Full-automatic intelligent continuous rack plating line body detection method and device

Abstract

The invention relates to the technical field of rack plating line body detection, and discloses a full-automatic intelligent continuous rack plating line body detection method and device.The method comprises the steps that real-time multi-modal data collection is conducted on the rack plating line body operation process, and rack plating line body state data and electroplating liquid multispectral data are obtained; joint feature extraction is carried out, and feature vectors representing the relation between the rack plating process and the electroplating liquid components are obtained; constructing a mapping model of rack plating production quality and recovery parameters; executing a variable genetic factor-based multi-objective optimization algorithm, creating a hierarchical cooperative control strategy, and generating rack plating line body production parameters and linkage control parameters of electroplating liquid recovery equipment; according to the method, accurate prediction of optimal recovery parameters under different working conditions is achieved, and the problem that traditional fixed parameter control is insufficient in prediction capacity in the face of complex change working conditions is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of detection of hanging plating line bodies, and in particular, to a fully automatic intelligent continuous hanging plating line body detection method and device. Background Art

[0002] Traditional electroplating solution recovery methods mainly rely on simple physical precipitation and filtration technologies, lacking the ability to monitor the operating state of the electroplating line body and the composition of the electroplating solution in real time, resulting in the separation of the recovery process from the production process. This separation not only makes the recovery efficiency low, but also cannot perform precise control for different electroplating working conditions and changes in the composition of the electroplating solution, causing fluctuations in electroplating quality and energy waste. Especially in the process of precious metal electroplating, due to the lack of accurate composition detection and control means, the recovery process often has problems of low efficiency and poor accuracy, and it is difficult to meet the requirements of high-quality electroplating production.

[0003] Existing hanging plating line body control systems mainly adopt a fixed parameter control method, which is difficult to cope with the dynamic changes in the composition of the electroplating solution and the process fluctuations caused by workpiece switching. At the same time, there is a lack of an effective coordination mechanism between the electroplating solution recovery equipment and the hanging plating line body, and the two operate independently, unable to achieve the optimal allocation of resources and the efficient utilization of energy. In addition, traditional control algorithms lack adaptability and cannot dynamically adjust control strategies according to the actual production situation, resulting in system response lag and insufficient control accuracy. Summary of the Invention

[0004] The present invention provides a fully automatic intelligent continuous hanging plating line body detection method and device. The present invention realizes the accurate prediction of the optimal recovery parameters under different working conditions, and solves the problem of insufficient prediction ability of traditional fixed parameter control in the face of complex changing working conditions.

[0005] In a first aspect, the present invention provides a fully automatic intelligent continuous hanging plating line body detection method, and the fully automatic intelligent continuous hanging plating line body detection method includes: Performing real-time multi-modal data acquisition on the operation process of the hanging plating line body to obtain hanging plating line body state data and electroplating solution multi-spectral data; Performing joint feature extraction on the hanging plating line body state data and the electroplating solution multi-spectral data to obtain a feature vector representing the relationship between the hanging plating process and the electroplating solution composition; Based on the feature vector, constructing an association function between the operating state of the hanging plating line body and the electroplating solution recovery efficiency to obtain a mapping model of the hanging plating production quality and the recovery parameters; According to the mapping model, executing a multi-objective optimization algorithm based on variable genetic factors and creating a hierarchical coordination control strategy to generate linkage control parameters for the hanging plating line body production parameters and the electroplating solution recovery equipment; Perform dynamic coordination of the rack plating speed and the electroplating solution treatment speed based on the linkage control parameters to obtain a synchronization strategy for the line body operation and the recycling treatment.

[0006] In a second aspect, the present invention provides a full-automatic intelligent continuous rack plating line body detection device, and the full-automatic intelligent continuous rack plating line body detection device includes: A data acquisition module, configured to perform real-time multimodal data acquisition on the operation process of the rack plating line body to obtain rack plating line body state data and electroplating solution multispectral data; A feature extraction module, configured to perform joint feature extraction on the rack plating line body state data and the electroplating solution multispectral data to obtain a feature vector characterizing the relationship between the plating process and the electroplating solution composition; A construction module, configured to construct an association function between the operation state of the rack plating line body and the electroplating solution recycling efficiency based on the feature vector to obtain a mapping model of the rack plating production quality and the recycling parameters; A multi-objective optimization module, configured to execute a multi-objective optimization algorithm based on variable genetic factors and create a hierarchical cooperative control strategy according to the mapping model, and generate linkage control parameters for the rack plating line body production parameters and the electroplating solution recycling equipment; A dynamic coordination module, configured to perform dynamic coordination of the rack plating speed and the electroplating solution treatment speed based on the linkage control parameters to obtain a synchronization strategy for the line body operation and the recycling treatment.

[0007] In the technical solution provided by the present invention, through the collaborative work of a variety of sensing devices such as a high-resolution vision sensor, a current density sensor, an infrared thermal imager, and a vibration sensor, the all-round monitoring of the operation state of the hanging plating line body is realized. At the same time, the accurate detection of the composition of the electroplating solution is achieved by combining ultraviolet-visible spectroscopy, near-infrared spectroscopy, and Raman spectroscopy. Through the joint feature extraction of the state data of the hanging plating line body and the multi-spectral data of the electroplating solution, a feature vector of the relationship between the hanging plating process and the composition of the electroplating solution is established, realizing a deep understanding of the complex relationship among the electroplating quality characteristics, uniformity characteristics, and the composition of the electroplating solution, breaking through the limitation of the traditional method that can only analyze singly. Based on the feature vector, an association function between the operation state of the hanging plating line body and the electroplating solution recovery efficiency is constructed. Through Bayesian sparse parameter polynomial regression and a working condition adaptive association function, the accurate prediction of the optimal recovery parameters under different working conditions is realized, solving the problem of insufficient prediction ability of the traditional fixed parameter control in the face of complex and changing working conditions. By introducing a variable genetic factor multi-objective optimization algorithm, dynamically adjusting the crossover probability and mutation probability of the genetic algorithm, the balanced optimization among electroplating quality, recovery efficiency, and energy consumption is realized, avoiding the defect that the traditional optimization method is easy to fall into local optimum, and improving the global optimization ability of the system. By constructing a three-layer control architecture of the hanging plating line body control layer, the electroplating solution recovery equipment control layer, and the global resource scheduling layer, the coordinated control of production parameters and recovery parameters is realized, solving the problem that each subsystem in the traditional control method runs independently and is disjointed from each other, and improving the coordination efficiency of the overall system. Based on the line speed-flow matching data, the dynamic coordination of the hanging plating speed and the electroplating solution treatment speed is realized. By switching the smooth transition scheme and the concentration adaptive treatment scheme, the system can flexibly respond to various working conditions such as workpiece switching, line speed change, and shutdown, enhancing the adaptability of the system to the changing environment and improving the overall stability of the electroplating process and the recovery process.

[0008] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are realized and obtained by the structures specifically pointed out in the specification, the claims, and the drawings.

[0009] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0010] Figure 1 It is a schematic diagram of an embodiment of the full-automatic intelligent continuous hanging plating line body detection method in the embodiment of the present invention; Figure 2 It is a schematic diagram of an embodiment of the full-automatic intelligent continuous hanging plating line body detection device in the embodiment of the present invention. Detailed Embodiments

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0012] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally further include other unlisted steps or units, or may optionally further include other steps or units inherent to these processes, methods, products, or devices.

[0013] To facilitate the understanding of this embodiment, a fully automatic intelligent continuous barrel plating line body detection method disclosed in the embodiments of the present invention will be introduced in detail first. As Figure 1 shown, this method includes the following steps: 101. Collect real-time multimodal data during the operation of the barrel plating line body to obtain barrel plating line body status data and electroplating solution multispectral data; It can be understood that the execution subject of the present invention can be a fully automatic intelligent continuous barrel plating line body detection device, or a terminal or a server. Specifically, it is not limited here. The embodiments of the present invention will be described by taking the server as the execution subject as an example.

[0014] Specifically, a high-resolution vision sensor is used to perform real-time imaging acquisition on the surface of electroplated workpieces on the hanging plating line. The resolution of this sensor reaches above 4K, capturing key features such as microscopic defects, coating thickness variations, and adhesion uniformity on the surface of the electroplated workpieces. At the same time, an image enhancement algorithm is combined to denoise, sharpen, and correct the illumination of the acquired images, obtaining workpiece surface image data. Meanwhile, current density sensors are used to continuously monitor the current distribution in the electroplating tank of the hanging plating line. These sensors are evenly arranged in various key areas of the electroplating tank, capturing the spatial variations of the current density in real time, and obtaining current density distribution data through time series analysis to ensure the timely monitoring of current uniformity and abnormal fluctuations during the electroplating process. An infrared thermal imager is used to dynamically scan the temperature field of the hanging plating line. The infrared thermal imager has high sensitivity and a wide band response range, capable of accurately monitoring the temperature changes of the electroplating tank, the workpiece surface, and various parts of the hanging plating line, forming temperature field mapping data. And a multi-channel vibration sensor is used to continuously monitor the mechanical operating state of the hanging plating line. The vibration sensors are installed on key moving parts of the hanging plating line, including drive motors, chains, conveying devices, etc. By analyzing the frequency characteristics, amplitude variations, and harmonic components of the vibration signals, vibration characteristic data is generated, which can effectively identify abnormal states or potential faults in the mechanical system. Through time synchronization and spatial registration algorithms, multi-modal fusion is performed on the workpiece surface image data, current density distribution data, temperature field mapping data, and vibration characteristic data. Time synchronization marks the acquisition timestamps of each data source through a high-precision clock signal, achieving microsecond-level synchronization; spatial registration uses feature matching and geometric transformation algorithms to ensure that the spatial correspondence relationships of different data sources remain consistent, generating hanging plating line state data. Ultraviolet-visible spectroscopy sensors, near-infrared spectroscopy sensors, and Raman spectroscopy sensors are used to perform multi-band spectral acquisition on the electroplating solution. The ultraviolet-visible spectroscopy sensor covers the 200 - 800 nm band and can accurately identify changes in metal ion concentrations; the near-infrared spectroscopy sensor covers the 800 - 2500 nm band and can detect the concentrations of organic additives, complexing agents, and impurities; while the Raman spectroscopy sensor analyzes the molecular structure and chemical bond changes in the electroplating solution through the laser scattering mechanism. A multi-channel fiber optic coupler enables efficient contact between the spectroscopy sensors and the electroplating solution, with a sampling frequency as high as 10 times per second, ensuring that the spectral data has high spatio-temporal resolution. After preprocessing such as denoising, baseline correction, and spectral normalization of the acquired electroplating solution multi-spectral data, it is jointly stored in an industrial-grade database with the hanging plating line state data.

