Method and system for rapid tomographic detection of lithium ion laminated batteries, equipment, medium and product

Abstract

The application provides a rapid tomography detection method of a lithium ion laminated battery, comprising the following steps: image acquisition, sequentially acquiring a plurality of projection images in a preset small-angle range; three-dimensional reconstruction, performing real-time three-dimensional reconstruction on the acquired images; feature detection, intercepting a CT tomogram in a preset direction, using a method combining deep learning and traditional algorithm to perform battery feature detection, and giving a result. The application relates to an electronic device, a storage medium, a program product and a rapid tomography detection system of a lithium ion laminated battery. The application improves the detection precision while adapting to the increasingly fast production rhythm of lithium batteries, performs rapid CT scanning on the lithium battery stack, and the detection of one stack battery angle can be completed within 2s, which can match the real production line speed, the result tomogram structure is clear, the pole piece layer endpoint is clear, the precision of the stack lithium battery pole difference detection is greatly improved, and the application can be perfectly applied to the current stack lithium battery industry.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery non-destructive testing, in particular to a rapid tomographic imaging detection method and system, equipment, medium and product for lithium ion laminated battery. BACKGROUND

[0002] With the development of economy and the urgent need for green energy, in recent years, great progress has been made in the research and production of lithium ion batteries. Due to its high energy density, good stability, no pollution and other advantages, lithium ion batteries have been widely used in many fields such as portable electronic products, new energy vehicles, energy storage, etc. Especially as a power source on electric vehicles, it has become a new trend of electric vehicle development. In the future, lithium ion batteries will occupy an important position in the field of electric vehicles and new energy. Therefore, the application safety performance of lithium ion batteries has also been widely concerned.

[0003] X-ray as a non-destructive testing method has been applied in the field of lithium ion laminated battery detection in recent years. Traditional X-ray laminated battery detection uses two-dimensional image detection, which has the advantages of simple detection mode and fast speed, but has the disadvantage that since the traditional industrial X-ray light source is a point light source, and the electrode plates are parallel to each other and have many layers, the edge electrode plates will overlap in the two-dimensional projection image, which will adversely affect the detection results. In addition, traditional X-ray detection cannot eliminate the influence of battery tab interference. Offline CT detection is usually used for new product research and development or production line sampling, and its detection results can clearly show the three-dimensional structure of the internal electrodes of the laminated battery, and are not affected by electrode plate overlap or tab interference, but offline CT detection usually takes a long time to detect, which cannot adapt to the increasingly fast lithium battery production rhythm. Therefore, the current industrial detection of lithium ion laminated battery needs higher precision and faster detection speed. SUMMARY

[0004] In order to overcome the shortcomings of the prior art, the purpose of the present application is to provide a rapid tomographic imaging detection method for lithium ion laminated battery, which can improve the detection precision and adapt to the increasingly fast lithium battery production rhythm.

[0005] The present application provides a rapid tomographic imaging detection method for lithium ion laminated battery, comprising the following steps:

[0006] Collecting images, sequentially collecting a plurality of projection images within a predetermined small angle range;

[0007] Three-dimensional reconstruction, real-time three-dimensional reconstruction of the collected images;

[0008] Feature detection, intercepting CT tomographic images in a predetermined direction, using a method combining deep learning and traditional algorithm for battery feature detection, and giving the results.

[0009] Further, in the three-dimensional reconstruction step, FDK three-dimensional image reconstruction algorithm is adopted to perform three-dimensional reconstruction on the collected images in real time.

[0010] Further, in the feature detection step, the battery is detected according to the position of the to-be-detected position in the scanning structure, and the battery features include battery pole difference, pole spacing, and deflection angle features.

[0011] An electronic device, comprising: a processor;

[0012] A memory; and a program, wherein the program is stored in the memory and is configured to be executed by the processor, and the program comprises a fast tomographic imaging detection method for a lithium ion laminated battery.

[0013] A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to perform a fast tomographic imaging detection method for a lithium ion laminated battery.

[0014] A computer program product comprising computer programs / instructions that, when executed by a processor, implement a fast tomographic imaging detection method for a lithium ion laminated battery.

[0015] A fast tomographic imaging detection system for a lithium ion laminated battery, comprising an X-ray light source, a flat panel detector, and a processor; a to-be-detected position of the lithium ion laminated battery is located at a motion center of the system, the X-ray light source and the flat panel detector are located on both sides of the to-be-detected position of the lithium ion laminated battery, the X-ray light source, the flat panel detector, and the lithium ion laminated battery move relative to each other, according to a motion speed, the flat panel detector moves while continuously exposing and collecting images, and the processor executes a fast tomographic imaging detection method for the lithium ion laminated battery.

