A low-energy consumption electroplating method, device and equipment based on recycled plastic

Abstract

The application relates to the technical field of image processing, and discloses a low-energy-consumption electroplating method, device and equipment based on recycled plastic, the method comprising the following steps: collecting surface characteristic parameters of the recycled plastic to obtain an electroplating characteristic data set; inputting the electroplating characteristic data set into a deep neural network for processing to obtain an electroplating parameter prediction value set; performing energy consumption sensitivity analysis on an electroplating process of the recycled plastic based on the electroplating parameter prediction value set to obtain energy consumption key factors and compensation coefficients of each stage; calculating first energy consumption optimization parameter sequences of each stage according to the energy consumption key factors and the compensation coefficients; monitoring process parameter deviation data corresponding to the electroplating process of the recycled plastic in real time, and dynamically adjusting the first energy consumption optimization parameter sequences of each stage to obtain second energy consumption optimization parameter sequences of each stage, and the application realizes dynamic monitoring and parameter adjustment of the electroplating process, and can effectively deal with problems such as local hot spot effect and non-uniformity of a plated layer.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to a low-energy consumption electroplating method, device and equipment based on recycled plastic. BACKGROUND

[0002] As an important way of resource recycling, recycled plastic electroplating has received widespread attention in recent years. However, traditional electroplating processes face many difficulties in dealing with recycled plastic. Due to the presence of residual plasticizers, ultraviolet aging and flame retardants in recycled plastic, conventional electroplating methods require an increase of 30-50% of energy consumption to achieve a plating layer effect comparable to that of virgin plastic, not only consuming a large amount of energy, but also being difficult to guarantee the quality of the plating layer. The existing technology mainly adopts uniformization treatment and fixed parameter control strategy, which cannot adapt to the non-uniformity of the surface of recycled plastic and the diversity of internal impurities, resulting in the generation of local high current area in the electroplating process, increasing the overall energy consumption by 38-76%, and the adhesion and uniformity of the plating layer are poor.

[0003] Traditional electroplating technology has three major technical problems when facing recycled plastic: high energy consumption, unstable plating layer quality and poor adaptability to recycled plastic. Especially for recycled plastic containing food residues and multi-layer composite structure, conventional constant parameter control cannot effectively cope with the diversity and instability of the material itself, resulting in low production efficiency and serious environmental pollution. The existing technology mainly adopts single parameter feedback and linear control method in detection and control, which cannot establish a quantitative relationship model between the degradation degree of recycled plastic molecules and electroplating parameters, and lacks fine parameter regulation mechanism for different types of recycled plastic. SUMMARY

[0004] The present application provides a low-energy consumption electroplating method, device and equipment based on recycled plastic, which realizes dynamic monitoring and parameter adjustment of the electroplating process, and can effectively cope with the problems of local hot spot effect and plating layer non-uniformity.

[0005] In the first aspect, the present application provides a low-energy consumption electroplating method based on recycled plastic, which comprises:

[0006] Collecting surface feature parameters of recycled plastic to obtain an electroplating feature data set;

[0007] Inputting the electroplating feature data set into a deep neural network for processing to obtain an electroplating parameter prediction value set;

[0008] Based on the electroplating parameter prediction value set, energy consumption sensitivity analysis is performed on the electroplating process of the recycled plastic to obtain energy consumption key factors and compensation coefficients at each stage;

[0009] The first energy consumption optimization parameter sequence of each stage is calculated according to the energy consumption key factor and the compensation coefficient.

[0010] The process parameter deviation data corresponding to the electroplating process of the recycled plastic is monitored in real time, and the first energy consumption optimization parameter sequence of each stage is dynamically adjusted to obtain the second energy consumption optimization parameter sequence of each stage.

[0011] In a second aspect, the present application provides a low-energy-consumption electroplating device based on recycled plastic, comprising:

[0012] The acquisition module is configured to acquire surface feature parameters of the recycled plastic to obtain an electroplating feature data set.

[0013] The processing module is configured to input the electroplating feature data set into a deep neural network for processing to obtain an electroplating parameter prediction value set.

[0014] The analysis module is configured to perform energy consumption sensitivity analysis on the electroplating process of the recycled plastic based on the electroplating parameter prediction value set to obtain an energy consumption key factor and a compensation coefficient of each stage.

[0015] The calculation module is configured to calculate a first energy consumption optimization parameter sequence of each stage according to the energy consumption key factor and the compensation coefficient.

[0016] The dynamic adjustment module is configured to monitor process parameter deviation data corresponding to the electroplating process of the recycled plastic in real time, and dynamically adjust the first energy consumption optimization parameter sequence of each stage to obtain a second energy consumption optimization parameter sequence of each stage.

[0017] In a third aspect, the present application provides a computer device, comprising a memory and at least one processor, wherein the memory stores instructions; and the at least one processor invokes the instructions in the memory to enable the computer device to perform the low-energy-consumption electroplating method based on recycled plastic.

[0018] The technical scheme provided by the application comprehensively analyzes the surface of the recycled plastic through various sensing devices such as a multispectral imaging device and an infrared spectrum analyzer, realizes accurate quantification of key parameters such as a degradation degree index, surface roughness and impurity distribution, provides a high-quality data basis for subsequent deep learning models, and significantly improves the accuracy of recycled plastic characteristic identification. The deep neural network comprising a multi-layer convolution structure and a nonlinear segmented activation function can accurately capture the complex relationship between the surface characteristics of the recycled plastic and the electroplating parameters, realize accurate prediction of the process parameters of the five electroplating stages, and through the cyclic energy optimization analysis method, the electroplating process is divided into five key stages and the key factors of energy consumption in each stage are identified. A compensation coefficient is designed for the interference factors in the recycled plastic, so that the energy consumption control is more targeted, and the total energy consumption of the recycled plastic electroplating can be reduced. The five-stage independent energy minimization control equation is constructed, and the key parameters of each stage are fine controlled, solving the problem of unstable quality of recycled plastic electroplating. Through the electrochemical impedance spectroscopy, infrared thermal imaging and coating thickness real-time detection system, a complete parameter feedback mechanism is constructed, realizing dynamic monitoring and parameter adjustment of the electroplating process, effectively dealing with the problems of local hot spot effect and uneven coating. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0020] Figure 1 The step schematic diagram of the low-energy electroplating method based on recycled plastic in the embodiment of the application;

[0021] Figure 2 The structure schematic diagram of the low-energy electroplating device based on recycled plastic in the embodiment of the application;

[0022] Figure 3 The structure schematic block diagram of the computer device in the embodiment of the application. DETAILED DESCRIPTION

[0023] The embodiment of the present application provides a low-energy-consumption electroplating method, device and equipment based on recycled plastic. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0024] For the convenience of understanding, the specific flow of the embodiment of the present application is described below. Please refer to Figure 1 One embodiment of the low-energy-consumption electroplating method based on recycled plastic in the embodiment of the present application comprises the following steps.

[0025] Step S1, collecting surface characteristic parameters of the recycled plastic to obtain an electroplating characteristic data set;

[0026] It can be understood that the execution subject of the present application can be a low-energy-consumption electroplating device based on recycled plastic, and can also be a terminal or a server, and the specific place is not limited. The embodiment of the present application takes the server as the execution subject for example.

