A method, apparatus and device for detecting a battery string

Abstract

The application provides a battery string detection method, device and equipment. The method comprises the following steps: acquiring a to-be-detected image photographed during the conveying process of a target battery string; in response to the acquisition of the to-be-detected image, splicing the to-be-detected image and a battery string image of the target battery string to obtain a spliced image, wherein the battery string image is spliced by to-be-detected images photographed during the conveying process of the target battery string; acquiring a battery sheet sub-image from the spliced image, wherein the battery sheet sub-image comprises a target battery sheet, and the target battery sheet is an undetected battery sheet; and performing defect detection on the target battery sheet based on the battery sheet sub-image. According to the application, the appearance of the battery string is detected while the data of the battery string is collected, so that the detection time is effectively shortened, and the detection efficiency and real-time performance are improved.

Description

Technical Field

[0001] This application relates to the field of machine vision technology, and in particular to a method, apparatus and equipment for detecting battery strings. Background Technology

[0002] The string soldering process for battery cells may include the following steps: 1. Clean the string soldering template before soldering to prevent solder dross or wires from falling and cracking the battery cells. 2. During the string soldering process, battery cells are taken from the area to be soldered and distributed to the string soldering template, from left to right. Then, each battery cell is soldered sequentially from right to left on the template. 3. After the string soldering is completed, clean the solder wires and solder dross from the battery cells.

[0003] In the stringing process, in addition to welding each individual cell, a cutting process may also be involved. For example, when a battery string consists of 15 cells, a cut is made between the 15th and 16th cells, thus forming a battery string of cells 1-15. A cut is made between the 30th and 31st cells, thus forming a battery string of cells 16-30, and so on.

[0004] During the stringing process of battery strings, various defects can easily occur, such as damage to the appearance, dirt on the appearance, and poor welding quality. Therefore, it is necessary to conduct visual inspection of the battery strings to promptly identify defective battery strings, assist in the repair and adjustment of the stringing equipment, and prevent defective battery strings from entering the market.

[0005] To perform visual inspection of battery strings, manual inspection is required to check for defects. However, due to the length of the battery strings and the numerous defect inspection items, manual inspection cannot detect all defects, and the results may be inaccurate. Furthermore, manual inspection requires physical contact with the battery strings, which may cause secondary damage. Summary of the Invention

[0006] This application provides a method for detecting a battery string, wherein the target battery string includes at least one battery cell. The method includes: acquiring an image to be detected captured during the transmission of the target battery string; in response to acquiring the image to be detected, stitching the image to be detected with an image of the battery string of the target battery string to obtain a stitched image, wherein the battery string image is formed by stitching together the image to be detected captured during the transmission of the target battery string; acquiring a battery cell sub-image from the stitched image, wherein the battery cell sub-image includes a target battery cell, and the target battery cell is a battery cell that has not been detected; and performing defect detection on the target battery cell based on the battery cell sub-image.

[0007] This application provides a battery string inspection device, the target battery string including at least one battery cell, comprising: an acquisition module for acquiring an image to be inspected captured during the transport of the target battery string; a stitching module for stitching the image to be inspected with a battery string image of the target battery string in response to acquiring the image to be inspected, wherein the battery string image is formed by stitching together the image to be inspected captured during the transport of the target battery string; acquiring a battery cell sub-image from the stitched image, the battery cell sub-image including a target battery cell, the target battery cell being an uninspected battery cell; and a detection module for performing defect detection on the target battery cell based on the battery cell sub-image.

[0008] This application provides a battery string inspection system, comprising: an image acquisition device, a battery string inspection device, a control device, a MES device, and a centralized control device; wherein: the image acquisition device is used to acquire images of the target battery string during transmission; the battery string inspection device is used to execute the aforementioned battery string inspection method based on the images to be inspected, and obtain defect detection results corresponding to the target battery string; the control device is used to control the transmission device and the image acquisition device; the MES device is used to acquire the defect detection results corresponding to the target battery string, and process the target battery string based on the defect detection results; the centralized control device is used to acquire the defect detection results corresponding to the target battery string, so that a user can manually inspect the target battery string for defects based on the defect detection results, obtain the manual inspection results of the target battery string, and return the manual inspection results to the battery string inspection device.

[0009] This application provides an electronic device, including: a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor; the processor is used to execute the machine-executable instructions to implement the above-described battery string detection method.

[0010] This application provides a computer program product, which may include a computer program that, when executed by a processor, implements the above-described battery string detection method.

[0011] This application provides a machine-readable storage medium storing machine-executable instructions that can be executed by a processor; wherein the processor is used to execute the machine-executable instructions to implement the above-described battery string detection method when the machine-executable instructions are executed.

[0012] As can be seen from the above technical solutions, in this embodiment, images of the battery string are acquired by a camera, and the presence of defects in the battery string is determined based on the images, enabling timely detection of defective battery strings. By detecting defects in the battery string through images, rapid and accurate defect detection is achieved for both ultra-long and standard-length battery strings, avoiding the subjectivity and errors of manual visual inspection, effectively improving detection quality and efficiency, reducing labor costs, and eliminating the need for contact with the battery string during the detection process, thus achieving non-destructive testing. It is applicable to the appearance inspection of battery strings of various sizes, performing appearance inspection on the battery string simultaneously with data acquisition, effectively shortening the inspection time and improving detection efficiency and real-time performance. Attached Figure Description

[0013] Figure 1 This is a flowchart illustrating a battery string detection method according to one embodiment of this application;

[0014] Figure 2 This is a schematic diagram of the system structure for battery string detection in one embodiment of this application;

[0015] Figure 3A This is a schematic diagram showing the appearance of an extra-long battery string in one embodiment of this application;

[0016] Figure 3B This is a schematic diagram showing the appearance of a conventional length battery string in one embodiment of this application;

[0017] Figure 4 This is a schematic diagram of the battery string detection system structure in one embodiment of this application;

[0018] Figure 5 This is a flowchart illustrating a battery string detection method according to one embodiment of this application;

[0019] Figure 6 This is a flowchart illustrating a battery string detection method according to one embodiment of this application;

[0020] Figure 7 This is a schematic diagram of the battery string splicing process in one embodiment of this application;

[0021] Figure 8 This is a schematic diagram of the structure of a battery string detection device in one embodiment of this application;

[0022] Figure 9 This is a hardware structure diagram of an electronic device according to one embodiment of this application. Detailed Implementation

[0023] This application proposes a method for detecting battery strings, wherein the target battery string includes at least one battery cell. See also... Figure 1The diagram shown is a flowchart of the method, which may include:

[0024] Step 101: Acquire the image to be detected captured during the transmission of the target battery string.

[0025] Step 102: In response to acquiring the image to be detected, the image to be detected is stitched together with the battery string image of the target battery string to obtain a stitched image. The battery string image is stitched together from the images to be detected captured during the transmission of the target battery string.

[0026] Step 103: Obtain the battery cell sub-image from the stitched image. The battery cell sub-image may include the target battery cell, and the target battery cell is an undetected battery cell. For example, the target battery cell may be a complete battery cell that has not been detected.

[0027] Step 104: Perform defect detection on the target battery cell based on the battery cell image.

[0028] For example, the images to be detected include an image of the upper surface of the target battery string acquired by a front-facing camera and / or an image of the lower surface of the target battery string acquired by a rear-facing camera; the front-facing camera is located above the target battery string, and the rear-facing camera is located below the target battery string. The image of the upper surface is used to perform defect detection on the upper surface of the target battery string; the image of the lower surface is used to perform defect detection on the lower surface of the target battery string. For example, based on the image of the upper surface of the target battery string acquired by the front-facing camera, steps 101-104 can be used to obtain the defect detection result of the upper surface of the target battery string. Similarly, based on multiple images of the upper surface of the target battery string, the defect detection results of all target battery cells can be obtained, and the defect detection results of all target battery cells constitute the defect detection result of the upper surface of the target battery string. Likewise, based on the image of the lower surface of the target battery string acquired by the rear-facing camera, steps 101-104 can be used to obtain the defect detection result of the lower surface of the target battery string. For example, based on the image of the target battery string on the upper surface acquired by the front camera, the defect detection result of the target battery string on the upper surface can be obtained; based on the image of the target battery string on the lower surface acquired by the back camera, the defect detection result of the target battery string on the lower surface can be obtained, that is, the defect detection results of the upper and lower surfaces can be obtained simultaneously.

