Lithium battery pole piece detection system
Through the integration of multiple sensing technologies and an automated system of dynamic simulation detection modules, the problems of low efficiency and insufficient accuracy of traditional detection methods are solved, and high-precision detection of the surface and internal defects of the lithium battery electrode plate are achieved, thereby improving the production line efficiency and consistency of quality.
Patent Information
- Application Number
- CN202411211774.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-11-29
AI Technical Summary
Traditional lithium battery electrode detection methods are inefficient and insufficiently accurate, and cannot fully cover complex defect types. The detection range of automation equipment is limited, so it is impossible to effectively detect internal defects.
An automated detection system with integrated optical imaging, infrared thermal imaging, ultrasonic detection and dynamic simulation detection modules is adopted, combined with AI image processing and data analysis, to achieve high-precision detection of surface and internal defects of the electrode sheet.
It significantly improves the coverage and accuracy of defect detection, improves detection speed and production line efficiency, reduces costs, meets large-scale production needs, and ensures the production quality and consistency of lithium batteries.
Smart Images

Figure CN119044173A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of lithium battery manufacturing, and in particular to a high-precision and high-efficiency automated detection system for detecting surface and internal defects of lithium battery pole pieces. Background Art
[0002] With the rapid development of new energy vehicles, portable electronic devices and other fields, the market demand for lithium batteries as core energy storage components has increased dramatically. The performance and safety of lithium batteries are directly affected by the quality of pole pieces. As an important component of lithium batteries, the surface and internal defects of pole pieces will significantly reduce the overall performance and service life of the battery. Therefore, comprehensive and accurate testing of pole pieces is an indispensable part of the lithium battery manufacturing process.
[0003] Traditional electrode inspection methods mainly rely on manual visual inspection, which has many shortcomings. First, manual inspection is inefficient and difficult to meet the needs of large-scale production; second, manual inspection is greatly affected by subjective factors, and the accuracy and consistency of the inspection results are difficult to guarantee; finally, with the continuous advancement of lithium battery technology, the types of defects in electrodes are becoming increasingly complex, and manual inspection is difficult to fully cover all defect types.
[0004] In order to overcome these defects, automated testing technology has emerged. However, most of the automated testing equipment on the market currently has a single function and can only detect some defects on the surface of the pole piece, but cannot effectively detect the internal defects of the pole piece. In addition, the existing equipment still needs to be improved in terms of detection accuracy, detection speed and system stability. Summary of the invention
[0005] The present invention proposes a lithium battery pole piece detection system that integrates multiple sensing technologies and a unique dynamic simulation detection module. The system can realize high-precision, high-efficiency automatic detection of pole piece surface and internal defects, significantly improve the production quality and consistency of lithium batteries, and reduce production costs.
[0006] The above technical objectives of the present invention are achieved through the following technical solutions: A lithium battery pole piece detection system, comprising:
[0007] A conveying device, used to convey the pole pieces to various inspection stations;
[0008] Optical imaging detection module, including industrial camera and customized light source, used to capture image information of the pole piece surface;
[0009] Infrared thermal imaging detection module, used to identify changes in heat distribution on the surface of the pole piece;
[0010] Ultrasonic detection module, which detects defects inside the pole piece by emitting ultrasonic waves and receiving their reflected signals;
[0011] Dynamic simulation test module, using two layers of foam as a dynamic simulation environment to evaluate the flatness, dimensional consistency and mechanical properties of the pole piece;
[0012] High light detection module, which uses high light to illuminate the surface of the pole piece to highlight defects at a specific angle;
[0013] Image processing center, including AI image processing module, defect coordinate and distribution map generation module, area focus detection module and multi-image overlay module, used to process and analyze image information;
[0014] The control system and data processing center are used to coordinate the work processes of each detection module and control the start and stop of the conveyor device. They are also used to analyze and process data from the image processing center in real time.
[0015] In some embodiments, a position sensor is provided on the conveying device for monitoring the position of the pole piece in real time.
[0016] In some embodiments, while the pole piece is being inspected by an infrared thermal imaging detection module, the pole piece is first heated and then cooled, and an infrared image of the pole piece during the process is captured in real time.
[0017] In some embodiments, the dynamic simulation detection also includes evaluating the electrochemical performance of the electrode in a simulated environment.
[0018] In some embodiments, multiple offline AI programs are integrated on the AI image processing module.
[0019] In some embodiments, the defect coordinate and distribution map generation module coordinates the detected defects, summarizes and organizes the statistics, and forms a defect distribution map.
