Coating detection system for surface treatment of lithium battery copper foil

Abstract

The invention relates to the technical field of coating detection, and particularly discloses a coating detection system for lithium battery copper foil surface treatment, which is characterized in that a coating thickness deviation value of each image subunit in a coating is obtained by processing a lithium battery copper foil coating image under the coating condition that the coating thickness uniformity requirement is met; constructing a first reference circle, a second reference circle and a regional feature circle by taking the image subunit with the maximum coating thickness deviation value and the image subunit with the minimum coating thickness deviation value as references, and respectively obtaining color feature values of the first reference circle and the second reference circle; obtaining a coating color difference value according to the color characteristic values of the first reference circle and the second reference circle, obtaining the area of the regional characteristic circle and the number of coating different points to obtain a coating different point ratio, and obtaining a coating behavior effective value based on the coating different point ratio, the coating color difference value and a coating offset difference dynamic value. And based on the coating behavior effective value, completing identification of the coating quality on the basis of meeting the coating thickness uniformity requirement.

Description

Technical Field

[0001] This invention relates to the field of coating inspection technology, and more specifically to a coating inspection system for the surface treatment of lithium battery copper foil. Background Technology

[0002] Copper foil is a crucial material in lithium-ion batteries. It's a metallic conductor responsible for connecting the positive and negative electrodes to form a current loop. In lithium-ion batteries, copper foil primarily serves to conduct electricity and heat, provide corrosion protection, and strengthen the current collector.

[0003] The existing processing requires coating the surface of the lithium battery copper foil. The main function of the coating is to improve the electrochemical performance of the battery. This coating can enhance the battery's lifespan, for example, by preventing internal stray reactions and corrosion from impurities in the electrolyte. In addition, the coating can also act as a physical isolation layer, which plays an important role in preventing internal stray reactions and corrosion from impurities in the electrolyte. Other materials, such as nanomaterials, are often added to the coating to further enhance the battery's performance.

[0004] In the existing technology, the coating quality detection method for the surface treatment of lithium battery copper foil is simple. Most of the time, the coating quality is considered qualified as long as the coating thickness uniformity is met. This method has great limitations because the quality of the coating also depends on whether the coating has color, whether it is smooth, etc. Based on this, the present invention provides a coating detection system for the surface treatment of lithium battery copper foil. Summary of the Invention

[0005] The purpose of this invention is to provide a coating detection system for the surface treatment of lithium battery copper foil. By segmenting the acquired coating image, several image sub-units of the same area are obtained. The variance of the coating thickness value of all image sub-units is processed, and the overall coating quality is identified from the perspective of coating thickness uniformity.

[0006] The objective of this invention can be achieved through the following technical solutions: A coating inspection system for lithium battery copper foil surface treatment includes: The image acquisition module is used to acquire a coating image, preprocess the acquired coating image, segment the preprocessed coating image to obtain several image sub-units of the same area, and transmit the image sub-units to the cloud management platform. The image primary processing module receives image sub-units sent by the cloud management platform, obtains the coating thickness value of each image sub-unit to obtain the coating thickness value group of the image sub-unit, performs variance processing on the coating thickness value group of the image sub-unit to obtain the coating quality signal, and sends the coating quality signal to the cloud management platform. The coating quality signal includes a normal coating quality signal and a abnormal coating quality signal. The coating secondary processing module receives a normal coating quality signal transmitted from the cloud management platform, obtains the coating thickness deviation value of the image sub-unit, processes the coating thickness deviation values ​​of multiple image sub-units to obtain the coating anomaly ratio and coating color difference value, calculates the coating behavior effective value by calculating the coating anomaly ratio and coating color difference value, and completes the coating quality identification based on the coating behavior effective value. The coating anomaly ratio is denoted as Tyb, and the coating color difference value Y12 is denoted as Tyb. RGB Through formula The effective value of coating behavior TYT is calculated, where a1, a2, and a3 are preset proportional coefficients, and a1, a2, and a3 are all greater than 0, and Tpc is the coating deviation variation value. Obtain the coating thickness deviation value of all image sub-units within the coating image, sum the coating thickness deviation values ​​of all image sub-units and take the average value to obtain the coating deviation variation value Tpc.