[0029] For example, front-side inspection data of the upper surface of the target battery string can also be obtained. This data includes information on whether defects exist on the upper surface of the target battery string. If defects exist, the front-side inspection data also includes the defect type and defect area. Furthermore, back-side inspection data of the lower surface of the target battery string can also be obtained. This data includes information on whether defects exist on the lower surface of the target battery string. If defects exist, the back-side inspection data also includes the defect type and defect area. The front-side and back-side inspection data are then summarized to obtain the appearance inspection data of the target battery string, allowing the user to manually inspect the target battery string for defects based on this data and obtain the manual inspection results.

[0030] For example, after performing defect detection on the target battery cell based on the battery cell image, the defect detection results of the target battery string can also be obtained. The defect detection results include at least one of the following: the results obtained when performing defect detection on the target battery cell based on the battery cell image (i.e., the detection results in step 104), front detection data, back detection data, appearance inspection data, and manual inspection results. Then, operation control instructions can be generated based on the defect detection results. These instructions are used to control the flow of the target battery string in the direction corresponding to the defect detection results. For example, if the defect detection result indicates no defects, the target battery string is controlled to flow into the market; if the defect detection result indicates defects, the target battery string is controlled not to flow into the market.

[0031] For example, in the process of transporting multiple battery strings (the sequence of battery strings to be detected may include multiple battery strings, the process of transporting multiple battery strings is the process of transporting the sequence of battery strings, and the battery string sequence is transported by a transmission device), each battery string passes through the field of view of the camera in sequence, and the target battery string is any battery string (i.e. the battery string currently in the field of view of the camera). When the target battery string passes through the field of view of the camera, the camera can acquire the image to be detected for the target battery string.

[0032] For example, stitching the image to be detected with the battery string image of the target battery string to obtain a stitched image may include, but is not limited to: determining whether the number of stitched images of the battery string image is 0; if yes, and the image to be detected contains the string head feature of the target battery string, then the image to be detected can be updated to the battery string image of the target battery string, and the number of stitched images can be updated to 1; if no, and the number of stitched images has not reached the number threshold, then the image to be detected can be stitched with the battery string image of the target battery string to obtain a stitched image, and the stitched image can be updated to the battery string image of the target battery string, and the number of stitched images can be incremented by 1. For example, the number threshold can be determined based on the configured maximum number of stitches.

[0033] For example, after determining whether the number of stitched images of the battery string image is 0, if not, and the number of stitched images reaches the threshold, it can be determined whether the image to be detected has the tail feature of the target battery string; if the tail feature is not present, the image to be detected can be stitched with the battery string image of the target battery string to obtain a stitched image, and the stitched image can be updated to the battery string image of the target battery string, and the number of stitched images can be incremented by 1; if the tail feature is present, the image to be detected can be stitched with the battery string image of the target battery string to obtain a stitched image, and the stitched image can be updated to the complete battery string image of the target battery string, the complete battery string image can be output, and the number of stitched images can be updated to 0.

[0034] For example, before updating the stitched image to a complete image of the target battery string and outputting the complete battery string image, if a tail-of-string feature exists, it can be determined whether a tail-of-string signal has been received, and this tail-of-string signal can indicate that the last battery cell of the target battery string has been transported into the camera's field of view; if so, the operation of updating the stitched image to a complete image of the target battery string and outputting the complete battery string image can be performed; if not, an error message can be output.

[0035] For example, the stitched image is updated to a complete battery string image of the target battery string. After outputting the complete battery string image, a sub-image of each battery cell can be determined from the complete battery string image, and the defect detection result of the battery cell can be added to the sub-image of the battery cell.

[0036] For example, before stitching the image to be detected with the battery string image of the target battery string to obtain the stitched image, it can be determined whether the image to be detected is a valid image. If it is a valid image, the operation of stitching the image to be detected with the battery string image of the target battery string to obtain the stitched image is performed. If it is an invalid image, the image to be detected is discarded. Specifically, if the average brightness of the battery cell area in the image to be detected is less than the brightness threshold, and at least one of the following is true: the image to be detected has a string head feature and the image to be detected has a string tail feature, then the image to be detected is a valid image; otherwise, the image to be detected is an invalid image.

[0037] For example, edge pixels of the target battery string can also be determined from the image to be detected. If a first edge line and a second edge line are fitted based on these edge pixels, and the distance between the first edge line and the second edge line is greater than a distance threshold, and the average brightness of the transition region between the first edge line and the second edge line is greater than a first brightness threshold, and the average brightness of the battery cell region in the image to be detected is less than a second brightness threshold, then it can be determined that the image to be detected has string head features and string tail features; wherein, the second brightness threshold can be less than the first brightness threshold.

[0038] For example, obtaining a battery cell image from a stitched image may include, but is not limited to: inputting the stitched image into a first target detection model, and having the first target detection model output a first predicted position of the main grid line region of the battery cell; and determining the region corresponding to the first predicted position as the battery cell image.

[0039] For example, defect detection of a target battery cell based on a battery cell image may include, but is not limited to: inputting the battery cell image into a second target detection model, which outputs a second predicted position and a predicted category; determining the region corresponding to the second predicted position as the defect region of the battery cell image, and determining the defect type of the defect region based on the predicted category.

[0040] As can be seen from the above technical solutions, in this embodiment, images of the battery string are acquired by a camera, and the presence of defects in the battery string is determined based on the images, enabling timely detection of defective battery strings. By detecting defects in the battery string through images, rapid and accurate defect detection is achieved for both ultra-long and standard-length battery strings, avoiding the subjectivity and errors of manual visual inspection, effectively improving detection quality and efficiency, reducing labor costs, and eliminating the need for contact with the battery string during the detection process, thus achieving non-destructive testing. It is applicable to the appearance inspection of battery strings of various sizes, performing appearance inspection on the battery string simultaneously with data acquisition, effectively shortening the inspection time and improving detection efficiency and real-time performance.

[0041] The technical solutions of the embodiments of this application will be described below in conjunction with specific application scenarios.

[0042] This application proposes a method for detecting battery strings, which involves acquiring images of the battery strings using a camera and determining whether defects exist based on the images. See also... Figure 2 The diagram shows a schematic of a battery string detection system. Multiple battery cells are placed on the stringing equipment; that is, the multiple battery cells are distributed to the stringing template of the equipment. In this way, the stringing equipment can sequentially weld each battery cell from right to left on the stringing template.

[0043] Camera 1 is deployed on the upper side of the stringing equipment to capture images of the upper surface of the solar cells, and camera 2 is deployed on the lower side of the stringing equipment to capture images of the lower surface of the solar cells. Alternatively, camera 1 can be deployed only on the upper side of the stringing equipment, or camera 2 can be deployed only on the lower side of the stringing equipment.

[0044] Taking a battery string consisting of 15 cells, with a total of M cells (e.g., 1500 cells), as an example, the string welding equipment welds cells 1, 2, ..., M sequentially from right to left. Furthermore, a cutting operation is performed between the 15th and 16th cells, forming a battery string from cells 1 to 15. A cutting operation is also performed between the 30th and 31st cells, forming a battery string from cells 16 to 30, and so on.

[0045] Based on this, each battery string sequentially passes through the field of view of the camera (camera 1 and / or camera 2). When battery string a1 (e.g., the 1st to 15th battery cells) passes through the camera's field of view, an image of battery string a1 can be captured by the camera, and the presence of defects in battery string a1 can be determined based on the image. When battery string a2 (e.g., the 16th to 30th battery cells) passes through the camera's field of view, an image of battery string a2 can be captured by the camera, and the presence of defects in battery string a2 can be determined based on the image, and so on.

[0046] Considering the limited field of view of the camera, the complete image of the battery string is not obtained through a single image acquisition, but rather through multiple image acquisitions and stitching together the multiple images to obtain the complete image of the battery string.

[0047] By acquiring and stitching images, we can obtain the appearance images of either ultra-long or standard-length battery strings. Ultra-long battery strings refer to those with a length exceeding a threshold, while standard-length battery strings refer to those with a length not exceeding the threshold. See also... Figure 3A The image shown is a schematic diagram of the external appearance of an ultra-long battery string. Based on this image, rapid and accurate defect detection of ultra-long battery strings can be achieved. See also... Figure 3B The image shown is a schematic diagram of the appearance of a standard-length battery string. Based on the appearance image of a standard-length battery string, rapid and accurate defect detection of standard-length battery strings can be achieved.

[0048] For example, see Figure 4 The diagram shows the structure of a battery string inspection system. This system may include, but is not limited to, image acquisition equipment, battery string inspection equipment, control equipment, MES (Manufacturing Execution System) equipment, and centralized control equipment. Furthermore, the battery string inspection system is used to detect defects in battery strings, and the image acquisition equipment can be a camera.

