Battery tray inner cavity defect detection system and method

By combining machine vision technology and a line laser profilometer with machine learning, high-precision and rapid detection of the inner surface of the battery tray has been achieved, solving the problems of low efficiency and large error in existing technologies and improving detection efficiency and data recording capabilities.

CN120900968APending Publication Date: 2025-11-07DONGGUAN UNIV OF TECH +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511112404.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-08-08
Publication Date
2025-11-07

Smart Images

  • Figure CN120900968A_ABST
    Figure CN120900968A_ABST
Patent Text Reader

Abstract

The invention provides a battery tray inner cavity defect detection system and method, and relates to the technical field of battery manufacturing and quality control, the detection system comprises a rack and a Y-axis conveying mechanism arranged on the rack, and the Y-axis conveying mechanism is provided with a clamp used for fixing a battery tray; the code scanner and the plane image collector are arranged on the rack, the code scanner is used for scanning a two-dimensional code of a battery tray fixed on the clamp so as to carry out identity recognition, and the plane image collector is used for collecting appearance image data of the battery tray; a wired laser profile measuring instrument is arranged on the rack and is used for emitting a laser beam and receiving a reflected light signal so as to reconstruct a three-dimensional profile of the surface of the inner cavity of the battery tray. The device has the advantages of being high in precision, high in efficiency, easy to integrate and the like, and the defects of protrusions, recesses, aluminum scraps and the like in the battery tray can be detected; and the detection time of a single product is shortened.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the field of battery manufacturing and quality control, and discloses an automatic detection equipment based on machine vision technology for detecting micro defects on the inner cavity surface of a battery tray. BACKGROUND

[0002] With the rapid development of emerging industries such as new energy vehicles and energy storage systems, the market demand for high-performance and high-safety batteries continues to grow. As an important structural component of battery assemblies, the battery tray not only bears the load and fixation function of the battery module, but also plays a role in heat management, sealing protection and structural support to a certain extent. Therefore, its manufacturing quality directly affects the overall performance and safety of the battery system.

[0003] During the processing of the battery tray, due to the influence of machining process, material properties or environmental factors, defects such as small protrusions, depressions, scratches and aluminum residue may occur on the inner cavity surface. If these defects are not detected and effectively treated in time, they may pierce the battery pack or cause local stress concentration during subsequent battery assembly and use, thereby leading to a decline in battery performance, and in severe cases, may even cause thermal runaway, fire or explosion accidents. Therefore, ensuring the integrity and cleanliness of the inner cavity surface of the battery tray is an important prerequisite for ensuring the safe operation of the battery system.

[0004] Currently, the detection of defects in the battery tray still mainly relies on manual visual inspection or simple magnifying tool assisted observation. Such detection methods not only have low efficiency, but also have large subjective errors, and are prone to miss or misjudge due to the experience, fatigue level or environmental light of the operator, which is difficult to meet the large-scale and high-precision production detection requirements. In addition, traditional detection methods cannot realize automatic recording and analysis of defect data, which is not conducive to the traceability management of product quality.

[0005] In order to improve the detection accuracy and efficiency, it is urgent to develop an equipment that can automatically, quickly and accurately detect the micro defects on the inner cavity surface of the battery tray, so as to effectively improve the quality control level in the battery manufacturing process and meet the urgent needs of the new energy industry for high-quality battery assemblies. SUMMARY

[0006] The present application overcomes the shortcomings of the prior art and provides a battery tray inner cavity defect detection system and method, which has high precision, high efficiency and is easy to integrate, can detect defects such as protrusions, depressions and aluminum residue inside the battery tray, and shortens the detection time of single product.

[0007] To solve the above technical problems, the present application is realized by the following technical scheme:

[0008] A battery tray inner cavity defect detection system, comprising a rack and a Y-axis conveying mechanism arranged on the rack, wherein a clamp for fixing a battery tray is arranged on the Y-axis conveying mechanism;

[0009] Further comprising a code scanner and a planar image collector arranged on the rack, wherein the code scanner is used for scanning a two-dimensional code of the battery tray fixed on the clamp for identity recognition, and the planar image collector is used for collecting appearance image data of the battery tray;

[0010] A line laser profilometer is arranged on the rack, which is used for emitting a laser beam and receiving a reflected light signal to reconstruct a three-dimensional profile of the inner cavity surface of the battery tray; further comprising a moving mechanism for driving the line laser profilometer to perform three-dimensional scanning, wherein the moving mechanism comprises an X-axis scanning feeding device mounted on the rack, a lifting module arranged on the X-axis scanning feeding device and driven to move along the X-axis by the X-axis scanning feeding device, and a rotating module arranged on the lifting module and connected with the line laser profilometer and driven to rotate around its own axis by the rotating module; the battery tray is driven by the Y-axis conveying mechanism to sequentially pass through the working areas of the code scanner and the planar image collector; the line laser profilometer is driven by the moving mechanism to realize scanning coverage of the inner cavity surface of the battery tray, and the scanning angle is adjusted by the rotation of the rotating module to adapt to the measurement of the edge area of the workpiece.