[0007] As a further aspect of the present invention: the process of acquiring the coating quality signal is as follows: Compare the coating variance with the preset coating variance; If the coating variance is less than or equal to the preset coating variance, it indicates that the coating quality of the workpiece is normal, and a normal coating quality signal is obtained. If the coating variance is greater than the preset coating variance, it indicates that the coating quality of the workpiece is abnormal, and a coating quality abnormality signal is obtained.

[0008] As a further aspect of the present invention: the process for obtaining the coating color difference is as follows: The image sub-unit that obtains the maximum value of the coating thickness deviation is denoted as the maximum value image sub-unit. The image sub-unit that obtains the minimum value of the coating thickness deviation is denoted as the minimum value image sub-unit. Connect the center point of the maximum value image sub-unit with the center point of the minimum value image sub-unit to obtain the straight-line distance of the deviation; With the center point of the maximum value image sub-unit as the center and the distance from the center point of the maximum value image sub-unit to the center of the deviation straight line as the radius, draw a circle to obtain the first reference circle; A second reference circle is obtained by drawing a circle with the center point of the minimum value image sub-unit as the center and the distance from the center point of the minimum value image sub-unit to the center of the deviation line as the radius.

[0009] As a further aspect of the present invention: the color of the first reference circle is extracted to obtain the RGB value of the first reference circle; Obtain the R value in the first reference circle, and denote it as R1; Obtain the G value in the first reference circle, and denote it as G1; Obtain the B value in the first reference circle, and denote it as B1; The R1, G1, and B1 values ​​in the first reference circle are weighted and the weight of the obtained R1 value is assigned as n1, the weight of the obtained G1 value is assigned as n2, and the weight of the obtained B1 value is assigned as n3. According to formula Y1 RGB The color feature value Y1 of the first reference circle is calculated as R1*n1+G1*n2+B1*b3. RGB , where n1+n2+n3=1, and n3, n2, and n1 are all greater than 0.

[0010] As a further aspect of the present invention: the color of the second reference circle is extracted to obtain the RGB value of the second reference circle; Obtain the R value in the second reference circle, denoted as R2; Obtain the G value in the second reference circle, and denote it as G2; Obtain the value of B in the second reference circle, and denote it as B2; The R2, G2, and B2 values ​​in the second reference circle are weighted and assigned as n1, n2, and n3 respectively. According to formula Y2 RGB The color characteristic value Y2 of the second reference circle is calculated as R2*n1+G2*n2+B2*b3. RGB Where n1+n2+n3=1, and n3, n2, and n1 are all greater than 0; The color feature value Y1 of the first reference circle RGB The color feature value Y2 of the second reference circle RGB The difference was calculated to obtain the coating color difference value Y12. RGB .

[0011] As a further aspect of the present invention: a regional feature circle is drawn with the center point of the deviation straight-line distance as the center and the length of the deviation straight-line distance as the diameter; The area value of the characteristic circle of the region is obtained according to the formula for calculating the area of ​​a circle. The number of coating anomalies within the feature circle of the region is obtained, and the ratio of the number of coating anomalies to the area value of the feature circle of the region is calculated to obtain the coating anomaly ratio. The process for obtaining the number of coating defects is as follows: The number of bubbles, particles, and cracks within the feature circle of the region is obtained. The sum of these numbers gives the number of coating anomalies.

[0012] As a further aspect of the present invention: a preset effective value threshold for coating behavior is tyt, and the effective value of coating behavior TYT is compared with the preset effective value threshold for coating behavior tyt; If the effective value of coating behavior TYT is greater than or equal to the threshold value tyt of the effective value of coating behavior, it indicates that the surface coating of the lithium battery copper foil has good processing quality. If the effective value of coating behavior TYT is less than the threshold value tyt of the effective value of coating behavior, it indicates that the surface coating of the lithium battery copper foil has poor processing quality.

