, the number of glue strips on the water cooling plate in the water cooling plate image can be first identified based on the glue shape contour, and the longitudinal spacing between two adjacent glue strips can be determined based on the vertical coordinates corresponding to each glue strip. If the longitudinal spacing between two adjacent glue strips is greater than or equal to the set spacing, and the number of glue strips is the set number, then the glue break detection result is determined to include the two adjacent glue strips being non-broken glue strips.

[0165] Understandably, this detection method includes the judgment of the number of rubber strips. This is because in some extreme cases, the longitudinal spacing of the rubber strips that were originally broken may be greater than or equal to the set spacing. In this case, it will be considered qualified according to the above detection method, so the judgment of the number of rubber strips will be more accurate.

[0166] According to the gluing process requirements, each water-cooling plate should have a set number of glue strips. For example, if the set number is 3, through the above-mentioned glue contour extraction, if 4 glue contours are extracted, it means that there are 4 glue strips. At this time, it is considered that there is a glue break. In this way, the test result can be directly judged as the glue coating quality is unqualified and there is a glue break. However, in some cases, if there are only two glue strips on the water-cooling plate, if there is a glue break, the glue contour extraction will obtain 3 glue contours, indicating that there are 3 glue strips. In this case, judging by the number of glue strips, it will be considered that there is no glue break. Therefore, it is necessary to further judge based on the longitudinal spacing between two adjacent glue strips. If the longitudinal spacing is greater than or equal to the set spacing, it can be considered that the glue strip is not broken. If the longitudinal spacing is less than the set spacing, it is considered that the glue strip is broken.

[0167] That is to say, in this detection method, you can also first judge based on the number of rubber strips. If the number of rubber strips is not the set number, you can directly judge that there are broken rubber strips, and the glue coating quality is considered unqualified. If the number of rubber strips is the set number, then further combine the longitudinal spacing between the two adjacent rubber strips to make a judgment, thereby improving the accuracy of its broken rubber detection.

[0168] In the above implementation process, if there is glue breakage, the number of glue strips will increase, and the glue breakage can be accurately detected by combining the number of glue strips. If there is insufficient glue application and glue breakage, the number of glue strips remains unchanged, and the glue breakage can be accurately detected by combining the longitudinal spacing.

[0169] (2) Glue width detection.

[0170] The above-mentioned detection of the pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image includes: extracting the rubber shape outline of each rubber strip on the water-cooling plate in the water-cooling plate image, and then extracting the coordinate information of each pixel point on the rubber shape outline, wherein the pixel coordinate information of each rubber strip includes the coordinate information of each pixel point on the rubber shape outline of the rubber strip, and then the rubber width detection result can be obtained based on the coordinate information of each pixel point on the rubber shape outline.

[0171] In this detection method, the edge of the rubber contour can be scanned from top to bottom through the "Rake" function of the LabVIEW software, so that the coordinate information of each pixel point of the upper contour and the coordinate information of each pixel point of the lower contour can be obtained. Here, the coordinate information of each pixel point refers to the XY coordinates of each pixel point.

[0172] When calculating the glue width, any two pixel points with the same horizontal coordinates located on the upper and lower contours of the same glue contour can be selected, and then the vertical distance between the two pixel points can be calculated. The vertical distance can be the glue width of the glue strip.

[0173] In the above implementation process, since the acquired coordinate information is the coordinate information of each pixel point on the rubber contour, it can reflect the coordinates of the boundary line of the rubber strip, so the rubber width of the rubber strip can be accurately measured according to the coordinates of these boundary lines.

[0174] In other embodiments, in order to facilitate the use of the same glue width detection standard for each glue strip, when performing glue width detection, each glue strip can be cut within the glue width detection area according to a pre-defined glue width detection area to obtain a partial glue strip corresponding to each glue strip, and then the coordinate information of the pixel points of the upper and lower contours of the partial glue strip is obtained from the coordinate information of each pixel point on the glue contour, and then the glue width detection result is determined to include the glue width of the partial glue strip based on the coordinate information of the pixel points of the upper and lower contours, and the glue width of the partial glue strip is the glue width of the corresponding glue strip.

[0175] As shown in Figure 5(a) and Figure 5(b), Figure 5 shows a pre-set glue width detection area. Partial glue strips of three glue strips can be intercepted within the glue width detection area. The partial glue strips are shown in Figure 5(b). In this way, a corresponding partial glue strip is obtained for each glue strip. At this time, the glue width of the glue strip can be detected by detecting the glue width of the partial glue strip. For example, for one of the partial glue strips, the vertical coordinates of the two pixel points located at the upper and lower contours under the same horizontal coordinate in the partial glue strip can be obtained. Then, the vertical spacing between the two pixel points can be calculated based on the vertical coordinates, and the vertical spacing can be used as the glue width of the glue strip.

[0176] Alternatively, in other embodiments, the coordinate information of the midpoint of the upper contour in the partial rubber strip can be first determined based on the coordinate information of the pixel points of the upper contour, and the coordinate information of the midpoint of the lower contour in the partial rubber strip can be determined based on the coordinate information of the pixel points of the lower contour. Then, the glue width of the partial rubber strip can be determined based on the coordinate information of the midpoint of the upper contour and the coordinate information of the midpoint of the lower contour. For example, the distance between the two midpoints can be calculated based on the coordinate information of the two midpoints (which can refer to the vertical coordinate or the XY coordinate), and this distance can be used as the glue width of the partial rubber strip.