[0027] Specifically, the recycled plastic is scanned by a multispectral imaging device, which captures the reflectance spectrum data of the plastic surface under different wavelengths of light, reflecting the surface color, texture characteristics of the material, and revealing the surface chemical properties and physical state of the material through specific band spectral information. At the same time, by analyzing the changes in reflectivity in the spectral data, the uniformity, smoothness and potential contamination of the plastic surface are evaluated, thereby refining the dimension of electroplating feature data. The molecular structure of the recycled plastic is detected by an infrared spectrum analyzer to obtain the degradation index (DI value). The infrared spectrum analyzer detects the absorption spectrum of the material under specific infrared light, identifies the molecular bond structure and chemical composition changes in the material. For recycled plastic, the molecular structure will degrade due to changes in heat, light, and chemical environment during recycling and reprocessing, which manifests as molecular chain breakage, functional group change, or cross-linking degree change. The DI value quantifies these changes, providing an effective means of evaluating the degradation of plastic materials. A higher DI value indicates more severe molecular chain breakage in the plastic material, which will directly affect the adhesion and uniformity of the electroplated layer. The surface roughness of the recycled plastic is measured by a surface roughness sensor through linear scanning, obtaining the surface roughness (Ra value). Surface roughness is an important parameter for evaluating the micro-topography of the material surface, and its size directly affects the flatness and adhesion of the plated layer during electroplating. The Ra value is calculated by scanning the linear profile curve of the plastic surface, usually expressed in microns. When the plastic surface is smooth, the Ra value is low, and the metal ions in the electroplating solution can uniformly deposit, resulting in a uniform plated layer. When the surface roughness is high, the electroplating solution forms an uneven electric field distribution on the surface, leading to uneven plated layer thickness and even defects such as bubbles and pinholes. The surface polarity distribution of the recycled plastic is measured by a resistivity meter through point array resistivity measurement, obtaining the surface polarity distribution map. The resistivity meter measures the resistance between each point in the array of electrodes on the plastic surface to evaluate the surface polarity distribution of the material. Since the electroplating process depends on the electrical conductivity of the material surface, the surface polarity distribution map can reveal whether there are areas of uneven electrical conductivity on the plastic surface, thereby predicting problems such as excessively high or low local current density during electroplating. To identify the distribution of impurities on the surface of the recycled plastic, a fluorescence analyzer is used to perform UV excitation imaging of the surface, obtaining the surface impurity distribution density. The fluorescence analyzer excites the material surface by emitting ultraviolet light (UV light) and uses the fluorescence reaction of impurities at a specific wavelength to form an image. The surface impurity distribution density is calculated by analyzing the fluorescence intensity distribution in the imaging image. The higher the value, the more dense the surface impurity distribution.The surface reflection spectrum data, the degradation degree index DI value, the surface roughness Ra value, the surface polarity distribution map and the surface impurity distribution density are standardized respectively to eliminate the dimensional differences between different data sources and convert all data into the same range or standard normal distribution. The standardized data set is represented as a multi-dimensional vector, each dimension corresponding to a characteristic parameter. These standardized data are combined to form the electroplating characteristic data set.

[0028] In step S2, the electroplating characteristic data set is input into a deep neural network for processing to obtain an electroplating parameter prediction value set.

[0029] Specifically, the electroplating feature dataset is converted into an input matrix. By integrating the normalized surface reflectance spectrum data, degradation index DI value, surface roughness Ra value, surface polarity distribution map, and surface impurity distribution density, each dimension of data corresponds to a row or a column in the matrix, forming a high-dimensional feature matrix. The input matrix is input into the encoder network of the deep neural network, and a 3x3 convolution operation is performed on the first convolution layer to extract the local features of the recycled plastic surface. The 3x3 convolution kernel captures small-scale surface detail features by sliding on the input matrix, such as microscopic concave-convex, local changes in impurity distribution, and fine-grained features of resistivity changes. The convolution operation performs a dot product operation with the local region of the input data through weights and an activation function such as ReLU to enhance nonlinear features. Through this convolution operation, the first feature map is output. The first feature map is input into the second convolution layer of the encoder network, and a 5x5 convolution operation is used to extract the correlation of surface features. Compared with the 3x3 convolution kernel, the 5x5 convolution kernel has a larger receptive field, capturing the relationship between a wider range of surface features. For example, when there are large areas of degradation or continuous conductivity changes on the plastic surface, the 5x5 convolution better correlates these local features, helping the model understand the macro distribution and trend changes of surface features. Through this process, the second feature map is obtained. The second feature map is sequentially passed through the convolution layers with 7x7, 5x5, 3x3, and 1x1 convolution kernels to extract multi-scale features of the recycled plastic surface. The 7x7 convolution kernel captures large-scale surface patterns such as overall surface finish and conductivity distribution trends through a larger receptive field, while the 5x5 and 3x3 convolution kernels focus on medium-scale and small-scale surface features, such as medium-sized impurity aggregation areas and fine surface texture changes. The 1x1 convolution serves the purpose of feature dimension reduction and fusion, compressing the feature dimension by linearly combining multi-channel feature maps, so that the model not only retains multi-scale features but also effectively reduces computational complexity, finally outputting a latent feature vector. A nonlinear piecewise activation function is applied to different elements in the latent feature vector to achieve adaptive processing of different degradation states of recycled plastic. The nonlinear piecewise activation function sets different activation function forms for different intervals of feature values, such as using linear activation for low degradation to maintain feature continuity, and using ReLU or Leaky ReLU function for high degradation to amplify the response of key features, so that the deep neural network can automatically adjust the sensitivity of the output features when facing recycled plastic with different degradation states. Through this step, an optimized feature vector is obtained. The optimized feature vector is input into the corresponding decoder network of the deep neural network for the five stages, and the decoder network is designed correspondingly to the encoder network but with reverse operations, restoring the latent feature vector to a specific set of electroplating parameter prediction values through upsampling and convolution operations.In the decoding process, each decoder network is trained for a specific electroplating stage, for example, the decoder network for the pre-treatment stage outputs temperature and stirring speed parameter predictions. In the micro-etching stage, the decoder network outputs current density and micro-etchant concentration parameter predictions, providing a fine etching of the plastic surface to provide a microstructure suitable for metal ion deposition. In the catalytic activation stage, the model predicts the activation agent concentration and pulse frequency to accurately control the thickness and uniformity of the catalytic layer. In the initial deposition stage, the prediction of current waveform and additive ratio parameters helps to stabilize the formation of the electroplated layer, preventing excessive or uneven deposition. In the final structure regulation stage, the predictions of temperature gradient and current density provide an important means of regulating the internal structure and stress distribution of the plated layer, so that the final plated layer not only meets the smoothness requirements in appearance, but also has good mechanical properties and stability in internal structure.

[0030] Step S3, based on the set of electroplating parameter predictions, energy consumption sensitivity analysis is performed on the electroplating process of the recycled plastic, to obtain the energy consumption key factors and compensation coefficients of each stage;

[0031] Specifically, a cyclic energy optimization analysis is performed based on the set of electroplating parameter prediction values. The electroplating process is divided into five key stages: pretreatment, microetching, catalytic activation, initial deposition, and structure regulation, each with specific process parameters, including temperature and stirring speed in the pretreatment stage, current density and microetching agent concentration in the microetching stage, activator concentration and pulse frequency in the catalytic activation stage, current waveform and additive ratio in the initial deposition stage, and temperature gradient and current density in the structure regulation stage. During the cyclic energy optimization analysis, small amplitude changes are tested for each process parameter in each electroplating stage to evaluate the degree of influence of these parameters on the energy consumption of the entire electroplating process. Each parameter is gradually adjusted within a certain range, and the energy consumption rate of the electroplating process is measured while keeping other parameters constant, such as by monitoring actual energy consumption data such as power consumption, current input, temperature change rate, etc. The energy consumption response curve caused by the change of each parameter is obtained, effectively quantifying the sensitivity of each process parameter to energy consumption. When the energy consumption rate of a certain parameter exceeds the preset target value, that parameter is marked as an energy consumption sensitive parameter, and thus determined as the energy consumption key factor of that stage. Feature extraction is performed on the degradation index DI value, ultraviolet aging index UV-I value, flame retardant content FR value, and plasticizer content PI value in the electroplating feature data set. These features reflect the chemical and physical state of the recycled plastic materials and have different degrees of interference with energy consumption in the electroplating process. For example, materials with high DI values have poor wettability in the electroplating solution, requiring higher stirring speed to maintain the uniformity of the electroplating solution, while plastic materials with high UV-I values have low surface activity, requiring adjustment of the activator concentration and pulse frequency in the catalytic activation stage. By normalizing and standardizing these features, an interference feature vector is constructed to represent the potential impact of material properties on the electroplating process. Correlation analysis is performed between the interference feature vector and the energy consumption key factors of each stage to calculate the influence weight of each interference feature on the energy consumption key factor. For example, by using Pearson correlation coefficient, partial correlation analysis, or feature importance evaluation method based on linear regression model, the correlation between each feature and the energy consumption key factor is quantified, and the weight coefficient effectively reflects the degree of influence of each material property on the specific energy consumption key factor. Based on the weight coefficient, a compensation coefficient is calculated to adjust the process parameters in the electroplating process to offset the energy consumption impact caused by changes in material properties. The compensation coefficient is calculated by constructing a linear or nonlinear model that relates the weight coefficient to the energy consumption key factor. The introduction of the compensation coefficient allows the energy consumption to be maintained within the ideal range during the actual electroplating process by automatically adjusting the key parameters when the material properties change. For example, when the increase in the plasticizer content (PI value) of the material is detected, causing an increase in the sensitivity of the current density, the compensation coefficient in the microetching stage is adjusted to reduce the energy consumption fluctuations caused by changes in the current density.