[0015] 102. Joint feature extraction is performed on the hanging plating line state data and the electroplating solution multi-spectral data to obtain a feature vector characterizing the relationship between the electroplating process and the electroplating solution composition; Specifically, electroplating defect recognition is performed on the workpiece surface image data in the barrel plating line body state data. The workpiece surface images obtained by the high-resolution vision sensor are used for feature extraction by a deep convolutional neural network. This network is pre-trained and undergoes transfer learning using an electroplated surface defect image library to accurately identify coating surface defects, including defect types such as pinholes, pockmarks, blisters, scorching, peeling, and uneven thickness. Feature parameters such as defect area, shape, distribution density, and depth are calculated to form an electroplating quality feature set. At the same time, for the current density distribution data in the barrel plating line body state data, the electric field uniformity is calculated by solving a three-dimensional electric field distribution model. This model is based on the finite element method, combines the geometric structure of the electroplating tank and the electrode arrangement, constructs an electric field distribution simulation model, and generates current density distribution data through boundary condition constraints and multiple iterative calculations. Then, the uniformity of the electric field distribution is quantified through the mean square error method and the current density deviation index, and key parameters such as the maximum current density, minimum current density, standard deviation, and uniformity coefficient are extracted to form an electroplating uniformity feature set, which is used to characterize the consistency of the current distribution during barrel plating. For the multi-spectral data of the electroplating solution, spectral feature extraction is carried out. Combining multi-dimensional data of ultraviolet-visible spectroscopy, near-infrared spectroscopy, and Raman spectroscopy, a spectral feature extraction framework based on a multi-layer convolutional neural network and a long short-term memory network is constructed. The original spectral data is preprocessed, including baseline correction, denoising, normalization, and dimensional compression. Then, the local features of the spectral signal are extracted through the convolutional layer, and the time-series related features are extracted through the long short-term memory network layer to obtain a composition feature set of the electroplating solution, which contains multi-dimensional information such as metal ion concentration, organic additive content, and impurity level. Through time-series correlation analysis of the electroplating quality feature set and the electroplating solution composition feature set, a correlation model between quality and composition is established. The dynamic time warping algorithm is used to perform time-series matching on the quality features and composition features at different times during the electroplating process, and the correlation coefficient matrix is calculated to identify the feature change trend at key time points, thereby extracting the quality-composition correlation features. At the same time, spatial correlation analysis is performed on the electroplating uniformity feature set and the electroplating solution composition feature set. Using the hot spot mapping algorithm, the electroplating tank area is divided into multiple micro-units, and spatial correlation calculations are performed on the current density uniformity features and electroplating solution composition of different micro-units based on spatial statistics. The key areas with uneven current distribution or abnormal electroplating solution composition in the electroplating tank are identified through the hot spot mapping algorithm to form the uniformity-composition correlation features. By fusing the quality-composition correlation features and the uniformity-composition correlation features, a multi-modal feature fusion algorithm (such as self-attention mechanism or graph neural network GNN) is used to form a feature vector that characterizes the relationship between the barrel plating process and the electroplating solution composition. The length of this feature vector is 128, which contains the workpiece surface quality, current uniformity, electroplating solution composition, and their time-series and spatial correlation features during the barrel plating process.

[0016] 103. Construct a correlation function between the operating state of the rack plating line and the electroplating solution recovery efficiency based on the eigenvector, and obtain a mapping model of the rack plating production quality and the recovery parameters; Specifically, the feature vectors are subjected to non-linear dimensionality reduction processing. Through the t-distribution neighborhood embedding or kernel principal component analysis method, the high-dimensional feature data is mapped into a low-dimensional embedding space. During the dimensionality reduction process, the key information in the feature vectors is retained, and redundant dimensions and noise interference are effectively removed to obtain the barrel plating-recovery feature dimensionality reduction data. A multi-input multi-output relationship network is constructed using the barrel plating-recovery feature dimensionality reduction data. This network adopts a multi-layer perceptron structure. By inputting the multi-modal feature dimensionality reduction data of the barrel plating line body, the electroplating solution recovery efficiency and related recovery parameters are output simultaneously. On this basis, Bayesian sparse parameter polynomial regression is adopted. By constructing a polynomial basis function set from the first order to the third order and introducing a Gaussian scale mixture prior, a sparsity constraint is set for the model parameters to achieve an accurate mapping between the feature vectors and the recovery efficiency. The model parameters are optimized by maximizing the evidence lower bound, and the adaptive L1 regularization is used to suppress the polynomial coefficients of non-critical terms to obtain a preliminary correlation function. For the preliminary correlation function, a working condition classification mechanism is introduced. The typical operating conditions of the barrel plating line body are identified through the K-means clustering algorithm. Combining key parameters such as current density distribution, electroplating solution temperature, metal ion concentration, and barrel plating speed, the operating data is divided into different working condition categories. For each type of working condition, a sub-model target training mechanism is adopted to independently model and train the feature dimensionality reduction data of each working condition category to form a working condition adaptive correlation function, ensuring that the model can be specifically optimized for different operating conditions, improving the prediction accuracy and model robustness. On this basis, a two-way mapping model of electroplating quality and recovery parameters is constructed. This model combines the working condition adaptive correlation function and, through a reverse inference algorithm, reversely infers the optimal recovery parameters from the target quality. The reverse inference adopts a reverse optimization process based on gradient descent. First, the target plating quality standard is fixed, and by minimizing the loss function of the deviation of the electroplating solution composition from the target concentration, the recovery parameters are gradually adjusted until the concentration of the recovery solution is consistent with the target quality requirements, and finally a recovery parameter prediction model is obtained. A speed collaborative response model is constructed by combining the recovery parameter prediction model with the real-time barrel plating line speed. This model adopts a dynamic time series modeling method to model the non-linear relationship between the change in the barrel plating line body speed and the recovery rate, realizing synchronous control between the two. The speed collaborative response model can automatically adjust the recovery rate according to the change in the barrel plating line speed, keep the composition of the electroplating solution within the optimal range, and prevent fluctuations in electroplating quality caused by speed changes. The speed collaborative response model and the electroplating tank liquid level control strategy are subjected to liquid level balance constraints. The liquid level balance control adopts an adaptive PID controller. By real-time monitoring the change in the electroplating tank liquid level, according to the dynamic balance relationship between the barrel plating line speed, the recovery rate, and the electroplating solution replenishment rate, the replenishment volume and the recovery rate are automatically adjusted to ensure that the electroplating solution liquid level is always maintained within the safe range, and finally a mapping model of barrel plating production quality and recovery parameters is obtained.

[0017] 104. Execute the multi-objective optimization algorithm based on variable genetic factors according to the mapping model and create a hierarchical collaborative control strategy to generate the linkage control parameters of the production parameters of the rack plating line body and the electroplating solution recovery equipment; Specifically, the mapping model between the mass production quality of rack plating and the recycling parameters is transformed into a multi-objective optimization problem. Its optimization objectives include maximizing the mass production quality of the rack plating line, improving the electroplating solution recycling efficiency, minimizing energy consumption, and enhancing system stability. At the same time, combining historical data and process expert rules, the weights of each objective are dynamically adjusted. To improve the optimization efficiency, a multi-objective optimization algorithm with variable genetic factors is used for solution. Based on the traditional genetic algorithm, this algorithm introduces an adaptive mutation rate and crossover rate, and dynamically adjusts the genetic factors according to the population evolution stage, so as to improve the global search ability and convergence speed. The objective weight configuration is based on Pareto front analysis, dynamically adjusts the weight allocation of the objective function, and combines the weighted summation method to normalize different objectives, so as to find the optimal solution in the multi-objective space. A control layer for the rack plating line is constructed based on the objective weight configuration. Based on the feature vectors and optimization parameters extracted from the mapping model, this control layer uses the model predictive control method to generate rack plating production control instructions. The rack plating production control instructions include key parameters such as the rack plating line speed, hanging angle, current density, and immersion time, and achieve precise control of the production process through rolling horizon optimization. At the same time, a control layer for the electroplating solution recycling equipment is constructed according to the mapping model. This control layer combines the Bayesian sparse parameter polynomial regression model to calculate the control instructions for the recycling equipment. The control instructions include key control variables such as the self-priming pump flow rate, centrifuge speed, heating coil power, and electric push rod position, and are dynamically adjusted through real-time monitoring data to ensure that the recycling equipment is in the best operating state. A cooperative execution mechanism for the rack plating production control instructions and the recycling equipment control instructions is designed. The cooperative mechanism ensures the linkage and safety of the rack plating and recycling processes by establishing a parameter change transfer function and an interlock protection logic. The parameter change transfer function is based on a multi-input multi-output system, constructs a dynamic correlation equation between the rack plating speed, current density, temperature change and the recycling rate, liquid level change, and realizes real-time parameter adjustment through a state feedback mechanism. The interlock protection logic is managed by a finite state machine, setting three operating states: normal, warning, and fault. Different protection strategies are triggered in different states to prevent the system from getting out of control due to parameter mutations or abnormal conditions. The cooperative mechanism ensures the dynamic matching of parameters between the rack plating production and the recycling equipment in each process stage, thus optimizing the overall performance of the system. At the same time, a global resource scheduling layer for the rack plating line and the recycling equipment is constructed. This scheduling layer takes the multi-objective optimization results as input, combines constraint conditions such as the real-time monitored equipment status, production task priority, and energy consumption limit, and uses a strategy combining integer linear programming and reinforcement learning to solve the overall optimization problem under resource constraints, and obtains the optimal allocation plan. Integrate the hierarchical cooperative control strategy and the optimal allocation plan, and manage the control conversion logic of different production stages through a state machine.The state machine management realizes the dynamic switching and coordinated adjustment of control parameters by establishing a state transition matrix for each production stage, defining the control logic for different stages such as barrel plating startup, acceleration, stabilization, deceleration, and stop, and triggering state transitions based on real-time monitoring data, and finally obtains the linkage control parameters of the barrel plating line production parameters and the electroplating solution recovery equipment.