[0049] For battery strings, the sequence of battery strings to be detected (e.g., 1500 battery cells) can include multiple battery strings (e.g., 100 battery strings), and each battery string can include multiple battery cells (e.g., 15 battery cells). All battery cells are located in a transmission device (the transmission device is a stringing device or other device with transmission function; this embodiment uses a stringing device as an example), and the stringing device transports each battery cell in the battery string sequence from right to left (or from left to right), so that each battery cell passes through the camera's field of view sequentially, that is, each battery string in the battery string sequence passes through the camera's field of view sequentially. The battery string can be a photovoltaic battery string or other types of battery strings; there is no limitation on the type of battery string.

[0050] The camera can be either a high-resolution or low-resolution camera; taking a high-resolution camera as an example, the camera is positioned at a fixed location and captures images of the battery string as it moves within its field of view, obtaining images of the battery string (one battery string will correspond to multiple images, meaning multiple images are obtained through multiple shots). Because the camera is high-resolution, it can obtain high-definition images of the battery string, ensuring that even the smallest details on the surface of the battery string are clearly displayed, facilitating defect detection.

[0051] A camera 1, which may be referred to as a front camera, can be deployed on the upper side of the stringing equipment and is used to acquire images of the upper surface of the solar cells. And / or, a camera 2, which may be referred to as a back camera, can be deployed on the lower side of the stringing equipment and is used to acquire images of the lower surface of the solar cells.

[0052] For battery string inspection equipment, the camera captures images and sends them to the equipment. The equipment then performs defect detection based on these images, executing battery string inspection methods to complete the defect detection. The battery string inspection equipment combines image processing technology and artificial intelligence algorithms to automatically identify and classify battery string defects, improving inspection efficiency and accuracy. The equipment can also statistically analyze the detected defect data, helping production managers to promptly identify the source and cause of defects, optimize production processes, and reduce production costs. The battery string inspection method will be described in detail later; the statistical analysis process for defect data will not be elaborated upon in this embodiment.

[0053] For the control equipment, it can be a PLC (Programmable Logic Controller), FPGA (Field Programmable Gate Array), CPLD (Complex Programmable Logic Device), etc., and there are no restrictions on the type of control equipment. The control equipment is used to control the stringer and the camera, such as linking the stringer and the camera together. For example, the control equipment can control the moving speed of the stringer and the interval between two consecutive camera acquisitions. For instance, assuming the camera's field of view is 10 cm and the interval between two consecutive camera acquisitions is 1 second, then the moving speed of the stringer needs to be controlled at 10 cm / 1 second. This ensures that the camera continuously acquires images without overlapping areas between adjacent images.

[0054] Of course, the above is just an example of controlling the stringing equipment and camera. There are no restrictions on this control method, as long as the camera continuously acquires images and there is no overlapping area between adjacent images.

[0055] For MES (Manufacturing Execution System) equipment, the battery string inspection device can send the defect detection results of the battery strings to the MES equipment. The MES equipment then retrieves the corresponding defect detection results and processes the battery strings based on these results. For example, the MES equipment can receive visual inspection results (such as defect detection results) and collect production data, providing strong support for subsequent quality analysis and defect tracing.

[0056] For example, MES equipment can dynamically monitor defects in battery strings, promptly identify problems and take measures, providing strong support for subsequent quality analysis and defect tracing.

[0057] For centralized control equipment, the equipment can obtain the defect detection results corresponding to the battery strings. For example, for a battery string with defects, the battery string detection equipment can send the defect detection results to the centralized control equipment. The centralized control equipment interacts with the user, who then decides whether the battery string is defective (i.e., the user manually checks the battery string for defects based on the defect detection results, obtaining a manual inspection result). The centralized control equipment can obtain the manual inspection result and return it (e.g., whether the battery string is defective or not) to the battery string detection equipment. The battery string detection equipment, based on the review result sent by the centralized control equipment, sends a corresponding result to the string welding control equipment (PLC), thereby determining the direction of the battery string flow. For example, the battery string detection equipment can obtain the defect detection results (such as the manual inspection results), generate operation control instructions based on the defect detection results, and send the operation control instructions to the string welding control equipment (PLC). The string welding control equipment (PLC) then controls the direction of the battery string flow according to the operation control instructions, corresponding to the defect detection results. For example, if the defect detection result is that there is no defect, the target battery string is controlled to flow into the market; if the defect detection result is that there is a defect, the target battery string is controlled not to flow into the market.

[0058] For example, if a centralized control device is deployed in the system, the battery string inspection device sends the manual inspection results of the battery strings to the MES device. If no centralized control device is deployed in the system, the battery string inspection device sends the defect detection results analyzed by the battery string inspection device itself to the MES device.

[0059] In the above application scenarios, this application proposes a method for detecting battery strings, see [link to relevant documentation]. Figure 5 The diagram shown illustrates the process of this method, which may include the following steps:

[0060] Step 501: Acquire images using the front camera. The image acquired by the front camera is the image of the upper surface of the battery string, and this image is called the front image (i.e., the image to be detected of the upper surface of the battery string obtained by the front camera). Acquire images using the back camera. The image acquired by the back camera is the image of the lower surface of the battery string, and this image is called the back image (i.e., the image to be detected of the lower surface of the battery string obtained by the back camera).

[0061] Step 502: Stitch together the front image and the back image. For example, the battery string detection device can acquire a front image from the front camera and stitch the front images together. The battery string detection device can acquire a back image from the back camera and stitch the back images together.

[0062] Step 503: Perform battery string detection based on the front-side stitched image and the back-side stitched image. For example, after the battery string detection device stitches the front-side image to obtain a front-side stitched image, it performs battery string detection on the upper surface of the battery string based on the front-side stitched image to detect whether there are defects on the upper surface of the battery string. That is, the image to be detected on the upper surface is used to detect defects on the upper surface of the battery string. After the battery string detection device stitches the back-side image to obtain a back-side stitched image, it performs battery string detection on the lower surface of the battery string based on the back-side stitched image to detect whether there are defects on the lower surface of the battery string. That is, the image to be detected on the lower surface is used to detect defects on the lower surface of the battery string.

[0063] Step 504: After obtaining the complete front image of the battery string, cache the complete front image of the battery string. After obtaining the complete back image of the battery string, cache the complete back image of the battery string.

[0064] For example, steps 501-504 are implemented by a battery string detection device, that is, the battery string detection device detects the battery string based on steps 501-504, and the detection process of the battery string is described in the following description.

[0065] Step 505: Calculate the detection data of the front side of the battery string and the detection data of the back side of the battery string.

[0066] For example, after performing battery string detection on the upper surface of the battery string based on the front-side stitched image, the battery string detection equipment statistically analyzes the front-side detection data of the battery string based on the detection results. The front-side detection data can include whether there are defects on the upper surface of the battery string. If there are defects on the upper surface, it can include the defect type, defect area, etc. That is, the front-side detection data includes statistical data and analysis data of upper surface defects.

[0067] After performing battery string detection on the lower surface of the battery string based on the reverse stitched image, the battery string detection equipment statistically analyzes the reverse detection data of the battery string based on the detection results. The reverse detection data may include whether there are defects on the lower surface of the battery string. If there are defects on the lower surface, it may include the defect type, defect area, etc. In other words, the reverse detection data includes statistical data and analysis data of defects on the lower surface.

[0068] Step 506: The battery string inspection device summarizes the front inspection data and the back inspection data of the battery string to obtain the appearance inspection data of the battery string, and caches the appearance inspection data.

[0069] Step 507: The battery string testing equipment outputs appearance inspection data.

[0070] For example, when inspecting a battery string, the battery string inspection device can cache the image data and appearance inspection data of the battery string, and output the appearance inspection data for further analysis and processing.

[0071] Step 508: The centralized control device acquires image data and appearance inspection data of the battery string. The centralized control device can display the image data and appearance inspection data to the user, allowing the user to decide whether the battery string has defects. In other words, the centralized control device can acquire the manual inspection results of the battery string (such as whether the battery string has defects or not), meaning the user manually inspects the battery string for defects based on the appearance inspection data.

[0072] Step 509: The battery string inspection equipment obtains the manual inspection results of the battery string and outputs the manual inspection results of the battery string to the MES equipment. The MES equipment processes the defect detection results.