[0032] Step S4, calculating the first energy consumption optimization parameter sequence of each stage according to the energy consumption key factor and the compensation coefficient;

[0033] Specifically, based on the energy consumption key factor and the compensation coefficient of the pretreatment stage, an energy consumption minimization control equation of the pretreatment stage is constructed. The form of this equation is: wherein, represents the energy consumption of the pretreatment stage, is the specific heat capacity of the solution, is the mass of the solution, is the real-time temperature, is the initial temperature, is the stirring speed, is the stirring power coefficient, is the end time of the pretreatment stage. This equation describes the contribution of temperature change and stirring speed to energy consumption in the pretreatment stage. By optimizing this equation, the optimal control strategy of temperature and stirring speed is determined, thereby realizing the minimization of energy consumption. In the micro-etching stage, based on the energy consumption key factor and the compensation coefficient of this stage, an energy consumption minimization control equation of the micro-etching stage is constructed. The form of the equation is: wherein, is the energy consumption of the micro-etching stage, is the current density, is the voltage, is the concentration of the micro-etching agent, is the energy consumption equivalent coefficient of the micro-etching agent, is the end time of the micro-etching stage. This equation reflects how the changes of current density, voltage and micro-etching agent concentration affect energy consumption. In actual operation, by adjusting these parameters, the energy consumption is minimized under the premise of ensuring the quality of electroplating, thereby improving the energy utilization efficiency of the process. In the catalytic activation stage, the energy consumption of this stage is optimized by constructing a corresponding energy consumption minimization control equation. The form of the equation is: wherein, is the energy consumption of the catalytic activation stage, is the concentration of the activator, is the energy consumption equivalent coefficient of the activator, is the pulse frequency, is the power coefficient of the pulse generator, is the end time of the catalytic activation stage. This equation describes the influence of activator concentration and pulse frequency on energy consumption. By adjusting these two parameters in the actual electroplating process, the energy consumption in the catalytic activation process is optimized, ensuring that the energy consumption reaches the optimal level. In the initial deposition stage, the energy consumption optimization control equation needs to consider the influence of current density, voltage, current waveform and additive ratio. The energy consumption minimization control equation of this stage is: wherein, is the energy consumption of the initial deposition stage, is the current density, is the voltage, is the current waveform of the duty cycle function, is the additive ratio, is the energy consumption equivalent coefficient of the additive, is the end time of the initial deposition stage. By regulating the current waveform and additive ratio, the energy consumption is reduced, thereby improving the energy efficiency of the deposition process. In the structure regulation stage, based on the energy consumption key factor of this stage and its compensation coefficient, the energy consumption minimization control equation of the structure regulation stage is constructed. The form of this equation is: wherein, is the energy consumption of the structure regulation stage, is the current density, is the voltage, is the temperature gradient, is the energy consumption equivalent coefficient of the temperature gradient, is the end time of the structure regulation stage. This equation reflects the influence of the temperature gradient and the current density on the energy consumption. When fine-tuning the material structure, accurate control of the current density and the temperature gradient helps to improve the energy efficiency. By solving the energy consumption minimization control equations of the above five stages, the first energy consumption optimization parameter sequence of each stage is obtained. The optimization process of each equation not only depends on the surface characteristics and degradation degree of the recycled plastic materials, but also needs to combine the real-time process parameters. By dynamically adjusting the operating conditions of different stages, the energy efficiency of the entire electroplating process is optimized in different stages.

[0034] Step S5, real-time monitoring of the process parameter deviation data corresponding to the electroplating process of the recycled plastic, and dynamically adjusting the first energy consumption optimization parameter sequence of each stage to obtain the second energy consumption optimization parameter sequence of each stage.

[0035] Specifically, the electrochemical impedance spectroscopy measurement device is used to perform sweep frequency measurement on the recycling plastic electroplating process, obtaining a set of electrochemical parameters including interface capacitance, charge transfer resistance, Warburg impedance coefficient, and solution resistance, reflecting the dynamic changes of the electrochemical behavior of the plastic surface during the electroplating process, and revealing the interface characteristics during metal deposition, such as the adsorption of metal ions on the plastic surface and the charge transfer efficiency. At the same time, the infrared thermal imaging system is used to scan the temperature distribution of the electroplated surface of the recycling plastic, obtaining a high-resolution surface temperature distribution map. The infrared thermal imaging system captures the surface thermal radiation signal to generate a real-time temperature distribution image, helping to identify local overheating or cold spot areas during the electroplating process. For example, when the local thickness of the plated layer increases, the electroplating current density increases, leading to local heat accumulation. These hot spot areas not only affect the quality of the plated layer, but also significantly increase energy consumption. The eddy current thickness detector is used to measure the electroplated surface of the recycling plastic, obtaining real-time plated layer thickness data. The eddy current thickness detection technology is based on electromagnetic induction principle, measuring the response change of electromagnetic field in the metal plated layer to calculate the actual thickness of the plated layer. The set of electrochemical parameters, surface temperature distribution map, and real-time plated layer thickness data are compared with the predicted value set of the electroplating parameters predicted by the deep neural network, obtaining the process parameter deviation data between the current electroplating process and the ideal state. During data processing, the difference between the actual parameter value and the predicted value is calculated, such as the deviation of the charge transfer resistance, local temperature abnormal points, and the over-limit situation of the plated layer thickness change rate, to construct a comprehensive deviation vector. After obtaining the deviation vector, the online identification method is used to update the Jacobian matrix in real time. The Jacobian matrix is an important tool in multivariable systems to describe the influence of input parameter changes on output. In the electroplating process, the process parameter deviation is related to the energy consumption change. Through online identification technology, the latest value of the Jacobian matrix is dynamically calculated during the electroplating process, accurately reflecting the immediate impact of process parameter adjustment on energy consumption. Through this calculation method, the corrected control parameters of each stage are obtained. According to the corrected control parameters of each stage, combined with the local effects detected during the electroplating process, various process control technologies are applied to achieve fine management of energy consumption. In dealing with local hot spot effects, the pulse frequency is dynamically adjusted to reduce local current density, thereby avoiding the increase of energy consumption caused by local overheating. The dynamic adjustment of pulse frequency is achieved by real-time control of the output frequency of the pulse power supply, so that the pulse frequency of the hot spot area is reduced, thereby slowing down the deposition rate of metal ions and balancing the temperature distribution of the overall electroplated surface. In the case of serious non-uniformity of the plated layer, auxiliary anode activation technology is used to adjust the electric field distribution by arranging auxiliary anodes near the non-uniform areas, so that metal ions preferentially deposit in the thin areas of the plated layer, thereby achieving uniformity of the plated layer thickness. For areas with insufficient activation, local catalyst injection technology is used to achieve precise control of the activator concentration.Catalyst injection technology uses a nozzle and a pressure control system to inject activators to areas with low electrochemical activity, thereby improving the catalytic efficiency of the area. By combining real-time monitoring, parameter deviation calculation, online identification, and various dynamic control technologies, the second energy consumption optimization parameter sequence of each stage is obtained.