[0018] According to the mapping model between barrel plating production quality and recycling parameters, different electroplating quality indicators are converted into absolute error functions. The recycling efficiency indicator is converted into a relative efficiency function, using the extraction rate of metal ions in the electroplating solution or the concentration change rate of key components in the electroplating solution as a relative indicator to measure the recycling efficiency, and the energy consumption indicator is converted into a unit cost function. The unit energy consumption cost is calculated by combining the electricity consumption per kilowatt-hour during the recycling process with the unit recycling amount, forming a multi-objective function set. According to the mapping model, the control parameters of the barrel plating line body (including barrel plating speed, current density, suspension angle, immersion time, etc.) and the control parameters of the electroplating solution recycling equipment (including self-priming pump flow rate, centrifuge speed, heating coil power, electric push rod position, etc.) are uniformly encoded into a multi-dimensional vector. This encoding uses real number encoding or binary encoding, specifically depending on the value range and accuracy requirements of the parameters, and the physical constraints of each control parameter (such as maximum current density, minimum flow rate, temperature range, etc.) are converted into variable boundary conditions, thus defining the decision space. Process constraint conditions are imposed on the decision space, including workpiece surface quality, coating uniformity, recycling rate stability, etc., and a coupling constraint equation between electroplating quality and recycling efficiency is established. These coupling constraints are modeled based on the non-linear relationships among electroplating solution composition changes, current density distribution, and recycling rate. At the same time, to prevent conflicts and unstable states between control parameters, balance constraint equations between each control parameter are modeled. These equations capture the dynamic balance relationships between different parameters through multivariate correlation analysis, resulting in a multi-objective optimization problem. Based on the multi-objective optimization problem, the decision variables are mapped into binary or real number chromosomes. Under the genetic algorithm framework, each chromosome corresponds to a possible solution, and a fitness function is defined to reflect the quality of the chromosome. The fitness function uses a weighted comprehensive evaluation method to perform a weighted sum of objective functions such as electroplating quality error, recycling efficiency improvement rate, and energy consumption, and the final fitness value is obtained according to the target weight configuration. The higher the fitness value, the better the quality of the solution. Based on this fitness function, a genetic factor adjustment mechanism of the multi-objective optimization algorithm is introduced. During the multi-objective evolutionary calculation process, the crossover probability and mutation probability are dynamically adjusted. The crossover probability is positively correlated with the population diversity, and the mutation probability shows a non-linear change with the number of evolutionary generations. To prevent the algorithm from falling into a local optimum, the genetic factor adjustment mechanism adopts an adaptive adjustment strategy to automatically adjust the crossover rate and mutation rate according to the fitness change rate, population convergence degree, and evolutionary stage, and dynamically calculates the adaptive genetic parameters. The multi-objective evolutionary calculation is performed using the adaptive genetic parameters, and a candidate weight configuration set is generated through the Pareto optimal solution set. This set covers the optimal solution sets under different target weight configurations. The candidate solutions are sorted through the decision preference function, and combined with domain expert rules, production experience, and target priority information, the optimal weight configuration is selected to obtain the target weight configuration of the multi-objective optimization problem.

[0019] 105. Based on the linkage control parameters, perform dynamic coordination of the hanging plating speed and the electroplating solution treatment speed to obtain a synchronization strategy for the line body operation and recovery treatment.

[0020] Specifically, based on the linkage control parameters, the proportional relationship between the speed of the rack plating line and the flow rate of the electroplating solution is analyzed. By establishing a mapping function between the line speed and the electroplating solution flow rate, multi-dimensional coupling analysis is carried out on variables such as the running speed of the rack plating line body, current density, and immersion time, and parameters such as the electroplating solution recovery flow rate, self-priming pump power, and centrifuge speed, to obtain line speed-flow matching data, which reflects the variation law of the electroplating solution treatment speed under different rack plating speeds. Based on the line speed-flow matching data, a dynamic flow rate adjustment mechanism is constructed, and model predictive control and Kalman filtering are used to quickly respond to changes in the rack plating line speed. When the rack plating line speed suddenly changes, the system recalculates the optimal flow rate adjustment plan within 50 ms and dynamically adjusts the self-priming pump flow rate, centrifuge speed, and heating coil power, so as to maintain the synchronous matching between the electroplating solution recovery equipment and the rack plating line speed. At the same time, combined with the running state of the line body and the change of workpiece size, a smooth transition plan for switching is designed, and the S-shaped curve acceleration / deceleration algorithm is used to gradually adjust the rack plating speed and the electroplating solution flow rate, avoiding fluctuations in the coating thickness or a decrease in the recovery efficiency caused by sudden speed changes or switching delays. Through this plan, a smooth transition during the switching of different batches of workpieces is effectively achieved, thereby maintaining the continuity and stability of the operation of the rack plating line body. At the same time, an adaptive mapping relationship between the component concentration and the treatment speed is constructed in combination with the real-time monitoring results of the electroplating solution components. Ultraviolet-visible spectroscopy, near-infrared spectroscopy, and Raman spectroscopy sensors are used to continuously monitor key parameters such as metal ions, organic additives, and impurity concentrations in the electroplating solution. Feature extraction and trend prediction are carried out on the changes in the component concentration at different times through a self-supervised learning model, and the treatment speed of the electroplating solution is dynamically adjusted according to different concentration levels to form a concentration adaptive treatment plan. The response analysis of the recovery equipment is carried out for the planned and unplanned shutdowns of the rack plating line body to obtain the treatment plan during the shutdown process. For planned shutdowns, the rack plating speed is gradually reduced before shutdown, and at the same time, the self-priming pump flow rate and centrifuge speed are reduced. The system load is gradually reduced through a linear annealing algorithm, so as to ensure a smooth shutdown process. For unplanned shutdowns, an emergency response mechanism is triggered. The shutdown cause is identified through a fast fault diagnosis model, and the priority drainage and electroplating solution cooling strategies are executed to prevent the electroplating solution components from deteriorating during the shutdown or the electroplating solution recovery equipment from entering an abnormal state. To prevent the electroplating solution concentration from becoming unbalanced due to long-term shutdown, a concentration balance strategy is automatically executed. When the shutdown is restored, the recovery flow rate and heating coil power are preferentially adjusted to quickly restore the electroplating solution to a stable state. By integrating the dynamic flow rate adjustment mechanism, the smooth transition plan for switching, the concentration adaptive treatment plan, and the shutdown process treatment plan, a synchronous strategy for the operation of the line body and the recovery treatment is formed.This synchronization strategy is managed by a hierarchical collaborative control mechanism, and is optimized in real time through the global resource scheduling layer. The control parameters are automatically adjusted at different production stages to achieve dynamic matching among the rack plating speed, the electroplating solution recovery speed, and the composition concentration. The control logic for different process stages is switched through the state machine control model to ensure that the system can achieve efficient coordination of the rack plating and recovery processes under various working conditions.

[0021] In the embodiments of the present invention, through the collaborative work of various sensing devices such as high-resolution vision sensors, current density sensors, infrared thermal imagers, and vibration sensors, the all-round monitoring of the operating state of the rack plating line body is realized. At the same time, the accurate detection of the electroplating solution composition is achieved by combining ultraviolet-visible spectroscopy, near-infrared spectroscopy, and Raman spectroscopy. Through the joint feature extraction of the rack plating line body state data and the electroplating solution multi-spectral data, a feature vector of the relationship between the rack plating process and the electroplating solution composition is established, realizing a deep understanding of the complex relationship among the electroplating quality characteristics, uniformity characteristics, and electroplating solution composition, breaking through the limitation of the traditional method that can only analyze singlely. Based on the feature vector, an association function between the operating state of the rack plating line body and the electroplating solution recovery efficiency is constructed. Through Bayesian sparse parameter polynomial regression and the working condition adaptive association function, the accurate prediction of the optimal recovery parameters under different working conditions is realized, solving the problem of insufficient prediction ability of the traditional fixed parameter control in the face of complex changing working conditions. By introducing a variable genetic factor multi-objective optimization algorithm, the crossover probability and mutation probability of the genetic algorithm are dynamically adjusted to achieve the balanced optimization among electroplating quality, recovery efficiency, and energy consumption, avoiding the defect that the traditional optimization method is easy to fall into local optimum and improving the global optimization ability of the system. By constructing a three-layer control architecture of the rack plating line body control layer, the electroplating solution recovery equipment control layer, and the global resource scheduling layer, the collaborative control of production parameters and recovery parameters is realized, solving the problem that each subsystem operates independently and is separated from each other in the traditional control method and improving the collaborative efficiency of the overall system. Based on the line speed-flow matching data, the dynamic coordination of the rack plating speed and the electroplating solution treatment speed is realized. By switching the smooth transition scheme and the concentration adaptive treatment scheme, the system can flexibly respond to various working conditions such as workpiece switching, line speed change, and shutdown, enhancing the adaptability of the system to the changing environment and improving the overall stability of the electroplating process and the recovery process.

