Automatic electroplating control system and method based on image recognition

Through image recognition and edge computing technology, real-time monitoring and adjustment of automated electroplating control systems is achieved, which solves the problems of quality instability and inefficiency caused by manual operations in traditional electroplating processes, and improves the degree of automation of the electroplating process and product quality.

CN118996590AInactive Publication Date: 2024-11-22WUHAN PURUI SAISHENG TECH CO LTD
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411098790.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-22
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional electroplating technology relies on manual operation, resulting in unstable electroplating quality, low efficiency, and easy to cause artificial errors, affecting product quality.

Method used

An automated plating control system based on image recognition is adopted, and the edge computing module and image acquisition module combine natural language processing and image recognition technology to monitor and adjust the plating process in real time to achieve automated control.

Benefits of technology

It significantly improves the degree of automation and production efficiency of the electroplating process, ensures the quality stability and uniformity of the electroplating layer, reduces rework and scrap rate, and improves the consistency and reliability of the electroplating quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118996590A_ABST
    Figure CN118996590A_ABST
Patent Text Reader

Abstract

The invention provides an automatic electroplating control system and method based on image recognition. The information acquisition module is in communication connection with the edge calculation module and is used for acquiring part machining information of the target part; the first image acquisition module is used for acquiring first image information of all target parts on the first storage table; after receiving the part machining information and the first image information, the edge calculation module generates module configuration information by combining the part machining information with the first image information and utilizing a natural language processing technology and an image recognition technology; the second image acquisition module is used for acquiring second image information of the target component on the second storage table; the edge calculation module receives the second image information and then generates feedback adjustment information by using an image recognition technology. The electroplating module receives the feedback adjustment information and adjusts the configuration of the second module according to the feedback adjustment information. The electroplating device has the effect of improving the electroplating quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of automated electroplating, and in particular relates to an automated electroplating control system and method based on image recognition. Background Art

[0002] With the advancement of science and technology and the intensification of market competition, the manufacturing industry has higher and higher requirements for electroplating technology, requiring not only stable and uniform quality of the electroplating layer, but also efficient and environmentally friendly production process. In modern industrial production, electroplating technology is widely used in many fields such as automobile manufacturing, electronic products, aerospace, medical equipment, etc. These industries have extremely high requirements for the performance of the electroplating layer. For example, in automobile manufacturing, the electroplating layer not only needs to have a good decorative effect, but also needs to have functions such as corrosion resistance and wear resistance to ensure the long-term use of the vehicle in various environments. In electronic products, the uniformity and conductivity of the electroplating layer directly affect the performance and life of the product.

[0003] In traditional electroplating processes, the control of electroplating quality usually relies on manual operation and experience judgment. This method is not only inefficient, but also prone to human errors, resulting in unstable electroplating quality. Workers need to judge the thickness, uniformity and surface quality of the electroplating layer based on experience during the operation, which is not only time-consuming and laborious, but also difficult to ensure consistent accuracy for each operation. Due to the different experience and skill levels of each worker, the quality of electroplating often fluctuates greatly. In addition, manual detection of electroplating quality is subjective, which can easily lead to misjudgment and missed judgment, affecting the quality of the final product. Summary of the invention

[0004] The present invention provides an automatic electroplating control system and method based on image recognition, so as to solve the problem of low electroplating quality in traditional electroplating methods.

[0005] In a first aspect, the present invention provides an automated electroplating control system based on image recognition, the system comprising a bracket, the bracket comprising a support frame and a support platform, the support platform being fixedly arranged at the bottom of the support frame, a plurality of cavities being opened in the support platform as storage rooms, an edge computing module being placed in the storage room, and the system further comprising: A first storage platform, disposed on the support platform, for storing target parts to be processed; An information acquisition module, which is in communication with the edge computing module and is used to acquire part processing information of the target part and send the part processing information to the edge computing module; A first image acquisition module, which is disposed on the top of the support frame and directly above the first storage platform, is communicatively connected to the edge computing module, and is used to acquire first image information of all the target parts located on the first storage platform, and send the first image information to the edge computing module; After receiving the part processing information and the first image information, the edge computing module combines the part processing information and the first image information and generates module configuration information by using natural language processing technology and image recognition technology; an activation processing module, which is in communication with the edge computing module, and is used to receive the module configuration information, change the preset activation processing module configuration to the first module configuration according to the module configuration information, and perform activation processing on the target part based on the first module configuration; A part preprocessing module, disposed on the support platform, for providing a part shielding block and a processing substrate adapted to the target part; an auxiliary robot arm, movably disposed on the support platform, used to clamp the target part and move it between the first storage platform, the activation processing module and the part pre-processing module, and also used to combine the target part, the part shielding block and the processing substrate into a target assembly in the part pre-processing module; an electroplating module, disposed on the support platform and the support frame and in communication connection with the edge computing module, for receiving the module configuration information, changing the preset electroplating module configuration to a second module configuration according to the module configuration information, and performing electroplating processing on the target component based on the second module configuration; A second storage table, disposed on the support platform, for storing the processed target components; A second image acquisition module, disposed on the top of the support frame and directly above the second storage platform, is communicatively connected to the edge computing module, and is used to acquire second image information of the target component located on the second storage platform, and send the second image information to the edge computing module; After receiving the second image information, the edge computing module generates feedback adjustment information using image recognition technology, and the electroplating module receives the feedback adjustment information and adjusts the second module configuration according to the feedback adjustment information; The auxiliary robot arm is also used to clamp the target component and move it between the part pretreatment module, the electroplating module and the second storage station.

[0006] Optionally, the activation treatment module includes an activation treatment container, a solution configuration unit, a waste liquid collection tank and an activation treatment control unit, the activation treatment container is arranged on the support platform, the activation treatment container includes an ultrasonic cleaning tank, an acid cleaning tank, an alkaline cleaning tank and an activation treatment tank, the waste liquid collection tank, the solution configuration unit and the activation treatment control unit are all arranged in the storage room, the solution configuration unit includes a plurality of solution tanks, and different types of pretreatment solutions are respectively stored in the plurality of solution tanks, all of the solution tanks are connected to the bottom of the activation treatment container through a lifting pump and a solenoid valve, and the waste liquid collection tank is connected to the bottom of the activation treatment container through the activation solenoid valve; The activation processing control unit is communicatively connected with the edge computing module, all the lifting pumps and all the activation solenoid valves, and the activation processing control unit receives the module configuration information sent by the edge computing module. The activation processing control unit changes the preset activation processing module configuration to the first module configuration according to the activation module configuration information in the module configuration information. The first module configuration includes the equipment start and stop time nodes of all the lifting pumps and all the activation solenoid valves. The activation processing control unit controls all the lifting pumps and all the activation solenoid valves based on the first module configuration to complete the pretreatment solution configuration work of the activation processing container.

[0007] Optionally, the system also includes a third image acquisition module, which is arranged on the support frame and located at any one of the two ends in the length direction of the support platform. The third image acquisition module is used to collect third image information of the target part when the auxiliary robotic arm clamps the target part and moves it from the activation processing module to the part preprocessing module, and send the third image information to the edge computing module. After receiving the third image information, the edge computing module uses image recognition technology to generate a solution replacement instruction, and sends the solution replacement instruction to the activation processing control unit. The activation processing control unit receives and executes the solution replacement instruction to adjust the first module configuration. The activation processing control unit controls all the lifting pumps and all the activation solenoid valves based on the adjusted first module configuration to complete the solution replacement work of the activation processing container.

[0008] Optionally, the target part surface includes a to-be-processed area that needs to be processed and a protection area that does not need to be processed, the processing substrate and the part shielding block are both made of corrosion-resistant materials, the cross-sectional shape of the part shielding block is the same as the shape formed by the protection area, a substrate liquid inlet hole and a substrate liquid outlet hole are formed through the processing substrate surface, and a drainage groove is also formed on the processing substrate surface, and one end of the drainage groove is connected to the substrate liquid outlet hole; When the auxiliary robot arm combines the target part, the part shielding block and the processing substrate into a target assembly in the part preprocessing module, the target part is fixed to the surface of the processing substrate, and a processing cavity filled with electroplating liquid is formed between the area to be processed on the surface of the target part and the surface of the processing substrate, the end of the drainage groove away from the substrate liquid outlet and all the substrate liquid inlet holes are located in the processing cavity, the substrate liquid outlet is located outside the processing cavity, the part shielding block is fixed to the protection area on the surface of the target part, and the part shielding block is tightly fitted to the surface of the target part.

[0009] Optionally, the electroplating module includes an electroplating control unit, an electroplating liquid storage tank, an electroplating waste liquid collection tank and a pressurizing unit, the pressurizing unit includes a hydraulic device fixedly arranged on the top of the support frame and a processing platform arranged on the supporting platform, the processing platform is located directly below the hydraulic device, and the processing platform is vertically penetrated by the top surface of the processing platform and the supporting platform to form a platform liquid inlet hole and a platform liquid outlet hole, when the auxiliary robot arm places the target component on the processing platform in the electroplating module, the base liquid inlet hole is correspondingly connected to the platform liquid inlet hole, and the base liquid outlet hole is correspondingly connected to the platform liquid outlet hole; The electroplating control unit, the electroplating liquid storage tank and the electroplating waste liquid collection tank are all arranged in the storage room, the electroplating liquid storage tank is connected to the inner top surface of the supporting platform through a liquid adding pipe, and all the platform liquid inlets are connected to the liquid adding pipe, and the liquid adding pipe is provided with a liquid adding solenoid valve, a liquid adding pump and an electronic flow meter, the electroplating waste liquid collection tank is connected to the inner top surface of the supporting platform through a liquid outlet pipe, and all the platform liquid outlets are connected to the liquid outlet pipe, and the liquid outlet pipe is provided with a liquid outlet solenoid valve and a liquid extraction pump; The electroplating control unit is communicatively connected with the edge computing module, the hydraulic device, the liquid adding solenoid valve, the liquid adding pump, the electronic flow meter, the liquid outlet solenoid valve and the liquid extraction pump. The electroplating control unit receives the module configuration information sent by the edge computing module. The electroplating control unit changes the preset electroplating module configuration to a second module configuration according to the electroplating module configuration information in the module configuration information. The second module configuration includes the equipment start and stop time nodes of the hydraulic device, the liquid adding solenoid valve, the liquid adding pump, the liquid outlet solenoid valve and the liquid extraction pump.