[0013] As a further aspect of the present invention, it also includes a coating anomaly identification module; The coating anomaly identification module, based on the coating quality anomaly signal, performs difference processing on the coating thickness value of each image sub-unit and the preset coating thickness value to obtain the coating thickness deviation value of the image sub-unit. Image sub-units whose coating thickness deviation values ​​fall within the preset range of coating thickness deviation values ​​are categorized as normal image sub-units. Image sub-units whose coating thickness deviation values ​​do not fall within the preset range of coating thickness deviation values ​​are recorded as abnormal image sub-units; Obtain the number of normal image sub-units and the number of abnormal image sub-units; The ratio of the number of abnormal image sub-units to the total number of image sub-units is calculated as follows: When the number of abnormal image sub-units / the total number of image sub-units Yz ≥ 0.6, it indicates that the current coating is at level three abnormality; When 0.6 > number of abnormal image sub-units / total number of image sub-units Yz ≥ 0.3, it indicates that the current coating is at level two anomaly; When 0.3 > number of abnormal image sub-units / total number of image sub-units Yz ≥ 0, it indicates that the current coating is at level one abnormality.

[0014] As a further aspect of the present invention, it also includes a decision analysis module; The decision analysis module obtains the effective value of the coating behavior after coating processing for each product. Lithium-ion battery copper foil with a coating behavior effective value TYT less than the coating behavior effective value threshold tyt is designated as the first-test lithium-ion battery copper foil. Taking the first lithium-ion battery copper foil as the starting point for testing, the effective values ​​of multiple consecutive lithium-ion battery copper foil coating behaviors are identified. Specifically: Establish a planar coordinate system with the effective value of coating behavior on the Y-axis and the number of lithium-ion copper foils on the X-axis. Mark the effective values ​​of coating behavior of multiple consecutive lithium-ion copper foils on the planar coordinate system to obtain the lithium-ion copper foil verification image.

[0015] As a further aspect of the present invention: if multiple consecutive lithium-ion battery copper foil verification images show banded changes based on the effective value threshold of coating behavior, it indicates that the lithium-ion battery copper foil coating equipment is working or that there is an abnormality in the lithium-ion battery copper foil, and an abnormality tracking signal is obtained. If the effective value of the coating behavior in multiple consecutive lithium-ion battery copper foil test images changes linearly with a decreasing trend, it indicates that the lithium-ion battery copper foil coating equipment is malfunctioning, and a signal of malfunction in the lithium-ion battery copper foil coating equipment is obtained. If the effective values ​​of the coating behavior in multiple consecutive lithium-ion battery copper foil test images change linearly with an increasing trend, it indicates that the lithium-ion battery copper foil coating equipment is working normally, and a signal indicating that the lithium-ion battery copper foil coating equipment is working normally is obtained.

[0016] The beneficial effects of this invention are: (1) In this invention, for a coating that meets the requirements for uniform coating thickness, the coating thickness deviation value of each image sub-unit in the coating is obtained. Then, based on the image sub-unit with the maximum coating thickness deviation value and the image sub-unit with the minimum coating thickness deviation value, a first reference circle, a second reference circle and a region feature circle are constructed. The color feature values ​​of the first reference circle and the second reference circle are obtained respectively. The coating color difference value of the coating is obtained based on the color feature values ​​of the first reference circle and the second reference circle. The area of ​​the region feature circle and the number of coating anomalies are obtained to obtain the coating anomaly ratio. Based on the coating anomaly ratio, the coating color difference value and the coating deviation variation value, the effective value of coating behavior is obtained. Based on the effective value of coating behavior, the coating quality under the benchmark of meeting the coating thickness uniformity requirement is identified. (2) The present invention monitors the effective value of coating behavior of each coating. When the effective value of coating behavior of any product is abnormal, the lithium-ion copper foil with the abnormality is recorded as the first verification lithium-ion copper foil. The first verification lithium-ion copper foil is used as the verification starting point to process the effective values ​​of coating behavior of multiple consecutive lithium-ion copper foils. The invention identifies whether the lithium-ion copper foil is an accidental processing abnormality or a processing fault during continuous processing. That is, the identification of the state of lithium-ion copper foil coating equipment and lithium-ion copper foil coating is more accurate. It will not judge the processing abnormality of lithium-ion copper foil coating equipment just because a certain lithium-ion copper foil coating is abnormal. The accuracy is high. Attached Figure Description

[0017] The invention will now be further described with reference to the accompanying drawings.