[0022] In a specific embodiment, the process of executing step 101 may specifically include the following steps: Use a high-resolution vision sensor to perform real-time imaging acquisition on the surface of the electroplated workpiece on the rack plating line body to obtain workpiece surface image data, and continuously monitor the current distribution in the electroplating tank of the rack plating line body through a current density sensor to obtain current density distribution data; Use an infrared thermal imager to dynamically scan the temperature field of the hanging plating line body to obtain temperature field mapping data, and use a multi-channel vibration sensor to continuously monitor the mechanical operating state of the hanging plating line body to obtain vibration characteristic data; Synchronize the time and register the space of the workpiece surface image data, current density distribution data, temperature field mapping data, and vibration characteristic data to obtain the state data of the hanging plating line body; Collect multi-band spectra of the electroplating solution through ultraviolet-visible spectroscopy sensors, near-infrared spectroscopy sensors, and Raman spectroscopy sensors to obtain multi-spectral data of the electroplating solution.

[0023] Specifically, a high-resolution vision sensor is used to perform real-time imaging acquisition on the surface of electroplated workpieces on the hanging plating line. The resolution of the high-resolution vision sensor is not less than 4K, the frame rate reaches above 30fps, and a CMOS or CCD image sensor is adopted to ensure that high-definition image data of the surface of electroplated workpieces can be captured during the operation of the high-speed hanging plating line. To improve the image quality, the vision sensor is configured with an adaptive exposure and automatic gain control algorithm, which dynamically adjusts the exposure time and gain parameters according to the running speed of the hanging plating line and the reflection characteristics of the workpiece surface, thus avoiding the problems of overexposure or underexposure of the image. At the same time, a multi-angle supplementary lighting system is used to provide uniform lighting conditions, and combined with image enhancement algorithms (such as histogram equalization, gamma correction, etc.), the collected image data is preprocessed to generate workpiece surface image data including the thickness of the coating on the workpiece surface, the uniformity of the coating, and the distribution of defects (such as pinholes, pockmarks, blisters, peeling, etc.). At the same time, a current density sensor is used to continuously monitor the current distribution in the electroplating tank of the hanging plating line. These current density sensors adopt Hall effect or distributed current probe technology, and multi-channel current density acquisition points are arranged at key positions in the electroplating tank, with a sampling frequency of above 100Hz, and the global data of the current density distribution is formed through multi-node signal fusion technology. To eliminate the noise interference in the current signal, the collected current density data is subjected to low-pass filtering and signal denoising processing, and combined with the current density distribution model and the electric field simulation model, the current density is spatially interpolated and distributed reconstructed by the finite element method to generate current density distribution data. At the same time, an infrared thermal imager is used to dynamically scan the temperature field of the hanging plating line. The resolution of the infrared thermal imager is not less than 640×480, the temperature measurement accuracy is within ±0.5°C, and it covers an infrared band range of 8-14μm, and the temperature changes of the hanging plating line, the workpiece surface, and the inside of the electroplating tank are captured in real time. The infrared thermal imager calibrates the thermal field data through a thermal field dynamic mapping algorithm, combined with the running trajectory and timestamp of the hanging plating line, and performs smoothing processing on the time-series data using Kalman filtering to obtain the temperature distribution data of the temperature field at different times and different positions, forming temperature field mapping data. To monitor the mechanical operating state of the hanging plating line in real time, multi-channel vibration sensors are arranged. These sensors are installed on key moving parts of the hanging plating line (such as drive motors, chains, rollers, etc.). The vibration sensors adopt MEMS accelerometers or piezoelectric sensors, with a sampling frequency of above 10kHz, and capture the amplitude, frequency, and harmonic characteristics of the mechanical vibration signals during the operation of the hanging plating line. The vibration signals are analyzed in the frequency domain through fast Fourier transform, and combined with time-frequency joint analysis methods (such as wavelet transform or Hilbert-Huang transform), the characteristic parameters of the vibration signals, such as vibration amplitude, harmonic energy, and vibration frequency change, are extracted to form vibration characteristic data. After the acquisition of workpiece surface image data, current density distribution data, temperature field mapping data, and vibration characteristic data is completed, the multi-modal data is fused through time synchronization and spatial registration algorithms.Time synchronization adopts high-precision clock synchronization technology to ensure that the acquisition timestamps of each data source are accurate to the microsecond level. Spatial registration unifies and transforms the spatial coordinate systems of different data sources through feature point matching and spatial mapping transformation, and uses the iterative closest point algorithm to accurately align the data, generating the state data of the rack plating line body under a unified spatio-temporal reference. At the same time, multi-band spectral acquisition of the electroplating solution is carried out through ultraviolet-visible spectral sensors, near-infrared spectral sensors, and Raman spectral sensors. The ultraviolet-visible spectral sensor covers the 200-800nm band and can analyze the change in the concentration of metal ions in the electroplating solution. The near-infrared spectral sensor covers the 800-2500nm band and detects the change in the concentration of organic additives and complexing agents in the electroplating solution. The Raman spectral sensor, through the laser scattering mechanism, identifies the vibration modes of different molecular bonds in the electroplating solution, thereby accurately detecting the chemical structure changes of the electroplating solution components. The multi-channel spectral acquisition system uses fiber optic coupling and signal beam splitting technology to ensure that spectral data in different bands can be acquired synchronously, and performs data preprocessing through spectral normalization and baseline correction algorithms to obtain the multi-spectral data of the electroplating solution.

[0024] In a specific embodiment, the process of executing step 102 may specifically include the following steps: Identify electroplating defects and extract defect feature parameters from the workpiece surface image data in the state data of the rack plating line body to obtain an electroplating quality feature set; Calculate the electric field uniformity for the current density distribution data in the state data of the rack plating line body to obtain an electroplating uniformity feature set; Perform spectral feature extraction on the multi-spectral data of the electroplating solution to obtain an electroplating solution component feature set; Analyze the temporal correlation relationship between the electroplating quality feature set and the electroplating solution component feature set to obtain a quality-component correlation feature; Perform spatial correlation analysis on the electroplating uniformity feature set and the electroplating solution component feature set, and identify key influencing regions through a hotspot mapping algorithm to obtain a uniformity-component correlation feature; Fuse the quality-component correlation feature and the uniformity-component correlation feature to form a feature vector representing the relationship between the rack plating process and the electroplating solution components.

[0025] Specifically, for the workpiece surface image data in the barrel plating line state data, electroplating defect recognition and defect feature parameter extraction are carried out. The surface image data collected by a high-resolution vision sensor is used, and feature extraction is combined with a deep convolutional neural network. The deep convolutional neural network uses ResNet50 or VGG16 as the backbone network, and extracts multi-dimensional information such as texture features, color distribution, and morphological structure of the plating surface through multiple convolutional kernels. At the same time, the attention mechanism is combined to strengthen the focusing ability on the defect area, and different defect types are classified and recognized, including defects such as pinholes, pockmarks, blisters, burning, peeling, and uneven plating thickness. The boundaries and feature parameters of the defect area are extracted through morphological analysis and image segmentation algorithms (such as U-Net), including defect area, perimeter, shape factor, density distribution, maximum / minimum size, depth information, etc., thus forming an electroplating quality feature set. For the current density distribution data in the barrel plating line state data, the electric field uniformity is calculated. A three-dimensional electric field simulation model is constructed using the finite element method. The model is boundary-constrained based on key parameters such as the geometric structure of the electroplating tank, the distance between the anode and cathode, and the spatial distribution of current density measurement points, and the simulation model is dynamically calibrated by combining the multi-point current data collected by the current density sensor. The electric field distribution is calculated by solving the Poisson equation, and the uniformity of the electric field distribution is quantitatively analyzed by combining the mean square error method, the uniformity coefficient, and the standard deviation index. Key features such as the maximum value, minimum value, mean value, uniformity index, and abnormal current interval of the current density are extracted to form an electroplating uniformity feature set, which reflects the degree of uniformity of the electric field distribution and the distribution of abnormal areas during the electroplating process. While extracting electroplating quality and uniformity features, spectral feature extraction is carried out on the multi-spectral data of the electroplating solution. The electroplating solution composition data collected by ultraviolet-visible spectroscopy, near-infrared spectroscopy, and Raman spectroscopy is used, and deep feature extraction is carried out through a spectral feature extraction framework that combines long short-term memory networks and convolutional neural networks. Preprocessing operations such as baseline correction, denoising, and dimensional compression are performed on the original spectral data, and then local spectral features are extracted through a convolutional neural network, and temporal features are extracted in combination with a long short-term memory network to generate an electroplating solution composition feature set containing multi-dimensional information such as metal ion concentration, organic additive content, impurity level, and complexing agent distribution, reflecting the change trend of the electroplating solution composition. Analyze the temporal correlation relationship between the electroplating quality feature set and the electroplating solution composition feature set. Through the dynamic time warping algorithm, the changes in the electroplating solution composition and the workpiece surface quality features in different time periods are temporally matched. The time-delay effect of the electroplating solution composition change on the coating quality is quantified using the correlation matrix. At the same time, Granger causality analysis is used to evaluate the direct impact of the electroplating solution composition change on specific defect types, and quality-composition correlation features are obtained to reveal the dynamic impact mechanism of the electroplating solution composition fluctuation on the coating quality change. At the same time, spatial correlation analysis is carried out on the electroplating uniformity feature set and the electroplating solution composition feature set, and key influence areas in the electroplating tank are identified through the hot spot mapping algorithm.This algorithm performs spatial interpolation on the electric field uniformity and the concentration distribution of the electroplating solution components based on the Kriging interpolation method, generates a three-dimensional spatial hot spot distribution map, and combines spatial domain weighted clustering to conduct a hierarchical evaluation of the hot spot areas, thereby identifying the key impact areas on the coating uniformity caused by uneven current density and abnormal electroplating solution concentration, and extracting the key characteristic parameters of the hot spot areas, such as current offset, area of the local concentration abnormal area, center coordinates of the hot spot area, etc., to form uniformity-component correlation characteristics. These characteristics help to accurately locate the high-risk areas in the electroplating tank that cause uneven coating or defects. By fusing the quality-component correlation characteristics and the uniformity-component correlation characteristics, using a multi-modal feature fusion algorithm (such as the self-attention mechanism) to perform feature weighting on data of different modalities, and combining a feature selection algorithm (such as principal component analysis) to extract the key feature subset, a feature vector representing the relationship between the rack plating process and the electroplating solution components is formed. The length of this feature vector is 128 dimensions, covering multi-dimensional information such as the surface quality of the workpiece, current uniformity, changes in electroplating solution components, and distribution of key impact areas.