[0010] In a second aspect, the present invention further provides an automated electroplating control method based on image recognition, which is applied to the automated electroplating control system described in the first aspect, and the method comprises the following steps: The first image acquisition module acquires first image information of all target parts located on the first storage table, and sends the first image information to the edge computing module; The information acquisition module acquires the part processing information of the target part and sends the part processing information to the edge computing module; After receiving the part processing information and the first image information, the edge computing module combines the part processing information and the first image information and generates module configuration information by using natural language processing technology and image recognition technology; The activation processing module receives the module configuration information, and changes the preset activation processing module configuration to the first module configuration according to the module configuration information; the electroplating module receives the module configuration information, and changes the preset electroplating module configuration to the second module configuration according to the module configuration information; The auxiliary robot arm clamps the target part and moves it from the first storage station to the activation processing module, and the activation processing module performs activation processing on the target part based on the first module configuration; The auxiliary robot arm holds the target part after activation treatment and moves it to a part pre-processing module that provides a part shielding block and a processing substrate adapted for the target part, and the auxiliary robot arm combines the target part, the part shielding block and the processing substrate into a target assembly in the part pre-processing module; The auxiliary robot arm clamps the target component and moves it to the electroplating module, and the electroplating module performs electroplating processing on the target component based on the configuration of the second module; The auxiliary robot arm clamps the target component after electroplating and moves it to the second storage platform, and places the target component on the second storage platform; The second image acquisition module acquires second image information of the target component located on the second storage table, and sends the second image information to the edge computing module; After receiving the second image information, the edge computing module generates feedback adjustment information using image recognition technology, and the electroplating module receives the feedback adjustment information and adjusts the second module configuration according to the feedback adjustment information.

[0011] Optionally, after the edge computing module receives the part processing information and the first image information, combining the part processing information and the first image information and using natural language processing technology and image recognition technology to generate module configuration information includes the following steps: After receiving the part processing information, the edge computing module uses natural language processing technology to extract part material type information and part electroplating process information from the part processing information; The edge computing module retrieves corresponding electroplating liquid type information from a preset electroplating processing database according to the part material type information; The edge computing module generates electroplating control timeline information of the electroplating module according to the part electroplating process information, and integrates the electroplating liquid type information and the electroplating control timeline information into electroplating module configuration information, wherein the electroplating control timeline information includes the start and stop time nodes of all devices in the electroplating module; After receiving the first image information, the edge computing module uses image recognition technology to analyze the first image information to obtain the part surface state information of the target part, and generates activation module configuration information by combining the part surface state information and the part material type information.

[0012] Optionally, after receiving the first image information, the edge computing module uses image recognition technology to analyze the first image information to obtain part surface state information of the target part, and generates activation module configuration information in combination with the part surface state information and the part material type information, including the following steps: The edge computing module retrieves corresponding pretreatment solution type information and pretreatment solution initial concentration information corresponding to each pretreatment solution type information from the electroplating processing database according to the part material type information, wherein the pretreatment solution type information includes an acid solution, an alkaline solution, and an activation treatment solution; After receiving the first image information, the edge computing module identifies all first target image regions containing the target parts in the first image information through a preset image recognition model, wherein the image recognition model is pre-trained using multiple types of part image data sets; The edge computing module extracts all the first target image areas from the first image information to obtain a plurality of first target part images; For each first target part image, the edge computing module preprocesses the first target part image into a first grayscale image, and processes the first grayscale image by a mathematical morphology method to complete the first surface impurity edge of the target part in the first grayscale image, the edge computing module uses a threshold segmentation algorithm to separate the first surface impurities from the image background of the first grayscale image, and extracts the first impurity image features of the first surface impurities in the first grayscale image, the edge computing module locates the first surface impurities in the first grayscale image based on the first impurity image features and uses a local binary pattern algorithm to obtain the first impurity size of the first surface impurities, and the edge computing module uses the ratio between the first impurity size and the image size of the first grayscale image as the first impurity coverage rate of the first target part image; The edge computing module calculates the first impurity coverage rate of all the first target part images by averaging to obtain an average impurity coverage rate, and uses the average impurity coverage rate as the part surface state information of the target part in the first image information; The edge computing module adjusts the initial concentration information of the pretreatment solution according to the average impurity coverage to obtain the target concentration information of the pretreatment solution, and generates activation module configuration information in combination with the pretreatment solution type information and the pretreatment solution target concentration information.

[0013] Optionally, the method further comprises the following steps: When the auxiliary robot arm holds the target part and moves it from the activation processing module to the part preprocessing module, the third image acquisition module acquires the third image information of the target part and sends the third image information to the edge computing module; After receiving the third image information, the edge computing module identifies all second target image regions containing the target parts in the third image information through the image recognition model; The edge computing module extracts all the second target image areas from the third image information to obtain a plurality of second target part images; For each second target part image, the edge computing module preprocesses the second target part image into a second grayscale image, and processes the second grayscale image by a mathematical morphology method to complete the second surface impurity edge of the target part in the second grayscale image, the edge computing module uses a threshold segmentation algorithm to separate the second surface impurities from the image background of the second grayscale image, and extracts the second impurity image features of the second surface impurities in the second grayscale image, the edge computing module locates the second surface impurities in the second grayscale image based on the second impurity image features and uses a local binary pattern algorithm to obtain the second impurity size of the second surface impurities, and the edge computing module uses the ratio between the second impurity size and the image size of the second grayscale image as the second impurity coverage rate of the second target part image; When the edge computing module determines that the second impurity coverage exceeds a preset coverage threshold, the edge computing module generates a solution replacement instruction and sends the solution replacement instruction to the activation processing control unit in the activation processing module; The activation process control unit receives and executes the solution replacement instruction to adjust the first module configuration, and the activation process control unit completes the solution replacement work of the activation process container based on the adjusted first module configuration.

[0014] Optionally, the edge computing module generates feedback adjustment information by using image recognition technology after receiving the second image information, including the following steps: After receiving the second image information, the edge computing module pre-processes the second image information; The edge computing module uses a target detection algorithm to identify a target component image region in the second image information, where the target component image region is an image region in the second image information that includes a to-be-processed region; The edge computing module extracts target component image features from the target component image region, wherein the target component image features include at least one or more features of image color features, image shape features, image edge features, and image texture features; The edge computing module compares the target component image features with preset electroplating quality standards and generates feedback adjustment information based on the comparison results.

[0015] The beneficial effects of the present invention are: First of all, the present invention greatly improves the automation level and production efficiency of the electroplating process. By introducing an automated control system, all steps are automatically completed by the system, reducing manual intervention and significantly improving production efficiency. The automated movement and operation of the auxiliary robot between modules ensures the continuity and efficiency of the electroplating process, and avoids time waste and errors caused by manual operation. Secondly, the present invention achieves accurate acquisition and real-time monitoring of part processing information by introducing image recognition and edge computing technology. The image acquisition module in the present invention can accurately collect image information of parts, and perform real-time analysis through the edge computing module to generate module configuration information. This precise image recognition and data analysis technology ensures the quality stability and uniformity of the electroplating layer, and avoids quality problems caused by human misjudgment.

[0016] On the other hand, the automated electroplating system of the present invention can automatically perform feedback adjustment, further improving the consistency and reliability of the electroplating quality. After the electroplating process is completed, the system uses the second image acquisition module to capture images of the processed target components, and sends the image information to the edge computing module for analysis. The edge computing module generates feedback adjustment information based on the analysis results and sends it to the electroplating module, which adjusts according to the feedback adjustment information. This closed-loop control system ensures that the quality of each electroplated component meets the expected standards and reduces rework and scrap rates due to substandard quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the structure of an automated electroplating control system based on image recognition in one embodiment of the present application.

[0018] Figure 2 It is a schematic structural diagram of an activation processing module in one embodiment of the present application.

[0019] Figure 3 It is a schematic structural diagram of a processed substrate in one embodiment of the present application.

[0020] Figure 4 This is a schematic diagram of the structure of an electroplating module in one embodiment of the present application.

[0021] Figure 5 It is a schematic flow chart of an automated electroplating control method based on image recognition in one embodiment of the present application.

[0022] Description of reference numerals: 1. Support frame; 2. Support platform; 3. Storage room; 4. Edge computing module; 5. First storage table; 7. First image acquisition module; 8. Activation processing module; 9. Electroplating module; 10. Auxiliary robot arm; 11. Parts pretreatment module; 12. Second storage table; 13. Second image acquisition module; 14. Third image acquisition module; 15. Processing substrate; 81. Activation processing container; 82. Solution configuration unit; 83. Waste liquid collection tank; 84. Activation processing control unit; 85. Lifting pump; 8 6. Activation solenoid valve; 811. Ultrasonic cleaning tank; 812. Pickling tank; 813. Alkaline cleaning tank; 814. Activation treatment tank; 151. Substrate liquid inlet hole; 152. Substrate liquid outlet hole; 153. Liquid discharge groove; 91. Electroplating control unit; 92. Electroplating liquid storage tank; 93. Electroplating waste liquid collection tank; 94. Pressurizing unit; 95. Liquid adding solenoid valve; 96. Liquid adding pump; 97. Electronic flow meter; 98. Liquid outlet solenoid valve; 99. Liquid extraction pump; 941. Hydraulic device; 942. Processing platform. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0024] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0025] Reference Figure 1 The present invention discloses an automatic electroplating control system based on image recognition. The system includes a bracket, which includes a support frame 1 and a support platform 2. The support platform 2 is fixedly arranged at the bottom of the support frame 1. A plurality of cavities are opened in the support platform 2 as storage rooms 3. An edge computing module 4 is placed in the storage room 3. The system also includes: A first storage table 5 is provided on the support platform 2 and is used to store target parts to be processed; An information acquisition module, which is in communication with the edge computing module 4, is used to acquire part processing information of a target part and send the part processing information to the edge computing module 4; The first image acquisition module 7 is arranged on the top of the support frame 1 and is located directly above the first storage platform 5, and is connected to the edge computing module 4 for communication, and is used to acquire the first image information of all target parts located on the first storage platform 5, and send the first image information to the edge computing module 4; After receiving the part processing information and the first image information, the edge computing module 4 combines the part processing information and the first image information and generates module configuration information by using natural language processing technology and image recognition technology; The activation processing module 8 is connected to the edge computing module 4 for receiving module configuration information, changing the preset activation processing module 8 configuration to the first module configuration according to the module configuration information, and performing activation processing on the target part based on the first module configuration; The part pre-processing module 11 is arranged on the supporting platform 2 and is used to provide a part shielding block and a processing substrate 15 adapted to the target part; The auxiliary robot arm 10 is movably disposed on the support platform 2, and is used to clamp the target part and move it between the first storage platform 5, the activation processing module 8 and the part pre-processing module 11, and is also used to combine the target part, the part shielding block and the processing substrate 15 into a target assembly in the part pre-processing module 11; The electroplating module 9 is arranged on the support platform 2 and the support frame 1 and is in communication connection with the edge computing module 4, and is used to receive module configuration information, change the preset electroplating module 9 configuration to the second module configuration according to the module configuration information, and perform electroplating processing on the target component based on the second module configuration; The second storage table 12 is arranged on the support platform 2 and is used to store the processed target components; The second image acquisition module 13 is arranged on the top of the support frame 1 and is located directly above the second storage platform 12, and is connected to the edge computing module 4 for communication, and is used to acquire the second image information of the target component located on the second storage platform 12, and send the second image information to the edge computing module 4; After receiving the second image information, the edge computing module 4 generates feedback adjustment information using image recognition technology, and the electroplating module 9 receives the feedback adjustment information and adjusts the second module configuration according to the feedback adjustment information; The auxiliary robot arm 10 is also used to clamp the target component and move it between the part pretreatment module 11, the electroplating module 9 and the second storage station 12.