[0018] Figure 1 This is a flowchart of the first embodiment of the present invention; Figure 2 This is a flowchart of the anomaly identification module of the first embodiment of the present invention; Figure 3 This is a flowchart of the second embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Example 1 Please see Figures 1-2 As shown, the present invention is a coating detection system for the surface treatment of lithium battery copper foil, including an image acquisition module, a primary coating processing module, a secondary coating processing module, a coating anomaly identification module, a decision analysis module, and a cloud management platform; The image acquisition module, the primary coating processing module, the secondary coating processing module, the coating anomaly identification module, and the decision analysis module are electrically connected to the cloud management and control platform. The image acquisition module is used to acquire coating images, preprocess the acquired coating images, segment the preprocessed coating images to obtain several image sub-units of the same area, and transmit the image sub-units to the cloud management platform. The image primary processing module receives image sub-units sent by the cloud management platform, obtains the coating thickness value of each image sub-unit, obtains the coating thickness value group of the image sub-unit, performs variance processing on the coating thickness value group of the image sub-unit to obtain the coating quality signal, and sends the coating quality signal to the cloud management platform. The coating quality signal includes a normal coating quality signal and a abnormal coating quality signal. The coating secondary processing module receives the coating quality normal signal transmitted by the cloud management platform, obtains the coating thickness deviation value of the image sub-unit, processes the coating thickness deviation value of multiple image sub-units to obtain the coating anomaly ratio and coating color difference value, calculates the coating behavior effective value by calculating the coating anomaly ratio and coating color difference value, and completes the coating quality identification based on the coating behavior effective value. The coating anomaly identification module receives coating quality anomaly signals transmitted by the cloud management platform, obtains the number of abnormal image sub-units in the image sub-unit, and compares the number of abnormal image sub-units with the total number of image sub-units to obtain the degree of coating anomaly. The decision analysis module obtains the effective value of coating behavior and evaluates the quality of multiple consecutive coating processes and the status of coating equipment based on the abrupt changes in the effective value of coating behavior.

[0021] The acquisition of coating images involves capturing images using devices such as cameras or scanners. Since the acquired coating images may have problems such as noise and uneven lighting, the preprocessing of coating images includes filtering, noise reduction, and contrast enhancement.

[0022] The image primary processing module is used to obtain the coating thickness value of each image sub-unit, and obtain the coating thickness value group of the image sub-unit; The coating variance is obtained by calculating the coating thickness values ​​of the image sub-units according to the variance calculation formula; Compare the coating variance with the preset coating variance; If the coating variance is less than or equal to the preset coating variance, it indicates that the coating quality of the workpiece is normal, and a normal coating quality signal is obtained. If the coating variance is greater than the preset coating variance, it indicates that the coating quality of the workpiece is abnormal, and a coating quality abnormality signal is obtained.