[0073] This application proposes a method for detecting battery strings, and describes the processing steps 501-504. In this embodiment, taking an image captured by a single camera (which may be a rear-facing or front-facing camera) as an example, the processing flow is similar when two cameras capture images simultaneously, except that it is based on image processing from two directions. See [link to documentation]. Figure 6 The diagram shown is a flowchart of the method, which may include:

[0074] Step 601: When the target battery string passes through the field of view of the camera, the camera acquires the image of the target battery string to be detected. The target battery string can be any battery string in the battery string sequence.

[0075] For example, all the battery strings to be inspected (i.e., all the battery strings placed on the stringing equipment) can be referred to as a battery string sequence, meaning the battery string sequence includes multiple battery strings. For each battery string, the battery string includes multiple battery cells (e.g., 15 battery cells). The stringing equipment can transport each battery string within the battery string sequence, meaning each battery string in the battery string sequence sequentially passes through the camera's field of view. The battery string currently passing through the camera's field of view is designated as the target battery string, meaning the target battery string passes through the camera's field of view.

[0076] For example, the stringing equipment transports battery strings according to a fixed pattern (such as a fixed moving speed). Every time the stringing equipment moves a certain distance, it triggers a camera to acquire an image of the corresponding distance to be detected. During the image acquisition process, the camera continuously acquires images of the target, and there is no overlap between adjacent images of the target.

[0077] For example, the camera first acquires image 1, which covers the first 0-10 cm of the battery string. When the stringing equipment transports the first 10-20 cm of the battery string into the camera's field of view, the camera is triggered to acquire image 2, which also covers the first 10-20 cm of the battery string. When the stringing equipment transports the first 20-30 cm of the battery string into the camera's field of view, the camera is triggered to acquire image 3, which also covers the first 20-30 cm of the battery string. And so on, the camera continuously acquires multiple images to be detected.

[0078] To achieve the aforementioned synchronization control, the moving speed of the string welding equipment can be directly configured, and the interval between two adjacent data acquisitions can be configured on the camera. Alternatively, the string welding equipment and the camera can be controlled by a control device, such as controlling the moving speed of the string welding equipment and the interval between two adjacent data acquisitions from the camera. For example, assuming the camera's field of view is 10 centimeters and the interval between two adjacent data acquisitions from the camera is 1 second, then the moving speed of the string welding equipment needs to be controlled at 10 centimeters / 1 second.

[0079] For example, the camera's field of view can also be controlled to be greater than the width of the battery cell. For instance, if the width of the battery cell is M, the camera's field of view needs to be greater than M so that the image captured by the camera can include at least one battery cell. For example, if the width of the battery cell is 8 cm, the camera's field of view is 10 cm; if the width of the battery cell is 10 cm, the camera's field of view is 12 cm, and so on, as long as the camera's field of view is greater than M.

[0080] If the moving direction of the stringing equipment corresponds to the lateral direction, then the field of view of the camera is the lateral field of view. If the moving direction of the stringing equipment corresponds to the longitudinal direction (height direction), then the field of view of the camera is the longitudinal field of view. In other words, the field of view of the camera is the height field of view.

[0081] For example, the interval between two adjacent cells within the same battery string is M1 (i.e., the distance between the centers of two adjacent cells, which is used as the width of the cell). The interval between two adjacent cells in different battery strings is M2, and M1 is less than M2. In other words, the width of different cells may be different. Therefore, the field of view of the camera needs to be greater than the maximum width of the cell (such as M2).

[0082] Step 602: When the image to be detected is obtained, determine whether the image to be detected is a valid image.

[0083] If yes, proceed to step 603. For example, if the image to be detected is a valid image, it means that a battery cell exists in the image, and stitching and detection operations can be performed based on the image. If not, discard the image to be detected. For example, if the image to be detected is an invalid image, it means that a battery cell does not exist in the image, and stitching and detection operations cannot be performed based on the image, so discard the image.

[0084] For example, if the average brightness of the battery cell region in the image to be detected is less than the brightness threshold, and at least one of the following conditions is met: the image to be detected has a header feature and the image to be detected has a tail feature, then the image to be detected is a valid image; otherwise, if the average brightness of the battery cell region in the image to be detected is not less than the brightness threshold, the image to be detected does not have a header feature, and the image to be detected does not have a tail feature, then the image to be detected is an invalid image.

[0085] For instructions on how to determine the battery cell region within the image to be detected, please refer to the subsequent steps. After obtaining the battery cell region, the brightness values ​​of all pixels within the battery cell region are counted, and the average brightness value is calculated based on the brightness values ​​of all pixels. Then, the average brightness value is compared to see if it is less than a brightness threshold. This brightness threshold can be configured empirically and is not subject to any restrictions. Since the brightness of the battery cell region is relatively low, if the average brightness value is less than the brightness threshold, it indicates that the image quality of the image to be detected is good; conversely, if the average brightness value is not less than the brightness threshold, it indicates that the image quality of the image to be detected is poor.

[0086] For details on how to determine whether the image to be detected has a header feature and how to determine whether the image to be detected has a tail feature, please refer to the subsequent steps, which will not be repeated here.

[0087] For example, after obtaining the image to be detected, before determining whether the image to be detected is a valid image, the image to be detected can be preprocessed to determine whether the preprocessed image is a valid image. For example, noise removal, brightness enhancement, white balance removal, etc., can be performed on the image to be detected; there are no restrictions on this.

[0088] Step 603: When the image to be detected is obtained, determine whether the number of stitched images of the battery string image is 0.

[0089] For example, in the initial state, the number of images stitched together in the battery string image is a preset value (such as 0, hereinafter 0), indicating that the processing of the previous battery string has been completed, and the current battery string (i.e. the target battery string) has not yet been processed. The image to be detected is the first image of the target battery string.

[0090] Each time an image to be detected is obtained, the number of stitched images will be adjusted, that is, the number of stitched images will be increased by a certain value (such as 1, which will be used as an example in the following).

[0091] If the number of stitched images of the battery string is not 0, it means that when the image to be detected is obtained, the target battery string has already been processed, and the image to be detected is not the first image of the target battery string.

[0092] If so, that is, the number of images to be stitched is 0, then step 604 can be executed.

[0093] If not, i.e., the number of images to be stitched is not 0, then step 606 can be executed.

[0094] Step 604: Determine whether the image to be detected contains the string head feature of the target battery string.

[0095] For example, if the number of stitched images is 0, it indicates that the image to be detected is the first image of the target battery string, and it is necessary to determine whether the image to be detected has the string head feature of the target battery string. If the image to be detected has the string head feature of the target battery string, it is determined that the image to be detected is the first image of the target battery string, and step 605 is executed. If the image to be detected does not have the string head feature of the target battery string, it is determined that the image to be detected is not the first image of the target battery string, and the number of stitched images can remain at 0, waiting to obtain the next image to be detected. When the next image to be detected is obtained, steps 602 and 603 are repeated.

[0096] Step 605: Update the image to be detected to the battery string image of the target battery string, and update the number of stitched images to 1. A number of stitched images of 1 indicates that one image of the target battery string has been obtained.

[0097] For example, when the image to be detected is the first image of the target battery string, image stitching cannot be performed because the target battery string image has not yet been cached. Therefore, the image to be detected is directly updated to the target battery string image. In this case, considering that the image to be detected may not have complete battery cells (it may contain partial battery cells from the previous battery string and partial battery cells from the target battery string), detection is not performed based on the image to be detected; that is, the possibility of defects in the target battery string is not yet detected.

[0098] Furthermore, upon obtaining the first image of the target battery string, the number of stitched images can be updated to 1, and the process can wait to obtain the next image to be detected, repeating the above steps based on the next image to be detected.

[0099] Step 606: Determine whether the number of spliced ​​images of the battery string image has reached the number threshold.

[0100] For example, a quantity threshold can be pre-configured, which can be determined based on the configured maximum number of stitches. For example, the quantity threshold can be less than the maximum number of stitches, such as the difference between the maximum number of stitches and 1, or the difference between the maximum number of stitches and 2.

[0101] The maximum number of splices represents the total number of cells in the target battery string. For example, if the target battery string includes 15 cells, the maximum number of splices can be 15. Therefore, the number threshold can be 13 or 14.

[0102] When the image to be detected is obtained, if the number of stitched images has not reached the threshold, it means that the image to be detected will not be the last image of the target battery string. The process of obtaining the next image to be detected for the target battery string can continue, i.e., waiting to obtain the next image to be detected and repeating the above steps. Based on this, step 607 can be executed.

[0103] When the image to be detected is obtained, if the number of stitched images reaches the number threshold, it means that the image to be detected may be the last image of the target battery string. Based on this, step 610 can be executed.