[0011] Further, a host computer and a PLC control system are further included, wherein the host computer is in communication connection with the PLC control system, and the PLC control system is used for controlling the actions of the Y-axis conveying mechanism and the X-axis scanning feeding device.

[0012] Further, a data acquisition and processing system is further included, wherein the data acquisition and processing system is in communication connection with the line laser profilometer through Ethernet, and is used for receiving, storing and processing the three-dimensional point cloud measurement data acquired by the line laser profilometer.

[0013] Further, the Y-axis conveying mechanism is a ball screw transmission module driven by a servo motor; and the X-axis scanning feeding device is a linear motor driving module.

[0014] Further, the Y-axis conveying mechanism is provided with two independent stations, each of which is provided with the clamp; and the line laser profilometer moves between the two stations through the X-axis scanning feeding device to realize a parallel operation mode in which the battery tray on one station is detected while the other station is performing loading or unloading operation.

[0015] Further, the rotation module drives the rotation angle of the line laser profile measuring instrument to be 0°-180°, so as to realize the segmented scanning of the edge region of the inner cavity of the battery tray.

[0016] The application also claims a battery tray inner cavity defect detection method based on the battery tray inner cavity defect detection system, comprising the following steps:

[0017] (a) fixing the battery tray to be detected on the clamp of the Y-axis conveying mechanism, and starting the detection process;

[0018] (b) driving the Y-axis conveying mechanism to move the battery tray to the code scanning station, scanning the tray two-dimensional code by the code scanner to complete the identity recognition, and then moving to the image acquisition station to acquire the appearance image data of the tray by the planar image acquisition device;

[0019] (c) driving the line laser profile measuring instrument to perform three-dimensional scanning on the inner cavity surface of the battery tray, and synchronously returning the acquired three-dimensional point cloud data to the data acquisition and processing system;

[0020] (d) performing filtering and denoising, coordinate transformation processing on the received three-dimensional point cloud data, converting the point cloud data from the sensor coordinate system to the reference coordinate system established based on the reference plane of the battery tray, and extracting the height distribution characteristics of the inner cavity surface based on the reference plane;

[0021] (e) inputting the height distribution characteristics into the pre-trained machine learning classification model, identifying the defect type of the inner cavity surface, and outputting the defect detection evaluation result;

[0022] (f) after the detection is completed, driving the Y-axis conveying mechanism to return the battery tray to the initial position or move out of the station.

[0023] Further, in step (c), when the line laser profile measuring instrument scans to the edge region of the inner cavity of the battery tray, the rotation module is controlled to drive the line laser profile measuring instrument to rotate by a preset angle, so as to complete the full coverage scanning of the edge region of the inner cavity in multiple sections.

[0024] Further, in the double-station configuration, the scanning operation in step (c) is performed in parallel with the feeding and discharging operations in steps (a) and (f): when one station of the Y-axis conveying mechanism performs the feeding or discharging operation, the line laser profile measuring instrument moves to the other station through the X-axis scanning feeding device to perform the scanning operation on the battery tray in the other station.

[0025] Further, the filter denoising processing in step (d) adopts a Gaussian filter algorithm; and the coordinate transformation processing converts the three-dimensional point cloud data from a sensor coordinate system of the line laser profilometer to a workpiece reference coordinate system defined by a battery tray reference plane by using calibration parameters.

[0026] Compared with the prior art, the present application has the following beneficial effects:

[0027] The battery tray inner cavity defect detection system adopts multi-component cooperation, in which a code scanner performs identity recognition, a plane image collector acquires appearance data, a line laser profilometer combined with a moving mechanism realizes three-dimensional profile reconstruction of the inner cavity, and defects can be accurately detected; in addition, a double-station parallel operation mode is adopted, so that feeding, discharging and scanning operations can be simultaneously performed, greatly improving the detection efficiency; in addition, the rotary module enables the line laser profilometer to segmentally scan the edge region, realizes comprehensive coverage, has the characteristics of high precision, high efficiency, easy integration, etc., and can detect defects such as protrusions, depressions and aluminum scraps inside the battery tray; and the detection time of a single product is shortened. BRIEF DESCRIPTION OF DRAWINGS