[0023] The coating secondary processing module, based on the normal coating quality signal, performs difference processing on the coating thickness value of each image sub-unit and the preset coating thickness value to obtain the coating thickness deviation value of the image sub-unit. The image sub-unit that obtains the maximum value of the coating thickness deviation is denoted as the maximum value image sub-unit. The image sub-unit that obtains the minimum value of the coating thickness deviation is denoted as the minimum value image sub-unit. Connect the center point of the maximum value image sub-unit with the center point of the minimum value image sub-unit to obtain the straight-line distance of the deviation; With the center point of the maximum value image sub-unit as the center and the distance from the center point of the maximum value image sub-unit to the center of the deviation straight line as the radius, draw a circle to obtain the first reference circle; A second reference circle is obtained by drawing a circle with the center point of the minimum value image sub-unit as the center and the distance from the center point of the minimum value image sub-unit to the center of the deviation line as the radius; The color of the first reference circle is extracted to obtain its RGB value; Obtain the R value in the first reference circle, and denote it as R1; Obtain the G value in the first reference circle, and denote it as G1; Obtain the B value in the first reference circle, and denote it as B1; The R1, G1, and B1 values ​​in the first reference circle are weighted and the weight of the obtained R1 value is assigned as n1, the weight of the obtained G1 value is assigned as n2, and the weight of the obtained B1 value is assigned as n3. According to formula Y1 RGB The color feature value Y1 of the first reference circle is calculated as R1*n1+G1*n2+B1*b3. RGB Where n1+n2+n3=1, and n3, n2, and n1 are all greater than 0; The color of the second reference circle is extracted to obtain its RGB value; Obtain the R value in the second reference circle, denoted as R2; Obtain the G value in the second reference circle, and denote it as G2; Obtain the value of B in the second reference circle, and denote it as B2; The R2, G2, and B2 values ​​in the second reference circle are weighted and assigned as n1, n2, and n3 respectively. According to formula Y2 RGB The color characteristic value Y2 of the second reference circle is calculated as R2*n1+G2*n2+B2*b3. RGB Where n1+n2+n3=1, and n3, n2, and n1 are all greater than 0; The color feature value Y1 of the first reference circle RGB The color feature value Y2 of the second reference circle RGB The difference was calculated to obtain the coating color difference value Y12. RGB ; Draw a feature circle for the region, with the center point of the deviation straight-line distance as the center and the length of the deviation straight-line distance as the diameter; The area value of the characteristic circle of the region is obtained according to the formula for calculating the area of ​​a circle. The number of coating anomalies within the feature circle of the region is obtained, and the ratio of the number of coating anomalies to the area value of the feature circle of the region is calculated to obtain the coating anomaly ratio. The process for obtaining the number of coating defects is as follows: The number of bubbles, particles, and cracks within the feature circle of the region is obtained. The sum of these three numbers gives the number of coating anomalies. The coating anomaly ratio is denoted as Tyb, and the coating anomaly ratio Tyb is compared with the coating color difference Y12. RGB Processing, that is, through formulas The effective value of coating behavior TYT is calculated, where a1, a2, and a3 are preset proportional coefficients, and a1, a2, and a3 are all greater than 0, and Tpc is the coating deviation variation value. The process for obtaining the coating deviation variation value is as follows: Obtain the coating thickness deviation value of all image sub-units within the coating image, sum the coating thickness deviation values ​​of all image sub-units and take the average value to obtain the coating deviation variation value Tpc; The preset effective value threshold for coating behavior is tyt. The effective value of coating behavior TYT is compared with the preset effective value threshold for coating behavior tyt. If the effective value of coating behavior TYT is greater than or equal to the threshold value tyt of the effective value of coating behavior, it indicates that the surface coating of the lithium battery copper foil has good processing quality. If the effective value of coating behavior TYT is less than the threshold value tyt of the effective value of coating behavior, it indicates that the surface coating of the lithium battery copper foil has poor processing quality.

[0024] The coating anomaly identification module, based on the coating quality anomaly signal, performs difference processing on the coating thickness value of each image sub-unit and the preset coating thickness value to obtain the coating thickness deviation value of the image sub-unit. Image sub-units whose coating thickness deviation values ​​fall within the preset range of coating thickness deviation values ​​are categorized as normal image sub-units. Image sub-units whose coating thickness deviation values ​​do not fall within the preset range of coating thickness deviation values ​​are recorded as abnormal image sub-units; Obtain the number of normal image sub-units and the number of abnormal image sub-units; The ratio of the number of abnormal image sub-units to the total number of image sub-units is calculated as follows: When the number of abnormal image sub-units / the total number of image sub-units Yz ≥ 0.6, it indicates that the current coating is at level three abnormality; When 0.6 > number of abnormal image sub-units / total number of image sub-units Yz ≥ 0.3, it indicates that the current coating is at level two anomaly; When 0.3 > number of abnormal image sub-units / total number of image sub-units Yz ≥ 0, it indicates that the current coating is at level one anomaly; Among them, the anomaly level of coating level three is higher than that of coating level two, and the anomaly level of coating level two is higher than that of coating level one. The higher the coating abnormality level, the worse the current processing quality of the lithium battery copper foil surface coating. Monitoring the degree of abnormality in the processing of the lithium battery copper foil surface coating facilitates management personnel to improve the processing quality of the lithium battery copper foil surface coating and realizes visualized management of the processing quality of the lithium battery copper foil surface coating.