[0020] In some embodiments, during detection, the region-focused detection module divides the pole piece into several regions for image acquisition, and focuses on detecting the regions where coordinates are densely distributed.
[0021] In some embodiments, a sorting device is also included to send qualified and unqualified electrodes to different collection chambers according to the detection results of the data processing center.
[0022] In summary, the present invention has the following beneficial effects:
[0023] The present invention achieves comprehensive and accurate detection of surface and internal defects of lithium battery pole pieces by integrating multiple sensing technologies such as optical imaging, infrared thermal imaging, and ultrasonic detection. This technological breakthrough solves the problems of limited detection range and insufficient accuracy in traditional detection methods. It can identify defects such as scratches, pits, stains, foreign matter, coating defects, exposed foil, and internal cracks, significantly improving the coverage and accuracy of defect detection. In addition, the unique dynamic simulation detection module of the present invention can evaluate the flatness, dimensional consistency, and mechanical properties of the pole piece, further improving the accuracy and reliability of detection.
[0024] The automated detection system of the present invention can efficiently complete the task of detecting electrode defects. Compared with the traditional manual detection method, the detection speed is faster and the overall operation efficiency of the production line is greatly improved. This not only reduces labor costs, but also reduces labor intensity, meeting the needs of large-scale production.
[0025] The system of the present invention integrates advanced image processing algorithms and data analysis software, and can process and analyze the collected image data in real time. This feature makes the detection results more accurate and reliable, and can quickly generate defect distribution maps, providing strong data support for subsequent process optimization and quality control. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 It is a schematic diagram of the system structure of the present invention;
[0027] Figure 2 The figure is a flowchart of the use of the present invention. DETAILED DESCRIPTION
[0028] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.
[0029] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.
[0030] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0031] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0032] like Figure 1-2 As shown, this embodiment provides a lithium battery pole piece detection system, which includes:
[0033] The conveyor is used to smoothly convey the pole piece to each inspection station. The conveyor is equipped with a precise position sensor to monitor the position of the pole piece in real time to ensure the accuracy of the inspection.
[0034] The optical imaging detection module, including a high-resolution industrial camera and a customized light source, is used to capture image information on the surface of the pole piece. Through image processing algorithms, scratches, pits, stains, foreign matter, coating defects, etc. on the surface of the pole piece can be identified.
[0035] The infrared thermal imaging detection module uses infrared thermal imaging technology to detect the heat distribution changes on the surface of the pole piece and identify the local temperature changes caused by defects, such as exposed foil, internal cracks, etc. In the present invention, the pole piece is first heated and then cooled to better capture the heat distribution changes.
[0036] The ultrasonic detection module detects defects inside the pole piece, such as pores, inclusions, etc., by emitting ultrasonic waves to the pole piece and receiving its reflected signal, and analyzing the changes in the signal. The ultrasonic detection module has the advantages of non-contact and non-destructive testing, and is suitable for pole pieces of various materials.
[0037] The dynamic simulation detection module uses two layers of thin foam as the dynamic simulation environment. When the pole piece passes through the foam layer, its dynamic changes (such as friction, vibration, etc.) are monitored to evaluate the flatness, dimensional consistency and mechanical properties of the pole piece. At the same time, the foam layer can also be used to simulate the working environment of the pole piece in the battery to further verify its performance stability.
[0038] The highlight detection module uses highlight light to illuminate the surface of the electrode and adjusts the direction of the highlight light to highlight defects that can only be seen at specific angles.
[0039] The AI image processing module integrates advanced AI programs to process the collected images to highlight defects more clearly and make the defective parts in the captured images more obvious.
[0040] The defect coordinate and distribution map generation module coordinates the detected defects, summarizes and organizes them, and forms a defect distribution map. The denser the coordinate distribution in the defect distribution map, the more likely it is to have defects in that part, which can be used to trace the specific process in the production process where the problem occurred.
[0041] The regional emphasis detection module divides the pole piece into several areas for image acquisition during detection, and focuses on detecting the areas with dense coordinate distribution to save detection time.
[0042] The multi-image overlay module uses images collected by different devices to reduce their transparency first, and then overlay multiple images together to obtain an overall view of the defect distribution.
[0043] The control system and data processing center integrate high-performance industrial control computers and advanced image processing and data analysis software. The control system is responsible for coordinating the workflow of each detection module, while the data processing center performs real-time analysis and processing of the collected data, outputs the detection results, and controls the sorting device to send qualified and unqualified electrodes into different collection chambers.