[0028] The accompanying drawings are included to provide a further understanding of the present application, together with explanations of the embodiments of the present application, and do not constitute limitations to the present application, and in the drawings:

[0029] Figure 1 It is a structural schematic diagram of the battery tray inner cavity defect detection system

[0030] Figure 2 It is a work flow diagram of the battery tray inner cavity defect detection system

[0031] Figure 3 It is a motion logic diagram of the line laser profilometer for double-station detection

[0032] Figure 4 It is a coordinate diagram of two independent stations of the Y-axis conveying mechanism

[0033] In the drawings: 1, 2: Y-axis scanning feeding device; 3, 4: code scanner; 5: line laser profilometer; 6: X-axis scanning feeding device; 7, 8: plane image collector; 9: rotary module; 10: lifting module. DETAILED DESCRIPTION

[0034] The preferred embodiments of the present application are described below in conjunction with the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and do not limit the present application.

[0035] As Figures 1 to 4As shown, the application claims a battery tray inner cavity defect detection system, comprising a rack and a Y-axis conveying mechanism 1, 2 arranged on the rack, and a clamp for fixing the battery tray is arranged on the Y-axis conveying mechanism 1, 2; wherein the rack is the supporting structure of the whole system, providing the installation basis for other components and ensuring the stable operation of each component. The Y-axis conveying mechanism 1, 2 adopts a ball screw transmission module driven by a servo motor, which has high transmission accuracy and stability. The clamp for fixing the battery tray is arranged on the Y-axis conveying mechanism 1, 2, which can firmly fix the battery tray and prevent displacement during conveying and detection.

[0036] In this embodiment, the Y-axis conveying mechanism 1, 2 is provided with two independent workstations, each of which is provided with a clamp, and the parallel operation of double workstations can be realized. The line laser profilometer 5 can move between the two workstations through the X-axis scanning feeding device 6, and when one workstation is performing loading or unloading operation, the line laser profilometer 5 can detect the battery tray in the other workstation, thereby improving the detection efficiency.

[0037] The code scanner 3, 4 is arranged on the rack, which is used for scanning the two-dimensional code of the battery tray fixed on the clamp, so as to complete the identity recognition of the battery tray and facilitate the management and tracing of the detection data. The planar image collector 7, 8 is also arranged on the rack, which is used for collecting the appearance image data of the battery tray, and can detect whether there is obvious damage or deformation on the appearance of the battery tray; in this embodiment, the planar image collector 7, 8 is a 2D camera.

[0038] The line laser profilometer 5 is arranged on the rack, and its main function is to emit a laser beam and receive a reflected light signal to reconstruct the three-dimensional profile of the inner cavity surface of the battery tray. Since the lens of the line laser profilometer 5 has a certain inclination with the horizontal plane, when scanning to the edge of the workpiece, it will be blocked by the four walls of the workpiece, resulting in the loss of some area data in a single scan, so a moving mechanism is arranged to drive the line laser profilometer 5 to perform three-dimensional scanning, and the moving mechanism specifically includes an X-axis scanning feeding device 6, a lifting module 10 and a rotating module 9. The lifting module 10 is arranged on the X-axis scanning feeding device 6 and can be driven by the X-axis scanning feeding device 6 to move along the X-axis, thereby realizing the position adjustment of the line laser profilometer 5 in the X-axis direction.

[0039] The rotating module 9 is arranged on the lifting module 10, and the line laser profilometer 5 is connected to the rotating module 9 and can be driven by the rotating module 9 to rotate around its own axis, with a rotation angle range of 0° to 180°, so as to realize the segmented scanning of the edge area of the battery tray inner cavity and ensure the comprehensive coverage scanning of the inner cavity surface.

[0040] In the embodiment, the X-axis scanning feeding device 6 is a linear motor driving module installed on the rack and has fast and accurate moving performance.

[0041] The host computer is in communication connection with the PLC control system, and the PLC control system is responsible for controlling the actions of the Y-axis conveying mechanism 1, 2 and the X-axis scanning feeding device 6, realizing the cooperative work of various components and ensuring the smooth progress of the detection process.

[0042] In the embodiment, the linear laser profile measuring instrument 5 is in communication connection with the Ethernet and is used for receiving, storing and processing the three-dimensional point cloud measurement data acquired by the linear laser profile measuring instrument 5.

[0043] The application also claims a battery tray inner cavity defect detection method based on the battery tray inner cavity defect detection system, comprising the following steps:

[0044] (a) The operator fixes the battery tray to be detected on the clamp of the Y-axis conveying mechanism 1, 2, ensures that the tray is fixed firmly, and then starts the detection process.