[0036] Based on the process parameter deviation data, a parameter time sequence matrix and a target deviation matrix are constructed. The parameter time sequence matrix is obtained by sampling the historical data of each process parameter in the electroplating process, taking the parameter state at each time as a row of the matrix, forming a multi-dimensional time sequence matrix. For example, for current density, temperature, stirring speed and other key process parameters, the actual values at each time point within the time window are recorded to obtain a matrix like , where represents the value of the th process parameter at the th time point. At the same time, the target deviation matrix is obtained by comparing the real-time monitored parameter data with the predicted ideal parameter set, calculating the deviation of each parameter at each time point, and obtaining the target deviation matrix , where represents the deviation value of the th parameter at the th time point. The recursive least squares algorithm is applied to the parameter time sequence matrix and the target deviation matrix to obtain the parameter sensitivity matrix. The recursive least squares algorithm minimizes the sum of squared errors between the predicted output and the actual target to achieve fast convergence of parameter estimation in dynamic systems. The parameter time sequence matrix is used as the input variable, and the target deviation matrix is used as the output variable to construct the state equation. The parameter sensitivity matrix obtained by continuously iterating and updating the weight matrix through the recursive least squares algorithm can quantify the influence degree of the change of each process parameter on the deviation result, i.e. the sensitivity of the process parameter. Each element in the matrix represents the contribution size of the change of a specific parameter in a specific process stage to the energy consumption deviation. Singular value decomposition is performed on the matrix to decompose the matrix into , where and are orthogonal matrices, is a diagonal matrix whose diagonal values are singular values. These singular values reflect the eigenvalue size of the parameter sensitivity matrix. Larger singular values indicate significant influence of the corresponding parameter on the system output, while smaller singular values indicate weaker influence of the corresponding parameter on the system response. In order to enhance the robustness of the system and avoid excessive response in the control process, the singular values less than a preset threshold are set to zero to obtain the truncated Jacobian matrix This processing can effectively reduce the influence of noise or small parameter changes on the stability of the system, while retaining the main parameter influence path. After obtaining the Jacobian matrix, the unconstrained control parameter correction amount is calculated by performing matrix multiplication operation on the bias vector and the Jacobian matrix . The unconstrained control parameter correction amount represents the optimal control adjustment amount required to eliminate the process parameter deviation under the current process state. In order to ensure that the control parameters do not exceed the safe range of the physical or process equipment, a saturation function constraint is applied to the unconstrained control parameter correction amount. For example, when the correction amount of current density exceeds the maximum current density allowed by the equipment, the correction amount is limited within the safe range by the saturation function, avoiding excessive adjustment that leads to system instability or rapid rise in energy consumption. The constrained control parameter correction amount is added to the first energy consumption optimization parameter sequence according to the five stages of the electroplating process (pretreatment, micro-etching, catalytic activation, initial deposition, and structure regulation), to obtain the modified control parameters of each stage. By linearly superimposing the correction amount and the original energy consumption optimization parameters, dynamic adjustment is achieved. For example, in the pretreatment stage, by adjusting the temperature and stirring speed parameters, the pretreatment operation is completed within the lowest range of energy consumption, while in the initial deposition stage, by optimizing the current waveform and additive ratio, the uniformity of the plated layer and energy efficiency are both improved.

[0037] In the embodiment of the present application, the surface of the recycled plastic is comprehensively analyzed by various sensing devices such as multispectral imaging devices and infrared spectrum analyzers, realizing accurate quantification of key parameters such as degradation degree index, surface roughness and impurity distribution, providing high-quality data basis for subsequent deep learning models, and significantly improving the accuracy of recycled plastic characteristic identification. The deep neural network containing multiple convolutional structures and nonlinear segmented activation functions can accurately capture the complex relationship between the surface characteristics of recycled plastic and electroplating parameters, realize accurate prediction of process parameters in the five electroplating stages, and through the cyclic energy optimization analysis method, the electroplating process is divided into five key stages and the key factors of energy consumption in each stage are identified, the compensation coefficient is designed according to the interference factors in the recycled plastic, the energy consumption control is more targeted, and the total energy consumption of the recycled plastic electroplating is reduced. The energy minimization control equation of the five stages is constructed, and the key parameters of each stage are controlled in detail, solving the problem of unstable quality of recycled plastic electroplating. Through the electrochemical impedance spectrum, infrared thermal imaging and plated layer thickness real-time detection system, a complete parameter feedback mechanism is constructed, realizing dynamic monitoring and parameter adjustment of the electroplating process, effectively dealing with the problems of local hot spot effect and plated layer unevenness.

[0038] In a specific embodiment, the process of performing step S1 can specifically include the following steps:

[0039] The surface of the recycled plastic is scanned by a multispectral imaging device to obtain surface reflectance spectrum data.

[0040] The molecular structure of the recycled plastic is detected by an infrared spectrum analyzer to obtain a degradation degree index DI value.

[0041] The surface line scanning measurement of the recycled plastic is performed by a surface roughness sensor to obtain a surface roughness Ra value.

[0042] The surface point array resistivity measurement of the recycled plastic is performed by a resistivity measuring instrument to obtain a surface polarity distribution map.

[0043] The surface UV excitation imaging of the recycled plastic is performed by a fluorescence analyzer to obtain a surface impurity distribution density.

[0044] The surface reflectance spectrum data, the degradation degree index DI value, the surface roughness Ra value, the surface polarity distribution map, and the surface impurity distribution density are standardized and combined to obtain the electroplating feature data set.

[0045] Specifically, the surface of the recycled plastic is scanned by a multispectral imaging device, and the reflectance information of the plastic surface in the visible, near-infrared, and ultraviolet spectral range is obtained by capturing the reflectance spectrum data of the material under different wavelengths of light. The multispectral imaging system decomposes white light into multiple wavelength narrow-band light beams through a spectrometer, and sequentially irradiates the surface of the plastic. The reflectance spectrum data of the surface is obtained by using a high-resolution light sensor to record the reflectance intensity under each wavelength. wherein represents the wavelength of light, represents the reflectance intensity corresponding to the wavelength. This data can reveal information such as color, texture, and chemical composition of the material surface, which is helpful for evaluating the surface uniformity and contamination level of the plastic. The molecular structure of the recycled plastic is detected by an infrared spectrum analyzer to obtain a degradation degree index DI value. The infrared spectrum analyzer measures the absorption of infrared light by the material molecules by scanning the surface of the material in a specific infrared wavelength range to obtain an infrared absorption spectrum wherein represents the wave number (reciprocal of wavelength) of infrared light. The intensity and position of the absorption peak are closely related to the molecular bond characteristics in the material, such as C-H, C=O, O-H, etc. The absorption peaks in different wave number regions have specific absorption peaks. By calculating the area change of the absorption peak of a specific functional group, the degradation of the material molecular chain is deduced, and the calculation formula of the DI value is defined as:

[0046]

[0047] wherein, represents the area of a specific degradation characteristic absorption peak, To stabilize the area of the characteristic absorption peak. The higher the DI value, the more severe the degradation of the material, which has a significant impact on predicting the adhesion and surface activity of the material during the electroplating process. To quantify the micro-topography of the plastic surface, a surface roughness sensor was used to perform a line scan measurement on the recycled plastic to obtain the surface roughness (Ra value). The surface roughness sensor uses laser or stylus scanning to move along a specific path on the material surface, records the changes in surface height, and obtains the surface profile curve wherein represents the position on the scanning path, is the surface height. The calculation formula of Ra value is:

[0048]