[0026] In a specific embodiment, the process of executing step 103 may specifically include the following steps: Perform non-linear dimensionality reduction on the feature vector to obtain the rack plating-recovery feature dimensionality reduction data; Use the rack plating-recovery feature dimensionality reduction data to construct a multi-input multi-output relationship network, and establish a mapping relationship between the feature vector and the recovery efficiency through Bayesian sparse parameter polynomial regression to obtain a preliminary correlation function; Introduce a rack plating line operation condition classification mechanism for the preliminary correlation function, identify typical operating conditions through a clustering algorithm and train target sub-models for each type of operating condition to obtain an operating condition adaptive correlation function; Based on the operating condition adaptive correlation function, construct a two-way mapping between electroplating quality and recovery parameters, and derive the optimal recovery parameters from the target quality through a reverse inference algorithm to obtain a recovery parameter prediction model; Combine the recovery parameter prediction model with the real-time rack plating line speed to establish a speed collaborative response model between the line speed and the recovery rate; Impose a liquid level balance constraint on the speed collaborative response model and the electroplating tank liquid level control strategy to obtain a mapping model of rack plating production quality and recovery parameters.

[0027] Specifically, nonlinear dimensionality reduction is performed on the feature vectors formed by the data of the rack plating line body state, the characteristics of the electroplating solution composition, and the electroplating uniformity characteristics. Since the dimension of the feature vectors is relatively high (128 dimensions or more), direct mapping will lead to an increase in computational complexity and a slowdown in the model convergence speed. The t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm or Kernel Principal Component Analysis (KPCA) is used for dimensionality reduction. Both of these dimensionality reduction methods can effectively retain the non-linear structure information of the high-dimensional data. t-SNE maps the feature vectors to a 20-dimensional embedding space by minimizing the Kullback-Leibler (KL) divergence between the original data space and the low-dimensional space, while KPCA maps the high-dimensional features to a low-dimensional feature space through a kernel function, while maintaining the non-linear relationship between the features. The data after dimensionality reduction retains the core information of the operation state of the rack plating line body, the change of the electroplating solution composition, and the electroplating uniformity characteristics, and generates the dimensionality-reduced data of the rack plating-recovery features. A multi-input multi-output relationship network is constructed using the dimensionality-reduced data of the rack plating-recovery features to establish the mapping relationship between the operation state of the rack plating line body, the coating quality, and the recovery efficiency. The multi-input multi-output relationship network adopts a multi-layer perceptron structure. The input layer receives the dimensionality-reduced feature data, and the output layer simultaneously generates multi-dimensional results such as recovery efficiency, coating uniformity, and target concentration change. On this basis, Bayesian sparse parameter polynomial regression is combined to model the output of the multi-input multi-output relationship network. Bayesian sparse parameter regression realizes the sparsity constraint of the polynomial coefficients by introducing a Gaussian scale mixture prior, assigns higher weights to the key variables in the regression model, and reduces the influence of irrelevant variables at the same time, obtaining a preliminary correlation function between the feature vectors and the recovery efficiency. The Bayesian sparse parameter polynomial regression model optimizes the parameters by maximizing the evidence lower bound, and iteratively updates the regression coefficients through variational inference to form a preliminary multi-dimensional correlation function. A rack plating line body operation condition classification mechanism is introduced for the preliminary correlation function. Different typical working conditions are identified through the K-means clustering algorithm, and the feature data is classified according to the working condition type. The K-means algorithm clusters the dimensionality-reduced feature data, divides the data into different categories such as low current density operation, high current density operation, stable rack plating speed, and high temperature working conditions, and trains a target sub-model for each working condition category. Transfer learning is used to fine-tune the parameters of the preliminary correlation function in different working condition categories to generate a working condition adaptive correlation function. These sub-models are adaptively optimized according to different operation states, thereby significantly improving the generalization ability and accuracy of the model. Based on the working condition adaptive correlation function, a bidirectional mapping model of electroplating quality and recovery parameters is constructed. This mapping model uses a bidirectional long short-term memory network to perform time series correlation modeling on the electroplating solution composition, rack plating speed, and coating quality, and through a reverse inference algorithm, derives the optimal recovery parameters from the target quality.The reverse inference algorithm uses the gradient backpropagation mechanism to reverse-derive quality indicators such as the target coating thickness and uniformity. By minimizing the error between the target quality and the model-predicted quality, the recycling parameters (such as recycling flow rate, centrifuge speed, heating coil power, etc.) are iteratively adjusted until the optimal matching between the recycling liquid concentration and the coating quality is achieved, forming a recycling parameter prediction model. Combining the recycling parameter prediction model with the real-time hanging plating line speed, a speed collaborative response model between the line speed and the recycling rate is established. This model models the dynamic relationship between the changes in the hanging plating line speed and the recycling rate based on a non-linear autoregressive model and dynamic time warping. The non-linear autoregressive model captures the lag response behavior of the recycling rate to changes in the hanging plating speed, and combines dynamic time warping to match the changing trends of the recycling rate under different speed change patterns, forming a speed collaborative response model that can adaptively adjust. This model automatically adjusts the control parameters of the recycling equipment according to the fluctuations in the hanging plating speed to ensure that the coating quality and the recycling efficiency always maintain the best matching state. To improve the stability of the hanging plating process and the electroplating solution recycling process, the speed collaborative response model is integrated with the electroplating bath liquid level control strategy, and a liquid level balance constraint mechanism is introduced to maintain the dynamic balance of the electroplating bath liquid level. The liquid level balance control strategy uses an adaptive PID controller to automatically adjust the replenishment volume and the recycling rate according to the dynamic balance relationship among the changes in the recycling rate, the changes in the hanging plating speed, and the electroplating solution replenishment rate, and predicts the liquid level change through Kalman filtering when there are liquid level fluctuations, so as to ensure that the electroplating bath liquid level is always at the optimal level. By introducing the liquid level balance constraint, the abnormal liquid level situation caused by the imbalance between the recycling rate and the replenishment rate is effectively avoided, realizing the multi-objective collaborative optimization of the hanging plating speed, the recycling rate, and the liquid level control. By integrating the speed collaborative response model and the liquid level balance constraint mechanism, a mapping model of the hanging plating production quality and the recycling parameters is constructed.

[0028] In a specific embodiment, the process of executing step 104 may specifically include the following steps: Convert the mapping model into a multi-objective optimization problem, and set the target weight configuration of the multi-objective optimization problem based on a multi-objective optimization algorithm with variable genetic factors; Construct a hanging plating line body control layer based on the target weight configuration, and generate hanging plating production control instructions according to the hanging plating line body control layer; Construct an electroplating solution recycling equipment control layer according to the mapping model, and calculate the recycling equipment control instructions through the electroplating solution recycling equipment control layer; Design a collaborative execution mechanism for the hanging plating production control instructions and the recycling equipment control instructions, and establish a parameter change transfer function and an interlock protection logic according to the collaborative execution mechanism to obtain a hierarchical collaborative control strategy; Construct a global resource scheduling layer for the hanging plating line body and the recycling equipment, and solve the overall optimization problem under resource constraints according to the global resource scheduling layer to obtain an optimal allocation plan; Integrate the hierarchical collaborative control strategy and the optimal allocation scheme, and manage the control conversion logic at different production stages through a state machine to obtain the linkage control parameters of the production parameters of the rack plating line body and the electroplating solution recovery equipment.