[0026] In this embodiment, the complete electroplating process flow of the automated electroplating control system based on image recognition is as follows: First, the target parts to be processed are placed on the first storage platform 5 set on the support platform 2. The first storage platform 5 is an area dedicated to storing parts to be processed, providing a stable platform to ensure that the parts are in the correct position before starting processing. The information acquisition module obtains the part processing information of these target parts through the electroplating processing scheduling system in the background, and sends this information to the edge computing module 4 stored in the support platform 2. The part processing information includes the specifications, dimensions, materials, etc. of the parts, which are important basis for subsequent processing steps. The edge computing module 4 is an efficient data processing unit that can perform data processing and analysis close to the data source, reducing the delay in data transmission. After receiving the part processing information, the edge computing module 4 will analyze it in combination with the first image information obtained from the first image acquisition module 7. The first image acquisition module 7 is set at the top of the support frame 1 and is located directly above the first storage platform 5. The image information of the target part is obtained through a camera or other image acquisition device. The image information includes the shape and surface state of the part, which will be used for subsequent image recognition and processing.

[0027] The edge computing module 4 generates module configuration information using natural language processing technology and image recognition technology. Natural language processing technology is an artificial intelligence technology that can understand and process human language and extract key information from part processing information. Image recognition technology is a computer vision technology that can identify specific patterns and features from images to determine the state and position of parts. Combining these two technologies, the module configuration information generated by the edge computing module 4 includes specific configuration parameters of each processing module, such as electroplating time, current intensity, etc. Next, the activation processing module 8 will communicate with the edge computing module 4, receive the generated module configuration information, and change the preset activation processing module 8 configuration to the first module configuration based on this information. The activation processing module 8 is a device for pre-treating the surface of a part, removing the oxide layer or contaminants on the surface of the part by chemical or physical methods, and increasing the activity of the surface of the part so that the subsequent electroplating process can be better carried out. The first module configuration is a configuration scheme customized according to the specific situation of the part to ensure the best effect of the activation treatment.

[0028] The processed target parts will be moved to the part preprocessing module 11 by the auxiliary robot arm 10. The auxiliary robot arm 10 is an automated mechanical device that can move parts between different processing modules to realize an automated production process. The part preprocessing module 11 is arranged on the support platform 2, and provides an adaptive part shielding block and a processing substrate 15. The part shielding block is a device used to protect the parts of the part that do not need to be electroplated, and prevents the plating solution from contacting these parts by means of a physical barrier. The processing substrate 15 is a device for fixing the parts to ensure that the parts remain stable during the electroplating process. The auxiliary robot arm 10 will combine the target parts, the part shielding block and the processing substrate 15 into a target assembly in the part preprocessing module 11. The target assembly is a part assembly that has been preprocessed and is ready for electroplating, including the parts to be electroplated, the shielding block for protection and the substrate for fixing. After the combination is completed, the auxiliary robot arm 10 will move the target assembly to the electroplating module 9.

[0029] The electroplating module 9 is arranged on the support platform 2 and the support frame 1, and is connected to the edge computing module 4 in communication. The electroplating module 9 is a device for electroplating parts, and a metal coating is formed on the surface of the parts through electrochemical reactions to improve the corrosion resistance, hardness and aesthetics of the parts. The electroplating module 9 receives module configuration information and changes the preset electroplating module 9 configuration to the second module configuration according to the information. The second module configuration is an electroplating scheme customized according to the specific conditions of the parts, including parameters such as the composition of the electroplating solution, the current intensity, and the electroplating time. In the electroplating module 9, the target component is immersed in the electroplating solution, and a uniform metal coating is formed on the surface of the part through an electrochemical reaction. After the electroplating process is completed, the processed target component is moved by the auxiliary robot arm 10 to the second storage platform 12 set on the support platform 2. The second storage platform 12 is an area dedicated to storing processed parts, providing a stable platform to ensure that the parts are in the correct position after processing.

[0030] At this time, the second image acquisition module 13 arranged on the top of the support frame 1 and directly above the second storage table 12 will collect the second image information of the target component and send this information to the edge computing module 4. The second image acquisition module 13 obtains the image information of the target component through a camera or other image acquisition device, and the image information includes the thickness, uniformity, surface state, etc. of the electroplating layer. This information will be used for subsequent quality inspection and feedback adjustment. After receiving the second image information, the edge computing module 4 will generate feedback adjustment information using image recognition technology. Image recognition technology can identify specific patterns and features from the image to judge the quality and state of the electroplating layer. The feedback adjustment information is an adjustment scheme generated based on the image recognition results, including adjusting parameters such as electroplating time and current intensity to ensure the stability and uniformity of the electroplating quality. After receiving the feedback adjustment information, the electroplating module 9 will adjust the second module configuration according to this information to ensure the stability and uniformity of the electroplating quality. During the whole process, the auxiliary robot arm 10 is also responsible for moving the target component between the part pretreatment module 11, the electroplating module 9 and the second storage table 12 to ensure the smooth progress of the entire electroplating process.

[0031] Through the above technical solution, the information acquisition module and the first image acquisition module 7 acquire the processing information and image information of the parts, and send this information to the edge computing module 4. The edge computing module 4 uses natural language processing technology and image recognition technology to generate module configuration information, and guides the activation processing module 8 and the electroplating module 9 to perform corresponding processing. The auxiliary robot arm 10 moves parts between modules to realize an automated production process. The second image acquisition module 13 acquires the image information of the parts after processing, and sends this information to the edge computing module 4. The edge computing module 4 uses image recognition technology to generate feedback adjustment information to guide the electroplating module 9 to make corresponding adjustments. Through closed-loop control, the entire system realizes the high efficiency, precision and stability of the electroplating process, meeting the needs of modern manufacturing for high quality, high efficiency and sustainable development.

[0032] In one embodiment, referring to Figure 2 The activation treatment module 8 includes an activation treatment container 81, a solution configuration unit 82, a waste liquid collection tank 83 and an activation treatment control unit 84. The activation treatment container 81 is arranged on the support platform 2. The activation treatment container 81 includes an ultrasonic cleaning tank 811, an acid cleaning tank 812, an alkaline cleaning tank 813 and an activation treatment tank 814. The waste liquid collection tank 83, the solution configuration unit 82 and the activation treatment control unit 84 are all arranged in the storage room 3. The solution configuration unit 82 includes a plurality of solution tanks, and different types of pretreatment solutions are stored in the plurality of solution tanks. All solution tanks are connected to the bottom of the activation treatment container 81 through a lifting pump 85 and a solenoid valve, and the waste liquid collection tank 83 is connected to the bottom of the activation treatment container 81 through an activation solenoid valve 86.

[0033] The activation processing control unit 84 is communicatively connected with the edge computing module 4, all lifting pumps 85 and all activation solenoid valves 86. The activation processing control unit 84 receives the module configuration information sent by the edge computing module 4. The activation processing control unit 84 changes the preset activation processing module 8 configuration to the first module configuration according to the activation module configuration information in the module configuration information. The first module configuration includes the equipment start and stop time nodes of all lifting pumps 85 and all activation solenoid valves 86. The activation processing control unit 84 controls all lifting pumps 85 and all activation solenoid valves 86 based on the first module configuration to complete the pretreatment solution configuration work of the activation processing container 81.

[0034] In this embodiment, the activation processing module 8 is a key component of the automated electroplating control system, and its main function is to perform surface pretreatment on the parts to be processed to ensure the smooth progress of the subsequent electroplating process and the improvement of the electroplating quality. The activation processing module 8 includes an activation processing container 81, a solution configuration unit 82, a waste liquid collection tank 83 and an activation processing control unit 84. The complete process flow of the activation processing module 8 will be described in detail below.

[0035] The activation treatment container 81 is arranged on the support platform 2, and is divided into four different treatment areas, namely, an ultrasonic cleaning tank 811, an acid cleaning tank 812, an alkaline cleaning tank 813 and an activation treatment tank 814. The ultrasonic cleaning tank 811 utilizes the cavitation effect of ultrasound to generate tiny bubbles in the liquid through high-frequency vibration. The impact force generated by these bubbles when they burst can effectively remove dirt and grease on the surface of the parts. The acid cleaning tank 812 and the alkaline cleaning tank 813 use acidic and alkaline solutions to clean the parts respectively. The acidic solution in the acid cleaning tank 812 can dissolve oxides and rust on the metal surface, while the alkaline solution in the alkaline cleaning tank 813 can neutralize the residual acid after acid cleaning and further clean the surface of the parts. The activation treatment tank 814 uses a specific activation solution to form an activation film on the surface of the parts through chemical reactions, thereby improving the activity of the surface of the parts and providing a good foundation for the subsequent electroplating process.

[0036] The solution configuration unit 82 includes a plurality of solution tanks, each of which stores different types of pretreatment solutions. The various pretreatment solutions can be used to prepare the acid solution used in the pickling tank 812, the alkaline solution used in the alkaline tank, and the activation solution used in the activation treatment tank 814. These solution tanks are connected to the bottom of the activation treatment container 81 through the lifting pump 85 and the solenoid valve. The lifting pump 85 is a mechanical device for conveying liquid, which conveys the solution from the solution tank to the activation treatment container 81 by increasing the pressure of the liquid. The solenoid valve is a device that uses electromagnetic force to control the opening and closing of the valve. By controlling the opening and closing of the solenoid valve, the flow rate and flow direction of the solution can be accurately controlled. The waste liquid collection tank 83 is connected to the bottom of the activation treatment container 81 through the solenoid valve, and is used to collect the waste liquid generated during the treatment process to ensure environmental protection and safety.

[0037] The activation processing control unit 84 is connected to the edge computing module 4, all lift pumps 85 and all solenoid valves in communication. After receiving the part processing information and the first image information, the edge computing module 4 generates module configuration information using natural language processing technology and image recognition technology, and sends this information to the activation processing control unit 84. Natural language processing technology is an artificial intelligence technology that can understand and process human language and extract key information from part processing information. Image recognition technology is a computer vision technology that can identify specific patterns and features from images to determine the state and position of parts. Combining these two technologies, the module configuration information generated by the edge computing module 4 includes specific configuration parameters of each processing module, such as activation processing time, solution type, etc. After receiving the module configuration information sent by the edge computing module 4, the activation processing control unit 84 changes the preset activation processing module 8 configuration to the first module configuration according to the activation module configuration information in the module configuration information. The first module configuration includes the equipment start and stop time nodes of all lift pumps 85 and all solenoid valves, that is, when to turn on or off specific lift pumps 85 and solenoid valves to ensure the correct configuration and delivery of the pretreatment solution. The activation process control unit 84 controls all the lift pumps 85 and all the solenoid valves based on the first module configuration to complete the pretreatment solution configuration work of the activation process container 81 .