[0016] Further, the lithium ion laminated battery is placed horizontally, and the flat panel detector sequentially collects a plurality of projection images within a preset small-angle range.

[0017] Further, the X-ray light source and the flat panel detector move at a uniform speed around the motion center in an arc motion, or the X-ray light source and the flat panel detector are fixed, the lithium ion laminated battery rotates, or the X-ray light source and the flat panel detector move in a straight line, or the X-ray light source is fixed, and the lithium ion laminated battery and the flat panel detector move in a straight line at different speeds.

[0018] Compared with the prior art, the present application has the following beneficial effects:

[0019] The application provides a rapid tomographic detection method for lithium ion laminated batteries, which is suitable for the increasing production rhythm of lithium batteries while improving the detection accuracy, and can complete the detection of a battery corner in 2s, match the real production line speed, and obtain clear tomographic images with clear electrode layer endpoints, thereby greatly improving the detection accuracy of lithium battery layers and being perfectly applied to the current lithium battery industry.

[0020] The above description is only a summary of the technical scheme of the application, in order to more clearly understand the technical means of the application and implement the content of the description, the preferred embodiments of the application are described in detail below with reference to the drawings. The specific embodiments of the application are described in detail by the following examples and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0021] The drawings described herein are used to provide further understanding of the application, form a part of the application, and the schematic embodiments of the application and their descriptions are used to explain the application and do not constitute an improper limitation on the application. In the drawings:

[0022] Figure 1 A flow chart of the rapid tomographic detection method for lithium ion laminated batteries of the application;

[0023] Figure 2 A top view of the rapid tomographic detection system for lithium ion laminated batteries of the application;

[0024] Figure 3 A front view of the rapid tomographic detection system for lithium ion laminated batteries of the application;

[0025] Figure 4 A to-be-detected image effect diagram of the rapid tomographic detection method for lithium ion laminated batteries not in use;

[0026] Figure 5 A to-be-detected image effect diagram of the rapid tomographic detection method for lithium ion laminated batteries in use;

[0027] Figure 6 A Figure 5 A result schematic diagram of battery feature detection by using a method combining deep learning and traditional algorithms. DETAILED DESCRIPTION

[0028] In the following, the application is further described in combination with the drawings and specific embodiments, and it should be noted that the following described embodiments or technical features can be combined in any manner to form new embodiments without conflict.

[0029] The rapid tomographic detection method for lithium ion laminated batteries, such as Figure 1As shown, comprising the following steps:

[0030] Collecting images, sequentially collecting several projection images in a preset small angle range; in this embodiment, 10-30 projection images are sequentially collected in a ±15° range.

[0031] Three-dimensional reconstruction, real-time three-dimensional reconstruction is performed on the collected images; in this embodiment, the FDK three-dimensional image reconstruction algorithm with fast reconstruction speed and simple and effective is used, and the reconstruction calculation can be performed synchronously during scanning, so that the CT tomographic results can be output synchronously at the end of scanning.

[0032] Feature detection, intercepting the CT tomographic image in the preset direction, using the method combining deep learning and traditional algorithm to detect the battery features, wherein the battery features include battery pole difference, pole spacing, deflection angle and other features, and the results are given. In this embodiment, the tomographic range is selected according to the position of the detection position in the scanning structure to detect the battery. The detection method uses deep learning method to achieve fast and accurate detection through training of detection data, and the whole detection process can be completed in about 2s.

[0033] An electronic device, comprising: a processor;

[0034] a memory; and a program, wherein the program is stored in the memory and configured to be executed by the processor, and the program comprises a fast tomographic imaging detection method for a lithium ion laminated battery.

[0035] A computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to perform a fast tomographic imaging detection method for a lithium ion laminated battery.

[0036] A computer program product comprising computer programs / instructions which, when executed by a processor, implement a fast tomographic imaging detection method for a lithium ion laminated battery.

[0037] A fast tomographic imaging detection system for a lithium ion laminated battery, as shown in Figure 2 , Figure 3 X-ray source, flat panel detector, processor; the lithium ion laminated battery is placed horizontally, the detection angle of the lithium ion laminated battery is placed in the system motion center, the X-ray source and the flat panel detector are located on both sides of the detection angle of the lithium ion laminated battery, and the X-ray source, the flat panel detector and the lithium ion laminated battery move relative to each other. According to the movement speed, the flat panel detector moves while continuously exposing and collecting images; in this embodiment, the flat panel detector sequentially collects several projection images in a preset small angle range such as ±15°. The processor executes a fast tomographic imaging detection method for a lithium ion laminated battery.