[0029] Specifically, for the core indicators such as rack plating production quality, recovery efficiency, and energy consumption, the mapping model between rack plating production quality and recovery parameters is transformed into a multi-objective optimization problem. In the mapping model, different objectives have competing characteristics. A multi-objective optimization model is used to mathematically model different objective functions, and a variable genetic factor mechanism is introduced to optimize the objective weight configuration. The variable genetic factor mechanism adaptively adjusts the crossover rate, mutation rate, and population size, and dynamically adjusts the genetic algorithm parameters according to the changes in different objective weights, improving the global search ability of the optimization algorithm under different objective weights. The objective weight configuration is optimized based on Pareto optimal front analysis. By weighing the mutual influences among rack plating production quality, electroplating solution recovery efficiency, and energy consumption, a set of candidate objective weight configuration sets are generated, and the candidate solutions are screened by combining with the decision preference function to determine the optimal objective weight configuration. Based on the objective weight configuration, a control layer for the rack plating line is constructed. This control layer is designed based on model predictive control, with the objective weight configuration as the input, and key control parameters such as rack plating speed, current density, immersion time, and hanging angle as control variables. The dynamic state transition equation is used to predict and optimize objective variables such as coating thickness and uniformity. The model predictive controller updates the objective function periodically through rolling horizon optimization, and adjusts the control instructions according to real-time monitoring data to generate rack plating production control instructions. These control instructions dynamically adapt to the changes in the operating state of the rack plating line, achieving the optimal control of coating quality and energy consumption. At the same time, according to the mapping model, a control layer for the electroplating solution recovery equipment is constructed. The recovery equipment control layer uses nonlinear model predictive control for control modeling. This model takes key control parameters of the recovery equipment such as the flow rate of the self-priming pump, the rotation speed of the centrifuge, the power of the heating coil, and the position of the electric push rod as input variables, and combines the Bayesian sparse parameter polynomial regression model to calculate the nonlinear mapping relationship between different recovery rates and changes in electroplating solution composition. The recovery parameters are iteratively updated through Bayesian optimization to obtain the recovery equipment control instructions. The nonlinear model predictive controller optimizes the control variables by predicting the system state at multiple future moments, keeping the recovery equipment always in an efficient operating state, ensuring the best match between electroplating solution recovery efficiency and coating quality. To achieve the coordinated operation of rack plating production and recovery equipment control, a cooperative execution mechanism for rack plating production control instructions and recovery equipment control instructions is designed. The cooperative mechanism transmits the influence of changes in variables such as rack plating speed and current density to the recovery equipment by constructing a parameter change transfer function, and introduces an interlock protection logic to prevent the system from becoming unstable due to sudden changes in key control parameters. The parameter change transfer function uses multi-input multi-output dynamic modeling to construct a linkage equation between the rack plating line and the recovery equipment, dynamically matching and adjusting control instructions at different stages. The interlock protection logic manages the state transition of different control stages through a finite state machine, sets up an anomaly detection mechanism, and immediately triggers the protection logic once the system is detected to deviate from the safety threshold, achieving safe cooperative control of the rack plating and recovery processes and forming a hierarchical cooperative control strategy.To improve the utilization efficiency of system resources, a global resource scheduling layer for the rack plating line and recycling equipment is constructed. The global resource scheduling layer dynamically allocates resources for rack plating production and recycling equipment through a combination of integer linear programming and reinforcement learning, and adjusts according to real-time production data. The integer linear programming model takes minimizing resource consumption and maximizing production capacity as the objective function, and the constraint conditions include equipment capacity limits, rack plating speed limits, and recycling liquid level thresholds, etc. Reinforcement learning adaptively learns among different resource allocation schemes through the Q-learning algorithm to continuously optimize the scheduling strategy. Combining the resource scheduling results and the working condition adaptive strategy to solve the overall optimization problem under resource constraints, and obtaining the optimal resource allocation scheme. After completing the construction of the hierarchical collaborative control strategy and the optimal allocation scheme, integrate the hierarchical collaborative control strategy and the optimal allocation scheme, and realize the parameter switching and control mode conversion in different operation stages through the state machine to manage the control conversion logic in different production stages. The state machine automatically switches different control states such as the acceleration stage, stable operation stage, recycling stage, and deceleration stage according to key variables such as the operation stage of the rack plating line, changes in the composition of the electroplating solution, and target quality deviation, and loads the corresponding control strategies in different states to realize the linkage adjustment of rack plating production parameters and recycling equipment control parameters. Through the dynamic switching logic of the state machine, ensure that the rack plating line and recycling equipment operate optimally in different stages, and avoid system instability problems caused by parameter mutations. Form a linkage control parameter system for rack plating line production parameters and electroplating solution recycling equipment. This system has core functions such as multi-objective optimization, adaptive control, resource scheduling, and state management, and can achieve efficient coordination between the rack plating production line and the recycling equipment.

[0030] In a specific embodiment, the process of executing the step of transforming the mapping model into a multi-objective optimization problem and setting the objective weight configuration of the multi-objective optimization problem based on the multi-objective optimization algorithm with variable genetic factors may specifically include the following steps: According to the mapping model, transform the electroplating quality index into an absolute error function, transform the recycling efficiency index into a relative efficiency function, and transform the energy consumption index into a unit cost function to obtain a set of multi-objective functions; According to the mapping model, uniformly encode the rack plating line control parameters and electroplating solution recycling equipment control parameters into multi-dimensional vectors, and at the same time transform the physical constraints of each parameter into variable boundary conditions to obtain the decision space; Apply process constraint conditions to the decision space, and establish a coupling constraint equation between electroplating quality and recycling efficiency and a balance constraint equation between each control parameter to obtain a multi-objective optimization problem; Based on the multi-objective optimization problem, map the decision variables to binary or real chromosomes, and at the same time define a fitness function to reflect the quality of the chromosomes; Introduce a genetic factor adjustment mechanism for the multi-objective optimization algorithm based on the multi-objective optimization problem and the fitness function, and dynamically calculate the crossover probability and mutation probability based on the genetic factor adjustment mechanism to obtain adaptive genetic parameters; Perform multi-objective evolutionary computation using the adaptive genetic parameters to obtain a set of candidate weight configurations, and apply a decision preference function based on the set of candidate weight configurations to select the optimal solution to obtain the objective weight configuration of the multi-objective optimization problem.

[0031] Specifically, different targets are mathematically modeled according to the mapping model between the quality of rack plating production and the parameters of plating solution recovery. For the plating quality index, the absolute error function is used for quantification, and the quality deviation of the plating process is measured by comparing the gap between the target coating thickness, uniformity or adhesion rate and the actual measured value. The recovery efficiency index is modeled by the relative efficiency function, and the relative performance of the recovery equipment under different working conditions is measured by calculating the ratio between the actual recovery efficiency and the theoretical maximum recovery efficiency. At the same time, the energy consumption index is converted into a unit cost function, and the total energy consumption during the system operation is compared with the rack plating production volume. Through this step, a multi-objective function set is formed. The control parameters of the rack plating line and the control parameters of the plating solution recovery equipment are encoded into a multidimensional vector. The continuous control variables (such as rack plating speed, current density, recovery flow, immersion time, etc.) are encoded in real numbers, while the discrete control variables (such as equipment start and stop status, recovery mode, etc.) are encoded in binary to form a high-dimensional control vector. At the same time, in order to ensure the feasibility of the optimization solution in actual production, the physical constraints of each control parameter are converted into variable boundary conditions, such as the current density range of the plating tank, the flow limit of the recycling equipment, the upper limit of the heating coil power, etc. These boundary conditions constrain the optimization solution, thereby defining a multidimensional decision space. Process constraints are imposed on the decision space, and the coupling constraint equation between the plating quality and the recycling efficiency and the balance constraint equation between the control parameters are established. The coupling constraint equation is used to capture the nonlinear effect of the change in the composition of the plating solution on the quality and recycling efficiency of the rack plating, so as to ensure that different control parameters can be coordinated with each other during the optimization solution; while the balance constraint equation achieves a dynamic balance between the plating process and the recycling process by modeling the multivariate association of the control parameters, thereby avoiding the situation where the system is unstable due to excessive changes in the control parameters. By imposing these constraints, the multi-objective optimization problem is converted into a multi-objective optimization problem with complex physical constraints and process constraints. Based on the multi-objective optimization problem, the decision variables are mapped into binary or real chromosomes, each chromosome represents a possible solution, and the fitness function reflects the quality of the chromosome. The fitness function combines different target weights, and performs weighted summation on the optimization targets of the quality deviation of the plating, recycling efficiency and unit cost to generate a comprehensive fitness value, which provides a target orientation for the optimization process of the genetic algorithm. At the same time, in order to prevent the genetic algorithm from falling into the local optimal solution or the loss of population diversity, the genetic factor adjustment mechanism of the multi-objective optimization algorithm is introduced. This mechanism monitors the evolutionary state of the genetic algorithm in real time, and dynamically adjusts the crossover probability and mutation probability according to the population convergence, the distribution density of the solution and the gradient change of the objective function to generate adaptive genetic parameters. The crossover probability controls the global search ability of the solution, and the mutation probability determines the exploration ability of the solution in the local area. The two are linked and optimized through the adaptive adjustment mechanism, so that the genetic algorithm can automatically adjust the strategy at different stages to improve the solution accuracy and global convergence speed.Under the guidance of adaptive genetic parameters, the system performs multi-objective evolutionary computation, and uses the fast non-dominated sorting genetic algorithm for multi-objective optimization of the population. The fast non-dominated sorting genetic algorithm divides the population solutions into different levels of Pareto fronts through the non-dominated sorting mechanism, and combines the crowding distance sorting and elitist retention strategies to screen out the optimal solution set, forming a set of candidate weight configuration sets. The candidate solution set is screened through Pareto front analysis, and the priority of the solutions is sorted by combining the decision preference function. The optimal weight configuration is selected according to the change trend of the objective function and the priority of the production process, and finally the objective weight configuration of the multi-objective optimization problem is obtained.

[0032] Introduce a variable genetic factor mechanism into the basic structure of the genetic algorithm. Construct a genetic factor adjustment function by analyzing the population diversity index and the degree of evolutionary stagnation, including: calculating the Hamming distance or Euclidean distance for each chromosome in the population, and obtaining the average distance between individuals in the population through normalization processing. Determine the population diversity index by comparing the relationship between the average distance and the preset threshold; construct a time series for the optimal fitness values of consecutive generations, and evaluate the degree of evolutionary stagnation by calculating the mean and standard deviation of the fitness improvement rate between adjacent generations; based on the population diversity index and the degree of evolutionary stagnation, construct a binary variable genetic factor adjustment function, which includes a regulation coefficient determined according to the characteristics of the electroplating line body; set boundary constraint conditions for the binary variable genetic factor adjustment function to prevent the genetic algorithm from falling into extreme parameters, and determine the value of the boundary value according to the special requirements of electroplating line body control; use the constrained variable genetic factor adjustment function to construct a piecewise adaptive crossover probability function and a mutation probability function, and differentially control the crossover and mutation operations according to the different characteristics of the population evolution stage; apply the piecewise adaptive crossover probability function and the mutation probability function to the evolutionary operations of the genetic algorithm, and recalculate the genetic factor value according to the characteristics of the new population after each generation of evolution, realizing the dynamic adaptive adjustment of the genetic operations.