[0038] Specifically, the activation treatment control unit 84 first turns on the corresponding lift pump 85 according to the instructions configured by the first module, and transports the pretreatment solution stored in the solution tank to each treatment tank of the activation treatment container 81. For example, when ultrasonic cleaning is required, the activation treatment control unit 84 turns on the lift pump 85 and the solenoid valve connected to the ultrasonic cleaning tank 811 to transport the cleaning solution to the ultrasonic cleaning tank 811. After the cleaning is completed, the activation treatment control unit 84 turns off the corresponding lift pump 85 and the solenoid valve, and at the same time turns on the solenoid valve of the waste liquid collection tank 83 to discharge the waste liquid in the ultrasonic cleaning tank 811 into the waste liquid collection tank 83. Next, the activation treatment control unit 84 controls the lift pump 85 and the solenoid valve in turn according to the instructions configured by the first module, and completes the solution configuration and waste liquid collection work of pickling, alkali cleaning and activation treatment. During the entire activation treatment process, the activation treatment control unit 84 monitors the solution state and treatment progress of each treatment tank in real time to ensure the stability and consistency of the treatment process. For example, the activation treatment control unit 84 can monitor the solution concentration, temperature and treatment time of each treatment tank through sensors, and adjust the working status of the lift pump 85 and the solenoid valve in real time according to the monitoring results to ensure the optimization of the treatment effect.

[0039] In summary, the activation processing module 8 realizes efficient, accurate and automated surface pretreatment of the parts to be processed through the coordinated work of the activation processing container 81, the solution configuration unit 82, the waste liquid collection tank 83 and the activation processing control unit 84. The ultrasonic cleaning tank 811, the pickling tank 812, the alkaline cleaning tank 813 and the activation processing tank 814 in the activation processing container 81 respectively undertake different pretreatment tasks, and remove dirt, oxides and pollutants on the surface of the parts through various means such as ultrasonic cleaning, pickling, alkaline cleaning and activation treatment, and increase the activity of the surface of the parts. The solution configuration unit 82 transports different types of pretreatment solutions to the activation processing container 81 through the lifting pump 85 and the solenoid valve, and collects the waste liquid generated during the treatment process through the waste liquid collection tank 83 to ensure environmental protection and safety. The activation processing control unit 84 receives the module configuration information and controls the working status of each device through the communication connection with the edge computing module 4, the lifting pump 85 and the solenoid valve to ensure the stability and consistency of the pretreatment process. The entire process flow realizes efficient, accurate and stable activation treatment through automated control and monitoring, providing a good foundation for subsequent electroplating processes.

[0040] In one embodiment, referring to Figure 1 The system also includes a third image acquisition module 14, which is arranged on the support frame 1 and located at any one of the two ends of the length direction of the support platform 2. The third image acquisition module 14 is used to collect the third image information of the target part when the auxiliary robot arm 10 clamps the target part and moves it from the activation processing module 8 to the part preprocessing module 11, and send the third image information to the edge computing module 4. After receiving the third image information, the edge computing module 4 uses image recognition technology to generate a solution replacement instruction, and sends the solution replacement instruction to the activation processing control unit 84. The activation processing control unit 84 receives and executes the solution replacement instruction to adjust the first module configuration. The activation processing control unit 84 controls all the lifting pumps 85 and all the activation solenoid valves 86 based on the adjusted first module configuration to complete the solution replacement work of the activation processing container 81.

[0041] In this embodiment, during the activation treatment process, the solutes in the solutions in the acid washing tank 812 and the alkaline washing tank 813 may be continuously consumed. When the solutes in the solutions are consumed to a certain extent, the impurity removal effects of the acid washing tank 812 and the alkaline washing tank 813 on the surface of the target parts will be greatly weakened. Therefore, the third image acquisition module 14 can be used to assist in identifying the impurity removal effect of the activation treatment process on the target parts. When it is identified that the impurity removal effect is weakened, it is necessary to execute a solution replacement instruction through the activation treatment control unit 84.

[0042] The specific process is as follows: When the auxiliary robot arm 10 clamps the target part and moves from the activation processing module 8 to the part pretreatment module 11, the third image acquisition module 14 starts to work. The third image acquisition module 14 is arranged on the support frame 1, and is located at either end of the length direction of the support platform 2. The module is used to collect the third image information of the target part through the camera, and send the information to the edge computing module 4. After receiving the third image information, the edge computing module 4 generates a solution replacement instruction using image recognition technology. Image recognition technology determines whether the treatment solution needs to be replaced by analyzing the state and treatment effect of the part surface to ensure the optimization of the treatment effect. When the activation processing control unit 84 receives the solution replacement instruction sent by the edge computing module 4, it will immediately execute the instruction. The solution replacement instruction includes the adjusted first module configuration, specifically including the time node of the solution replacement and the required solution type. When executing the solution replacement instruction, all other modules of the system suspend their actions until the activation processing control unit 84 completes the solution replacement work of the activation processing container 81. This suspension mechanism ensures the safety and stability of the solution replacement process, and avoids the problems of cross contamination and inconsistent treatment that may occur during the solution replacement process.

[0043] Specifically, the activation control unit 84 first turns on the corresponding lift pump 85 and solenoid valve according to the instructions of the adjusted first module configuration, and discharges the old solution into the waste liquid collection tank 83. The waste liquid collection tank 83 is connected to the bottom of the activation treatment container 81 through the solenoid valve, and is used to collect the waste liquid generated during the treatment process. Next, the activation control unit 84 turns on the lift pump 85 and solenoid valve corresponding to the new solution, and transports the new solution from the solution tank to the activation treatment container 81. The entire solution replacement process is carried out under the precise control of the activation control unit 84 to ensure the accuracy and consistency of each step of the operation.

[0044] In one embodiment, referring to Figure 3 The surface of the target part includes a to-be-processed area that needs to be processed and a protection area that does not need to be processed. The processing substrate 15 and the part shielding block are both made of corrosion-resistant materials. The cross-sectional shape of the part shielding block is the same as the shape formed by the protection area. A substrate liquid inlet hole 151 and a substrate liquid outlet hole 152 are provided on the surface of the processing substrate 15. A drainage groove 153 is also provided on the surface of the processing substrate 15, and one end of the drainage groove 153 is connected to the substrate liquid outlet hole 152.

[0045] When the auxiliary robot 10 combines the target part, the part shielding block and the processing substrate 15 into a target assembly in the part preprocessing module 11, the target part is fixed to the surface of the processing substrate 15, and a processing cavity filled with electroplating liquid is formed between the area to be processed on the surface of the target part and the surface of the processing substrate 15. The end of the drainage groove 153 away from the substrate liquid outlet hole 152 and all the substrate liquid inlet holes 151 are located in the processing cavity, the substrate liquid outlet hole 152 is located outside the processing cavity, the part shielding block is fixed to the protective area on the surface of the target part, and the part shielding block is tightly fitted to the surface of the target part.

[0046] In this embodiment, refer to Figure 4 The electroplating module 9 includes an electroplating control unit 91, a plating liquid storage tank 92, an electroplating waste liquid collection tank 93 and a pressurizing unit 94. The pressurizing unit 94 includes a hydraulic device 941 fixedly arranged on the top of the support frame 1 and a processing platform 942 arranged on the supporting platform 2. The processing platform 942 is located directly below the hydraulic device 941. The processing platform 942 vertically penetrates the processing platform 942 and the supporting platform 2 from the top surface to form a platform liquid inlet hole and a platform liquid outlet hole. When the auxiliary robot arm 10 places the target component on the processing platform 942 in the electroplating module 9, the base liquid inlet hole 151 is correspondingly connected to the platform liquid inlet hole, and the base liquid outlet hole is correspondingly connected to the platform liquid outlet hole.

[0047] The electroplating control unit 91, the electroplating liquid storage tank 92 and the electroplating waste liquid collection tank 93 are all arranged in the storage room 3. The electroplating liquid storage tank 92 is connected to the inner top surface of the supporting platform 2 through a liquid adding pipe, and all the platform liquid inlets are connected to the liquid adding pipe. The liquid adding pipe is provided with a liquid adding solenoid valve 95, a liquid adding pump 96 and an electronic flow meter 97. The electroplating waste liquid collection tank 93 is connected to the inner top surface of the supporting platform 2 through a liquid outlet pipe, and all the platform liquid outlets are connected to the liquid outlet pipe. The liquid outlet pipe is provided with a liquid outlet solenoid valve 98 and a liquid extraction pump 99.

[0048] The electroplating control unit 91 is communicatively connected with the edge computing module 4, the hydraulic device 941, the liquid adding solenoid valve 95, the liquid adding pump 96, the electronic flow meter 97, the liquid outlet solenoid valve 98 and the liquid extraction pump 99. The electroplating control unit 91 receives the module configuration information sent by the edge computing module 4. The electroplating control unit 91 changes the preset electroplating module 9 configuration to the second module configuration according to the electroplating module 9 configuration information in the module configuration information. The second module configuration includes the equipment start and stop time nodes of the hydraulic device 941, the liquid adding solenoid valve 95, the liquid adding pump 96, the liquid outlet solenoid valve 98 and the liquid extraction pump 99.

[0049] In this embodiment, after the pretreatment is completed, the auxiliary robot arm 10 places the pretreated target component (including the target part, the part shielding block and the processing substrate 15) on the processing platform 942 of the electroplating module 9. At this time, the substrate liquid inlet 151 is correspondingly connected to the platform liquid inlet, and the substrate liquid outlet 152 is correspondingly connected to the platform liquid outlet, ensuring that the electroplating liquid can be smoothly injected and discharged. The core part of the electroplating module 9 is the electroplating control unit 91. The electroplating control unit 91 receives the module configuration information sent by the edge computing module 4, and changes the preset electroplating module 9 configuration to the second module configuration according to the electroplating module 9 configuration information in the configuration information. The second module configuration includes equipment start and stop time nodes of the hydraulic device 941, the liquid adding solenoid valve 95, the liquid adding pump 96, the liquid outlet solenoid valve 98 and the liquid extraction pump 99.

[0050] The hydraulic device 941 is a device for transmitting power through liquid pressure. During the electroplating process, the hydraulic device 941 is used to apply appropriate pressure to ensure that the plating liquid evenly covers the area to be processed. The liquid adding solenoid valve 95 is a valve that controls the flow of liquid through an electrical signal. Its opening and closing determine the injection and stopping of the plating liquid. The liquid adding pump 96 is a device for transporting the plating liquid from the plating liquid storage tank 92 to the processing platform 942. The liquid outlet solenoid valve 98 is similar to the liquid adding solenoid valve 95 and is used to control the discharge of the plating liquid. The liquid extraction pump 99 is a device for discharging the plating liquid from the processing cavity.

[0051] The electroplating control unit 91 controls the opening of the liquid adding solenoid valve 95 and the liquid adding pump 96, and transports the electroplating liquid from the electroplating liquid storage tank 92 to the inner top surface of the support platform 2 through the liquid adding pipe, and injects it into the processing cavity through the platform liquid inlet hole. The electroplating liquid is a solution containing metal ions. Under the action of the electric field, these metal ions will be deposited on the area to be processed of the target part to form a uniform and strong coating. After the electroplating liquid is injected into the processing cavity, the electroplating control unit 91 controls the hydraulic device 941 to apply appropriate pressure to ensure that the electroplating liquid evenly covers the area to be processed. Under the action of the electric field, the metal ions are deposited on the area to be processed of the target part to form a uniform and strong coating. During the entire electroplating process, the electroplating control unit 91 monitors the flow of the electroplating liquid in real time through the electronic flowmeter 97 to ensure the stability and consistency of the electroplating process.