[0177] In the above implementation process, in order to avoid the problem of inconsistent testing standards caused by testing the glue width of different glue strips at different positions, which affects the subsequent quality inspection results, a glue width detection area is set up, and part of the glue strips of each glue strip are intercepted in the glue width detection area, so that the glue width of part of the glue strips can be detected in the same glue width detection area, thereby improving the accuracy of glue width detection.

[0178] On the basis of the above embodiment, in order to detect some situations where the glue width of the glue strip at different positions is different due to uneven glue coating, multiple glue width detection areas can be set. The above glue width detection areas are detection areas at multiple different positions. In this way, each glue strip can be intercepted within each glue width detection area according to the pre-defined multiple glue width detection areas to obtain the partial glue strip corresponding to each glue strip, wherein the glue width of the partial glue strip includes the glue width at the position where each glue width detection area is located.

[0179] For example, glue width detection areas at the left, center, and right positions can be set. In this way, for one glue strip, its glue width at the left, center, and right positions can be obtained. Then, for three glue strips, the glue width detection values ​​of the detection items numbered 2-10 in the above Table 1 can be obtained (wherein, glue width i in Table 1 represents the glue width of the i-th glue strip, and i is 1, 2, or 3).

[0180] Subsequently, when judging whether the gluing quality of the water-cooling plate is qualified based on the glue width test results, it can be judged based on the three glue widths of each glue strip. For example, it can be judged whether the three glue widths of each glue strip are all within the set glue width range. If so, the gluing quality is considered qualified, otherwise, the gluing quality is considered unqualified.

[0181] In the above implementation process, the glue width of each glue strip is detected in the glue width detection area at different positions, so that the glue width of each glue strip at different positions can be obtained, which can better detect the glue coating quality.

[0182] (3) Detection of rubber strip position.

[0183] On the basis of the above-mentioned glue width detection, the glue strip position detection result is obtained according to the coordinate information of each pixel point on the glue shape contour, including: according to the pre-defined glue width detection area, each glue strip is intercepted within the glue width detection area to obtain the partial glue strip corresponding to each glue strip, and then the coordinate information of the partial glue strip is determined according to the coordinate information of each pixel point on the glue shape contour, and then the glue strip position detection result is determined according to the coordinate information of the partial glue strip corresponding to each glue strip, including the position information of each glue strip, and the position information includes the spacing between each glue strip and / or the spacing between each glue strip and the edge of the image detection area.

[0184] It should be noted that in the rubber strip position detection method, the method of obtaining the pixel coordinate information of each rubber strip is the same as the method of obtaining the pixel coordinate information of each rubber strip in the above-mentioned rubber width detection result. Both are through extracting the rubber shape contour of each rubber strip on the water-cooling plate in the water-cooling plate image, and then extracting the coordinate information of each pixel point on the rubber shape contour. Please refer to the relevant description of the above embodiment for the specific implementation process, and no further details will be repeated here.

[0185] The glue width detection area here is the same as the glue width detection area in the above-mentioned glue width detection method, and both refer to the same glue width detection area. For example, a glue strip is intercepted within the glue width detection area to obtain the part of the glue strip intercepted by the glue strip. The coordinate information of this part of the glue strip can represent the coordinate information of the glue strip, so the position information of each glue strip can be determined based on its coordinate information.

[0186] In the above implementation process, the coordinate information of the intercepted portion of the rubber strip is obtained within the rubber width detection area to determine the position of the entire rubber strip, thereby accurately obtaining the position information of the rubber strip.

[0187] In some embodiments, the method of obtaining the coordinate information of a portion of the rubber strip may include: obtaining the coordinate information of the pixel points of the upper contour and the coordinate information of the pixel points of the lower contour in the portion of the rubber strip from the coordinate information of each pixel point on the rubber contour, and then determining the coordinate information of the midpoint of the upper contour based on the coordinate information of the pixel points of the upper contour, and determining the coordinate information of the midpoint of the lower contour based on the coordinate information of the pixel points of the lower contour, and then determining the coordinate information of the midpoint of the connecting line segment of the midpoints of the two contours based on the coordinate information of the midpoint of the upper contour and the coordinate information of the midpoint of the lower contour, and the coordinate information of the midpoint of the connecting line segment is the coordinate information of the portion of the rubber strip.

[0188] Among them, the glue width detection area can be a rectangular area, so the shape of the intercepted part of the glue strip is also rectangular (the glue strip is similar to a rectangle), so it is easy to obtain the coordinate information of the midpoints of the upper and lower contours of the part of the glue strip. For example, if the upper contour has 31 pixels, the coordinate information of the midpoint is the coordinate information of the 16th pixel (such as x1, y1). Similarly, if the lower contour also includes 31 pixels, the coordinate information of the midpoint is the coordinate information of the 16th pixel (such as x2, y2). Then connect these two pixel points to determine the coordinate information of the midpoint of the connecting line segment. The coordinate information of the midpoint of the connecting line segment is (x2 (or x1) + (|x2-x1|) / 2, y2 + (y1-y2) / 2). The coordinate information of the midpoint can represent the coordinate information of part of the glue strip, and can also represent the coordinate information of the position of the entire glue strip, such as Figure 6 shown.

[0189] In the above implementation process, the midpoint of the connecting line segment between the midpoints of the upper and lower contours is used as the coordinate information of the rubber strip, which can better reflect the position of each rubber strip and improve the accuracy of its position detection.

[0190] It is understandable that in some other embodiments, the coordinate information of part of the rubber strip can also be replaced by the coordinate information of any pixel point on its rubber contour, such as the coordinate information of the midpoint of the upper contour, or the coordinate information of the midpoint of the lower contour.