[0025] Example 2 Please see Figure 2 As shown, the present invention is a coating inspection system for the surface treatment of lithium battery copper foil. Based on Example 1, in order to solve the problem of coating quality and coating equipment status when a single product quality problem occurs during continuous coating processing; Specifically, the decision analysis module obtains the effective value of the coating behavior after coating processing for each product; Lithium-ion battery copper foil with a coating behavior effective value TYT less than the coating behavior effective value threshold tyt is designated as the first-test lithium-ion battery copper foil. Taking the first lithium-ion battery copper foil as the starting point for testing, the effective values ​​of multiple consecutive lithium-ion battery copper foil coating behaviors are identified. Specifically: Establish a plane coordinate system with the effective value of coating behavior as the Y-axis and the number of lithium battery copper foils as the X-axis. Mark the effective values ​​of coating behavior of multiple consecutive lithium battery copper foils on the plane coordinate system to obtain the lithium battery copper foil verification image. If multiple consecutive lithium-ion battery copper foil verification images show banded changes based on the effective value threshold of coating behavior, it indicates that the lithium-ion battery copper foil coating equipment is working or that there is an abnormality in the lithium-ion battery copper foil, and an abnormality tracking signal is obtained. If the effective value of the coating behavior in multiple consecutive lithium-ion battery copper foil test images changes linearly with a decreasing trend, it indicates that the lithium-ion battery copper foil coating equipment is malfunctioning, and a signal of malfunction in the lithium-ion battery copper foil coating equipment is obtained. If the effective values ​​of the coating behavior in multiple consecutive lithium-ion battery copper foil test images change linearly with an increasing trend, it indicates that the lithium-ion battery copper foil coating equipment is working normally, and a signal indicating that the lithium-ion battery copper foil coating equipment is working normally is obtained.

[0026] Based on the anomaly tracking signal, the coated lithium battery copper foil is inspected first. If there is no problem with the lithium battery copper foil, the lithium battery copper foil coating equipment is inspected. Based on the abnormal operation signals of the lithium battery copper foil coating equipment, the lithium battery copper foil coating equipment is inspected.

[0027] One of the core points of this invention is that by segmenting the acquired coating image to obtain several image sub-units of the same area, and performing variance processing on the coating thickness values ​​of all image sub-units, the quality of the entire coating can be identified from the perspective of coating thickness uniformity. One of the core points of this invention is to obtain the coating thickness deviation value of each image sub-unit in the coating that meets the coating thickness uniformity requirement, and then construct a first reference circle, a second reference circle, and a region feature circle based on the image sub-unit with the maximum coating thickness deviation value and the image sub-unit with the minimum coating thickness deviation value. The color feature values ​​of the first reference circle and the second reference circle are obtained respectively. The coating color difference value of the coating is obtained based on the color feature values ​​of the first reference circle and the second reference circle. The area of ​​the region feature circle and the number of coating anomalies are obtained to obtain the coating anomaly ratio. Based on the coating anomaly ratio, the coating color difference value, and the coating deviation variation value, the effective value of coating behavior is obtained. Based on the effective value of coating behavior, the coating quality under the benchmark of meeting the coating thickness uniformity requirement is identified. One of the core aspects of this invention is the monitoring of the effective value of coating behavior for each coating. When the effective value of coating behavior for any product is abnormal, the lithium-ion copper foil with the abnormality is recorded as the first verified lithium-ion copper foil. Using the first verified lithium-ion copper foil as the verification starting point, the effective values ​​of coating behavior for multiple consecutive lithium-ion copper foils are processed to identify whether the abnormality in the continuous processing of the lithium-ion copper foil is an accidental processing abnormality or a processing fault. In other words, the identification of the state of the lithium-ion copper foil coating equipment and the lithium-ion copper foil coating is more accurate. It will not determine that the processing of the lithium-ion copper foil coating equipment is abnormal just because a certain lithium-ion copper foil coating is abnormal, thus achieving high accuracy.