[0052] The electronic flow meter 97 is an instrument for measuring the flow of liquid. By measuring the flow of the electroplating solution, the stability and consistency of the electroplating process can be ensured. The electroplating control unit 91 adjusts the working state of the liquid adding solenoid valve 95, the liquid adding pump 96, the liquid outlet solenoid valve 98 and the liquid extraction pump 99 according to the real-time monitoring data to ensure that the flow and pressure of the electroplating solution are always in the best state. After the electroplating process is completed, the electroplating control unit 91 controls the opening of the liquid outlet solenoid valve 98 and the liquid extraction pump 99, discharges the electroplating solution from the processing cavity through the liquid outlet pipe, and transports it to the electroplating waste liquid collection tank 93. The drainage groove 153 guides the electroplating solution to flow to the substrate outlet hole 152 to ensure that the electroplating solution can be discharged smoothly. The electroplating waste liquid collection tank 93 is used to collect and store the discharged electroplating solution to prevent it from polluting the environment.

[0053] Finally, the auxiliary robot arm 10 removes the target component from the processing platform 942 and sends it to the subsequent processing process. At this time, the area to be processed of the target part has been electroplated to form a uniform and strong coating. Post-processing includes steps such as cleaning, drying and inspection. Cleaning is to use deionized water or other cleaning agents to remove the residual plating solution on the surface of the part. Drying is to evaporate the moisture on the surface of the part through hot air or vacuum drying equipment. The process flow of the entire electroplating module 9 realizes comprehensive monitoring and control of the electroplating process through the communication connection of each device by the electroplating control unit 91. The electroplating liquid storage tank 92 and the electroplating waste liquid collection tank 93 are used to store the electroplating liquid and collect the waste liquid respectively to ensure the environmental protection and safety of the electroplating process. The pressurizing unit 94 provides pressure through the hydraulic device 941 to ensure uniform coverage of the electroplating liquid. Through automated control and monitoring, an efficient, accurate and stable electroplating process is achieved, providing a guarantee for high-quality electroplating of the target parts.

[0054] The successful implementation of the electroplating process also requires consideration of multiple factors, including the composition of the plating solution, current density, temperature, time, etc. The composition of the plating solution directly affects the quality and performance of the coating. Different metals and alloys require plating solutions with different compositions. Current density refers to the current intensity per unit area, which determines the deposition rate of metal ions. Temperature affects the viscosity of the plating solution and the migration rate of metal ions. Time determines the thickness of the coating.

[0055] Reference Figure 5 , Figure 5 The figure is a flow chart of an automated electroplating control method based on image recognition in one embodiment. Figure 5 The automated electroplating control method based on image recognition is applied to Figure 1 The automated electroplating control system based on image recognition is shown in FIG. Figure 5The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 5 At least part of the steps in the above method may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps. Figure 5 As shown, the automatic electroplating control method based on image recognition disclosed in the present invention specifically includes the following steps: S101. The first image acquisition module acquires first image information of all target parts located on the first storage table, and sends the first image information to the edge computing module.

[0056] Among them, the first image acquisition module is responsible for collecting the first image information of all target parts located on the first storage table. Specifically, this module is usually composed of a high-resolution industrial camera, which can shoot the target parts in all directions and at multiple angles to ensure that all details of the parts are captured. These image information not only includes the appearance shape, size, and surface state of the parts, but may also involve information such as the identification code of the parts. The collected first image information is sent to the edge computing module through a high-speed data transmission interface (such as Ethernet or USB interface). In this process, the image acquisition module needs to have good lighting conditions and a stable shooting environment to ensure the clarity and accuracy of the image.

[0057] S102. The information acquisition module acquires the part processing information of the target part and sends the part processing information to the edge computing module.

[0058] Among them, part processing information usually includes the material type, dimensional tolerance, surface roughness requirements, electroplating thickness requirements, etc. This information can be obtained in a variety of ways, such as extracting it from the company's production management system (ERP system) or reading the barcode or QR code on the part through a barcode scanner. The information acquisition module needs to have efficient data processing capabilities to quickly and accurately extract and transmit this processing information. In this way, the system can fully understand the specific processing requirements of each part and provide precise guidance for subsequent processing processes.

[0059] S103. After receiving the part processing information and the first image information, the edge computing module combines the part processing information and the first image information and generates module configuration information using natural language processing technology and image recognition technology.

[0060] Among them, the edge computing module is usually composed of high-performance embedded computing devices with powerful data processing and analysis capabilities. Natural language processing technology is used to parse the text description in the part processing information and extract key information; image recognition technology is used to analyze image information and identify the shape, size, surface state, etc. of the parts. By comprehensively processing these two parts of information, the edge computing module generates specific module configuration information, including the configuration parameters of the activation processing module and the electroplating module. This configuration information will serve as a guide for the subsequent processing process to ensure that each part can be processed according to its specific requirements.

[0061] S104. The activation processing module receives the module configuration information, and changes the preset activation processing module configuration to the first module configuration according to the module configuration information. The electroplating module receives the module configuration information, and changes the preset electroplating module configuration to the second module configuration according to the module configuration information.

[0062] Among them, activation treatment is an important step before electroplating, which aims to remove oxides and impurities on the surface of parts by chemical or electrochemical methods to enhance the adhesion of the coating. The activation treatment module adjusts the working state of the equipment according to the configuration of the first module. For example, if the module configuration information requires the use of sulfuric acid solution for pickling, the activation treatment module will automatically adjust the type and concentration of the solution to ensure that the treatment process meets the requirements. In this way, the system can realize personalized activation treatment for different parts and improve the quality of electroplating.

[0063] S105. The auxiliary robot arm clamps the target part and moves it from the first storage station to the activation processing module, and the activation processing module performs activation processing on the target part based on the first module configuration.

[0064] Among them, the auxiliary robot arm is usually composed of a multi-joint robot with high-precision motion control capabilities, which can achieve accurate positioning and handling of target parts. In this process, the motion path and clamping force of the robot arm are controlled by a pre-programmed control system to ensure that the parts are not damaged during handling. The activation processing module works according to the configuration of the first module. The specific operation includes immersing the parts in the activation processing container and processing them according to the preset processing time and parameters. After the treatment is completed, the robot arm removes the parts from the activation processing container and performs necessary cleaning and drying operations. In this way, the system can efficiently and accurately complete the activation treatment of the parts and prepare for the subsequent electroplating process.

[0065] S106. The auxiliary robot arm grips the target part after activation and moves it to a part preprocessing module that provides a part shielding block and a processing substrate suitable for the target part. The auxiliary robot arm combines the target part, the part shielding block and the processing substrate into a target assembly in the part preprocessing module.

[0066] The parts pre-processing module usually includes multiple workstations, each equipped with different tools and fixtures to complete the pre-processing operations of the parts. The parts shielding block is used to protect the non-electroplating area of ​​the parts from corrosion by the electroplating solution; the processing substrate is used to fix the parts to ensure their stability during the electroplating process. The auxiliary robot arm combines the parts, shielding blocks and substrates one by one according to the preset program to form a complete target component. In this process, the movement path and clamping force of the robot arm are precisely controlled by the control system to ensure that the combination process of each component is accurate.

[0067] S107. The auxiliary robot arm clamps the target component and moves it to the electroplating module, and the electroplating module performs electroplating processing on the target component based on the second module configuration.

[0068] S108. The auxiliary robot arm clamps the target component after electroplating and moves it to the second storage table, and places the target component on the second storage table.

[0069] After the electroplating is completed, the target component needs to be processed and inspected. The auxiliary robot arm moves the target component from the electroplating module to the second storage table according to the preset program to ensure that the component is not damaged during the transportation process. The second storage table is usually equipped with a protective device to ensure that the target component is not affected by the external environment during the storage process.

[0070] S109. The second image acquisition module acquires second image information of the target component located on the second storage table, and sends the second image information to the edge computing module.

[0071] Among them, the second image acquisition module is similar to the first image acquisition module, usually composed of a high-resolution industrial camera, which can shoot the target component in all directions and at multiple angles to ensure that all details of the component are captured. The collected second image information is sent to the edge computing module through a high-speed data transmission interface. In this process, the image acquisition module needs to have good lighting conditions and a stable shooting environment to ensure the clarity and accuracy of the image. In this way, the system can obtain comprehensive information about the target component and provide basic data for subsequent quality inspections.

[0072] S110. After receiving the second image information, the edge computing module generates feedback adjustment information using image recognition technology. The electroplating module receives the feedback adjustment information and adjusts the configuration of the second module according to the feedback adjustment information.

[0073] Among them, the edge computing module uses image recognition technology to analyze the second image information and identify the coating quality of the target component, including the thickness, uniformity, surface state, etc. of the coating. By comparing with the preset quality standards, the edge computing module generates feedback adjustment information to point out problems and improvement measures in the electroplating process. After receiving the feedback adjustment information, the electroplating module adjusts the configuration of the second module according to this information and optimizes the electroplating parameters to improve the quality and consistency of the subsequent electroplating process. In this way, the system can achieve closed-loop control of the electroplating process to ensure that the coating quality of each target component meets the requirements.

[0074] In one embodiment, after receiving the part processing information and the first image information, the edge computing module generates the module configuration information by combining the part processing information and the first image information and using natural language processing technology and image recognition technology, including the following steps: After receiving the part processing information, the edge computing module uses natural language processing technology to extract the part material type information and part electroplating process information from the part processing information; The edge computing module retrieves the corresponding electroplating liquid type information from the preset electroplating processing database according to the part material type information; The edge computing module generates the electroplating control timeline information of the electroplating module according to the part electroplating process information, and integrates the electroplating liquid type information and the electroplating control timeline information into the electroplating module configuration information. The electroplating control timeline information includes the start and stop time nodes of all equipment in the electroplating module. After receiving the first image information, the edge computing module uses image recognition technology to analyze the first image information, obtains part surface state information of the target part, and generates activation module configuration information in combination with the part surface state information and part material type information.

[0075] In this embodiment, after the edge computing module receives the part processing information, it first uses natural language processing technology to parse this information. Natural language processing technology can decompose text information into structured data and extract key part material type information and part electroplating process information. For example, the part processing information may contain "the part is made of aluminum alloy and needs to go through three steps of pretreatment, nickel plating and chrome plating". By parsing these text information, the edge computing module can identify the material type of "aluminum alloy" and the three electroplating process steps of "pretreatment, nickel plating, and chrome plating". The core of natural language processing technology lies in its ability to understand and process the complexity of human language, and convert unstructured text information into actionable data through steps such as lexical analysis, syntactic analysis, and semantic analysis. In this way, the system can accurately extract the material type and electroplating process of the parts, and provide basic data for subsequent processing.

[0076] Next, the edge computing module retrieves the corresponding electroplating solution type information from the preset electroplating processing database based on the extracted part material type information. The electroplating processing database stores the electroplating solution types and their formulas corresponding to different material types. For example, for aluminum alloy materials, the database may store specific formulas for nickel plating solutions and chromium plating solutions suitable for aluminum alloys, including solution composition, concentration, temperature and other parameters. By querying the database, the edge computing module can quickly obtain these electroplating solution type information and use it as a reference for subsequent electroplating processes. The database query process is usually implemented through SQL statements, such as "SELECT * FROM electroplating_solutions WHERE material_type ='aluminum alloy'".