[0045] (b) The Y-axis conveying mechanism 1, 2 drives the battery tray to move to the code scanning station, the code scanner 3, 4 scans the two-dimensional code of the tray, completes the identity recognition of the battery tray, and then the Y-axis conveying mechanism 1, 2 continues to drive the battery tray to move to the image acquisition station, the planar image collector 7, 8 collects the appearance image data of the tray, and provides a basis for subsequent appearance defect analysis.

[0046] (c) The moving mechanism starts to work, the X-axis scanning feeding device 6, the lifting module 10 and the rotating module 9 cooperatively drive the linear laser profile measuring instrument 5 to perform three-dimensional scanning on the inner cavity surface of the battery tray.

[0047] When the linear laser profile measuring instrument 5 scans to the edge area of the battery tray inner cavity, the rotating module 9 is controlled to drive the linear laser profile measuring instrument 5 to rotate by a preset angle, and the full coverage scanning of the edge area of the inner cavity is completed in multiple sections.

[0048] In the double-station configuration, the scanning operation and the feeding and discharging operation are performed in parallel. When one station of the Y-axis conveying mechanism 1, 2 performs the feeding or discharging operation, the linear laser profile measuring instrument 5 moves to the other station through the X-axis scanning feeding device 6 to perform the scanning operation on the battery tray in the other station.

[0049] In the scanning process, the linear laser profile measuring instrument 5 synchronously returns the acquired three-dimensional point cloud data to the data acquisition and processing system.

[0050] (d) After the data acquisition and processing system receives the three-dimensional point cloud data, firstly, a Gaussian filtering algorithm is adopted to filter and denoise the data, and remove the noise interference in the data.

[0051] The three-dimensional point cloud data is converted from the sensor coordinate system of the line laser profilometer 5 to the workpiece reference coordinate system defined by the battery tray reference plane using the calibration parameters, realizing coordinate transformation processing.

[0052] Based on the reference plane, the height distribution characteristics of the inner cavity surface are extracted, providing a data basis for subsequent defect identification.

[0053] (e) The extracted height distribution characteristics are input into a pre-trained machine learning classification model, which identifies the defect type of the inner cavity surface and outputs a defect detection evaluation result, such as whether there are cracks, pores, etc. and the specific location and severity of the defects.

[0054] (f) After detection, the Y-axis conveying mechanism 1, 2 drives the battery tray back to the initial position or moves out of the station for subsequent processing, such as repairing or scrapping the defective tray.

[0055] The working mode of the detection system is described in conjunction with the coordinate diagram of Figure 4 The working process is described in conjunction with the coordinate diagram of The Y-axis conveying mechanism 1, 2 transports the battery tray to the code scanner 3, 4 (code scanner gun) at (A, y1) for scanning the two-dimensional code. Through the above scanning, it is judged whether there is a battery tray in the clamp; if there is no battery tray, it is pushed to the loading position at (A, y0) for loading; if there is a battery tray, the planar image collector 7, 8 (2D camera) takes a photo for archiving. Then the Y-axis conveying mechanism 1, 2 continues to transport to (A, y2) to wait for scanning; then it is judged whether the station is in place and the angle of the line laser profilometer 5 (3D camera) is in place; if not, the workpiece is moved by the Y-axis conveying mechanism 1, 2 and re-judged, if in place, the line laser profilometer 5 performs a scan, during which the line laser profilometer 5 scans from (x1, c) to (x2, c), the line laser profilometer 5 rotates 180° and moves to (x3, c), then scans from (x4, c), thus completing the first area scanning; then the workpiece moves to (A, y3); then the line laser profilometer 5 scans from (x4, c) to (x2, c), the line laser profilometer 5 rotates 180° and moves to (x3, c), then scans from (x1, c), thus completing the second area scanning. Then the line laser profilometer 5 moves to (x5, c), the workpiece moves to (A, y0) and the next workpiece detection is performed.