[0028] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A coating inspection system for the surface treatment of lithium battery copper foil, characterized in that, include: The image acquisition module is used to acquire a coating image, preprocess the acquired coating image, segment the preprocessed coating image to obtain several image sub-units of the same area, and transmit the image sub-units to the cloud management platform. The image primary processing module receives image sub-units sent by the cloud management platform, obtains the coating thickness value of each image sub-unit to obtain the coating thickness value group of the image sub-unit, performs variance processing on the coating thickness value group of the image sub-unit to obtain the coating quality signal, and sends the coating quality signal to the cloud management platform. The coating quality signal includes a normal coating quality signal and a abnormal coating quality signal. The coating secondary processing module receives a normal coating quality signal transmitted from the cloud management platform, obtains the coating thickness deviation value of the image sub-unit, processes the coating thickness deviation values ​​of multiple image sub-units to obtain the coating anomaly ratio and coating color difference value, calculates the coating behavior effective value by calculating the coating anomaly ratio and coating color difference value, and completes the coating quality identification based on the coating behavior effective value. The coating anomaly ratio is denoted as Tyb, and the coating color difference value Y12 is denoted as Tyb. RGB Through formula The effective value of coating behavior TYT is calculated, where a1, a2, and a3 are preset proportional coefficients, and a1, a2, and a3 are all greater than 0, and Tpc is the coating deviation variation value. Obtain the coating thickness deviation value of all image sub-units within the coating image, sum the coating thickness deviation values ​​of all image sub-units and take the average value to obtain the coating deviation variation value Tpc.

2. The coating inspection system for lithium battery copper foil surface treatment according to claim 1, characterized in that, The process of acquiring coating quality signals is as follows: Compare the coating variance with the preset coating variance; If the coating variance is less than or equal to the preset coating variance, it indicates that the coating quality of the workpiece is normal, and a normal coating quality signal is obtained. If the coating variance is greater than the preset coating variance, it indicates that the coating quality of the workpiece is abnormal, and a coating quality abnormality signal is obtained.

3. The coating inspection system for lithium battery copper foil surface treatment according to claim 1, characterized in that, The process of obtaining the coating color difference is as follows: The image sub-unit that obtains the maximum value of the coating thickness deviation is denoted as the maximum value image sub-unit. The image sub-unit that obtains the minimum value of the coating thickness deviation is denoted as the minimum value image sub-unit. Connect the center point of the maximum value image sub-unit with the center point of the minimum value image sub-unit to obtain the straight-line distance of the deviation; With the center point of the maximum value image sub-unit as the center and the distance from the center point of the maximum value image sub-unit to the center of the deviation straight line as the radius, draw a circle to obtain the first reference circle; A second reference circle is obtained by drawing a circle with the center point of the minimum value image sub-unit as the center and the distance from the center point of the minimum value image sub-unit to the center of the deviation line as the radius.

4. The coating inspection system for lithium battery copper foil surface treatment according to claim 3, characterized in that, The color of the first reference circle is extracted to obtain its RGB value; Obtain the R value in the first reference circle, and denote it as R1; Obtain the G value in the first reference circle, and denote it as G1; Obtain the B value in the first reference circle, and denote it as B1; The R1, G1, and B1 values ​​in the first reference circle are weighted and the weight of the obtained R1 value is assigned as n1, the weight of the obtained G1 value is assigned as n2, and the weight of the obtained B1 value is assigned as n3. According to formula Y1 RGB The color feature value Y1 of the first reference circle is calculated as R1*n1+G1*n2+B1*b3. RGB , where n1+n2+n3=1, and n3, n2, and n1 are all greater than 0.

5. A coating inspection system for lithium battery copper foil surface treatment according to claim 4, characterized in that, The color of the second reference circle is extracted to obtain its RGB value; Obtain the R value in the second reference circle, and denote it as R2; Obtain the G value in the second reference circle, and denote it as G2; Obtain the value of B in the second reference circle, and denote it as B2; The R2, G2, and B2 values ​​in the second reference circle are weighted and assigned as n1, n2, and n3 respectively. According to formula Y2 RGB The color characteristic value Y2 of the second reference circle is calculated as R2*n1+G2*n2+B2*b3. RGB Where n1+n2+n3=1, and n3, n2, and n1 are all greater than 0; The color feature value Y1 of the first reference circle RGB The color feature value Y2 of the second reference circle RGB The difference was calculated to obtain the coating color difference value Y12. RGB .