[0191] In this detection method, the glue width detection area can also be detection areas at multiple different positions. In the method of intercepting and obtaining partial glue strips, each glue strip can be intercepted within each glue width detection area according to multiple pre-delineated glue width detection areas to obtain the partial glue strips corresponding to each glue strip, wherein the coordinate information of each glue strip includes the coordinate information of each glue strip at the position of each glue width detection area.

[0192] For example, the glue width detection area includes detection areas at three positions: left, middle, and right. The length of a glue width detection area is generally set to cover the longitudinal width of the area where multiple glue strips are located in the water-cooling plate image. That is to say, if there are three glue strips arranged vertically in the image, then part of these three glue strips can be intercepted within a glue width detection area. Therefore, if there is no glue breakage, there are three glue width detection areas, and nine partial glue strips will be intercepted, each of which corresponds to the three partial glue strips on the left, middle, and right. The coordinate information of each partial glue strip can be obtained in the above manner.

[0193] In the method of obtaining the position information of each rubber strip, for example, for the first rubber strip at the top, it corresponds to three parts of the left, middle and right rubber strips. Then, the distances of the three parts of the rubber strips from the upper edge of the image detection area can be obtained based on the coordinate information of the three parts of the rubber strips, thereby obtaining the detection values ​​of detection items 11, 15 and 19 in Table 1 above. Then, the distance between the left part of the first rubber strip and the left part of the second rubber strip in the middle, the distance between the middle part of the first rubber strip and the middle part of the second rubber strip, and the distance between the right part of the first rubber strip and the right part of the second rubber strip are calculated respectively, thereby obtaining the detection values ​​of detection items 12, 16 and 20 in Table 1 above. In the same way, the distances between the second rubber strip and the corresponding parts of the third rubber strip can be calculated, thereby obtaining the detection values ​​of detection items 13, 17 and 21 in Table 1 above. And the distance between the third rubber strip and the lower edge of the image detection area is calculated, thereby obtaining the detection values ​​of detection items 14, 18 and 22 in Table 1 above.

[0194] Regarding the method for calculating the distance between each rubber strip and the left and right edges of the image detection area, the pixel point with the smallest X coordinate value among all pixels on the rubber strip's rubber contour can be used as the left endpoint of the rubber strip. The distance between each left endpoint and the left edge of the image detection area is then calculated to obtain the detection values ​​of detection items 23, 24, and 25 in Table 1 above. Similarly, the pixel point with the largest X coordinate value among all pixels on the rubber strip's rubber contour is used as the right endpoint of the rubber strip. The distance between each right endpoint and the right edge of the image detection area is then calculated to obtain the detection values ​​of detection items 26, 27, and 28 in Table 1 above.

[0195] In the above implementation process, the position accuracy of the rubber strip is detected at the locations where the multiple rubber width detection areas are located, so that a more comprehensive detection can be achieved and the accuracy of the position accuracy detection can be improved.

[0196] Based on the above embodiment, in the method of detecting the pixel coordinate information of each rubber strip, each rubber strip on the water cooling plate in the water cooling plate image can be first identified to obtain the rubber strips that meet the set conditions, and then the pixel coordinate information of the rubber strips that meet the set conditions in the water cooling plate image can be detected.

[0197] That is to say, the rubber strips that are quality inspected in the above embodiment refer to the rubber strips that meet the set conditions, that is, the rubber strips that meet the set conditions are the rubber strips that need to be quality inspected, and the rubber strips that do not meet the set conditions may be incorrect in image recognition and are not real rubber strips, so there is no need to perform quality inspection on these rubber strips, thereby reducing misjudgments.

[0198] In the method of identifying each rubber strip to obtain the rubber strip that meets the set conditions, the rubber shape outline of the rubber strip on the water cooling plate can be first extracted from the water cooling plate image, and then the rubber strip formed by the rubber shape outline can be identified according to the set conditions to obtain the rubber strip that meets the set conditions.

[0199] The method for extracting the rubber strip's contour here is the same as that used in the above-mentioned embodiment, and will not be repeated here. It should be noted that, while the above-mentioned embodiment requires extracting the rubber strip's contour from the pixel coordinate information of the rubber strip when detecting it, in this embodiment, the rubber strip's contour is extracted when the rubber strip is identified. These two steps can be combined, that is, the rubber strip's contour can be extracted when the rubber strip is identified. Then, when subsequently acquiring the rubber strip's pixel index information, the extracted contour can be directly read. Then, coordinate detection can be performed on the rubber strip's contour that meets the set conditions, without the need to extract the contour again.

[0200] Similarly, when extracting the glue contour here, the water-cooling plate image can be first binarized using a binarization function to obtain a binarized water-cooling plate image, and then the glue contour of the glue strip on the water-cooling plate in the water-cooling plate image can be extracted based on the contour lines formed in the binarized water-cooling plate image.

[0201] The binarization function can be a function in LabVIEW. For example, as shown in Figure 4(c), the resulting binarized image clearly shows the shape of each adhesive strip, making it easy to extract the adhesive contour. It is understood that in practical applications, the binarization function can also be a function provided by other software.

[0202] Here, the rubber strips formed by the rubber-shaped contour are identified according to the set conditions, which can be understood as screening the rubber strips formed therefrom to screen out the real rubber strips, and screening out some rubber strip particles that are not actual rubber strips but are mistakenly identified as rubber strips, thereby reducing subsequent misjudgments of the rubber strip quality inspection (for example, if the quality inspection of these rubber strips mistakenly identified as rubber strips is likely to be unqualified, then the entire gluing quality will be judged to be unqualified, but in fact these misidentified rubber strips are caused by factors such as image photography, and it is meaningless to conduct quality inspection on these rubber strips).