[0038] In an embodiment, the X-ray light source and the flat panel detector respectively do uniform circular motion around the motion center, and move in the direction shown in Figure 3 In an embodiment, the X-ray light source and the flat panel detector respectively do uniform circular motion around the motion center, and move in the direction shown in

[0039] In an embodiment, the X-ray light source and the flat panel detector are fixed, and the lithium ion laminated battery rotates.

[0040] In an embodiment, the X-ray light source and the flat panel detector do linear motion.

[0041] In an embodiment, the X-ray light source is fixed, and the lithium ion laminated battery and the flat panel detector do linear motion at different speeds.

[0042] Figure 4 For the image imaging effect of not using the method, for the two-dimensional projection diagram of the laminated battery, it can be seen that the electrode layers near the left and right edges of the battery overlap in the projection diagram, which will affect the actual detection effect and manual judgment. The three-dimensional tomographic diagram obtained by using the method of the present application is shown in Figure 5 It can be seen that the end points of each pole piece are clear and explicit, and the influence between the pole pieces is eliminated. Figure 6 For Figure 5 The results of using the method of combining deep learning and traditional algorithm for battery feature detection show that the positioning of the end points of each pole piece is accurate, which brings great convenience for subsequent battery pole difference calculation, and the detection accuracy is greatly improved.

[0043] The above is only a preferred embodiment of the present application, and does not limit the present application in any form; any ordinary skilled person in the art can easily implement the present application according to the drawings shown in the specification and the above; however, any equivalent changes, modifications and evolution of the above disclosed technical content within the scope of the technical solutions of the present application are equivalent embodiments of the present application; at the same time, any equivalent changes, modifications and evolution of the above embodiments according to the essential technology of the present application are still within the protection scope of the technical solutions of the present application.

Claims

1. A method for rapid tomographic detection of lithium-ion laminated batteries, characterized in that, The method comprises the following steps: Collecting images, sequentially collecting a plurality of projection images in a preset small angle range, the preset small angle range being ±15°; The collecting of the projection images comprises: the angle to be detected of the lithium ion laminated battery being located at a motion center, an X-ray light source and a flat panel detector for collecting the projection images being located on two sides of the angle to be detected, a side of the lithium ion laminated battery being opposite to the X-ray light source and the flat panel detector, when collecting images, the X-ray light source and the flat panel detector respectively performing uniform circular motion upwards and downwards around the motion center, and the collecting speed of the projection images being determined according to the motion speed of the flat panel detector; Three-dimensional reconstruction, performing three-dimensional reconstruction on the collected images in real time; Feature detection, intercepting a CT tomogram in a preset direction, performing battery feature detection by using a method combining deep learning and traditional algorithms, and giving a result, the battery features including battery pole difference, pole spacing, and deflection angle feature.

2. The method of claim 1, wherein: In the three-dimensional reconstruction step, FDK three-dimensional image reconstruction algorithm is used to perform three-dimensional reconstruction on the collected images in real time.

3. The method of claim 1, wherein: In the feature detection step, the tomogram range is selected according to the position of the position to be detected in the scanning structure for battery detection.

4. An electronic device, characterized in that... The computer program is executed by the processor to perform the method of any one of claims 1-3. The computer program is executed by the processor to perform the method of any one of claims 1-3. The computer program / instruction is executed by the processor to perform the method of any one of claims 1-3. The computer program / instruction is executed by the processor to perform the method of any one of claims 1-3.

5. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program / instruction is executed by the processor to perform the method of any one of claims 1-3.

6. A computer program product comprising computer programs / instructions, characterized in that, The lithium ion laminated battery is horizontally placed; the flat panel detector sequentially collects a plurality of projection images in a preset small angle range.

7. A fast tomographic inspection system for lithium-ion stacked batteries, characterized by: The X-ray light source and the flat panel detector respectively perform uniform circular motion around the motion center, or the X-ray light source and the flat panel detector are fixed, the lithium ion laminated battery rotates, or the X-ray light source and the flat panel detector perform linear motion, or the X-ray light source is fixed, and the lithium ion laminated battery and the flat panel detector perform linear motion at different speeds.

8. The fast tomographic inspection system for lithium-ion stacked batteries of claim 7, wherein: ​ 9. The fast tomographic inspection system for lithium-ion stacked batteries of claim 7, wherein: ​

Images