6. The coating inspection system for lithium battery copper foil surface treatment according to claim 3, characterized in that, Draw a feature circle for the region, with the center point of the deviation straight line distance as the center and the length of the deviation straight line distance as the diameter; The area value of the regional characteristic circle is obtained according to the formula for calculating the area of ​​a circle. The number of coating anomalies within the feature circle of the region is obtained, and the ratio of the number of coating anomalies to the area value of the feature circle of the region is calculated to obtain the coating anomaly ratio. The process for obtaining the number of coating defects is as follows: The number of bubbles, particles, and cracks within the feature circle of the region is obtained. The sum of these numbers gives the number of coating anomalies.

7. The coating inspection system for lithium battery copper foil surface treatment according to claim 1, characterized in that, The preset effective value threshold for coating behavior is tyt. The effective value of coating behavior TYT is compared with the preset effective value threshold for coating behavior tyt. If the effective value of coating behavior TYT is greater than or equal to the threshold value tyt of the effective value of coating behavior, it indicates that the surface coating of the lithium battery copper foil has good processing quality. If the effective value of coating behavior TYT is less than the threshold value tyt of the effective value of coating behavior, it indicates that the surface coating of the lithium battery copper foil has poor processing quality.

8. The coating inspection system for lithium battery copper foil surface treatment according to claim 1, characterized in that, It also includes a coating anomaly detection module; The coating anomaly identification module, based on the coating quality anomaly signal, performs difference processing on the coating thickness value of each image sub-unit and the preset coating thickness value to obtain the coating thickness deviation value of the image sub-unit. Image sub-units whose coating thickness deviation values ​​fall within the preset range of coating thickness deviation values ​​are categorized as normal image sub-units. Image sub-units whose coating thickness deviation values ​​do not fall within the preset range of coating thickness deviation values ​​are recorded as abnormal image sub-units; Obtain the number of normal image sub-units and the number of abnormal image sub-units; The ratio of the number of abnormal image sub-units to the total number of image sub-units is calculated as follows: When the number of abnormal image sub-units / the total number of image sub-units Yz ≥ 0.6, it indicates that the current coating is at level three abnormality; When 0.6 > number of abnormal image sub-units / total number of image sub-units Yz ≥ 0.3, it indicates that the current coating is at level two anomaly; When 0.3 > number of abnormal image sub-units / total number of image sub-units Yz ≥ 0, it indicates that the current coating is at level one abnormality.

9. A coating inspection system for lithium battery copper foil surface treatment according to claim 1, characterized in that, It also includes a decision analysis module; The decision analysis module obtains the effective value of the coating behavior after coating processing for each product. Lithium-ion battery copper foil with a coating behavior effective value TYT less than the coating behavior effective value threshold tyt is designated as the first-test lithium-ion battery copper foil. Taking the first lithium-ion battery copper foil as the starting point for testing, the effective values ​​of multiple consecutive lithium-ion battery copper foil coating behaviors are identified. Specifically: Establish a planar coordinate system with the effective value of coating behavior on the Y-axis and the number of lithium-ion copper foils on the X-axis. Mark the effective values ​​of coating behavior of multiple consecutive lithium-ion copper foils on the planar coordinate system to obtain the lithium-ion copper foil verification image.

10. A coating inspection system for lithium battery copper foil surface treatment according to claim 9, characterized in that, If multiple consecutive lithium battery copper foil verification images show banded changes based on the effective value threshold of coating behavior, it indicates that the lithium battery copper foil coating equipment is working or that there is an abnormality in the lithium battery copper foil, and an abnormality tracking signal is obtained. If the effective value of the coating behavior in multiple consecutive lithium-ion battery copper foil test images changes linearly with a decreasing trend, it indicates that the lithium-ion battery copper foil coating equipment is malfunctioning, and an abnormal signal for the lithium-ion battery copper foil coating equipment is obtained. If the effective values ​​of the coating behavior in multiple consecutive lithium-ion battery copper foil test images change linearly with an increasing trend, it indicates that the lithium-ion battery copper foil coating equipment is working normally, and a signal indicating that the lithium-ion battery copper foil coating equipment is working normally is obtained.

Images