[0203] In the above implementation process, by identifying each rubber strip, the rubber strips that meet the set conditions are obtained, and the rubber strips that meet the set conditions are subsequently subjected to glue coating quality inspection. In this way, the rubber strips that do not meet the set conditions can be filtered out first to reduce the impact of these rubber strips on the glue coating quality inspection results.

[0204] On the basis of the above embodiment, in the above method of identifying rubber strips, in order to improve the recognition effect, a morphological closing operation can be performed on the rubber contour to obtain a rubber contour with a closed contour, and then the rubber strips formed by the rubber contours whose width is less than a set value and extends to the edge of the image detection area are filtered, and the remaining rubber contours after filtering are filled to obtain the rubber strips formed after filling, wherein the rubber strips that meet the set conditions include the rubber strips after filling.

[0205] Since the lines of the gel contour extracted from the binary image may not always be closed, the gel contour can also be processed by morphological closing operation. The closing operation function in LabVIEW software can also be used here to process it so that its contour lines are closed. After closing, some small particles can be filtered, such as filtering out the glue strips formed by the gel contour with a width less than 30 pixels (30 pixels is the set value) and extending to the edge of the image detection area. In this way, some small particle glue strips formed by the image and the small particle glue strips that are in contact with the edge of the image detection area can be filtered out, and then the "filling holes in particles" operation is performed, that is, regional filling is performed, that is, the area formed by the gel contour is filled. The reason for closing operation and then filling here is that if the contour lines are not closed first and filling is performed, image abnormalities will occur. The image obtained after filling is as follows Figure 7 shown.

[0206] The principle of the morphological closing operation here is to dilate first and then erode. Its purpose is to eliminate small holes, smooth the contours of objects, connect narrow discontinuities and gullies, and fill broken contours, so that the broken contours can be closed.

[0207] In the above implementation process, some tiny rubber strip particles can be filtered through the above method, thereby filtering out misidentified rubber strips to reduce the impact of these rubber strips on subsequent glue coating quality detection.

[0208] The image obtained after the above filling may still contain interfering particles that have not been filtered out and are stuck to the rubber strips. Therefore, a morphological corrosion operation can be performed on the rubber strips formed after filling to obtain separated rubber strips. Then, the separated rubber strips with a length less than a set value are filtered, and a morphological expansion operation is performed on the remaining rubber strips after filtering to obtain the final separated rubber strips. Among them, the rubber strips that meet the set conditions include the final separated rubber strips.

[0209] Here, the image is first morphologically eroded to separate the rubber strips in the image, and then the particles with a length less than 1200 pixels (1200 pixels is the set value, and in actual applications, the set value can be set according to actual needs) are filtered out. Then, a morphological dilation operation is performed to restore the rubber strips to their original size, thus obtaining the final separated rubber strips, as shown in Figure 2. Figure 8 As shown in the figure, the subsequent process only requires quality inspection of each strip finally separated.

[0210] In the above implementation process, the adhesive strip particles that are adhered to normal adhesive strips can be filtered out in the above manner, thereby filtering out misidentified adhesive strips to reduce the impact of these adhesive strips on subsequent adhesive coating quality detection.

[0211] On the basis of the above embodiments, in actual situations, the glue strips may be excessively drawn and stuck together during glue application, or the glue strips may be deliberately stuck together (continuous glue application is to save the running time of the glue application equipment). The above-mentioned "corrosion" and then "expansion" operations may not be able to completely separate the glue strips. Therefore, in this solution, a shielding detection area can also be set at the adhesion position of the two glue strips in the water-cooling plate image. The shielding detection area indicates the area where the glue strips are not identified.

[0212] Among them, the shielding detection area can be a rectangular area of ​​a fixed size. Of course, its size can be changed according to needs under actual circumstances. And after obtaining the water-cooling plate image, you can first add the image detection area, glue width detection area and shielding detection area to the water-cooling plate image. The shielding detection area is generally set at a fixed position in the water-cooling plate image. For example, when applying glue, the gluing equipment applies glue from left to right. Then the first glue strip and the second glue strip may be stuck at the right end, and the second glue strip and the third glue strip may be stuck at the left end. So in this case, corresponding shielding detection areas can be set at the right and left ends. The glue strips identified in the shielding detection area are considered invalid, so the three glue strips can be separated well.

[0213] It can be understood that in the actual detection process, the gluing order of a group of glue-coated products is generally fixed, so a fixed shielding detection area can be set initially, and then the size and position of the shielding detection area are applied to the gluing detection of this group of water-cooling plate images. If the gluing order of the subsequent glue-coated products changes, the setting position and / or size of the shielding detection area can be adjusted to adapt to the detection of different glue-coated products.

[0214] It should be noted that the image detection area in the above embodiment refers to the detection area of ​​the water-cooling plate image, which is a rectangular frame area. The above-mentioned glue width detection area is also a rectangular frame area, which is used to intercept each glue strip to obtain a part of the glue strip and then detect the glue width and glue strip position. The shielding detection area is also a rectangular area. The setting diagram of each detection area in the water-cooling plate image is shown in the figure. Figure 9 It is understandable that the specific shape of each detection area can be adjusted in actual application, for example, it can also be an ellipse or other shape.

[0215] On the basis of the above embodiment, when performing quality inspection on the rubber strips, in order to improve the detection efficiency of good and defective products, each rubber strip can be first detected for rubber breakage based on the pixel coordinate information to obtain the rubber breakage detection result. If the rubber breakage detection result is not rubber breakage, the rubber width detection and / or rubber strip position detection of each rubber strip is continued to be performed to obtain the corresponding rubber width detection result and / or rubber strip position detection result.