[0104] Step 607: Stitch the image to be detected with the battery string image of the target battery string to obtain a stitched image, update the stitched image with the battery string image of the target battery string, and increment the number of stitched images by 1.

[0105] For example, when the first image to be detected of the target battery string is obtained, this image is updated to the battery string image a1 of the target battery string, and the number of stitched images is updated to 1. When the second image to be detected of the target battery string is obtained, this image is stitched with the battery string image a1 to obtain a stitched image, and the stitched image is updated to the battery string image a2 of the target battery string. The number of stitched images is incremented by 1, that is, the number of stitched images is 2, indicating that two images to be detected of the target battery string have been obtained.

[0106] When stitching the image to be detected with the battery string image a1, the image to be detected can be stitched after the battery string image a1, that is, serial stitching. Serial stitching can also be called hard stitching.

[0107] When the third image to be detected of the target battery string is obtained, the image to be detected is stitched together with the battery string image a2 to obtain a stitched image. The stitched image is then updated to the battery string image a3 of the target battery string, and the number of stitched images is updated to 3. Similarly, assuming the number threshold is 13, when the 13th image to be detected of the target battery string is obtained, the image to be detected is stitched together with the battery string image a12 to obtain a stitched image. The stitched image is then updated to the battery string image a13 of the target battery string, and the number of stitched images is updated to 13.

[0108] Step 608: When the stitched image is obtained, the battery cell sub-image is obtained from the stitched image. The battery cell sub-image may include the target battery cell, and the target battery cell is a complete battery cell that has not been detected.

[0109] For example, when the image to be detected is stitched together with the battery string image a1 to obtain the stitched image (battery string image a2), if the stitched image only includes one battery cell b1, then the battery cell sub-image c1 of battery cell b1 is obtained from the stitched image, that is, the target battery cell is battery cell b1. If the stitched image includes battery cell b1 and battery cell b2, then the battery cell sub-image c1 of battery cell b1 and the battery cell image c2 of battery cell b2 are obtained from the stitched image. The following example will be based on only including one battery cell b1.

[0110] When the image to be detected is stitched together with the battery string image a2 to obtain the stitched image (battery string image a3), if the stitched image includes battery cell b1 and battery cell b2, since battery cell b1 is a battery cell that has already been detected (i.e., the detection of battery cell b1 has been completed in the previous detection process), the target battery cell is battery cell b2. Thus, the battery cell sub-image c2 of battery cell b2 can be obtained from the stitched image.

[0111] Similarly, when the image to be detected is stitched together with the battery string image a12 to obtain the stitched image (battery string image a13), the battery cell sub-image c12 of battery cell b12 can be obtained from the stitched image.

[0112] For example, when obtaining a battery cell image from a stitched image, the stitched image can be input to a first target detection model, and the first target detection model can output the first predicted position of the main grid line region of the battery cell. The region corresponding to the first predicted position can be determined as the battery cell image.

[0113] For example, a first initial detection model can be obtained. This first initial detection model can be a deep learning model or other types of models. Training data can be used to train the first initial detection model to obtain a trained first object detection model. There are no restrictions on this training process.

[0114] Based on the trained first object detection model, when the stitched image is obtained, it can be input into the first object detection model. The first object detection model processes the stitched image to obtain the first predicted position of the main grid line region of the battery cell (i.e., the harpoon region), and outputs the first predicted position of the main grid line region of the battery cell. Assuming that the main grid line region of the battery cell is a rectangular region, the first predicted position can be the coordinates of the four corner points of the main grid line region, or the coordinates of one corner point plus the length and width of the main grid line region, or the coordinates of the center point plus the length and width of the main grid line region. There are no restrictions on the first predicted position, as long as it can represent the main grid line region of the battery cell.

[0115] After obtaining the first predicted position, the area corresponding to the first predicted position (such as the area of ​​the main grid line of the battery cell corresponding to the coordinates of the four corner points) can be determined as the battery cell image.

[0116] When the stitched image includes multiple battery cells, the first target detection model can output multiple first predicted positions. The last first predicted position can be selected from the multiple first predicted positions. The last first predicted position corresponds to the battery cell sub-image of the target battery cell, which is the battery cell image that has not yet been detected, while the previous first predicted positions correspond to the battery cell images of the battery cells that have been detected.

[0117] In the above embodiments, it is involved to determine the battery cell region within the image to be detected. Based on this, the image to be detected can be input to a first target detection model, and the first target detection model outputs the first predicted position of the main grid line region of the battery cell. The region corresponding to the first predicted position can be determined as the battery cell region.

[0118] Step 609: Perform defect detection on the target battery cell based on the battery cell image.

[0119] For example, after obtaining image c1 of the battery cell, defect detection can be performed on the target battery cell b1 based on image c1, such as detecting whether the target battery cell b1 has defects such as appearance damage, dirt, poor welding quality, abnormal shape (such as bending), and abnormal cell spacing. After obtaining image c2 of the battery cell, defect detection can be performed on the target battery cell b2 based on image c2, and so on.

[0120] For example, when performing defect detection on a target battery cell, a sub-image of the battery cell can be input into a second target detection model, which then outputs a second predicted location and a predicted category. The region corresponding to this second predicted location can be identified as the defect region of the battery cell sub-image (i.e., the defect region contains a defect), and the defect type of the defect region can be determined based on the predicted category. In addition to the second predicted location and predicted category, the second target detection model can also output the size of the defect region.

[0121] For example, a second initial detection model can be obtained. This second initial detection model can be a deep learning model, a neural network, or other types of models. Training data can be used to train the second initial detection model to obtain a trained second object detection model. There are no restrictions on this training process.

[0122] Based on the trained second object detection model, when a battery cell image is obtained, it can be input into the second object detection model, which can then process the image. If a defect exists in the battery cell image, the second object detection model can obtain a second predicted location and predicted category, and output these two values. If no defect exists in the battery cell image, the second object detection model can output a detection result indicating that no defect exists.

[0123] Assuming the defect area in the battery cell image is rectangular, the second predicted position can be the coordinates of the four corner points of the defect area, the coordinates of one corner point plus its length and width, or the coordinates of the center point plus its length and width. There are no restrictions, as long as it represents the defect area. The predicted category can indicate the defect type of the defect area. For example, a prediction category of 1 indicates that the defect area has an external damage defect; a prediction category of 2 indicates that the defect area has an external dirt defect; a prediction category of 3 indicates that the defect area has a poor welding quality defect, and so on.

[0124] After obtaining the second predicted position and the predicted category, the area corresponding to the second predicted position (such as the main grid line area of ​​the battery cell corresponding to the coordinates of the four corner points) can be identified as the defect area of ​​the battery cell sub-image. Then, the defect type of the defect area can be determined based on the predicted category.

[0125] For example, after obtaining the battery cell image and inputting it into the second target detection model, image preprocessing can be performed on the battery cell image. The preprocessed image can then be input into the second target detection model. Image preprocessing enhances the image features of the battery string and reduces interference from other contaminants on the battery string. For example, noise removal, brightness enhancement, and white balance removal can be performed on the battery cell image; there are no limitations on this.

[0126] For example, besides inputting the battery cell image into the second target detection model, the battery cell image can also be directly analyzed to determine whether the target battery cell has defects. For instance, the distance between the target battery cell and its adjacent cells can be statistically analyzed based on the battery cell image; if this distance is greater than a threshold, it indicates that the target battery cell has a defect. This is just one example. In summary, a combination of model-based and non-model-based methods can be used for defect detection.

[0127] For example, in the above method, a sliding window detection method of simultaneous stitching and detection is adopted (using a dynamic window of variable length to perform complete battery cell appearance detection on the battery string). That is, when a stitched image of a portion of the images to be detected is obtained, the battery cell images are directly obtained from the stitched image, and detection is performed based on the battery cell images, instead of obtaining the battery cell images from the stitched image only when all the images to be detected are obtained. For instance, when the image to be detected is stitched with the battery string image a1 to obtain the stitched image, the battery cell image c1 is directly obtained for detection. When the image to be detected is stitched with the battery string image a2 to obtain the stitched image, the battery cell image c2 is directly obtained for detection.

[0128] By adopting a sliding window inspection method that involves simultaneous splicing and inspection, the appearance inspection of battery strings of various sizes can be applied (i.e., different battery strings can have different sizes). While collecting data from the battery strings, the appearance inspection of the battery strings is carried out simultaneously, which effectively shortens the inspection time and improves the inspection efficiency and real-time performance.