[0077] After obtaining the plating liquid type information, the edge computing module generates the plating control timeline information of the plating module according to the part plating process information. The plating control timeline information contains the start and stop time nodes of each device in the electroplating process. For example, for the three steps of "pretreatment, nickel plating, and chrome plating", the edge computing module needs to determine the specific time schedule for each step. By reasonably arranging these time nodes, the edge computing module generates complete plating control timeline information. The process of generating timeline information usually involves time series analysis and task scheduling algorithms to ensure that the various steps are connected reasonably and avoid idle equipment and waste of resources. Finally, the edge computing module integrates the plating liquid type information and the plating control timeline information into the electroplating module configuration information.

[0078] After receiving the first image information, the edge computing module uses image recognition technology to analyze these images to obtain the surface status information of the target part. Image recognition technology can identify the state of the part surface, such as whether there is an oxide layer, surface roughness, etc., by extracting features and recognizing patterns from images. For example, through grayscale analysis and edge detection of the image, the system can determine the smoothness of the part surface and whether there are scratches. The core of image recognition technology is that it can train a large amount of image data through machine learning algorithms, thereby having high-precision recognition capabilities. In this way, the edge computing module can obtain the surface status information of the part and provide a basis for subsequent activation processing.

[0079] Finally, the edge computing module combines the part surface state information and the part material type information to generate the activation module configuration information. Activation treatment is an important step before electroplating, which aims to remove oxides and impurities on the surface of parts by chemical or electrochemical methods to enhance the adhesion of the coating. For example, for aluminum alloy parts with an oxide layer on the surface, the activation treatment may require the use of pickling solution for treatment, and the specific formula and treatment time are adjusted according to the surface state and material type. The edge computing module generates specific activation treatment parameters such as the type, concentration, temperature and treatment time of the pickling solution by comprehensively analyzing the surface state information and material type information. These parameters will serve as the configuration basis for the activation module to ensure that each part can be activated according to its specific requirements. In this way, the system can realize personalized activation treatment for different parts, improve the quality of electroplating, and ensure that the final product meets quality standards.

[0080] In one embodiment, after receiving the first image information, the edge computing module uses image recognition technology to analyze the first image information to obtain part surface state information of the target part, and generates activation module configuration information in combination with the part surface state information and part material type information, including the following steps: The edge computing module retrieves the corresponding pretreatment solution type information and the initial concentration information of the pretreatment solution corresponding to each pretreatment solution type information from the electroplating processing database according to the part material type information. The pretreatment solution type information includes an acid solution, an alkaline solution, and an activation treatment solution. After receiving the first image information, the edge computing module identifies all first target image regions containing target parts in the first image information through a preset image recognition model, and the image recognition model completes model training in advance using multiple types of part image data sets; The edge computing module extracts all first target image regions from the first image information to obtain a plurality of first target part images; For each first target part image, the edge computing module preprocesses the first target part image into a first grayscale image, and processes the first grayscale image by a mathematical morphology method to complete the first surface impurity edge of the target part in the first grayscale image. The edge computing module uses a threshold segmentation algorithm to separate the first surface impurities from the image background of the first grayscale image, and extracts the first impurity image features of the first surface impurities in the first grayscale image. The edge computing module locates the first surface impurities in the first grayscale image based on the first impurity image features and uses a local binary pattern algorithm to obtain the first impurity size of the first surface impurities. The edge computing module uses the ratio between the first impurity size and the image size of the first grayscale image as the first impurity coverage rate of the first target part image. The edge computing module calculates the first impurity coverage of all first target part images by averaging to obtain an average impurity coverage, and uses the average impurity coverage as part surface state information of the target part in the first image information; The edge computing module adjusts the initial concentration information of the pretreatment solution according to the average impurity coverage to obtain the target concentration information of the pretreatment solution, and generates the activation module configuration information in combination with the pretreatment solution type information and the pretreatment solution target concentration information.

[0081] In this embodiment, after the edge computing module receives the part material type information, it retrieves the corresponding pretreatment solution type information and the initial concentration information of each pretreatment solution from the preset electroplating processing database. The pretreatment solution types mainly include acidic solutions, alkaline solutions and activation treatment solutions. For example, for aluminum alloy parts, the database may provide an acidic solution for removing the oxide layer, an alkaline solution for cleaning the surface oil, and an activation treatment solution for enhancing the adhesion of the electroplating layer. Next, the edge computing module receives the first image information and identifies the first target image area containing the target part through a preset image recognition model. The image recognition model pre-trains the model using multiple types of part image data sets so that it can accurately identify the image features of different types of parts. The training process usually uses deep learning algorithms such as convolutional neural networks (CNNs). By learning a large amount of annotated image data, the model can extract the key features of the parts and achieve high-precision recognition. After identifying the first target image area, the edge computing module extracts all first target image areas from the first image information to obtain multiple first target part images. Each first target part image contains a complete target part, and the edge computing module uses these images as input for subsequent processing. The interception process is usually implemented through image cropping technology, such as using the cropping function in the OpenCV library to separate the identified target image area from the original image. In this way, the system can obtain multiple independent target part images to provide data support for subsequent image processing and analysis.

[0082] For each first target part image, the edge computing module preprocesses it into a first grayscale image, and processes the first grayscale image through mathematical morphology methods to complete the surface impurity edges of the target part. Grayscale image processing is a basic step in image processing. By converting a color image into a grayscale image, the complexity of the image can be simplified and key image information can be retained. Mathematical morphology methods include corrosion, expansion, opening operations, and closing operations. Through these operations, the edge features in the image can be enhanced to make the edges of surface impurities clearer. For example, the system can use the morphological transformation function in the OpenCV library to process the grayscale image to enhance the integrity of the impurity edges.

[0083] After obtaining the processed grayscale image, the edge computing module uses the threshold segmentation algorithm to separate the surface impurities from the image background and extract the image features of the impurities in the grayscale image. The threshold segmentation algorithm divides the pixels in the image into foreground and background by setting a threshold. For example, the Otsu algorithm is used to automatically calculate the optimal threshold to separate the impurity area in the grayscale image. In this way, the system can extract the image features of the impurities, such as area, shape, etc., to provide data support for the subsequent impurity location and size calculation. Then, the edge computing module locates the surface impurities in the grayscale image based on the extracted impurity image features and uses the local binary pattern algorithm to obtain the size of the impurities. The local binary pattern algorithm is a texture analysis method that generates a binary pattern by comparing the grayscale values ​​of each pixel in the image with its neighboring pixels to characterize the local texture features of the image. In this way, the system can accurately locate the position of the impurity and calculate its size. For example, the system can use the local binary pattern function in the OpenCV library to perform texture analysis on the grayscale image and obtain the size data of each impurity.

[0084] The edge computing module uses the ratio between the impurity size and the image size of the grayscale image as the impurity coverage of the target part image. Impurity coverage is an important indicator to measure the degree of impurities on the surface of a part. The impurity coverage can be obtained by calculating the ratio of the impurity area to the total image area. For example, for a grayscale image with a size of 100x100 pixels, if the impurity area is 100 pixels, the impurity coverage is 1%.

[0085] Finally, the edge computing module calculates the impurity coverage of all target part images by averaging to obtain the average impurity coverage, and uses it as the surface state information of the target part in the image information. The average impurity coverage is a comprehensive evaluation of the impurity coverage of multiple part images. By calculating the average value of all images, an overall impurity coverage can be obtained. For example, for three part images, the impurity coverage is 1%, 1.5% and 2% respectively, and the average impurity coverage is 1.5%. In this way, the system can obtain the overall surface state information of the target part and provide a basis for the subsequent pretreatment concentration adjustment. According to the average impurity coverage, the edge computing module adjusts the initial concentration information of the pretreatment solution to obtain the target concentration information of the pretreatment solution. The concentration of the pretreatment solution is usually adjusted according to the size of the impurity coverage. For example, when the impurity coverage is high, the concentration of the solution needs to be increased to enhance the cleaning effect. In this way, the system can dynamically adjust the concentration of the pretreatment solution according to the actual surface state of the part to ensure the effectiveness of the pretreatment process.

[0086] In one embodiment, the method further comprises the steps of: When the auxiliary robot arm holds the target part and moves it from the activation processing module to the part preprocessing module, the third image acquisition module acquires the third image information of the target part and sends the third image information to the edge computing module; After receiving the third image information, the edge computing module identifies all second target image regions containing target parts in the third image information through an image recognition model; The edge computing module extracts all second target image regions from the third image information to obtain a plurality of second target part images; For each second target part image, the edge computing module preprocesses the second target part image into a second grayscale image, and processes the second grayscale image by a mathematical morphology method to complete the second surface impurity edge of the target part in the second grayscale image. The edge computing module uses a threshold segmentation algorithm to separate the second surface impurities from the image background of the second grayscale image, and extracts the second impurity image features of the second surface impurities in the second grayscale image. The edge computing module locates the second surface impurities in the second grayscale image based on the second impurity image features and uses a local binary pattern algorithm to obtain the second impurity size of the second surface impurities. The edge computing module uses the ratio between the second impurity size and the image size of the second grayscale image as the second impurity coverage rate of the second target part image. When the edge computing module determines that the second impurity coverage exceeds a preset coverage threshold, the edge computing module generates a solution replacement instruction and sends the solution replacement instruction to the activation processing control unit in the activation processing module; The activation process control unit receives and executes the solution replacement instruction to adjust the first module configuration, and the activation process control unit completes the solution replacement work of the activation process container based on the adjusted first module configuration.

[0087] In this embodiment, in the process of the auxiliary robot arm clamping the target part and moving it from the activation processing module to the part preprocessing module, the third image acquisition module will collect the third image information of the target part in real time and send the image information to the edge computing module. The third image acquisition module is usually composed of a high-resolution industrial camera, which can capture clear image data during the movement of the part. In order to ensure the stability and accuracy of the image, the image acquisition module may adopt a multi-angle and multi-light source shooting method to avoid image quality degradation due to changes in light or changes in part position. In this way, the system can obtain image information of the target part in real time during the movement, providing basic data for subsequent image processing.

[0088] After receiving the third image information, the edge computing module first identifies all the second target image areas containing the target parts in the third image information through a preset image recognition model. The implementation of this step depends on deep learning algorithms, especially convolutional neural network (CNN) models. During the training process, the model uses a large amount of annotated part image data for learning and extracts the key features of the parts, such as shape and texture. By extracting and classifying the input image, the model can accurately identify the area containing the target parts in the image. For example, the system can load a pre-trained image recognition model through a deep learning framework such as TensorFlow or PyTorch, process the third image information, and identify all image areas containing the target parts.

[0089] After identifying the second target image area, the edge computing module extracts all second target image areas from the third image information to obtain multiple second target part images. The image capture process is usually implemented through image cropping technology, such as using the cropping function in the OpenCV library to separate the identified target image area from the original image. In this way, the system can obtain multiple independent target part images to provide data support for subsequent image processing and analysis. In order to ensure the accuracy of the capture process, the system may perform boundary expansion or scaling on the identified image area to ensure that the captured image contains the complete target part.