[0216] In other words, you can first perform a glue break test. If the glue break test result is qualified, then proceed to the subsequent glue width test and / or glue strip position test. If the glue break test result is unqualified, then the glue coating quality of the glue strip can be directly judged as unqualified and defective, so no subsequent tests are required. Because the glue break test method is faster, performing the glue break test first can obtain a test result more quickly. If the test result is unqualified, then the glue coating quality can be directly judged as unqualified, which is more efficient.

[0217] Of course, if the glue break detection result is qualified, a detection sequence can also be set for the detection of glue width and glue strip position. For example, the glue width detection is performed first. If the glue width detection is qualified, the glue strip position detection is performed. If the glue width detection is unqualified, it can be directly determined that the glue coating quality is unqualified at this time, and there is no need to perform glue strip position detection. Of course, it is also possible to perform glue strip position detection first. When the glue strip position detection result is unqualified, it is directly determined that the glue coating quality is unqualified, and there is no need to perform glue width detection. When the glue strip position detection result is qualified, glue width detection is performed. It should be noted that, through the above-mentioned methods of glue break detection, glue width detection and glue strip position detection, some steps in the three detection methods can be reused. For details, please refer to the description in the above implementation process.

[0218] In practical applications, the three test items can also be tested in parallel, so that three test results can be obtained. Then, when any test result is unqualified, it is determined that the glue coating quality is unqualified, and the water cooling plate can be judged as a defective product. Only when all three test results are qualified, it is determined that the glue coating quality is qualified and the water cooling plate is a good product.

[0219] It is understandable that, in actual situations, at least one test may be performed, that is, the test results may include at least one of the following results: a glue breakage detection result, a glue width detection result, and a glue strip position detection result.

[0220] This solution displays test results on the host computer. For example, all test items are assigned a "lower limit deviation" value, an "upper limit deviation" value, and a standard value (using the standard value from a tested, qualified product). During testing, the "test value," "deviation," and "judgment" results are displayed in a table on the interface. The "deviation" value is the difference between the "test value" and the "standard value." The measured "deviation" value must be within the set "lower limit deviation" and "upper limit deviation" range to be considered "OK." If any test item fails, the overall test result will be "NG." This solution has been proven in production to reliably and effectively detect adhesive defects such as breakage, excessive adhesive width, left-right deviation, and up-down deviation.

[0221] Please refer to Figure 10 , Figure 10This is a structural block diagram of a glue detection device 300 provided in an embodiment of the present application. The device 300 may be a module, program segment or code on an electronic device. It should be understood that the device 300 is similar to the above-mentioned Figure 2 The method embodiment corresponds to the embodiment that can be executed Figure 2 The various steps involved in the method embodiment and the specific functions of the device 300 can be found in the description above. To avoid repetition, detailed description is appropriately omitted here.

[0222] Optionally, the apparatus 300 includes:

[0223] An image acquisition module 310 is used to acquire an image of a water cooling plate of a battery cell;

[0224] An information acquisition module 320 is configured to detect pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image;

[0225] The detection module 330 is used to perform quality detection on each rubber strip according to the pixel coordinate information to obtain a detection result.

[0226] Optionally, the information acquisition module 320 is specifically configured to extract the contour of each rubber strip on the water-cooling plate in the water-cooling plate image; determine the vertical coordinate of each rubber strip according to the contour of the rubber strip, wherein the pixel coordinate information of each rubber strip includes the vertical coordinate;

[0227] The detection module 330 is specifically configured to perform quality detection on each rubber strip according to the vertical coordinate to obtain a rubber breakage detection result.

[0228] Optionally, the detection module 330 is specifically used to determine the longitudinal distance between two adjacent rubber strips according to the longitudinal coordinates corresponding to each rubber strip; if the longitudinal distance between two adjacent rubber strips is less than the set distance, the rubber break detection result is determined to include the two adjacent rubber strips being broken rubber strips.

[0229] Optionally, the detection module 330 is specifically used to identify the number of rubber strips on the water cooling plate in the water cooling plate image based on the rubber-shaped contour; determine the longitudinal spacing between two adjacent rubber strips based on the vertical coordinates corresponding to each rubber strip; if the longitudinal spacing between two adjacent rubber strips is greater than or equal to the set spacing and the number of rubber strips is the set number, then determine that the broken rubber detection result includes that the two adjacent rubber strips are not broken rubber strips.

[0230] Optionally, the information acquisition module 320 is specifically configured to extract the rubber contour of each rubber strip on the water-cooling plate in the water-cooling plate image; and extract coordinate information of each pixel point on the rubber contour, wherein the pixel coordinate information of each rubber strip includes coordinate information of each pixel point on the rubber contour of the rubber strip;

[0231] The detection module 330 is specifically configured to obtain a glue width detection result and / or a glue strip position detection result based on coordinate information of each pixel point on the glue profile.

[0232] Optionally, the detection module 330 is specifically used to intercept each rubber strip within the pre-defined rubber width detection area to obtain the partial rubber strip corresponding to each rubber strip; obtain the coordinate information of the pixel points of the upper and lower contours of the partial rubber strip from the coordinate information of each pixel point on the rubber-shaped contour; and determine that the rubber width detection result includes the rubber width of the partial rubber strip based on the coordinate information of the pixel points of the upper and lower contours, and the rubber width of the partial rubber strip is the rubber width of the corresponding rubber strip.