[0033] Perform multi-objective evolutionary computation using adaptive genetic parameters, and select elite individuals through Pareto non-dominated sorting and crowding distance calculation, including: calculating the multi-objective function values for several chromosomes in the initial population respectively, and dividing the population into different non-dominated ranks based on the Pareto dominance relationship; calculating the crowding distance for the chromosomes in each non-dominated rank, and obtaining the sparsity degree of the individual distribution in the solution space by summing the normalized distances of adjacent solutions on each objective function dimension; designing a selection operator by combining the non-dominated rank and the crowding distance, and selecting the parent individuals through a binary tournament selection strategy with the non-dominated rank being prioritized and the crowding distance being secondary; applying a crossover operation controlled by adaptive genetic parameters to the selected parent individuals, generating offspring chromosomes through simulated binary crossover or uniform crossover, and the crossover probability is dynamically adjusted by a variable genetic factor; performing a mutation operation on the offspring chromosomes after crossover, introducing random perturbations through polynomial mutation or Gaussian mutation, and the mutation probability is inversely adjusted by the variable genetic factor to maintain the population diversity; merging the parent population and the offspring population generated through crossover and mutation to form an intermediate population with double the size, and performing non-dominated sorting and crowding calculation again, selecting the optimal individuals to form a new generation population; repeating the above evolutionary process until the termination condition is reached, and saving the individuals with the highest non-dominated rank in each generation of evolution to the external archive set as an approximation of the Pareto optimal solution set.

[0034] In a specific embodiment, the process of executing step 105 may specifically include the following steps: Perform an analysis of the proportional relationship between the speed of the rack plating line and the flow rate of the electroplating solution according to the linkage control parameters to obtain the line speed-flow rate matching data; Utilize the line speed-flow rate matching data to achieve a fast response to the change in the speed of the rack plating line, obtain a dynamic flow rate adjustment mechanism, and at the same time perform transitional control for the workpiece switching process of the rack plating line body to obtain a smooth switching transition plan; Establish an adaptive mapping relationship between the component concentration and the treatment speed by combining the real-time monitoring results of the electroplating solution components to obtain a concentration adaptive treatment plan; Perform a response analysis of the recovery equipment for the planned and unplanned shutdowns of the rack plating line body to obtain a treatment plan for the shutdown process; Integrate the dynamic flow rate adjustment mechanism, the smooth switching transition plan, the concentration adaptive treatment plan, and the treatment plan for the shutdown process to obtain a synchronization strategy for the operation of the line body and the recovery treatment.

[0035] Specifically, according to the linkage control parameters, the proportional relationship between the speed of the rack plating line and the flow rate of the electroplating solution is analyzed to construct a line speed-flow rate matching model. This model establishes a matching relationship by analyzing the non-linear relationship between the speed of the rack plating line, current density, immersion time, change in coating thickness, and the treatment speed of the electroplating solution. The matching model is built using multivariate regression analysis or support vector regression, trained with historical data, and combined with the dynamic time warping algorithm for temporal matching of the electroplating solution flow rate adjustment under different speed changes to generate line speed-flow rate matching data. The matching data covers the optimal adjustment range of the electroplating solution flow rate at different rack plating speeds and can automatically adjust the matching parameters according to the coating thickness targets of different batches of workpieces to ensure that the ratio between the rack plating speed and the electroplating solution treatment speed always remains optimal. Based on the line speed-flow rate matching data, a dynamic flow rate adjustment mechanism is constructed. This mechanism uses model predictive control and adaptive proportional-integral-derivative control to quickly respond to changes in the rack plating line speed. When the rack plating line speed changes, the model predictive controller calculates the optimal flow rate adjustment command within 50 ms to dynamically adjust the flow rate of the self-priming pump, the rotational speed of the centrifuge, and the power of the heating coil, thereby maintaining the matching relationship between the electroplating solution flow rate and the rack plating line speed. At the same time, to address the transitional control during workpiece switching on the rack plating line body, a smooth switching transition scheme is designed. This scheme achieves smooth switching of the acceleration, constant speed, and deceleration processes through an S-shaped speed curve, dynamically smooths the rack plating line speed through multi-order Bezier curve interpolation, and dynamically corrects abnormal speed changes through Kalman filtering, thereby achieving stable transitions of the coating quality and electroplating solution flow rate during workpiece switching. The smooth switching transition scheme can effectively avoid problems such as uneven coating thickness or fluctuations in recovery efficiency caused by sudden speed changes, thus maintaining the stability of the rack plating process. At the same time, an adaptive mapping relationship between the composition concentration and the treatment speed is constructed in combination with the real-time monitoring results of the electroplating solution composition. The system uses ultraviolet-visible spectroscopy, near-infrared spectroscopy, and Raman spectroscopy sensors to perform multi-band spectral analysis on the electroplating solution, extracts spectral features using long short-term memory networks and convolutional neural networks, and performs feature enhancement and concentration change prediction through a self-supervised learning mechanism to establish a concentration adaptive treatment scheme. This scheme dynamically adjusts the operating parameters of the recovery equipment by analyzing the relationship between the optimal treatment speed and the coating quality at different electroplating solution concentrations. When significant changes in the metal ion concentration, organic additive content, or impurity level in the electroplating solution are detected, the system updates the recovery flow rate, centrifuge rotational speed, and replenishment speed within 100 ms to ensure that the electroplating solution composition always remains within the optimal concentration range and prevent adverse effects on the rack plating quality caused by composition imbalance. A response analysis of the recovery equipment is carried out for planned and unplanned shutdowns of the rack plating line body, and a shutdown process treatment plan is constructed. The different stages of the shutdown process are managed through a finite state machine, including key states such as shutdown preparation, deceleration, stop, recovery treatment, and restart.During planned shutdowns, the system executes a linear annealing algorithm to gradually reduce the rack plating speed, and simultaneously adjusts the electroplating solution recovery speed and replenishment speed to ensure that the coating thickness and composition concentration remain stable during the shutdown process. In the case of unplanned shutdowns, the system triggers an emergency response mechanism, identifies the cause of the shutdown through a rapid fault detection and diagnosis model, and performs backtracking adjustment of key control parameters through an adaptive parameter recovery algorithm to ensure that the recovery equipment can resume its optimal operating state in the shortest possible time. At the same time, a concentration balance strategy is combined to rebalance the composition concentration after shutdown. When the system restarts, by adjusting the heating coil power, recovery flow rate, and replenishment rate, the composition of the electroplating solution is quickly restored to a stable state, thereby ensuring the coating quality and recovery efficiency after the rack plating line restarts. By integrating a dynamic flow regulation mechanism, a smooth transition scheme for switching, a concentration adaptive processing scheme, and a shutdown process processing scheme, a synchronous strategy for line operation and recovery processing is formed.

[0036] The above describes the full-automatic intelligent continuous rack plating line body detection method in the embodiments of the present invention. Next, the full-automatic intelligent continuous rack plating line body detection device in the embodiments of the present invention will be described. Please refer to Figure 2 One embodiment of the full-automatic intelligent continuous rack plating line body detection device in the embodiments of the present invention includes: A data acquisition module 201 for performing real-time multimodal data acquisition on the operation process of the rack plating line body to obtain rack plating line body state data and electroplating solution multispectral data; A feature extraction module 202 for jointly extracting features from the rack plating line body state data and electroplating solution multispectral data to obtain a feature vector representing the relationship between the plating process and the electroplating solution composition; A construction module 203 for constructing an association function between the operation state of the rack plating line body and the electroplating solution recovery efficiency based on the feature vector to obtain a mapping model of the rack plating production quality and recovery parameters; A multi-objective optimization module 204 for executing a multi-objective optimization algorithm based on variable genetic factors according to the mapping model and creating a hierarchical collaborative control strategy to generate linkage control parameters for the rack plating line body production parameters and the electroplating solution recovery equipment; A dynamic coordination module 205 for performing dynamic coordination of the rack plating speed and the electroplating solution treatment speed based on the linkage control parameters to obtain a synchronous strategy for line operation and recovery processing.

[0037] Through the collaborative cooperation of the above-mentioned various components, through the collaborative work of a variety of sensing devices such as high-resolution visual sensors, current density sensors, infrared thermal imagers, and vibration sensors, the all-round monitoring of the operation status of the hanging plating line body is realized. At the same time, the precise detection of the composition of the electroplating solution is achieved by combining ultraviolet-visible spectroscopy, near-infrared spectroscopy, and Raman spectroscopy. Through the joint feature extraction of the status data of the hanging plating line body and the multi-spectral data of the electroplating solution, a feature vector of the relationship between the hanging plating process and the composition of the electroplating solution is established, realizing a deep understanding of the complex relationship among the electroplating quality characteristics, uniformity characteristics, and the composition of the electroplating solution, breaking through the limitation of the traditional method that can only analyze singlely. Based on the feature vector, an association function between the operation status of the hanging plating line body and the electroplating solution recovery efficiency is constructed. Through Bayesian sparse parameter polynomial regression and working condition adaptive association function, the accurate prediction of the optimal recovery parameters under different working conditions is realized, solving the problem of insufficient prediction ability of the traditional fixed parameter control in the face of complex changing working conditions. By introducing a variable genetic factor multi-objective optimization algorithm, dynamically adjusting the crossover probability and mutation probability of the genetic algorithm, the balance optimization among electroplating quality, recovery efficiency, and energy consumption is realized, avoiding the defect that the traditional optimization method is prone to falling into local optimum, and improving the global optimization ability of the system. By constructing a three-layer control architecture of the hanging plating line body control layer, the electroplating solution recovery equipment control layer, and the global resource scheduling layer, the collaborative control of production parameters and recovery parameters is realized, solving the problem that each subsystem operates independently and is disjointed in the traditional control method, and improving the collaborative efficiency of the overall system. Based on the line speed-flow matching data, the dynamic coordination of the hanging plating speed and the electroplating solution treatment speed is realized. By switching the smooth transition scheme and the concentration adaptive processing scheme, the system can flexibly respond to various working conditions such as workpiece switching, line speed change, and shutdown, enhancing the adaptability of the system to the changing environment and improving the overall stability of the electroplating process and the recovery process.