[0049] wherein, represents the total length of the scanning path, is the average value of the surface height. The Ra value reflects the degree of micro-unevenness of the material surface, and a higher Ra value leads to uneven distribution of the electroplating solution on the surface, thereby affecting the quality of the plated layer. During the electroplating process, the electrical properties of the material surface also affect the process parameters. A resistivity measurement instrument was used to perform a surface dot array resistivity measurement on the recycled plastic to obtain a surface polarity distribution map. In this process, by arranging a grid-shaped electrode array on the plastic surface, the resistance values between each point were measured wherein and represent the position coordinates in the two-dimensional plane, respectively. By calculating the resistivity of each grid point wherein is the electrode area, is the electrode spacing, a resistivity distribution image is generated. Since the electroplating process depends on the electrical conductivity of the material surface, the surface polarity distribution map can reveal the unevenness of the electrical conductivity of the material surface, helping to identify hot spot areas during the electroplating process, thereby adjusting the process parameters to optimize energy consumption. At the same time, in order to analyze the distribution of impurities on the plastic surface, a fluorescence analyzer was used to perform UV excitation imaging on the recycled plastic to obtain the surface impurity distribution density. The fluorescence analyzer irradiates the material surface with ultraviolet light (UV light) of a specific wavelength, and when the impurity molecules are excited by the UV light, they will produce fluorescence, and the fluorescence sensor records the impurity distribution image wherein represents the fluorescence intensity at position . By counting the fluorescence signal intensity in the image, the impurity distribution density is calculated:

[0050]

[0051] wherein, Total area of the measured surface. The electroplating feature dataset is obtained by combining all the normalized feature data .

[0052] In a specific embodiment, the process of performing step S2 can specifically include the following steps:

[0053] The electroplating feature dataset is converted into an input matrix, which is input into the first convolutional layer of the encoder network of the deep neural network, and a 3x3 convolution operation is performed on the input matrix to extract the local features of the recycled plastic surface to obtain a first feature map;

[0054] The first feature map is input into the second convolutional layer of the encoder network to perform a 5x5 convolution operation to extract the correlation of the surface features to obtain a second feature map;

[0055] The second feature map is sequentially input into the convolutional layers with 7x7, 5x5, 3x3 and 1x1 convolution kernels to extract the multi-scale features of the recycled plastic surface to obtain a latent feature vector;

[0056] A nonlinear piecewise activation function is applied to the elements in the latent feature vector corresponding to different degradation degree intervals to realize adaptive processing of different degradation states of the recycled plastic to obtain an optimized feature vector;

[0057] The optimized feature vector is input into the corresponding decoder network of the five stages in the deep neural network, respectively, to output a set of electroplating parameter prediction values including the pre-treatment stage, the micro-etching stage, the catalytic activation stage, the initial deposition stage and the structure regulation stage, wherein the pre-treatment stage includes temperature and stirring speed, the micro-etching stage includes current density and micro-etching agent concentration, the catalytic activation stage includes activator concentration and pulse frequency, the initial deposition stage includes current waveform and additive ratio, and the structure regulation stage includes temperature gradient and current density.

[0058] Specifically, the electroplating feature dataset is converted into an input matrix , wherein is the surface reflectance spectrum data, is the degradation degree index, is the surface roughness, is the surface polarity distribution map, is the surface impurity distribution density. The dimension of the input matrix is , wherein and respectively represent the spatial dimensions of the matrix, This represents the number of feature channels, each corresponding to a type of feature data, such as spectral data, chemical composition, physical morphology, or electrical properties. By standardizing these feature data, we ensure that the data for each channel falls within the same numerical range, allowing the deep neural network to learn the importance of each feature in a balanced way during training. The input matrix... The first convolutional layer of the encoder network, fed into the deep neural network, performs a 3×3 convolution operation to extract local features from the recycled plastic surface. In the convolution operation, the 3×3 convolution kernel... With step size Slide the convolution kernel across the input matrix and perform element-wise dot products with local regions of the input data to obtain the first feature map. The mathematical expression for convolution is:

[0059]

[0060] in, Indicates the location of the first feature map pixel values, These are the weights of the convolution kernel. It is the value of the input matrix at the corresponding position. This is the bias term. Through 3×3 convolution, it captures texture features, microstructure, and spectral variations within a small area of ​​the plastic surface, helping to identify small-scale contamination or defect areas on the material surface. The first feature map... The input is fed into the second convolutional layer of the encoder network, where a 5x5 convolution operation is performed to extract the correlations between surface features. In this layer, the 5x5 convolution kernels... By extracting features through a larger receptive field, the model learns feature relationships over a wider range, such as the coherence of degradation regions on the surface of plastic materials and the overall trend of electrical property distribution. Second feature map The calculation formula is:

[0061]

[0062] in, These are the weights of the 5×5 convolution kernel. This is the bias term. Through this convolution operation, the model can focus on local features and incorporate the spatial relationships between these features into the feature map. In the second feature map... Based on this, in order to extract multi-scale features, the feature map is sequentially passed through convolutional layers with 7×7, 5×5, 3×3 and 1×1 kernels to obtain latent feature vectors. This multi-scale convolution operation allows the model to learn both large-scale and small-scale features simultaneously. For example, a 7×7 convolution captures the overall surface temperature distribution trend, while 5×5 and 3×3 convolutions focus on medium- and small-scale impurity distribution. Convolution plays a role of feature fusion, which realizes the compression of feature dimension and the enhancement of expression ability through linear combination of multi-channel feature maps. The latent feature vector is a dimensional vector, and each element corresponds to a specific surface feature or feature expression of a process parameter. In order to adapt to the recycled plastic materials in different degradation states, a nonlinear piecewise activation function is applied to the elements in the latent feature vector for adaptive processing. The nonlinear piecewise activation function is expressed as:

[0063]

[0064] wherein, is the activated feature value, , and are activation coefficients in different intervals, and are the threshold values of the piecewise function. Through the activation function, when the material degradation degree is low , linear activation is used to maintain the stability of the feature; when the degradation is moderate , the square function is used to amplify the feature response to enhance the sensitivity of the model to the change of material characteristics; when the degradation is high , the logarithmic activation function is used to realize the slow growth of the response, so as to prevent the increase of energy consumption or the decline of electroplating quality caused by excessive adjustment of process parameters. The optimized feature vector after nonlinear activation is input into the decoder network corresponding to the five stages in the deep neural network, and through the inverse convolution and upsampling operation of the decoder network, the final output of the electroplating parameter prediction value set of each stage is output. These parameters include the temperature and stirring speed in the pretreatment stage, the current density and micro-etching agent concentration in the micro-etching stage, the activator concentration and pulse frequency in the catalytic activation stage, the current waveform and additive ratio in the initial deposition stage, and the temperature gradient and current density in the structure regulation stage.

[0065] In a specific embodiment, the process of performing step S3 can specifically include the following steps:

[0066] ​Cyclic energy optimization analysis was performed based on the predicted values ​​of electroplating parameters, and parameter variation tests were conducted on the temperature and stirring speed in the pretreatment stage, the current density and micro-etching agent concentration in the micro-etching stage, the activator concentration and pulse frequency in the catalytic activation stage, the current waveform and additive ratio in the initial deposition stage, and the temperature gradient and current density in the structure regulation stage.

[0067] Record the energy consumption change rate corresponding to each parameter, and identify the parameters whose energy consumption change rate exceeds the preset target value as energy consumption sensitive parameters to obtain the key energy consumption factors at each stage;

[0068] Feature extraction was performed on the degradation index (DI), ultraviolet aging index (UV-I), flame retardant content (FR), and plasticizer content (PI) values ​​in the electroplating feature dataset to construct an interference feature vector.

[0069] Correlation analysis is performed between the interference feature vector and the key energy consumption factors to calculate the weight coefficients. Based on the weight coefficients, the compensation coefficients are calculated to obtain the compensation coefficients for the key energy consumption factors.