[0129] Step 610: Determine whether the image to be detected has the tail feature of the target battery string.

[0130] For example, if the number of stitched images reaches a threshold, it indicates that the image to be detected may be the last image of the target battery string, and it is necessary to determine whether the image to be detected has the tail feature of the target battery string. If the image to be detected has the tail feature of the target battery string, it is determined that the image to be detected is the last image of the target battery string, and step 611 is executed. If the image to be detected does not have the tail feature of the target battery string, it is determined that the image to be detected is not the last image of the target battery string, and step 607 is executed, that is, the image to be detected is stitched with the battery string image of the target battery string to obtain a stitched image, the stitched image is updated to the battery string image of the target battery string, the number of stitched images is incremented by 1, the battery cell image is obtained from the stitched image, and defect detection of the target battery cell is performed based on the battery cell image.

[0131] Step 611: If the tail signal is present, determine whether the tail signal has been received.

[0132] For example, a control device (such as a PLC) is used to control the stringing equipment and can determine which cell the stringing equipment is delivering to the camera's field of view. If the control device determines that the stringing equipment is delivering the last cell of the target cell string to the camera's field of view, it sends a string tail signal to the cell string detection device, and the string tail signal indicates that the last cell of the target cell string has been delivered to the camera's field of view.

[0133] When a tail-end feature is present, the battery string detection device determines whether a tail-end signal has been received. If a tail-end signal is received, it confirms that the image to be detected is the last image of the target battery string. That is, through double confirmation (tail-end feature + tail-end signal), it is determined that the image to be detected is the last image of the target battery string, and step 612 is executed. If a tail-end signal is not received, it is confirmed that the image to be detected is not the last image of the target battery string. That is, the results of the tail-end feature and the tail-end signal are inconsistent. Therefore, an error message can be output. This error message indicates that the results of the tail-end feature and the tail-end signal are inconsistent, and the user needs to repair the tail-end logic or the string welding control device. This embodiment does not limit this repair process.

[0134] Step 612: Stitch the image to be detected with the battery string image of the target battery string to obtain a stitched image, update the stitched image to the complete battery string image of the target battery string, and output the complete battery string image. Additionally, obtain battery cell images from the stitched image, which may include the target battery cell, and perform defect detection on the target battery cell based on the battery cell images.

[0135] For example, if the image to be detected is the last image of the target battery string, then after obtaining the stitched image, the stitched image is the complete battery string image for the target battery string. This complete battery string image can be cached. See [link to documentation]. Figure 3A or Figure 3B The image shown is a schematic diagram of the complete battery string.

[0136] After obtaining the stitched image, the battery cell images can be obtained from the stitched image, and the target battery cell can be defect-detected based on the battery cell images, see steps 308 and 309.

[0137] For example, after obtaining the complete battery string image and the defect detection results of each battery cell, a sub-image of each battery cell can be determined from the complete battery string image (the sub-image of each battery cell has already been obtained during the defect detection process, i.e., the aforementioned battery cell sub-image). Thus, for each battery cell, the defect detection result of that battery cell is added to the sub-image of that battery cell. The defect detection result can indicate whether the battery cell has a defect. If a defect exists, it can also indicate the defect area and defect type.

[0138] For example, if the image to be detected is the last image of the target battery string, the number of stitched images can be updated to 0, and then the process can return to step 602, that is, repeat the above steps based on the image to be detected.

[0139] Clearly, this image to be detected serves as the last image in the target battery string, completing the image stitching of the target battery string. Furthermore, this image to be detected can also serve as the first image in the stitching process of the next battery string; in the stitching process of the next battery string, this image to be detected needs to be used as the first image for stitching.

[0140] In one possible implementation, after obtaining the image to be detected, it can be determined whether the image to be detected contains the head feature of the target battery string, or whether it contains the tail feature of the target battery string. To determine whether the image to be detected contains the head and tail features of the target battery string, the following method can be used: edge pixels of the target battery string can be identified from the image to be detected. For example, the features of edge pixels (such as brightness features, texture features, gradient features, etc., without limitation on the type of feature) are different from the features of non-edge pixels. Therefore, for each pixel in the image to be detected, if the feature of the pixel is similar to the feature of an edge pixel, then the pixel is identified as an edge pixel; if the feature of the pixel is similar to the feature of a non-edge pixel, then the pixel is identified as a non-edge pixel. In this way, the edge pixels of the target battery string are identified from the image to be detected.

[0141] If a first edge line and a second edge line are fitted based on these edge pixels, and the distance between the first edge line and the second edge line is greater than a distance threshold (which can be configured empirically), and the average brightness of the transition region between the first edge line and the second edge line is greater than a first brightness threshold, and the average brightness of the battery cell region in the image to be detected is less than a second brightness threshold (which can be less than the first brightness threshold), then it is determined that the image to be detected has string start and string end features. The first edge line (the edge line at the front of the image) is the string end line of the previous battery cell, and the second edge line (the edge line at the back of the image) is the string start line of the next battery cell. For example, if the image to be detected has string start and string end features, then the image to be detected has the string end line of the previous battery cell and the string start line of the next battery cell. Based on this, if two edge lines cannot be fitted based on these edge pixels, it is determined that the image to be detected does not have string start and string end features.

[0142] If two edge lines are fitted based on these edge pixels, namely the first edge line and the second edge line, considering that the distance between the tail line of the previous battery string and the head line of the next battery string is large, it is necessary to determine whether the distance between the first edge line and the second edge line is greater than the distance threshold. If not, it is determined that the image to be detected does not have head and tail features.

[0143] If the distance between the first edge line and the second edge line is greater than a distance threshold, considering that the average brightness of the transition region (the area between the two battery strings) between the first edge line and the second edge line is relatively large, the brightness value of each pixel in the transition region between the first edge line and the second edge line can be statistically analyzed, and the average brightness value of these pixels can be calculated. If the average brightness value is not greater than the first brightness threshold, it is determined that the image to be detected does not have string beginning or string end features.

[0144] If the average brightness value is greater than the first brightness threshold, considering that the average brightness value of the battery cell region (i.e., the region where the battery cell is located) is relatively small, the brightness value of each pixel in the battery cell region of the image to be detected can also be counted, and the average brightness value of these pixels can be calculated. If the average brightness value of the battery cell region is not less than the second brightness threshold, it is determined that the image to be detected does not have header or tail features.

[0145] If the average brightness of the battery cell area is less than the second brightness threshold, then it is finally determined that the image to be detected has a string head feature and a string tail feature. That is, the first edge line is the string tail line of the previous battery string, and the second edge line is the string head line of the next battery string.

[0146] In one possible implementation, the default value of the tail signal is 0, indicating that no tail signal has been received. When a tail feature is present, the battery string detection device determines whether a tail signal has been received. If a tail signal is received, its value is changed to 1, indicating that a tail signal has been received. After outputting the complete battery string image, the value of the tail signal is changed back to 0, indicating that no tail signal has been received.

[0147] In one possible implementation, the battery string detection device can maintain a small image detection queue and a full string image queue. When an image to be detected is obtained, if the number of stitched images in the small image detection queue is 0, the image to be detected is stored in the small image detection queue. When an image to be detected is obtained, if the number of stitched images in the small image detection queue is 1, the image to be detected is stored in the small image detection queue. When an image to be detected is obtained, if the number of stitched images in the small image detection queue is 2, it is determined whether the current image in the small image detection queue is a valid image. If yes, the second image to be detected in the small image detection queue is stored in the full string image queue, and the small image detection queue is cleared. If no, the first image to be detected in the small image detection queue is removed. When an image to be detected is obtained, if the number of stitched images is greater than or equal to 3, the image to be detected is stored in the full string image queue, and so on, until the number of stitched images is 0.

[0148] By maintaining a small image detection queue and a full image queue, image stitching and defect detection are not performed on the images to be detected in the small image detection queue. For the images to be detected in the full image queue, image stitching and defect detection are performed, and the image stitching and defect detection process can be found in the above embodiment.

[0149] In one possible implementation, see Figure 7 The diagram shown illustrates the process of battery string splicing. In battery string inspection, the splicing method plays a crucial role in ensuring the integrity of the battery string.

[0150] Step 701: Determine if the serial header flag signal is true. If not, i.e., the serial header flag signal is false, then proceed to step 702; if yes, then proceed to step 705.

[0151] Step 702: Determine whether the number of images in the small image detection image queue is equal to 2.

[0152] If yes, then proceed to step 703; if no, then proceed to step 704.