[0056] Finally, it should be noted that the above is only the preferred embodiment of the present application, and is not intended to limit the present application, although the embodiments are described in detail with reference to the present application, for those skilled in the art, the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced, but any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A battery tray inner cavity defect detection system, characterized by, The machine frame and the Y-axis conveying mechanism arranged on the machine frame, the clamp for fixing the battery tray is arranged on the Y-axis conveying mechanism; The machine frame is provided with a code scanner and a planar image collector, the code scanner is used for scanning the two-dimensional code of the battery tray fixed on the clamp for identity recognition, and the planar image collector is used for collecting appearance image data of the battery tray; the machine frame is provided with a line laser profilometer, which is used for emitting a laser beam and receiving a reflected light signal to reconstruct a three-dimensional profile of the inner cavity surface of the battery tray; the machine frame is further provided with a moving mechanism for driving the line laser profilometer to perform three-dimensional scanning, the moving mechanism comprises an X-axis scanning feeding device, the X-axis scanning feeding device is installed on the machine frame, the X-axis scanning feeding device is provided with a lifting module, the X-axis scanning feeding device drives the lifting module to move along the X-axis, the lifting module is provided with a rotating module, the line laser profilometer is connected to the rotating module and driven by the rotating module to rotate around its own axis; the battery tray is driven by the Y-axis conveying mechanism to pass through the working areas of the code scanner and the planar image collector in sequence; the line laser profilometer realizes scanning coverage of the inner cavity surface of the battery tray under the action of the moving mechanism, and adjusts the scanning angle through the rotation of the rotating module to adapt to the measurement of the edge area of the workpiece.

2. The battery tray intracavity defect detection system of claim 1, wherein, The machine frame is further provided with a main control computer and a PLC control system, the main control computer is in communication connection with the PLC control system, and the PLC control system is used for controlling the actions of the Y-axis conveying mechanism and the X-axis scanning feeding device.

3. The battery tray inner cavity defect detection system of claim 1, wherein, The machine frame is further provided with a data acquisition and processing system, the data acquisition and processing system is in communication connection with the line laser profilometer through Ethernet, and is used for receiving, storing and processing three-dimensional point cloud measurement data acquired by the line laser profilometer.

4. The battery tray inner cavity defect detection system of claim 1, wherein, The Y-axis conveying mechanism is a ball screw transmission module driven by a servo motor; the X-axis scanning feeding device is a linear motor driving module.

5. The battery tray intracavity defect detection system of claim 4, wherein, The Y-axis conveying mechanism is provided with two independent stations, each station is provided with the clamp; the line laser profilometer moves between the two stations through the X-axis scanning feeding device to realize a parallel operation mode of detecting the battery tray on one station during the loading or unloading operation of the other station.

6. The battery tray inner cavity defect detection system of claim 1, wherein, The rotating module drives the line laser profilometer to rotate within an angle range of 0° to 180°, so as to realize segmented scanning of the edge area of the inner cavity of the battery tray.

7. A method for detecting defects in the inner cavity of a battery tray based on the system for detecting defects in the inner cavity of a battery tray according to any one of claims 1 to 6, characterized in that, The machine frame is further provided with a main control computer and a PLC control system, the main control computer is in communication connection with the PLC control system, and the PLC control system is used for controlling the actions of the Y-axis conveying mechanism and the X-axis scanning feeding device. (b) the Y-axis conveying mechanism drives the battery tray to move to a code scanning station, the code scanner scans the tray two-dimensional code to complete identity recognition, and then moves to an image acquisition station, the planar image collector collects tray appearance image data; (c) the moving mechanism drives the line laser profilometer to perform three-dimensional scanning on the inner cavity surface of the battery tray, and synchronously returns the collected three-dimensional point cloud data to the data acquisition and processing system; ​ (d) The data acquisition and processing system performs filtering denoising and coordinate transformation processing on the received three-dimensional point cloud data, converts the point cloud data from the sensor coordinate system to the reference coordinate system established based on the battery tray reference plane, and extracts the height distribution characteristics of the inner cavity surface based on the reference plane; (e) The height distribution characteristics are input into a pre-trained machine learning classification model to identify the defect type of the inner cavity surface and output a defect detection evaluation result; (f) After detection is completed, the Y-axis conveying mechanism drives the battery tray to return to the initial position or move out of the work station.

8. The method of claim 7, wherein, In step (c), when the line laser profilometer scans to the edge area of the battery tray inner cavity, the rotary module drives the line laser profilometer to rotate by a preset angle to complete full coverage scanning of the inner cavity edge area in multiple sections.

9. The method of claim 7, wherein, In the double-station configuration, the scanning operation in step (c) is performed in parallel with the loading and unloading operations in steps (a) and (f): when one station of the Y-axis conveying mechanism performs loading or unloading operation, the line laser profilometer moves to the other station through the X-axis scanning feed device to perform scanning operation on the battery tray in the other station.

10. The method of claim 7, wherein, In step (d), the filtering denoising processing uses a Gaussian filtering algorithm; and the coordinate transformation processing uses calibration parameters to convert the three-dimensional point cloud data from the sensor coordinate system of the line laser profilometer to the workpiece reference coordinate system defined based on the battery tray reference plane.