[0070] Specifically, in the energy optimization analysis, based on the set of predicted electroplating parameters obtained from deep neural networks, the key process parameters for each of the five stages—pretreatment, micro-etching, catalytic activation, initial deposition, and structure regulation—were tested for parameter changes one by one. In the pretreatment stage, temperature was considered... and stirring speed By setting different increment step sizes and ), calculate the energy consumption under each parameter variation. Rate of change. The formula for calculating the rate of change in energy consumption is:

[0071]

[0072] in, and These represent the rate of change in energy consumption due to temperature and stirring speed, respectively. and This refers to the energy consumption under the current parameter values. In the micro-etching stage, a similar method is used to control the current density (…). ) and micro-etchant concentration ( ) Conduct parameter change tests to obtain the energy consumption change rate:

[0073]

[0074] Similarly, in the catalytic activation stage, the initial deposition stage, and the structure regulation stage, the concentration of the activator ( ), pulse frequency ( ), current waveform ( ), additive ratio ( ), temperature gradient ( ) and current density ( Tests were conducted separately to obtain the energy consumption change rate of each parameter. Throughout the cycle energy optimization analysis, the energy consumption response to changes in each parameter was automatically recorded. Parameters with energy consumption change rates exceeding preset target values ​​were marked as energy-sensitive parameters, thereby identifying key energy consumption factors at each stage. For example, when the rate of change of current density... Exceeding the preset target value At that time, current density These were identified as key energy consumption factors in the micro-etching stage. After identifying these key energy consumption factors, to analyze the impact of material properties on them, feature extraction was performed on the DI, UV-I, FR, and PI values ​​in the electroplating feature dataset to construct an interference feature vector. ,in Indicates the degree of material degradation. Reflects UV aging status, It refers to the flame retardant content. The plasticizer content is used. These features are normalized to ensure they fall within the same numerical range (e.g., [0,1]), eliminating dimensional differences between features and guaranteeing a balanced contribution of each feature to energy consumption in subsequent calculations. To quantify the impact of interfering features on key energy consumption factors, correlation analysis is used to calculate the weighting coefficient between each interfering feature and the key energy consumption factor. Correlation analysis uses Pearson correlation coefficient or partial correlation analysis methods, and the calculation formula is as follows:

[0075] ;

[0076] in, It is the first The weight coefficients of each interfering feature, It is a key factor in energy consumption. The first in Key factor values, and These are interference features and key factors The mean of the values. The magnitude of the weighting coefficient reflects the sensitivity of the disturbance feature to key energy consumption factors; the higher the weighting coefficient, the greater the impact of the feature on energy consumption changes. Compensation coefficients are applied based on the weighting coefficients. The calculation is used to dynamically adjust key energy consumption factors. The formula for calculating the compensation coefficient is:

[0077]

[0078] in, It is aimed at the first a compensation coefficient of the energy consumption key factor, a sensitivity factor of the key factor change, is a basic compensation value obtained through experimental data or historical experience data. For example, in the initial deposition stage, when the additive ratio is identified as the energy consumption key factor and the plasticizer content has a greater impact on it, the compensation coefficient is obtained by multiplying the weight coefficient and the sensitivity factor , so as to dynamically adjust the additive ratio in the actual electroplating process, and ensure that the energy consumption is within a safe and economic range.

[0079] In a specific embodiment, the process of performing step S4 can specifically include the following steps:

[0080] Based on the energy consumption key factors and their compensation coefficients in the pretreatment stage, a pretreatment stage energy consumption minimization control equation is constructed , wherein E1 is the pretreatment stage energy consumption, cp is the specific heat capacity, m is the solution mass, T1(t) is the temperature, T0 is the initial temperature, V1(t) is the stirring speed, P1 is the stirring power coefficient, and t1 is the pretreatment stage end time;

[0081] Based on the energy consumption key factors and their compensation coefficients in the micro-etching stage, a micro-etching stage energy consumption minimization control equation is constructed , wherein E2 is the micro-etching stage energy consumption, I2(t) is the current density, U2(t) is the voltage, C2(t) is the micro-etching agent concentration, λ2 is the energy consumption equivalent coefficient of the micro-etching agent consumption, and t2 is the micro-etching stage end time;

[0082] Based on the energy consumption key factors and their compensation coefficients in the catalytic activation stage, a catalytic activation stage energy consumption minimization control equation is constructed , wherein E3 is the catalytic activation stage energy consumption, C3(t) is the activator concentration, λ3 is the energy consumption equivalent coefficient of the activator, F3(t) is the pulse frequency, P3 is the pulse generator power coefficient, and t3 is the catalytic activation stage end time;

[0083] Based on the energy consumption key factors and their compensation coefficients in the initial deposition stage, an initial deposition stage energy consumption minimization control equation is constructed , wherein E4 is the initial deposition stage energy consumption, I4(t) is the current density, U4(t) is the voltage, D4(W4) is the duty cycle function of the current waveform W4, R4(t) is the additive ratio, λ4 is the energy consumption equivalent coefficient of the additive, and t4 is the initial deposition stage end time;

[0084] Based on the key factors of energy consumption and compensation coefficient in the structure regulation stage, the energy consumption minimization control equation of the structure regulation stage is constructed , wherein E5 is the energy consumption of the structure regulation stage, I5(t) is the current density, U5(t) is the voltage, G5(t) is the temperature gradient, λ5 is the energy consumption equivalent coefficient of the temperature gradient, and t5 is the end time of the structure regulation stage;

[0085] By solving the energy consumption minimization control equation of the five stages, the first energy consumption optimization parameter sequence of each stage in the recycling plastic electroplating process is obtained.

[0086] Specifically, in the pretreatment stage, the energy consumption optimization is realized by regulating the temperature and the stirring speed . The energy consumption of the pretreatment stage mainly includes the energy consumption of solution heating and mechanical stirring, and the constructed energy consumption minimization control equation is:

[0087]

[0088] , wherein is the total energy consumption of the pretreatment stage, is the specific heat capacity of the solution, is the mass of the solution, is the initial temperature of the solution, is the power coefficient of the stirring device, is the end time of the pretreatment stage. In order to realize energy consumption minimization, the temperature and the stirring speed are taken as control variables, and by optimizing the change curves of these variables, the consumption of heating and stirring power is minimized. For example, when it is detected that the degradation degree of the recycled plastic is high (high DI value), the heating temperature and the stirring speed are appropriately reduced, the energy consumption is reduced by adjusting the compensation coefficient, the process effect is maintained, and the energy waste is reduced. In the micro-etching stage, the energy consumption mainly comes from the electrical energy consumption and etchant consumption in the electrolysis process. The energy consumption minimization control equation of the micro-etching stage is:

[0089]

[0090] , wherein is the energy consumption of the micro-etching stage, is the current density, is the voltage, is the concentration of the micro-etching agent, is the energy consumption equivalent coefficient of the micro-etching agent consumption, is the end time of the micro-etching stage. In this stage, the current density and the micro-etching agent concentration Dynamic adjustments are made to achieve optimal energy control in the electroplating process. For example, when the material surface roughness is high (high Ra value), the etching effect is achieved while reducing energy consumption by decreasing the current density and increasing the concentration of the micro-etchant. In the catalytic activation stage, energy consumption mainly consists of the energy consumption of the chemical reaction of the activator and the power consumption of the pulse generator. The constructed energy consumption minimization control equation is:

[0091]

[0092] in, Energy consumption during the catalytic activation stage. It is the concentration of the activator. It is the energy consumption equivalence coefficient of the activator. It is the pulse frequency. It is the power coefficient of the pulse generator. This marks the end time of the catalytic activation stage. In practical applications, when the UV-I value of the recycled plastic material is high, the surface activity of the material is low, requiring an appropriate increase in the activator concentration and a reduction in the pulse frequency to control energy consumption and keep overall energy consumption at a minimum. In the initial deposition stage, this is mainly achieved by adjusting the current waveform. and additive ratio To achieve energy consumption optimization, the energy consumption minimization control equation is:

[0093]