[0153] Step 703: The image queue is entered into the small image detection process based on the small image detection.

[0154] In the small image detection process, it is determined whether the image to be detected in the small image detection image queue is a valid image. If so, the currently acquired image to be detected is added to the entire image queue. If the small image stitching image only contains the beginning feature, the entire image queue is cleared, two images are added to the small image detection image queue, the small image detection image queue is cleared again, the beginning flag signal is set to true, and the current small image stitching process ends. Alternatively, if the small image stitching image has no beginning or end features, the first image in the small image detection image queue is removed, and the current small image stitching process ends. Alternatively, if the small image stitching image contains the end feature, the small image detection image queue is cleared, the last image in the entire image queue is retained, and the current small image stitching process ends.

[0155] If not, remove the first image from the small image detection image queue and end the current small image stitching process.

[0156] Step 704: Add the currently acquired image to be detected to the small image detection image queue.

[0157] Step 705: Add the currently acquired image to be detected to the entire image queue.

[0158] Step 706: Determine if the total number of images in the entire image queue is less than a quantity threshold. For example, this quantity threshold could be the difference between the maximum number of images to be stitched and 2, where the maximum number of images to be stitched represents the total number of battery cells in the target battery string. If yes, proceed to step 707; otherwise, end the processing flow.

[0159] Step 707: Set the serial head flag signal to False, that is, the serial head flag signal is not true, add the currently acquired image to be detected to the small image detection image queue, and end the processing flow.

[0160] As can be seen from the above technical solutions, in this embodiment, defects in battery strings are detected through images, enabling rapid and accurate defect detection for both ultra-long and standard-length battery strings. This avoids the subjectivity and errors of manual visual inspection, effectively improving detection quality and efficiency, reducing labor costs, and eliminating the need for contact with the battery strings during the detection process, thus achieving non-destructive testing. Employing a "sliding window" dynamic area detection and machine vision-based non-destructive testing method, and using a sliding window detection approach that inspects while assembling, it is applicable to the appearance inspection of battery strings of various sizes. While collecting data from the battery strings, appearance inspection is performed simultaneously, effectively shortening the inspection time and improving detection efficiency and real-time performance. It can automatically identify and judge the appearance defects of battery strings according to user-defined battery string standards, achieving rapid and accurate defect detection. Clearly displaying battery string images and statistically analyzing the detection results helps determine the source and cause of defects, reducing production costs, increasing capacity, and promoting technological advancement. By identifying the splicing method of the battery string heads and tails, stable splicing of battery strings is achieved, preventing incorrect or missing splices.

[0161] Based on the same concept as the above method, this application proposes a battery string detection device, wherein the target battery string includes at least one battery cell, see [link to relevant documentation]. Figure 8 The diagram shows the structure of the device, which may include: an acquisition module 81, used to acquire an image to be inspected captured during the transmission of the target battery string; a stitching module 82, used to stitch the image to be inspected with an image of the target battery string in response to acquiring the image to be inspected, wherein the battery string image is formed by stitching together the images to be inspected captured during the transmission of the target battery string; acquiring a battery cell image from the stitched image, wherein the battery cell image includes a target battery cell, which is an uninspected battery cell; and a detection module 83, used to perform defect detection on the target battery cell based on the battery cell image.

[0162] For example, the image to be detected includes an image of the upper surface of the target battery string acquired by the front camera and / or an image of the lower surface of the target battery string acquired by the back camera; the front camera is located above the target battery string and the back camera is located below the target battery string;

[0163] The image to be detected on the upper surface is used to detect defects on the upper surface of the target battery string; the image to be detected on the lower surface is used to detect defects on the lower surface of the target battery string.

[0164] For example, the acquisition module 81 is further configured to acquire front detection data of the upper surface of the target battery string, the front detection data including information on whether there are defects on the upper surface of the target battery string, and if there are defects on the upper surface, the front detection data also includes the defect type and defect area of ​​the upper surface of the target battery string; acquire back detection data of the lower surface of the target battery string, the back detection data including information on whether there are defects on the lower surface of the target battery string, and if there are defects on the lower surface, the back detection data also includes the defect type and defect area of ​​the lower surface of the target battery string; summarize the front detection data and the back detection data to obtain the appearance detection data of the target battery string, so that the user can manually inspect whether there are defects in the target battery string based on the appearance detection data, and obtain the manual inspection result of the target battery string.

[0165] For example, the acquisition module 81 is further configured to acquire the defect detection result of the target battery string after performing defect detection on the target battery cell based on the battery cell image, the defect detection result including at least one of the following: the result obtained when performing defect detection on the target battery cell based on the battery cell image, front detection data, back detection data, appearance detection data, and manual inspection result; and generate a movement control command based on the defect detection result, the movement control command being used to control the flow direction of the target battery string to the direction corresponding to the defect detection result.

[0166] For example, during the transport of multiple battery strings, each battery string passes through the field of view of the camera in sequence. The target battery string is any battery string. When the target battery string passes through the field of view of the camera, the camera acquires an image of the target battery string to be detected.

[0167] For example, when the stitching module 82 stitches the image to be detected with the battery string image of the target battery string to obtain a stitched image, it is specifically used to: determine whether the number of stitched images of the battery string image is 0; if yes, and the image to be detected has the string head feature of the target battery string, then the image to be detected is updated to the battery string image of the target battery string, and the number of stitched images is updated to 1; if no, and the number of stitched images has not reached the number threshold, then the image to be detected is stitched with the battery string image of the target battery string to obtain a stitched image, and the stitched image is updated to the battery string image of the target battery string, and the number of stitched images is incremented by 1; wherein, the number threshold is determined based on the configured maximum number of stitches.

[0168] For example, the stitching module 82 is further configured to, after determining whether the number of stitched images of the battery string image is 0, if not, and the number of stitched images reaches the number threshold, determine whether the image to be detected has the tail feature of the target battery string; if the tail feature does not exist, stitch the image to be detected with the battery string image of the target battery string to obtain a stitched image, update the stitched image to the battery string image of the target battery string, and increment the number of stitched images by 1; if the tail feature exists, stitch the image to be detected with the battery string image of the target battery string to obtain a stitched image, update the stitched image to the complete battery string image of the target battery string, output the complete battery string image, and update the number of stitched images to 0.

[0169] For example, the stitching module 82 is further configured to, before updating the stitched image to a complete battery string image of the target battery string and outputting the complete battery string image, determine whether a tail signal is received if a tail feature exists. The tail signal indicates that the last battery cell of the target battery string has been transported to the field of view of the camera. If yes, the operation of updating the stitched image to a complete battery string image of the target battery string and outputting the complete battery string image is performed. If no, an error message is output. After updating the stitched image to a complete battery string image of the target battery string and outputting the complete battery string image, a sub-image of each battery cell is determined from the complete battery string image, and the defect detection result of the battery cell is added to the sub-image of the battery cell.

[0170] For example, the stitching module 82 is further configured to determine whether the image to be detected is a valid image before stitching the image to be detected with the battery string image of the target battery string to obtain a stitched image; if the image to be detected is a valid image, then the operation of stitching the image to be detected with the battery string image of the target battery string to obtain a stitched image is performed; if the image to be detected is an invalid image, then the image to be detected is discarded; wherein, if the average brightness of the battery cell area in the image to be detected is less than a brightness threshold, and at least one of the following is true: the image to be detected has a string head feature and the image to be detected has a string tail feature, then the image to be detected is a valid image; otherwise, the image to be detected is an invalid image.

[0171] For example, the stitching module 82 is further configured to determine edge pixels of the target battery string from the image to be detected; if a first edge line and a second edge line are fitted based on the edge pixels, the distance between the first edge line and the second edge line is greater than a distance threshold, the average brightness of the transition region between the first edge line and the second edge line is greater than a first brightness threshold, and the average brightness of the battery cell region in the image to be detected is less than a second brightness threshold, then it is determined that the image to be detected has string head features and string tail features; wherein, the second brightness threshold is less than the first brightness threshold.

[0172] Based on the same concept as the above method, this application proposes an electronic device, see [link to previous application]. Figure 9 As shown, the electronic device includes a processor 91 and a machine-readable storage medium 92, the machine-readable storage medium 92 storing machine-executable instructions that can be executed by the processor 91; the processor 91 is used to execute the machine-executable instructions to implement the battery string detection method disclosed in the above example of this application.