[0233] Optionally, the glue width detection area is a detection area at multiple different positions, and the detection module 330 is specifically used to intercept each glue strip within each glue width detection area according to multiple pre-delineated glue width detection areas, and obtain the partial glue strip corresponding to each glue strip; wherein the glue width of the partial glue strip includes the glue width at the position where each glue width detection area is located.

[0234] Optionally, the detection module 330 is specifically used to determine the coordinate information of the midpoint of the upper contour based on the coordinate information of the pixel points of the upper contour, and to determine the coordinate information of the midpoint of the lower contour based on the coordinate information of the pixel points of the lower contour; and to determine the glue width of the partial glue strip based on the coordinate information of the midpoint of the upper contour and the coordinate information of the midpoint of the lower contour.

[0235] Optionally, the detection module 330 is specifically used to intercept each rubber strip within the pre-defined rubber width detection area to obtain a partial rubber strip corresponding to each rubber strip; determine the coordinate information of the partial rubber strip based on the coordinate information of each pixel point on the rubber shape contour; determine the rubber strip position detection result including the position information of each rubber strip based on the coordinate information of the partial rubber strip corresponding to each rubber strip, and the position information includes the spacing between each rubber strip and / or the spacing between each rubber strip and the edge of the image detection area.

[0236] Optionally, the detection module 330 is specifically used to obtain the coordinate information of the pixel points of the upper contour and the coordinate information of the pixel points of the lower contour in the partial rubber strip from the coordinate information of each pixel point on the rubber-shaped contour; determine the coordinate information of the midpoint of the upper contour according to the coordinate information of the pixel points of the upper contour, and determine the coordinate information of the midpoint of the lower contour according to the coordinate information of the pixel points of the lower contour; determine the coordinate information of the midpoint of the connecting line segment of the midpoints of the two contours according to the coordinate information of the midpoint of the upper contour and the coordinate information of the midpoint of the lower contour, and the coordinate information of the midpoint of the connecting line segment is the coordinate information of the partial rubber strip.

[0237] Optionally, the glue width detection area is a detection area at multiple different positions, and the detection module 330 is specifically used to intercept each glue strip within each glue width detection area according to multiple pre-delineated glue width detection areas, and obtain the partial glue strip corresponding to each glue strip; wherein the coordinate information of each glue strip includes the coordinate information of each glue strip at the position of each glue width detection area.

[0238] Optionally, the information acquisition module 320 is further configured to identify each rubber strip on the water-cooling plate in the water-cooling plate image to obtain rubber strips that meet set conditions; and detect pixel coordinate information of the rubber strips that meet the set conditions in the water-cooling plate image.

[0239] Optionally, the information acquisition module 320 is specifically configured to extract a rubber shape outline of a rubber strip on the water-cooling plate in the water-cooling plate image; identify the rubber strip formed by the rubber shape outline according to set conditions, and obtain a rubber strip that meets the set conditions.

[0240] Optionally, the information acquisition module 320 is specifically used to perform a morphological closing operation on the rubber contour to obtain a rubber contour with a closed contour; filter the rubber strips formed by the rubber contours whose width is less than a set value and extends to the edge of the image detection area; fill the remaining rubber contours after filtering to obtain the rubber strips formed after filling, wherein the rubber strips that meet the set conditions include the rubber strips after filling.

[0241] Optionally, the information acquisition module 320 is also used to perform a morphological corrosion operation on each rubber strip formed after filling to obtain separated rubber strips; filter the separated rubber strips whose length is less than a set value; and perform a morphological expansion operation on the remaining rubber strips after filtering to obtain the finally separated rubber strips, wherein the rubber strips that meet the set conditions include the finally separated rubber strips.

[0242] Optionally, the information acquisition module 320 is specifically used to binarize the water cooling plate image using a binarization processing function to obtain a binarized water cooling plate image; and extract the glue-shaped contour of the glue strip on the water cooling plate in the water cooling plate image based on the contour lines formed in the binarized water cooling plate image.

[0243] Optionally, the apparatus 300 further includes:

[0244] The shielding detection module is used to set a shielding detection area at the adhesion position of the two rubber strips in the water-cooling plate image, wherein the shielding detection area represents an area where the rubber strips are not identified.

[0245] Optionally, the detection module 330 is specifically used to perform glue break detection on each glue strip according to the pixel coordinate information to obtain a glue break detection result; if the glue break detection result is not glue break, then continue to perform glue width detection and / or glue strip position detection on each glue strip to obtain corresponding glue width detection results and / or glue strip position detection results.

[0246] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0247] Please refer to Figure 11 , Figure 11 A structural diagram of an electronic device for executing a glue coating detection method provided in an embodiment of the present application, the electronic device may include: at least one processor 410, such as a CPU, at least one communication interface 420, at least one memory 430 and at least one communication bus 440. Among them, the communication bus 440 is used to realize direct connection and communication between these components. Among them, the communication interface 420 of the device in the embodiment of the present application is used to communicate signaling or data with other node devices. The memory 430 can be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory. The memory 430 can optionally also be at least one storage device located away from the aforementioned processor. Computer-readable instructions are stored in the memory 430. When the computer-readable instructions are executed by the processor 410, the electronic device executes the above-mentioned Figure 2 The method process shown.

[0248] I understand. Figure 11 The structure shown is only for illustration, and the electronic device may also include Figure 11 More or fewer components than shown, or with Figure 11 Different configurations shown. Figure 11 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0249] The embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program performs the following operations: Figure 2 The method process in the illustrated method embodiment is performed by the electronic device.

[0250] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can perform the methods provided in the above method embodiments, for example, including:

[0251] Get the water cooling plate image of the battery cell;

[0252] Detecting pixel coordinate information of each rubber strip on the water-cooling plate in the water-cooling plate image;

[0253] The quality of each rubber strip is tested according to the pixel coordinate information to obtain a test result.