[0094] in, Energy consumption during the initial deposition stage. It is the current density. It's voltage. It is a current waveform. The duty cycle function, It's about the additive ratio. It is the energy consumption equivalence coefficient of the additive. This is the end time of the initial deposition stage. The duty cycle of the current waveform is adjusted accordingly. and additive ratio To ensure coating quality while minimizing excessive additive consumption, for example, when the plasticizer content (PI value) is high, selecting a suitable current waveform reduces energy consumption during the electroplating process. In the final structural control stage, energy consumption is primarily driven by the temperature gradient. and current density The governing equation for minimizing energy consumption is determined to be:

[0095]

[0096] in, This refers to energy consumption during the structural adjustment phase. It's voltage. It is the energy consumption equivalence coefficient of the temperature gradient. This marks the end of the structural control phase. In this phase, energy consumption is minimized during the internal structural control of the coating by dynamically adjusting the temperature gradient and current density. By solving the energy-minimizing control equations for these five phases and applying optimal control methods (such as gradient descent or dynamic programming), the first energy-optimized parameter sequence for each phase is obtained. These parameter sequences effectively address variations in different material properties (such as DI, UV-I, FR, and PI values) and are dynamically adjusted by introducing compensation coefficients, enabling the entire electroplating process to achieve optimal energy consumption control.

[0097] In one specific embodiment, the process of performing step S5 may specifically include the following steps:

[0098] The electrochemical impedance spectroscopy (EIS) device was used to perform frequency sweep measurements on the electroplating process of recycled plastics to obtain a set of electrochemical parameters including interfacial capacitance, charge transfer resistance, Warburg impedance coefficient, and solution resistance.

[0099] The surface temperature distribution map was obtained by scanning the temperature distribution of the electroplated surface of recycled plastic using an infrared thermal imaging system.

[0100] The eddy current thickness gauge was used to measure the electroplated surface of recycled plastic to obtain real-time data on the coating thickness.

[0101] The electrochemical parameter set, surface temperature distribution map, and real-time coating thickness data are compared with the electroplating parameter prediction set to obtain process parameter deviation data, and a deviation vector is constructed based on the process parameter deviation data.

[0102] The Jacobian matrix is ​​updated in real time using an online identification method, and the control parameter correction is calculated based on the deviation vector and the Jacobian matrix to obtain the corrected control parameters for each stage.

[0103] Based on the revised control parameters for each stage, combined with the dynamic adjustment of pulse frequency for local hot spot effects, the auxiliary anode activation for coating non-uniformity, and the local catalyst injection technology for under-activated areas, the second energy consumption optimization parameter sequence for each stage is obtained.

[0104] Specifically, frequency sweep measurements were performed on the electroplating process of recycled plastic using an electrochemical impedance spectroscopy (EIS) measurement device to obtain data including interfacial capacitance. ), charge transfer resistance ( ), Warburg impedance coefficient ( ) and solution resistance ( Electrochemical parameter set In electrochemical impedance spectroscopy (EIS) measurements, an AC voltage within a specific frequency range is applied to the device. , by recording the response of the corresponding alternating current

[0105]

[0106] where, is the angular frequency of the alternating signal. At different frequencies, the real and imaginary parts of the impedance respectively resolve various electrochemical parameters, such as the interfacial capacitance , charge transfer resistance , and Warburg impedance coefficient , which are obtained by fitting the impedance data in the low-frequency region. These parameters can reflect the interfacial reaction rate, ion diffusion ability, and solution conductivity characteristics during the deposition of metal ions on the plastic surface during electroplating. At the same time, an infrared thermal imaging system is used to scan the temperature distribution of the electroplated surface of the recycled plastic, obtaining a surface temperature distribution map , where and represent the two-dimensional coordinates of the electroplated surface, represents the temperature value at that position. The infrared thermal imaging technology converts the infrared radiation intensity of the material surface into temperature information by detecting it, and monitors the temperature changes caused by electrochemical reactions, heating, or current passing in real time during electroplating, which helps to identify whether there are local hot spots (i.e., areas with abnormally high temperatures) on the electroplated surface, because these hot spots usually indicate uneven distribution of electroplating current or changes in material adsorption state, leading to increased energy consumption or decreased plating layer quality. In order to monitor the quality and thickness uniformity of the electroplated layer in real time, an eddy current thickness detector is used to measure the electroplated surface of the recycled plastic, obtaining real-time data of the plating layer thickness . The eddy current detection technology is based on the principle of electromagnetic induction, which generates an alternating magnetic field to induce eddy currents in the metal plating layer, and measures the change in eddy current intensity to calculate the plating layer thickness. The formula for calculating the plating layer thickness is:

[0107] ;

[0108] where, is the calibration coefficient, is the voltage induced at position , and is the frequency of the excitation magnetic field. Through this method, non-contact and rapid measurement of the plating layer thickness during electroplating is achieved, and these data are generated in the form of a dot matrix thickness distribution map, providing feedback information for dynamic regulation of the electroplating process. The obtained set of electrochemical parameters , surface temperature distribution map , and real-time data of the plating layer thickness are combined with the set of predicted values of the electroplating parameters ​​The deviation data of process parameters are obtained by comparison calculation wherein represents the deviation between the actual value and the predicted value of the th process parameter. Based on these deviation data, the deviation vector is constructed:

[0109]

[0110] The deviation vector can quantify the gap between the current process state and the ideal process. In order to realize the automatic correction of process parameters, the Jacobian matrix is updated in real time by online identification method wherein represents the sensitivity of the system energy consumption to the process parameter change, which is defined as:

[0111]

[0112] wherein, is the element in the th row and the th column of the Jacobian matrix, which represents the influence of the th control parameter on the deviation of the th process parameter . By online identification method (such as recursive least squares method), the Jacobian matrix is updated in real time during the electroplating process, so that the system can dynamically adapt to the changes of process state. After obtaining the updated Jacobian matrix, the control parameter correction amount is calculated by matrix operation:

[0113]

[0114] wherein, is the control parameter correction amount, and the negative sign represents eliminating the deviation by adjusting the parameter in the opposite direction. In practical application, in order to ensure that the control parameter correction amount is within the safe range, the saturation function is applied to constrain the correction amount, for example:

[0115]

[0116] wherein, and These represent the maximum and minimum allowable values ​​of the control parameters. This operation prevents the control system from becoming unstable or experiencing a surge in energy consumption due to over-adjustment. Based on the corrected control parameters for each stage, and combined with dynamic control techniques in the specific process, such as dynamic adjustment of pulse frequency to address local hotspot effects, optimization of electric field distribution in areas of uneven coating through auxiliary anode activation, and the use of local catalyst injection technology in areas of insufficient activation, the energy consumption optimization operations for each stage are refined. By incorporating these corrections into the control parameters of each stage, the second energy consumption optimization parameter sequence for each stage is calculated.

[0117] In one specific embodiment, the process of updating the Jacobian matrix in real time using an online identification method and calculating the control parameter correction based on the deviation vector and the Jacobian matrix to obtain the corrected control parameters for each stage can specifically include the following steps:

[0118] Construct a parameter time series matrix and a target deviation matrix based on process parameter deviation data;

[0119] The recursive least squares algorithm is applied to the parameter time series matrix and the target deviation matrix to calculate the weight matrix and obtain the parameter sensitivity matrix;

[0120] Perform singular value decomposition (SVD) on the parameter sensitivity matrix and truncate singular values ​​smaller than the threshold τ to obtain the Jacobian matrix;

[0121] The deviation vector is multiplied by the Jacobian matrix to obtain the unconstrained control parameter correction. The saturation function constraint is then applied to the unconstrained control parameter correction to obtain the constrained control parameter correction.

[0122] The correction amount of the constraint control parameters is added to the first energy consumption optimization parameter sequence according to each stage to obtain the corrected control parameters for each stage.