[0173] Based on the same application concept as the above method, this application embodiment also provides a battery string detection system, including: an image acquisition device, a battery string detection device, a control device, a MES device, and a centralized control device; wherein: the image acquisition device is used to acquire an image to be detected during the transmission of the target battery string; the battery string detection device is used to execute the battery string detection method of the above example based on the image to be detected to obtain a defect detection result corresponding to the target battery string; the control device is used to control the transmission device and the image acquisition device; the MES device is used to acquire the defect detection result corresponding to the target battery string and process the target battery string based on the defect detection result; the centralized control device is used to acquire the defect detection result corresponding to the target battery string so that a user can manually detect whether the target battery string has defects based on the defect detection result, obtain the manual detection result of the target battery string, and return the manual detection result to the battery string detection device.

[0174] Based on the same concept as the above method, this application also provides a machine-readable storage medium storing a plurality of computer instructions, which, when executed by a processor, can implement the battery string detection method disclosed in the above examples of this application.

[0175] The aforementioned machine-readable storage medium can be any electronic, magnetic, optical, or other physical storage device that can contain or store information, such as executable instructions, data, etc. For example, machine-readable storage media can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0176] Based on the same application concept as the above method, this application embodiment also provides a computer program product, which may include a computer program. When the computer program is executed by a processor, it implements the battery string detection method disclosed in the above examples of this application.

[0177] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0178] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for detecting battery strings, characterized in that, The target battery string includes at least one battery cell, and the method includes: Acquire the image to be detected captured during the transmission of the target battery string; The method further includes determining whether the image to be detected is a valid image; wherein, if the average brightness of the battery cell region within the image to be detected is less than a brightness threshold, and at least one of the following conditions is met: the image to be detected has a string beginning feature and a string end feature, then the image to be detected is a valid image; otherwise, the image to be detected is an invalid image; wherein, the method further includes: determining edge pixels of the target battery string from the image to be detected; if a first edge line and a second edge line are fitted based on the edge pixels, the distance between the first edge line and the second edge line is greater than a distance threshold, the average brightness of the transition region between the first edge line and the second edge line is greater than a first brightness threshold, and the average brightness of the battery cell region within the image to be detected is less than a second brightness threshold, then it is determined that the image to be detected has string beginning and string end features; wherein, the second brightness threshold is less than the first brightness threshold; If the image to be detected is invalid, then the image to be detected is discarded; If the image to be detected is a valid image, in response to acquiring the image to be detected, the image to be detected is stitched together with the battery string image of the target battery string to obtain a stitched image. The battery string image is stitched together from the image to be detected captured during the transmission of the target battery string. The battery cell image is obtained from the stitched image, the battery cell image including the target battery cell, the target battery cell being the undetected battery cell; Defect detection is performed on the target battery cell based on the battery cell image.

2. The method according to claim 1, characterized in that, The image to be detected includes the image to be detected of the upper surface of the target battery string acquired by the front camera and / or the image to be detected of the lower surface of the target battery string acquired by the back camera; the front camera is located above the target battery string and the back camera is located below the target battery string; The image to be detected on the upper surface is used to detect defects on the upper surface of the target battery string; the image to be detected on the lower surface is used to detect defects on the lower surface of the target battery string.

3. The method according to claim 2, characterized in that, The method further includes: Obtain front detection data of the upper surface of the target battery string. The front detection data includes information on whether there are defects on the upper surface of the target battery string. If there are defects on the upper surface, the front detection data also includes the defect type and defect area of ​​the upper surface of the target battery string. Obtain reverse detection data of the lower surface of the target battery string. The reverse detection data includes information on whether there are defects on the lower surface of the target battery string. If there are defects on the lower surface, the reverse detection data also includes the defect type and defect area of ​​the lower surface of the target battery string. The front and back inspection data are summarized to obtain the appearance inspection data of the target battery string, so that the user can manually inspect the target battery string for defects based on the appearance inspection data and obtain the manual inspection results of the target battery string.

4. The method according to any one of claims 1-3, characterized in that, After performing defect detection on the target battery cell based on the battery cell sub-image, the method further includes: Obtain the defect detection results of the target battery string, the defect detection results including at least one of the following: the results obtained when performing defect detection on the target battery cell based on the battery cell sub-image, front detection data, back detection data, appearance detection data, and manual inspection results; Based on the defect detection results, operation control instructions are generated, which are used to control the flow direction of the target battery string to the direction corresponding to the defect detection results.

5. The method according to claim 1, characterized in that, During the transport of multiple battery strings, each battery string passes through the field of view of the camera in sequence. The target battery string is any battery string. When the target battery string passes through the field of view of the camera, the camera acquires an image of the target battery string to be detected. The step of stitching the image to be detected with the battery string image of the target battery string to obtain the stitched image includes: Determine if the number of stitched images in the battery string image is 0; If so, and the image to be detected contains the string head feature of the target battery string, then the image to be detected is updated to the battery string image of the target battery string, and the number of stitched images is updated to 1; If not, and the number of stitched images does not reach the threshold, then the image to be detected is stitched with the battery string image of the target battery string to obtain a stitched image, and the stitched image is updated to the battery string image of the target battery string, and the number of stitched images is incremented by 1; The quantity threshold is determined based on the configured maximum number of splices.

6. The method according to claim 5, characterized in that, After determining whether the number of stitched images of the battery string image is 0, the method further includes: If not, and the number of stitched images reaches the threshold, then it is determined whether the image to be detected has the tail feature of the target battery string; if the tail feature does not exist, then the image to be detected is stitched with the battery string image of the target battery string to obtain a stitched image, the stitched image is updated to the battery string image of the target battery string, and the number of stitched images is incremented by 1. If a tail feature exists, the image to be detected is stitched together with the battery string image of the target battery string to obtain a stitched image. The stitched image is then updated to the complete battery string image of the target battery string, the complete battery string image is output, and the number of stitched images is updated to 0.

7. The method according to claim 6, characterized in that, Before updating the stitched image to a complete battery string image of the target battery string and outputting the complete battery string image, the method further includes: if a tail-of-string feature exists, determining whether a tail-of-string signal is received, the tail-of-string signal indicating that the last battery cell of the target battery string has been transported to the field of view of the camera; if yes, then performing the operation of updating the stitched image to a complete battery string image of the target battery string and outputting the complete battery string image; if no, then outputting an error message. After updating the stitched image to a complete battery string image of the target battery string and outputting the complete battery string image, the method further includes: determining a sub-image of each battery cell from the complete battery string image, and adding the defect detection result of the battery cell to the sub-image of the battery cell.

8. A detection device for battery strings, characterized in that, The target battery string includes at least one battery cell, and the device includes: The acquisition module is used to acquire the image to be detected captured during the transmission of the target battery string; A stitching module is used to determine whether the image to be detected is a valid image. If the image to be detected is a valid image, in response to acquiring the image to be detected, the image to be detected is stitched together with the battery string image of the target battery string to obtain a stitched image. The battery string image is stitched together from the images to be detected captured during the transmission of the target battery string. Battery cell images are obtained from the stitched image. The battery cell images include target battery cells, which are undetected battery cells. If the image to be detected is an invalid image, it is discarded. Wherein, if the average brightness of the battery cell region within the image to be detected is less than a brightness threshold, the image to be detected has string head features and the image to be detected... If at least one of the following features is present, the image to be detected is a valid image; otherwise, the image to be detected is an invalid image. The stitching module is further configured to determine the edge pixels of the target battery string from the image to be detected. If a first edge line and a second edge line are fitted based on the edge pixels, and the distance between the first edge line and the second edge line is greater than a distance threshold, the average brightness of the transition region between the first edge line and the second edge line is greater than a first brightness threshold, and the average brightness of the battery cell region within the image to be detected is less than a second brightness threshold, then it is determined that the image to be detected possesses both a string beginning feature and a string end feature; wherein the second brightness threshold is less than the first brightness threshold. The detection module is used to perform defect detection on the target battery cell based on the battery cell image.

9. A battery string detection system, characterized in that, include: Image acquisition equipment, battery string detection equipment, control equipment, MES equipment, and centralized control equipment; among which: The image acquisition device is used to acquire images to be detected during the transmission of the target battery string; The battery string detection device is used to execute the method according to any one of claims 1-7 based on the image to be detected, and obtain the defect detection result corresponding to the target battery string; The control device is used to control the transmission device and the image acquisition device; The MES device is used to acquire the defect detection results corresponding to the target battery string, and process the target battery string based on the defect detection results; The centralized control device is used to acquire the defect detection results corresponding to the target battery string, so that the user can manually detect whether the target battery string has defects based on the defect detection results, obtain the manual detection results of the target battery string, and return the manual detection results to the battery string detection device.

Images