[0254] In summary, the embodiments of the present application provide a glue coating detection method, system, device, electronic device and storage medium. The method obtains the water-cooling plate image of the battery cell, detects the pixel coordinate information of each glue strip on the water-cooling plate in the water-cooling plate image, and then performs quality inspection on each glue strip based on the pixel coordinate information to obtain the inspection results. Since the pixel coordinate information of each glue strip obtained in this scheme can provide more detailed feedback on the glue coating quality of the glue strip, the glue coating quality of each glue strip is detected according to the pixel coordinate information, which is more accurate and can effectively reduce misjudgment.

[0255] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0256] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0257] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0258] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any actual relationship or order between these entities or operations.

[0259] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for detecting glue coating, characterized in that: The method comprises: Get the water cooling plate image of the battery cell; Detecting pixel coordinate information of each rubber strip on the water cooling plate in the water cooling plate image; The quality of each rubber strip is tested according to the pixel coordinate information to obtain a test result.

2. The method according to claim 1, characterized in that The detecting pixel coordinate information of each rubber strip on the water cooling plate in the water cooling plate image includes: Extracting the glue shape contour of each glue strip on the water cooling plate in the water cooling plate image; Determining the ordinate of each rubber strip according to the rubber shape contour, wherein the pixel coordinate information of each rubber strip includes the ordinate; The step of performing quality inspection on each rubber strip according to the pixel coordinate information to obtain the inspection result includes: The quality of each rubber strip is inspected according to the vertical coordinate to obtain the rubber breaking inspection result.

3. The method according to claim 2, characterized in that The step of performing quality inspection on each rubber strip according to the vertical coordinate to obtain a rubber breaking inspection result includes: Determine the longitudinal spacing between two adjacent rubber strips according to the longitudinal coordinates corresponding to each rubber strip; If the longitudinal spacing between two adjacent rubber strips is less than the set spacing, it is determined that the rubber break detection result includes that the two adjacent rubber strips are broken rubber strips.

4. The method according to claim 2, characterized in that: The step of performing quality inspection on each rubber strip according to the vertical coordinate to obtain a rubber breaking inspection result includes: Identify the number of rubber strips on the water cooling plate in the water cooling plate image according to the rubber-shaped contour; Determine the longitudinal spacing between two adjacent rubber strips according to the longitudinal coordinates corresponding to each rubber strip; If the longitudinal spacing between two adjacent rubber strips is greater than or equal to a set spacing and the number of the rubber strips is a set number, then determining that the rubber break detection result includes that the two adjacent rubber strips are non-broken rubber strips.

5. The method according to claim 1, characterized in that The detecting pixel coordinate information of each rubber strip on the water cooling plate in the water cooling plate image includes: Extracting the glue shape contour of each glue strip on the water cooling plate in the water cooling plate image; Extracting coordinate information of each pixel point on the rubber-shaped contour, wherein the pixel coordinate information of each rubber strip includes coordinate information of each pixel point on the rubber-shaped contour of the rubber strip; The step of performing quality inspection on each rubber strip according to the pixel coordinate information to obtain the inspection result includes: According to the coordinate information of each pixel point on the glue profile, the glue width detection result and / or the glue strip position detection result are obtained.

6. The method according to claim 5, characterized in that The step of obtaining the glue width detection result according to the coordinate information of each pixel point on the glue shape contour includes: According to a pre-defined glue width detection area, each glue strip is intercepted within the glue width detection area to obtain a partial glue strip corresponding to each glue strip; Obtaining coordinate information of pixel points of upper and lower contours of the partial rubber strip from coordinate information of each pixel point on the rubber-shaped contour; According to the coordinate information of the pixel points of the upper and lower contours, it is determined that the glue width detection result includes the glue width of the partial glue strip, and the glue width of the partial glue strip is the glue width of the corresponding glue strip.

7. The method according to claim 6, characterized in that The glue width detection area is a detection area at multiple different positions. According to the pre-defined glue width detection area, each glue strip is intercepted in the glue width detection area to obtain a partial glue strip corresponding to each glue strip, including: According to a plurality of pre-defined adhesive width detection areas, each adhesive strip is intercepted in each adhesive width detection area to obtain a partial adhesive strip corresponding to each adhesive strip; The glue width of the partial glue strip includes the glue width at the location of each glue width detection area.

8. The method according to claim 6, characterized in that The step of determining the adhesive width of the portion of the adhesive strip according to the coordinate information of the pixel points of the upper and lower contours includes: Determine the coordinate information of the midpoint of the upper contour according to the coordinate information of the pixel points of the upper contour, and determine the coordinate information of the midpoint of the lower contour according to the coordinate information of the pixel points of the lower contour; The glue width of the partial glue strip is determined according to the coordinate information of the midpoint of the upper contour and the coordinate information of the midpoint of the lower contour.

9. The method according to claim 5, characterized in that The step of obtaining the rubber strip position detection result according to the coordinate information of each pixel point on the rubber strip contour includes: According to a pre-defined glue width detection area, each glue strip is intercepted within the glue width detection area to obtain a partial glue strip corresponding to each glue strip; Determining coordinate information of the portion of the rubber strip according to coordinate information of each pixel point on the rubber-shaped contour; According to the coordinate information of the part of the rubber strips corresponding to each rubber strip, it is determined that the rubber strip position detection result includes the position information of each rubber strip, and the position information includes the distance between each rubber strip and / or the distance between each rubber strip and the edge of the image detection area.