[0044] The lithium battery pole piece detection system of the present invention realizes high-precision and high-efficiency automatic detection of pole piece surface and internal defects by integrating multiple sensing technologies and unique dynamic simulation detection modules. At the same time, the accuracy and efficiency of detection are further improved through technical means such as defect coordinateization and distribution map generation, regional focus detection, and AI image processing. The application of this system will significantly improve the production quality and consistency of lithium batteries, reduce production costs, and has broad market application prospects.
[0045] like Figure 2 As shown, the following is the complete detection process of the lithium battery pole piece detection system:
[0046] A)Transmission and positioning
[0047] The pole piece is placed stably on the conveyor, which is driven by a high-precision motor to ensure the stability of the pole piece during the conveying process.
[0048] The conveyor is provided with an accurate position sensor, such as a photoelectric sensor or a magnetic sensor, to monitor the position and speed of the pole piece in real time.
[0049] The control system adjusts the movement of the conveyor according to the feedback from the position sensor to ensure that the pole piece can accurately reach each inspection station.
[0050] B) Optical imaging detection
[0051] When the pole piece arrives at the optical imaging inspection station, high-resolution industrial cameras and customized light sources start working.
[0052] The camera uses a high frame rate to capture subtle changes in the surface of the pole piece. The custom light source provides uniform and moderate lighting to highlight surface defects.
[0053] Through image processing algorithms such as edge detection and grayscale analysis, the system identifies scratches, pits, stains, foreign matter, coating defects, etc. on the surface of the pole piece and marks the defect information on the image.
[0054] C) Infrared thermal imaging detection
[0055] After completing the previous inspection steps, the pole piece will be transferred to the infrared thermal imaging inspection station. In this station, the infrared thermal imager plays a key role. It first heats the pole piece, which is usually achieved through a built-in heating element, such as an infrared lamp or a heating plate. During the heating process, the system will accurately control the temperature to ensure that the pole piece is heated evenly. Then, the heating element stops working, and the cooling system starts to start and quickly cool the pole piece. This heating and cooling process changes the heat distribution on the surface of the pole piece, and the defective part will produce local temperature changes due to differences in thermal conductivity.
[0056] Infrared thermal imagers can capture these changes in heat distribution in real time and convert them into visual thermal images. This thermal image uses different colors to represent different temperature areas, thereby intuitively showing the temperature distribution on the surface of the pole piece. By analyzing these thermal images, the system can identify local temperature changes caused by defects. For example, the exposed foil area has better thermal conductivity due to the exposed metal, so it may appear as a colder or hotter area on the thermal image. Similarly, internal cracks can also cause changes in thermal conductivity, resulting in obvious temperature differences on the thermal image.
[0057] Once the system identifies these defects, it will automatically mark the defect information on the thermal image, including the location, size and type of the defect, etc. This information is crucial for subsequent defect analysis and quality control.
[0058] D) Ultrasonic testing
[0059] At the ultrasonic testing station, the ultrasonic transmitter emits high-frequency ultrasonic waves to the pole piece and receives its reflected signal.
[0060] The reflected signal is amplified, filtered and digitized by the signal processor to extract useful defect information.
[0061] By analyzing signal changes, such as amplitude and frequency, the system detects defects inside the pole piece, such as pores and inclusions, and marks the defect information on the ultrasonic image.
[0062] E) Dynamic simulation detection
[0063] After completing the ultrasonic test, the pole piece will enter the dynamic simulation test module. This module consists of two layers of thin foam, which simulates the actual working environment of the pole piece in the battery. The foam layer has a certain elasticity and friction coefficient, which can simulate the mechanical effects such as squeezing and friction on the pole piece in the battery.
[0064] When the pole piece passes through these two layers of foam, the system monitors its dynamic changes, such as friction and vibration. These changes are converted into electrical signals by sensors and relevant data is recorded. These data include kinematic parameters such as displacement, velocity, acceleration, and mechanical parameters such as friction and extrusion force of the pole piece when it passes through the foam layer.
[0065] By analyzing this data, the system can evaluate the flatness, dimensional consistency and mechanical properties of the pole piece. For example, if the pole piece shows obvious vibration or displacement deviation when passing through the foam layer, this may mean that there is a problem with its flatness or dimensional consistency. Similarly, if the friction or extrusion force is abnormal, it may also indicate that the mechanical properties of the pole piece do not meet the requirements.