[0038] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0039] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0040] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A full-automatic intelligent continuous rack plating line body detection method, characterized in that, The method includes: Performing real-time multimodal data acquisition on the running process of the rack plating line body to obtain rack plating line body state data and electroplating solution multispectral data; Performing joint feature extraction on the rack plating line body state data and the electroplating solution multispectral data to obtain a feature vector characterizing the relationship between the electroplating process and the electroplating solution composition; Constructing a correlation function between the running state of the rack plating line body and the electroplating solution recovery efficiency based on the feature vector to obtain a mapping model of the rack plating production quality and the recovery parameters; Executing a multi-objective optimization algorithm based on variable genetic factors and creating a hierarchical collaborative control strategy according to the mapping model to generate linkage control parameters for the rack plating line body production parameters and the electroplating solution recovery equipment; Performing dynamic coordination of the rack plating speed and the electroplating solution treatment speed based on the linkage control parameters to obtain a synchronization strategy for the line body operation and the recovery treatment.

2. The full-automatic intelligent continuous barrel plating line body detection method according to claim 1, wherein, The performing real-time multimodal data acquisition on the running process of the rack plating line body to obtain rack plating line body state data and electroplating solution multispectral data includes: Using a high-resolution vision sensor to perform real-time imaging acquisition on the surface of the electroplated workpiece on the rack plating line body to obtain workpiece surface image data, and continuously monitoring the current distribution in the electroplating tank of the rack plating line body through a current density sensor to obtain current density distribution data; Using an infrared thermal imager to perform dynamic scanning on the temperature field of the rack plating line body to obtain temperature field mapping data, and continuously monitoring the mechanical running state of the rack plating line body using a multi-channel vibration sensor to obtain vibration characteristic data; Performing time synchronization and spatial registration on the workpiece surface image data, the current density distribution data, the temperature field mapping data, and the vibration characteristic data to obtain rack plating line body state data; Performing multi-band spectral acquisition on the electroplating solution through an ultraviolet-visible spectral sensor, a near-infrared spectral sensor, and a Raman spectral sensor to obtain electroplating solution multispectral data.

3. The full-automatic intelligent continuous barrel plating line body detection method according to claim 2, wherein The performing joint feature extraction on the rack plating line body state data and the electroplating solution multispectral data to obtain a feature vector characterizing the relationship between the electroplating process and the electroplating solution composition includes: Performing electroplating defect identification and defect feature parameter extraction on the workpiece surface image data in the rack plating line body state data to obtain an electroplating quality feature set; Calculating the electric field uniformity for the current density distribution data in the rack plating line body state data to obtain an electroplating uniformity feature set; Performing spectral feature extraction on the electroplating solution multispectral data to obtain an electroplating solution composition feature set; Analyzing the temporal correlation relationship between the electroplating quality feature set and the electroplating solution composition feature set to obtain a quality-composition correlation feature; Performing spatial correlation analysis on the electroplating uniformity feature set and the electroplating solution composition feature set, and identifying key influence regions through a hot spot mapping algorithm to obtain a uniformity-composition correlation feature; Fusing the quality-composition correlation feature and the uniformity-composition correlation feature to form a feature vector characterizing the relationship between the electroplating process and the electroplating solution composition.

4. The full-automatic intelligent continuous barrel plating line body detection method according to claim 1, wherein, The constructing a correlation function between the running state of the rack plating line body and the electroplating solution recovery efficiency based on the feature vector to obtain a mapping model of the rack plating production quality and the recovery parameters includes: Perform non - linear dimensionality reduction on the feature vector to obtain the dimensionality - reduced data of barrel plating - recycling features; Use the dimensionality - reduced data of barrel plating - recycling features to construct a multi - input multi - output relationship network, and establish a mapping relationship between the feature vector and the recycling efficiency through Bayesian sparse parameter polynomial regression to obtain a preliminary correlation function; Introduce a barrel plating line operating condition classification mechanism for the preliminary correlation function, identify typical operating conditions through a clustering algorithm, and train target sub - models for each type of operating condition to obtain an operating - condition adaptive correlation function; Based on the operating - condition adaptive correlation function, construct a two - way mapping between electroplating quality and recycling parameters, and derive the optimal recycling parameters from the target quality through a reverse inference algorithm to obtain a recycling parameter prediction model; Combine the recycling parameter prediction model with the real - time barrel plating line speed to establish a speed - collaborative response model between the line speed and the recycling rate; Perform liquid - level balance constraints on the speed - collaborative response model and the electroplating bath liquid - level control strategy to obtain a mapping model of barrel plating production quality and recycling parameters; 5. The full-automatic intelligent continuous barrel plating line body detection method according to claim 1, characterized in that, Execute a multi - objective optimization algorithm based on variable genetic factors according to the mapping model and create a hierarchical collaborative control strategy to generate linkage control parameters for the barrel plating line production parameters and the electroplating solution recycling equipment, including: Convert the mapping model into a multi - objective optimization problem, and set the target weight configuration of the multi - objective optimization problem based on the multi - objective optimization algorithm with variable genetic factors; Construct a barrel plating line control layer based on the target weight configuration, and generate barrel plating production control instructions according to the barrel plating line control layer; Construct an electroplating solution recycling equipment control layer according to the mapping model, and calculate the recycling equipment control instructions through the electroplating solution recycling equipment control layer; Design a collaborative execution mechanism for the barrel plating production control instructions and the recycling equipment control instructions, and establish a parameter change transfer function and an interlock protection logic according to the collaborative execution mechanism to obtain a hierarchical collaborative control strategy; Construct a global resource scheduling layer for the barrel plating line and the recycling equipment, and solve the overall optimization problem under resource constraints according to the global resource scheduling layer to obtain an optimal allocation plan; Integrate the hierarchical collaborative control strategy and the optimal allocation plan, and manage the control conversion logic of different production stages through a state machine to obtain the linkage control parameters of the barrel plating line production parameters and the electroplating solution recycling equipment; 6. The full-automatic intelligent continuous barrel plating line body detection method according to claim 5, characterized in that, The conversion of the mapping model into a multi - objective optimization problem and the setting of the target weight configuration of the multi - objective optimization problem based on the multi - objective optimization algorithm with variable genetic factors include: According to the mapping model, convert the electroplating quality index into an absolute error function, convert the recycling efficiency index into a relative efficiency function, and convert the energy consumption index into a unit cost function to obtain a multi - objective function set; According to the mapping model, uniformly encode the barrel plating line control parameters and the electroplating solution recycling equipment control parameters into a multi - dimensional vector, and at the same time convert the physical constraints of each parameter into variable boundary conditions to obtain a decision space; Apply process constraint conditions to the decision space, and establish a coupling constraint equation between electroplating quality and recycling efficiency and a balance constraint equation between each control parameter to obtain a multi - objective optimization problem; Map the decision variables into binary or real - valued chromosomes based on the multi - objective optimization problem, and define a fitness function to reflect the quality of the chromosomes. Introduce a genetic factor adjustment mechanism for the multi - objective optimization algorithm based on the multi - objective optimization problem and the fitness function, and dynamically calculate the crossover probability and mutation probability based on the genetic factor adjustment mechanism to obtain adaptive genetic parameters. Use the adaptive genetic parameters to perform multi - objective evolutionary computation to obtain a set of candidate weight configurations, and select the optimal solution based on the candidate weight configuration set by applying a decision preference function to obtain the target weight configuration of the multi - objective optimization problem.

7. The fully automatic intelligent continuous barrel plating line body detection method according to claim 1, wherein The dynamic coordination of the rack plating speed and the electroplating solution treatment speed based on the linkage control parameters to obtain a synchronization strategy for the line body operation and the recycling treatment, including: Perform an analysis of the proportional relationship between the rack plating line speed and the electroplating solution flow rate according to the linkage control parameters to obtain line speed - flow rate matching data. Utilize the line speed - flow rate matching data for a fast response to changes in the rack plating line speed to obtain a dynamic flow rate adjustment mechanism, and at the same time perform transitional control for the workpiece switching process of the rack plating line body to obtain a smooth switching transition plan. Establish an adaptive mapping relationship between the component concentration and the treatment speed by combining the real - time monitoring results of the electroplating solution components to obtain a concentration adaptive treatment plan. Conduct a response analysis of the recycling equipment for the planned and unplanned shutdowns of the rack plating line body to obtain a treatment plan for the shutdown process. Integrate the dynamic flow rate adjustment mechanism, the smooth switching transition plan, the concentration adaptive treatment plan, and the treatment plan for the shutdown process to obtain a synchronization strategy for the line body operation and the recycling treatment.

8. An automatic intelligent continuous barrel plating line body detection device, characterized in that, For executing the full - automatic intelligent continuous rack plating line body detection method according to any one of claims 1 - 7, the full - automatic intelligent continuous rack plating line body detection device includes: A data acquisition module for performing real - time multi - modal data acquisition on the operation process of the rack plating line body to obtain rack plating line body state data and electroplating solution multi - spectral data. A feature extraction module for jointly extracting features from the rack plating line body state data and the electroplating solution multi - spectral data to obtain a feature vector characterizing the relationship between the electroplating process and the electroplating solution components. A construction module for constructing an association function between the operation state of the rack plating line body and the electroplating solution recycling efficiency based on the feature vector to obtain a mapping model of the electroplating production quality and the recycling parameters. A multi - objective optimization module for performing a multi - objective optimization algorithm based on variable genetic factors according to the mapping model and creating a hierarchical collaborative control strategy to generate linkage control parameters for the rack plating line body production parameters and the electroplating solution recycling equipment. A dynamic coordination module for performing dynamic coordination of the rack plating speed and the electroplating solution treatment speed based on the linkage control parameters to obtain a synchronization strategy for the line body operation and the recycling treatment.

Images