10. The method according to claim 9, characterized in that The step of determining the coordinate information of the portion of the rubber strip according to the coordinate information of each pixel point on the rubber-shaped contour includes: Obtaining coordinate information of pixel points of an upper contour and coordinate information of pixel points of a lower contour in the portion of the rubber strip from coordinate information of each pixel point on the rubber-shaped contour; Determine the coordinate information of the midpoint of the upper contour according to the coordinate information of the pixel points of the upper contour, and determine the coordinate information of the midpoint of the lower contour according to the coordinate information of the pixel points of the lower contour; The coordinate information of the midpoint of the upper contour and the midpoint of the lower contour are used to determine the coordinate information of the midpoint of the connecting line segment of the midpoints of the two contours. The coordinate information of the midpoint of the connecting line segment is the coordinate information of the portion of the rubber strip.

11. The method according to claim 9, characterized in that The glue width detection area is a detection area at multiple different positions. According to the pre-defined glue width detection area, each glue strip is intercepted in the glue width detection area to obtain a partial glue strip corresponding to each glue strip, including: According to a plurality of pre-defined adhesive width detection areas, each adhesive strip is intercepted in each adhesive width detection area to obtain a partial adhesive strip corresponding to each adhesive strip; The coordinate information of each rubber strip includes the coordinate information of each rubber strip at the location of each rubber width detection area.

12. The method according to any one of claims 1 to 11, characterized in that: The detecting pixel coordinate information of each rubber strip on the water cooling plate in the water cooling plate image includes: Identify each rubber strip on the water-cooling plate in the water-cooling plate image to obtain a rubber strip that meets a set condition; Detect pixel coordinate information of the rubber strip that meets the set conditions in the water cooling plate image.

13. The method according to claim 12, characterized in that The step of identifying each rubber strip on the water cooling plate in the water cooling plate image to obtain a rubber strip that meets a set condition includes: Extracting the glue shape contour of the glue strip on the water cooling plate in the water cooling plate image; The rubber strip formed by the rubber-shaped contour is identified according to set conditions to obtain a rubber strip that meets the set conditions.

14. The method according to claim 13, characterized in that The step of identifying the rubber strip formed by the rubber-shaped contour according to set conditions to obtain the rubber strip that meets the set conditions includes: Performing a morphological closing operation on the colloid contour to obtain a colloid contour with a closed contour; Filter the rubber strips formed by the rubber contours whose width is less than the set value and which extend to the edge of the image detection area; The remaining rubber-shaped contours after filtering are filled to obtain the rubber strips formed after filling, wherein the rubber strips satisfying the set conditions include the rubber strips after filling.

15. The method according to claim 14, characterized in that After obtaining the glue strips formed after filling, the method further includes: Performing morphological corrosion operation on each rubber strip formed after filling to obtain separated rubber strips; Filter the separated rubber strips whose length is less than the set value; The rubber strips remaining after filtration are subjected to a morphological expansion operation to obtain the rubber strips finally separated, wherein the rubber strips satisfying the set conditions include the rubber strips finally separated.

16. The method according to claim 13, characterized in that The step of extracting the glue shape contour of the glue strip on the water cooling plate in the water cooling plate image comprises: Using a binarization function to perform binarization processing on the water cooling plate image to obtain a binarized water cooling plate image; The glue-shaped contour of the glue strip on the water-cooling plate in the water-cooling plate image is extracted according to the contour lines formed in the binarized water-cooling plate image.

17. The method according to claim 12, characterized in that The method further comprises: A shielding detection area is set at the adhesion position of the two rubber strips in the water-cooling plate image, wherein the shielding detection area represents an area where the rubber strips are not identified.

18. The method according to claim 1, characterized in that The step of performing quality inspection on each rubber strip according to the pixel coordinate information to obtain the inspection result includes: Perform glue break detection on each glue strip according to the pixel coordinate information to obtain a glue break detection result; If the glue break detection result is not glue break, then continue to perform glue width detection and / or glue strip position detection on each glue strip to obtain corresponding glue width detection results and / or glue strip position detection results.

19. A glue coating detection system, characterized in that: The glue coating detection system comprises: An image collector, used to collect images of the water cooling plate of the battery cell; A logic control device, used for controlling the transport device to transport the water-cooling plate of the battery cell to a set position, so that the image collector can collect images of the water-cooling plate; A host computer is used to receive the water-cooling plate image transmitted by the image collector, and use the water-cooling plate image to execute the glue coating detection method described in any one of claims 1-18.

20. The glue coating detection system according to claim 19, characterized in that: The logic control device is further used to change the detection signal to a set state after receiving a preparation signal sent by the transport device, wherein the preparation signal is sent by the transport device after the transport device transports the water-cooled plate to a set position; The host computer is further used to read the state of the detection signal of the logic control device at a set time interval, and after determining that the detection signal changes to a set state, send an image acquisition signal to the image collector; The image collector is further used to collect the water-cooling plate image of the water-cooling plate according to the image collection signal.

21. The glue coating detection system according to claim 19, characterized in that: The host computer is also used to determine whether the rubber strip on the water cooling plate is qualified according to the detection result; if it is unqualified, the logic control device is controlled to output an alarm prompt.

22. A glue coating detection device, characterized in that: The device comprises: An image acquisition module, used to acquire an image of a water cooling plate of a battery cell; An information acquisition module, used to detect pixel coordinate information of each rubber strip on the water cooling plate in the water cooling plate image; The detection module is used to perform quality detection on each rubber strip according to the pixel coordinate information to obtain a detection result.

23. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 18 is executed.

24. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 18 is executed.

Images