[0066] After the evaluation is completed, the system will mark the evaluation results on the dynamic simulation images. These images show the performance of the pole piece during the dynamic simulation test in a visual way, providing an important reference for subsequent quality control and process improvement.
[0067] Preferably, in the dynamic simulation detection module, consider adding an evaluation of the electrochemical performance of the electrode in a simulated environment. The actual performance of the electrode in the battery is not only affected by its physical properties, but also closely related to its electrochemical performance. By simulating the working environment of the battery, such as electrolyte concentration, temperature, current density, etc., key indicators such as the charge and discharge performance, cycle stability, and safety of the electrode can be more comprehensively evaluated.
[0068] At the same time, in order to more accurately simulate the performance of the battery under different working environments, adjustable mechanical parameters such as pressure and friction coefficient can be introduced. Changes in these parameters will affect the mechanical and electrochemical properties of the pole piece, thereby affecting the overall performance of the battery. By adjusting these parameters, the working conditions of the battery under extreme conditions, such as high temperature, high pressure or high humidity environment, can be simulated to more comprehensively evaluate the performance of the pole piece.
[0069] F) Highlight detection
[0070] At the high light inspection station, a high-brightness light source is irradiated onto the surface of the electrode.
[0071] By adjusting the direction and intensity of the light source, the system highlights defects that are only visible at specific angles, such as tiny bumps and depressions.
[0072] The highlight inspection camera captures images of these defects and transmits them to the image processing module for further analysis and processing.
[0073] G) AI image processing and defect coordinates
[0074] The previously collected images will be sent to the AI image processing module for processing. This module integrates advanced deep learning algorithms and image processing technology to perform in-depth analysis of images.
[0075] The AI tool analyzes the image pixel by pixel, identifying and highlighting the defective parts by comparing the characteristic differences between normal and defective electrodes. This deep learning algorithm can automatically extract the characteristic information in the image and classify and identify it based on this information. By training a large number of normal and defective electrode images, the algorithm can learn the characteristic differences between them and accurately identify the defective parts.
[0076] The processed image is then fed into the defect coordinate and distribution map generation module. This module coordinates the detected defects and records the location, size, and type of each defect. This information is represented in the form of data points on the defect distribution map, where the horizontal and vertical axes represent the width and length of the pole piece, respectively.
[0077] By summarizing and arranging these data points, a defect distribution map is eventually formed. In this map, the denser the coordinate distribution, the more likely defects are to occur in that part. This visual representation allows quality control personnel to intuitively understand the defect distribution of the pole piece and make process improvements and quality control decisions based on this. At the same time, the defect distribution map can also be used as a real-time monitoring tool in the production process to help timely discover and solve potential quality problems.
[0078] Preferably, in the AI image processing module, the deep learning algorithm can be continuously updated and trained to improve the accuracy and efficiency of defect recognition. This includes using more actual production data to train the algorithm so that it can better adapt to changes in the actual production environment. At the same time, it is also possible to consider introducing unsupervised learning technology to automatically discover and classify new and unknown defect types. Unsupervised learning technology can extract useful information and patterns from large amounts of data without pre-labeling the data. This will help to promptly discover and respond to new problems in production and further improve the accuracy and efficiency of detection. The specific operations are as follows:
[0079] Regularly collect actual data of electrode defect detection from the production line, including images of qualified electrodes and electrodes with various defects, and annotate and classify the collected data for use in the training of deep learning algorithms;
[0080] Use newly collected production data to retrain or fine-tune existing deep learning algorithms, optimize the algorithm's network structure and parameter settings to improve the accuracy and efficiency of defect identification, and test and verify the trained algorithm to ensure that its performance meets production requirements;
[0081] Select appropriate unsupervised learning algorithms such as clustering algorithms or autoencoder models, use unlabeled production data to train the unsupervised learning algorithms to extract useful features and patterns, and analyze the output of the unsupervised learning algorithms to discover new and unknown defect types and perform corresponding classification processing;
[0082] The updated deep learning algorithm and unsupervised learning technology are integrated into the defect detection system to achieve more comprehensive defect identification capabilities, and the integrated system is comprehensively tested to ensure its stability and reliability meet production requirements.
[0083] H) Area Focus Detection and Multi-Image Overlay
[0084] After a comprehensive inspection of the pole piece, the area-focused inspection determines the areas that need special attention based on the defect distribution map. These areas may be where defects occur more frequently, or where they have a critical impact on the performance of the pole piece. By performing more intensive image acquisition and processing in these areas, the accuracy and reliability of the inspection can be improved, ensuring that defects in key areas are identified without omission.