[0090] For each second target part image, the edge computing module preprocesses it into a second grayscale image, and processes the second grayscale image through mathematical morphology methods to complete the second surface impurity edge of the target part in the second grayscale image. Grayscale image processing is a basic step in image processing. By converting a color image into a grayscale image, the complexity of the image can be simplified and key image information can be retained. Mathematical morphology methods include corrosion, expansion, opening and closing operations, etc., through which edge features in the image can be enhanced to make the edges of surface impurities clearer. For example, the system can use the morphological transformation function in the OpenCV library to process grayscale images to enhance the integrity of the impurity edges.

[0091] After obtaining the processed grayscale image, the edge computing module uses a threshold segmentation algorithm to separate the second surface impurities from the image background of the second grayscale image, and extracts the second impurity image features of the second surface impurities in the second grayscale image. The threshold segmentation algorithm divides the pixels in the image into foreground and background by setting a threshold, for example, using the Otsu algorithm to automatically calculate the optimal threshold and separate the impurity area in the grayscale image. In this way, the system can extract the image features of the impurities, such as area, shape, etc., to provide data support for subsequent impurity positioning and size calculation. For example, the system can use the threshold segmentation function in the OpenCV library to segment the processed grayscale image to obtain the image feature data of the impurities.

[0092] Next, the edge computing module locates the second surface impurities in the second grayscale image based on the second impurity image features and uses the local binary pattern algorithm to obtain the second impurity size of the second surface impurities. The local binary pattern algorithm is a texture analysis method that generates a binary pattern by comparing the grayscale values ​​of each pixel in the image with its neighboring pixels to characterize the local texture features of the image. In this way, the system can accurately locate the position of the impurity and calculate its size. For example, the system can use the local binary pattern function in the OpenCV library to perform texture analysis on the grayscale image to obtain the size data of each impurity. In this way, the system can accurately obtain the size information of the impurity and provide data support for the subsequent impurity coverage calculation.

[0093] The edge computing module uses the ratio between the second impurity size and the image size of the second grayscale image as the second impurity coverage of the second target part image. Impurity coverage is an important indicator to measure the degree of impurities on the surface of a part. The impurity coverage can be obtained by calculating the ratio of the impurity area to the total area of ​​the image. For example, for a grayscale image with a size of 100x100 pixels, if the impurity area is 100 pixels, the impurity coverage is 1%. In this way, the system can quantify the degree of impurities on the surface of the part and provide a basis for subsequent solution replacement decisions.

[0094] When the edge computing module determines that the second impurity coverage exceeds the preset coverage threshold, the edge computing module generates a solution replacement instruction and sends the solution replacement instruction to the activation processing control unit in the activation processing module. The preset coverage threshold is set according to actual production needs and quality standards, for example, it is set to 2%. When the impurity coverage exceeds this threshold, it means that the level of impurities on the surface of the part has exceeded the allowable range and the solution needs to be replaced to ensure the pretreatment effect. Finally, the activation processing control unit completes the solution replacement of the activation processing container based on the adjusted first module configuration.

[0095] In one embodiment, after receiving the second image information, the edge computing module generates feedback adjustment information using image recognition technology, including the following steps: After receiving the second image information, the edge computing module pre-processes the second image information; The edge computing module uses a target detection algorithm to identify a target component image region in the second image information, where the target component image region is an image region in the second image information that includes a region to be processed; The edge computing module extracts target component image features from the target component image region, where the target component image features include at least one or more features of image color features, image shape features, image edge features, and image texture features; The edge computing module compares the target component image features with the preset electroplating quality standards and generates feedback adjustment information based on the comparison results.

[0096] In this embodiment, after the edge computing module receives the second image information, it first preprocesses the second image information. The preprocessing steps include operations such as image denoising, image enhancement, and image normalization, the purpose of which is to improve image quality and consistency. Image denoising can be achieved by methods such as median filtering or Gaussian filtering, which can effectively remove random noise in the image and make the image clearer. Image enhancement can use histogram equalization or adaptive histogram equalization to enhance the contrast of the image and make the image details more obvious. Image normalization is to normalize the pixel values ​​of the image to a fixed range, such as between 0 and 1, so that different images have the same scale in subsequent processing. Through these preprocessing operations, it can be ensured that the subsequent target detection and feature extraction steps are carried out on the basis of high-quality and consistent images.

[0097] After the preprocessing is completed, the edge computing module uses the target detection algorithm to identify the target component image area in the second image information. The target detection algorithm can use models such as YOLO (You Only Look Once) or Faster R-CNN (Region-based Convolutional Neural Networks) based on deep learning. After identifying the target component image area, the edge computing module extracts the image features of the target component from the target component image area. Image features include color features, shape features, edge features, and texture features. Color features can be represented by calculating the color histogram or color moment of the image, such as the mean and variance of the RGB color space. Shape features can be extracted by methods such as Hu moment or Fourier descriptor, which can describe the geometric shape of the target component. Edge features can be extracted by methods such as Canny edge detection or Sobel operator, which can reflect the contour information of the target component. Texture features can be extracted by methods such as gray level co-occurrence matrix (GLCM) or local binary pattern (LBP), which can describe the surface texture of the image. Through these feature extraction methods, various aspects of the target component can be fully described, providing detailed feature data for subsequent quality assessment.

[0098] After extracting the image features of the target component, the edge computing module compares these features with the preset electroplating quality standards. Electroplating quality standards usually include indicators such as color consistency, surface smoothness, edge clarity, and texture uniformity. The comparison process can be achieved by calculating the similarity or difference between features, such as using methods such as Euclidean distance, cosine similarity, or chi-square test. In specific implementation, the extracted color features can be compared with the standard color features to calculate the color difference; the extracted shape features can be compared with the standard shape features to calculate the shape similarity; the extracted edge features can be compared with the standard edge features to calculate the edge clarity; the extracted texture features can be compared with the standard texture features to calculate the texture consistency. Through these comparison methods, the electroplating quality of the target component can be comprehensively evaluated to determine whether it meets the preset standards.

[0099] According to the comparison results, the edge computing module generates feedback adjustment information. The feedback adjustment information includes adjustment suggestions and specific operation instructions for the electroplating process. For example, if the comparison results show that the color of the target component is inconsistent, feedback adjustment information for adjusting the concentration of the electroplating solution or the electroplating time can be generated; if the comparison results show that the surface of the target component is not smooth, feedback adjustment information for adjusting the electroplating current or the electroplating temperature can be generated; if the comparison results show that the edge of the target component is not clear, feedback adjustment information for adjusting the electroplating voltage or the electroplating process can be generated. The edge computing module sends the feedback adjustment information to the electroplating module, so that the electroplating module automatically adjusts the electroplating parameters to ensure that the electroplating quality meets the preset standards. Through this feedback adjustment mechanism, the electroplating process can be monitored and optimized in real time to improve production efficiency and product quality.

[0100] A person skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of protection of the present application is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0101] One or more embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application should be included in the protection scope of the present application.

Claims

1. An automated electroplating control system based on image recognition, characterized in that: The system comprises a support, wherein the support comprises a support frame (1) and a support platform (2), wherein the support platform (2) is fixedly arranged at the bottom of the support frame (1), wherein a plurality of cavities are provided in the support platform (2) as storage rooms (3), wherein an edge computing module (4) is placed in the storage room (3), and the system further comprises: A first storage platform (5), arranged on the supporting platform (2), for storing target parts to be processed; an information acquisition module, connected in communication with the edge computing module (4), for acquiring part processing information of the target part, and sending the part processing information to the edge computing module (4); a first image acquisition module (7), arranged on the top of the support frame (1) and located directly above the first storage platform (5), and connected to the edge computing module (4) for acquiring first image information of all the target parts located on the first storage platform (5), and sending the first image information to the edge computing module (4); After receiving the part processing information and the first image information, the edge computing module (4) combines the part processing information and the first image information and generates module configuration information by using natural language processing technology and image recognition technology; an activation processing module (8) which is in communication with the edge computing module (4), and is used to receive the module configuration information, change the preset activation processing module (8) configuration to a first module configuration according to the module configuration information, and perform activation processing on the target part based on the first module configuration; A part preprocessing module (11), arranged on the support platform (2), for providing a part shielding block and a processing substrate (15) adapted for the target part; an auxiliary robot arm (10), movably disposed on the support platform (2), used for clamping the target part and moving it between the first storage platform (5), the activation processing module (8) and the part pre-processing module (11), and also used for combining the target part, the part shielding block and the processing substrate (15) into a target assembly in the part pre-processing module (11); an electroplating module (9), arranged on the support platform (2) and the support frame (1) and in communication connection with the edge computing module (4), for receiving the module configuration information, changing the preset electroplating module (9) configuration to a second module configuration according to the module configuration information, and for performing electroplating processing on the target component based on the second module configuration; A second storage table (12), arranged on the support platform (2), for storing the processed target components; a second image acquisition module (13), arranged on the top of the support frame (1) and located directly above the second storage platform (12), and connected in communication with the edge computing module (4), and used for acquiring second image information of the target component located on the second storage platform (12), and sending the second image information to the edge computing module (4); After receiving the second image information, the edge computing module (4) generates feedback adjustment information using image recognition technology, and the electroplating module (9) receives the feedback adjustment information and adjusts the second module configuration according to the feedback adjustment information; The auxiliary robot arm (10) is also used to clamp the target component and move it between the part pretreatment module (11), the electroplating module (9) and the second storage table (12).

2. The automatic electroplating control system based on image recognition according to claim 1 is characterized in that: The activation treatment module (8) comprises an activation treatment container (81), a solution configuration unit (82), a waste liquid collection tank (83) and an activation treatment control unit (84); the activation treatment container (81) is arranged on the support platform (2); the activation treatment container (81) comprises an ultrasonic cleaning tank (811), an acid cleaning tank (812), an alkaline cleaning tank (813) and an activation treatment tank (814); the waste liquid collection tank (83), the solution configuration unit (82) and the activation treatment control unit (84) are all arranged in the storage room (3); the solution configuration unit (82) comprises a plurality of solution tanks, each of which stores different types of pretreatment solutions; all of the solution tanks are connected to the bottom of the activation treatment container (81) via a lifting pump (85) and an activation solenoid valve (86); the waste liquid collection tank (83) is connected to the bottom of the activation treatment container (81) via the activation solenoid valve (86); The activation processing control unit (84) is communicatively connected with the edge computing module (4), all the lifting pumps (85) and all the activation solenoid valves (86). The activation processing control unit (84) receives the module configuration information sent by the edge computing module (4). The activation processing control unit (84) changes the preset activation processing module (8) configuration to a first module configuration according to the activation module configuration information in the module configuration information. The first module configuration includes the equipment start and stop time nodes of all the lifting pumps (85) and all the activation solenoid valves (86). The activation processing control unit (84) controls all the lifting pumps (85) and all the activation solenoid valves (86) based on the first module configuration to complete the pretreatment solution configuration work of the activation processing container (81).

3. The automatic electroplating control system based on image recognition according to claim 2 is characterized in that: The system further comprises a third image acquisition module (14), wherein the third image acquisition module (14) is arranged on the support frame (1) and is located at any one of the two ends in the length direction of the support platform (2). The third image acquisition module (14) is used for acquiring third image information of the target part when the auxiliary robot arm (10) clamps the target part and moves it from the activation processing module (8) to the part pre-processing module (11), and sending the third image information to the edge computing module (4). After receiving the third image information, the edge computing module (4) generates a solution replacement instruction using image recognition technology, and sends the solution replacement instruction to the activation processing control unit (84). The activation processing control unit (84) receives and executes the solution replacement instruction to adjust the first module configuration. The activation processing control unit (84) controls all the lifting pumps (85) and all the activation solenoid valves (86) based on the adjusted first module configuration to complete the solution replacement work of the activation processing container (81).

4. The automatic electroplating control system based on image recognition according to claim 3 is characterized in that: The target part surface comprises a to-be-processed area that needs to be processed and a protection area that does not need to be processed; the processing substrate (15) and the part shielding block are both made of corrosion-resistant materials; the cross-sectional shape of the part shielding block is the same as the shape formed by the protection area; a substrate liquid inlet hole (151) and a substrate liquid outlet hole (152) are formed through the surface of the processing substrate (15); a liquid discharge groove (153) is also formed on the surface of the processing substrate (15); one end of the liquid discharge groove (153) is connected to the substrate liquid outlet hole (152); When the auxiliary robot arm (10) combines the target part, the part shielding block and the processing substrate (15) into a target component in the part preprocessing module (11), the target part is fixed to the surface of the processing substrate (15), and a processing cavity filled with electroplating liquid is formed between the area to be processed on the surface of the target part and the surface of the processing substrate (15), the end of the drainage groove (153) away from the substrate liquid outlet (152) and all the substrate liquid inlet holes (151) are located in the processing cavity, the substrate liquid outlet (152) is located outside the processing cavity, the part shielding block is fixed to the protection area on the surface of the target part, and the part shielding block is tightly fitted with the surface of the target part.

5. The automatic electroplating control system based on image recognition according to claim 4 is characterized in that: The electroplating module (9) comprises an electroplating control unit (91), an electroplating liquid storage tank (92), an electroplating waste liquid collection tank (93) and a pressurizing unit (94); the pressurizing unit (94) comprises a hydraulic device (941) fixedly arranged on the top of the support frame (1) and a processing platform (942) arranged on the supporting platform (2); the processing platform (942) is located directly below the hydraulic device (941); the processing platform (942) vertically penetrates the processing platform (942) and the supporting platform (2) from the top surface to form a platform liquid inlet hole and a platform liquid outlet hole; when the auxiliary robot arm (10) places the target component on the processing platform (942) in the electroplating module (9), the base liquid inlet hole (151) is correspondingly connected to the platform liquid inlet hole, and the base liquid outlet hole is correspondingly connected to the platform liquid outlet hole; The electroplating control unit (91), the electroplating liquid storage tank (92) and the electroplating waste liquid collection tank (93) are all arranged in the storage room (3); the electroplating liquid storage tank (92) is connected to the inner top surface of the supporting platform (2) through a liquid adding pipe, and all the platform liquid inlets are connected to the liquid adding pipe, and the liquid adding pipe is provided with a liquid adding solenoid valve (95), a liquid adding pump (96) and an electronic flow meter (97); the electroplating waste liquid collection tank (93) is connected to the inner top surface of the supporting platform (2) through a liquid outlet pipe, and all the platform liquid outlets are connected to the liquid outlet pipe, and the liquid outlet pipe is provided with a liquid outlet solenoid valve (98) and a liquid extraction pump (99); The electroplating control unit (91) is communicatively connected with the edge computing module (4), the hydraulic device (941), the liquid adding solenoid valve (95), the liquid adding pump (96), the electronic flow meter (97), the liquid outlet solenoid valve (98) and the liquid extraction pump (99), and the electroplating control unit (91) receives the module configuration information sent by the edge computing module (4). The electroplating control unit (91) changes the preset electroplating module (9) configuration to a second module configuration according to the electroplating module (9) configuration information in the module configuration information, and the second module configuration includes the equipment start and stop time nodes of the hydraulic device (941), the liquid adding solenoid valve (95), the liquid adding pump (96), the liquid outlet solenoid valve (98) and the liquid extraction pump (99).

6. An automated electroplating control method based on image recognition, characterized in that: Applied to the automated electroplating control system according to claim 5, the method comprises the following steps: The first image acquisition module acquires first image information of all target parts located on the first storage table, and sends the first image information to the edge computing module; The information acquisition module acquires the part processing information of the target part and sends the part processing information to the edge computing module; After receiving the part processing information and the first image information, the edge computing module combines the part processing information and the first image information and generates module configuration information by using natural language processing technology and image recognition technology; The activation processing module receives the module configuration information, and changes the preset activation processing module configuration to the first module configuration according to the module configuration information; the electroplating module receives the module configuration information, and changes the preset electroplating module configuration to the second module configuration according to the module configuration information; The auxiliary robot arm clamps the target part and moves it from the first storage station to the activation processing module, and the activation processing module performs activation processing on the target part based on the first module configuration; The auxiliary robot arm holds the target part after activation treatment and moves it to a part pre-processing module that provides a part shielding block and a processing substrate adapted for the target part, and the auxiliary robot arm combines the target part, the part shielding block and the processing substrate into a target assembly in the part pre-processing module; The auxiliary robot arm clamps the target component and moves it to the electroplating module, and the electroplating module performs electroplating processing on the target component based on the configuration of the second module; The auxiliary robot arm clamps the target component after electroplating and moves it to the second storage platform, and places the target component on the second storage platform; The second image acquisition module acquires second image information of the target component located on the second storage table, and sends the second image information to the edge computing module; After receiving the second image information, the edge computing module generates feedback adjustment information using image recognition technology, and the electroplating module receives the feedback adjustment information and adjusts the second module configuration according to the feedback adjustment information.

7. The automatic electroplating control method based on image recognition according to claim 6, characterized in that: After the edge computing module receives the part processing information and the first image information, combining the part processing information and the first image information and using natural language processing technology and image recognition technology to generate module configuration information includes the following steps: After receiving the part processing information, the edge computing module uses natural language processing technology to extract part material type information and part electroplating process information from the part processing information; The edge computing module retrieves corresponding electroplating liquid type information from a preset electroplating processing database according to the part material type information; The edge computing module generates electroplating control timeline information of the electroplating module according to the part electroplating process information, and integrates the electroplating liquid type information and the electroplating control timeline information into electroplating module configuration information, wherein the electroplating control timeline information includes the start and stop time nodes of all devices in the electroplating module; After receiving the first image information, the edge computing module uses image recognition technology to analyze the first image information to obtain the part surface state information of the target part, and generates activation module configuration information by combining the part surface state information and the part material type information.

8. The automatic electroplating control method based on image recognition according to claim 7, characterized in that: After receiving the first image information, the edge computing module uses image recognition technology to analyze the first image information to obtain the part surface state information of the target part, and generates activation module configuration information in combination with the part surface state information and the part material type information, including the following steps: The edge computing module retrieves corresponding pretreatment solution type information and pretreatment solution initial concentration information corresponding to each pretreatment solution type information from the electroplating processing database according to the part material type information, wherein the pretreatment solution type information includes an acid solution, an alkaline solution, and an activation treatment solution; After receiving the first image information, the edge computing module identifies all first target image regions containing the target parts in the first image information through a preset image recognition model, wherein the image recognition model is pre-trained using multiple types of part image data sets; The edge computing module extracts all the first target image areas from the first image information to obtain a plurality of first target part images; For each first target part image, the edge computing module preprocesses the first target part image into a first grayscale image, and processes the first grayscale image by a mathematical morphology method to complete the first surface impurity edge of the target part in the first grayscale image, the edge computing module uses a threshold segmentation algorithm to separate the first surface impurities from the image background of the first grayscale image, and extracts the first impurity image features of the first surface impurities in the first grayscale image, the edge computing module locates the first surface impurities in the first grayscale image based on the first impurity image features and uses a local binary pattern algorithm to obtain the first impurity size of the first surface impurities, and the edge computing module uses the ratio between the first impurity size and the image size of the first grayscale image as the first impurity coverage rate of the first target part image; The edge computing module calculates the first impurity coverage rate of all the first target part images by averaging to obtain an average impurity coverage rate, and uses the average impurity coverage rate as the part surface state information of the target part in the first image information; The edge computing module adjusts the initial concentration information of the pretreatment solution according to the average impurity coverage to obtain the target concentration information of the pretreatment solution, and generates activation module configuration information in combination with the pretreatment solution type information and the pretreatment solution target concentration information.

9. The automatic electroplating control method based on image recognition according to claim 8, characterized in that: The method further comprises the steps of: When the auxiliary robot arm holds the target part and moves it from the activation processing module to the part preprocessing module, the third image acquisition module acquires the third image information of the target part and sends the third image information to the edge computing module; After receiving the third image information, the edge computing module identifies all second target image regions containing the target parts in the third image information through the image recognition model; The edge computing module extracts all the second target image areas from the third image information to obtain a plurality of second target part images; For each second target part image, the edge computing module preprocesses the second target part image into a second grayscale image, and processes the second grayscale image by a mathematical morphology method to complete the second surface impurity edge of the target part in the second grayscale image, the edge computing module uses a threshold segmentation algorithm to separate the second surface impurities from the image background of the second grayscale image, and extracts the second impurity image features of the second surface impurities in the second grayscale image, the edge computing module locates the second surface impurities in the second grayscale image based on the second impurity image features and uses a local binary pattern algorithm to obtain the second impurity size of the second surface impurities, and the edge computing module uses the ratio between the second impurity size and the image size of the second grayscale image as the second impurity coverage rate of the second target part image; When the edge computing module determines that the second impurity coverage exceeds a preset coverage threshold, the edge computing module generates a solution replacement instruction and sends the solution replacement instruction to the activation processing control unit in the activation processing module; The activation process control unit receives and executes the solution replacement instruction to adjust the first module configuration, and the activation process control unit completes the solution replacement work of the activation process container based on the adjusted first module configuration.

10. The automatic electroplating control method based on image recognition according to claim 6, characterized in that: After receiving the second image information, the edge computing module generates feedback adjustment information by using image recognition technology, including the following steps: After receiving the second image information, the edge computing module pre-processes the second image information; The edge computing module uses a target detection algorithm to identify a target component image region in the second image information, where the target component image region is an image region in the second image information that includes a to-be-processed region; The edge computing module extracts target component image features from the target component image region, wherein the target component image features include at least one or more features of image color features, image shape features, image edge features, and image texture features; The edge computing module compares the target component image features with preset electroplating quality standards and generates feedback adjustment information based on the comparison results.

Citation Information

Cited By

  • Monitoring method and system for equipment operation

    CN119194580A

  • Chip clamp automatic adjusting method and system

    CN120199710A

  • Plating selection control system and method based on positioning and tracking

    CN120931714A