[0085] Multi-image overlay is to overlay images collected from different inspection modules or at different time points. Before overlaying, the transparency of each image is reduced so that the overlaid image can display information from multiple layers at the same time. In this way, users can see the defect distribution of the electrode under different inspection conditions in one view, which is convenient for comprehensive analysis of the quality status of the electrode. Multi-image overlay technology helps to improve the overall understanding of electrode defects and provide more comprehensive data support for quality control and process improvement.
[0086] I) Data processing and sorting
[0087] Data processing is a key link in the lithium battery pole piece inspection system. The data processing center is responsible for collecting data transmitted by each inspection module and performing real-time analysis and processing. By adopting advanced data analysis algorithms and machine learning technology, the data processing center can classify, identify and count defects, thereby accurately evaluating the quality status of the pole piece. In addition, the data processing center can also generate visual reports such as defect distribution maps to provide quality control personnel with intuitive decision-making basis.
[0088] Sorting is to distinguish qualified and unqualified pole pieces according to the test results of the data processing center, and send them to different collection chambers respectively. The sorting device is usually composed of automated equipment such as robotic arms, cylinders or conveyor belts, which can realize fast and accurate sorting operations. Through sorting, it can be ensured that only qualified pole pieces enter the next production link, thereby ensuring the overall quality and performance of lithium batteries. At the same time, the timely removal of unqualified pole pieces also helps to reduce production costs and avoid potential quality risks.
[0089] From the above technical solutions, we can know that the system combines a variety of sensing technologies and a unique dynamic simulation detection module to achieve high-precision, high-efficiency automated detection of surface and internal defects of the pole piece. At the same time, through the application of technical means such as defect coordinateization and distribution map generation, regional focus detection, and AI image processing, the accuracy and efficiency of detection are further improved. The application of this system will significantly improve the production quality and consistency of lithium batteries, reduce production costs, and has broad market application prospects.
[0090] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.
Claims
1. A lithium battery pole piece detection system, characterized in that: include: A conveying device, used to convey the pole pieces to various inspection stations; Optical imaging detection module, including industrial camera and customized light source, used to capture image information of the pole piece surface; Infrared thermal imaging detection module, used to identify changes in heat distribution on the surface of the pole piece; Ultrasonic detection module, which detects defects inside the pole piece by emitting ultrasonic waves and receiving their reflected signals; Dynamic simulation test module, using two layers of foam as a dynamic simulation environment to evaluate the flatness, dimensional consistency and mechanical properties of the pole piece; High light detection module, which uses high light to illuminate the surface of the pole piece to highlight defects at a specific angle; Image processing center, including AI image processing module, defect coordinate and distribution map generation module, area focus detection module and multi-image overlay module, used to process and analyze image information; The control system and data processing center are used to coordinate the work processes of each detection module and control the start and stop of the conveyor device. They are also used to analyze and process data from the image processing center in real time.
2. A lithium battery pole piece detection system according to claim 1, characterized in that: A position sensor is provided on the conveying device for real-time monitoring of the position of the pole piece.
3. A lithium battery pole piece detection system according to claim 1, characterized in that: While the pole piece is being inspected by the infrared thermal imaging detection module, the pole piece is first heated and then cooled, and the infrared image of the pole piece in the process is captured in real time.
4. A lithium battery pole piece detection system according to claim 1, characterized in that: Dynamic simulation testing also includes the evaluation of the electrochemical performance of the electrode in a simulated environment.
5. A lithium battery pole piece detection system according to claim 1, characterized in that: The AI image processing module integrates multiple offline AI programs.
6. A lithium battery pole piece detection system according to claim 1, characterized in that: The defect coordinate and distribution map generation module coordinates the detected defects, summarizes and organizes the statistics, and forms a defect distribution map.
7. A lithium battery pole piece detection system according to claim 6, characterized in that: During detection, the regional emphasis detection module divides the pole piece into several regions for image acquisition, and focuses on detecting the regions with dense coordinate distribution.
8. A lithium battery pole piece detection system according to claim 1, characterized in that: It also includes a sorting device, which sends qualified and unqualified electrodes to different collection chambers according to the test results of the data processing center.
Citation Information
Cited By
Waste recovery method, system and equipment and storable medium
CN119542598A
A waste recycling method, system, device and storage medium
CN119542598B