[0123] Specifically, a parameter time series matrix and a target deviation matrix are constructed based on process parameter deviation data. During the electroplating process, the deviation between the actual and predicted values ​​of process parameters is monitored in real time to obtain a process parameter deviation dataset, reflecting parameter fluctuations during electroplating and revealing the changing trend of system energy consumption. The process of constructing the parameter time series matrix involves arranging historical process parameter data in chronological order to form a matrix. ,in Indicates the first The first time point Each process parameter value. For example, in the micro-etching stage, process parameters include current density, micro-etchant concentration, and voltage; the values ​​of these parameters at different time points constitute a time series matrix. Simultaneously, the target deviation matrix... The deviation values ​​of each process parameter at each time point are recorded, calculated by comparing the actual monitored parameter values ​​with the predicted target values. These data are used to dynamically track process deviations during electroplating. This results in the obtained parameter time series matrix. and target deviation matrix Then, the weight matrix is ​​calculated using a recursive least squares algorithm. The parameter sensitivity matrix is ​​obtained. The recursive least squares algorithm dynamically updates the weight matrix by minimizing the sum of squared prediction errors with each new data arrival, enabling the system to adapt to changes in process conditions in real time. (Weight matrix) Each element in Indicate process parameters For deviation The greater the weight of the parameter, the more sensitive it is to a specific deviation. The iterative update formula using the recursive least squares algorithm is as follows:

[0124]

[0125] in, It is the first The weight matrix of the next iteration. It is the gain matrix. and These are the current target deviation and the parameter time series matrix, respectively. This formula automatically adjusts the weight matrix when new deviation data is input, ensuring the parameter sensitivity matrix remains optimal. (Regarding the parameter sensitivity matrix...) Perform singular value decomposition to decompose the parameter sensitivity matrix into ,in and It is an orthogonal matrix. It is a diagonal matrix, with its diagonal elements being singular values. These singular values ​​represent the characteristic strength of the parameter sensitivity matrix; larger singular values ​​correspond to important parameter dimensions, while smaller singular values ​​represent noise or irrelevant information. To ensure the robustness of the control system, the singular values ​​are truncated after decomposition, with those smaller than a preset threshold being removed. By setting the singular values ​​to zero, we obtain the Jacobian matrix. This process effectively filters out low-impact factors, making the control system's calculations more accurate and its resistance to external disturbances stronger. After obtaining the Jacobian matrix, the deviation vector is then... Jacobian matrix Perform matrix multiplication to calculate the unconstrained control parameter correction. This process is equivalent to calculating the direction and magnitude of adjustment in the parameter space to eliminate the deviation of process parameters as much as possible. Saturation function constraints are applied to the control parameter correction to ensure that the control parameters are always within a safe and controllable range. The saturation function constraint operation is implemented by the following function:

[0126]

[0127] wherein, is the unconstrained control parameter correction, is the constrained correction, and are the maximum and minimum allowed values of the parameter, respectively. The constrained control parameter correction is added to the first energy consumption optimization parameter sequence according to the five stages of the electroplating process, namely pretreatment, microetching, catalytic activation, initial deposition, and structure regulation, to obtain the modified control parameters of each stage. For example, in the pretreatment stage, the minimum energy consumption in the heating and stirring process is achieved by applying the correction to the temperature and stirring speed parameters; in the catalytic activation stage, the activation effect of the material surface is ensured while maintaining the lowest energy consumption by adjusting the activator concentration and pulse frequency. Through this series of dynamic adjustment operations, the system always maintains the optimal state of energy consumption in the complex and variable electroplating process.

[0128] The above describes the low-energy electroplating method based on recycled plastic in the embodiments of the present application. The low-energy electroplating device based on recycled plastic in the embodiments of the present application is described below. Please refer to Figure 2 The low-energy electroplating device based on recycled plastic in the embodiments of the present application includes:

[0129] The acquisition module is used to collect the surface feature parameters of the recycled plastic to obtain an electroplating feature data set.

[0130] The processing module is used to input the electroplating feature data set into a deep neural network for processing to obtain an electroplating parameter prediction value set.

[0131] The analysis module is used to perform energy consumption sensitivity analysis on the electroplating process of the recycled plastic based on the electroplating parameter prediction value set to obtain energy consumption key factors and compensation coefficients of each stage.

[0132] The calculation module is used to calculate the first energy consumption optimization parameter sequence of each stage according to the energy consumption key factors and compensation coefficients.

[0133] The dynamic adjustment module is used to monitor the process parameter deviation data corresponding to the electroplating process of the recycled plastic in real time and dynamically adjust the first energy consumption optimization parameter sequence of each stage to obtain the second energy consumption optimization parameter sequence of each stage.

[0134] Through the synergistic cooperation of the above-mentioned various components, the surface of the recycled plastic is comprehensively analyzed by various sensing devices such as multispectral imaging devices and infrared spectrum analyzers, realizing the accurate quantification of key parameters such as degradation degree index, surface roughness and impurity distribution, providing high-quality data basis for subsequent deep learning models, and significantly improving the accuracy of recycled plastic characteristic identification. The deep neural network containing multi-layer convolution structure and nonlinear segmented activation function can accurately capture the complex relationship between the surface characteristics of recycled plastic and the electroplating parameters, realize accurate prediction of the process parameters of the five electroplating stages, and through the cyclic energy optimization analysis method, the electroplating process is divided into five key stages and the key factors of energy consumption in each stage are identified, the compensation coefficient is designed according to the interference factors in the recycled plastic, the energy consumption control is more targeted, and the total energy consumption of the recycled plastic electroplating can be reduced. The energy minimization control equation of the five stages is constructed, and the key parameters of each stage are fine controlled, solving the problem of unstable quality of recycled plastic electroplating. Through the electrochemical impedance spectroscopy, infrared thermal imaging and coating thickness real-time detection system, a complete parameter feedback mechanism is constructed, realizing dynamic monitoring and parameter adjustment of the electroplating process, effectively dealing with the problems of local hot spot effect and uneven coating.

[0135] Reference Figure 3 In the embodiments of the present application, a computer device is also provided, which can be a server, and the internal structure thereof can be as shown in Figure 3 The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in the embodiments. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement the above method.

[0136] Those skilled in the art can understand Figure 3 that the structure shown in the above description is only a block diagram of part of the structure related to the present application scheme, and does not constitute a limitation on the computer device to which the present application scheme is applied.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-mentioned system, system and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0138] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0139] The above description and the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features. These modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A low energy consumption electroplating method based on recycled plastic, characterized by, The method comprises: Surface feature parameter acquisition is performed on the recycled plastic to obtain an electroplating feature data set, wherein the surface feature parameters include surface reflectance spectrum data, degradation index DI value, surface roughness Ra value, surface polarity distribution map, and surface impurity distribution density; The electroplating feature data set is input into a deep neural network for processing, and an electroplating parameter prediction value set containing a pretreatment stage, a micro-etching stage, a catalytic activation stage, an initial deposition stage, and a structure regulation stage is output, wherein the pretreatment stage includes temperature and stirring speed, the micro-etching stage includes current density and micro-etching agent concentration, the catalytic activation stage includes activator concentration and pulse frequency, the initial deposition stage includes current waveform and additive ratio, and the structure regulation stage includes temperature gradient and current density; Energy consumption sensitivity analysis is performed on the electroplating process of the recycled plastic based on the electroplating parameter prediction value set to obtain energy consumption key factors and compensation coefficients of each stage; First energy consumption optimization parameter sequences of each stage are calculated according to the energy consumption key factors and the compensation coefficients; Process parameter deviation data corresponding to the electroplating process of the recycled plastic are monitored in real time, and the first energy consumption optimization parameter sequences of each stage are dynamically adjusted to obtain second energy consumption optimization parameter sequences of each stage.

2. The low energy consumption electroplating method based on recycled plastic according to claim 1, wherein, The surface feature parameter acquisition on the recycled plastic to obtain the electroplating feature data set comprises: A multispectral imaging device is used to perform surface scanning on the recycled plastic to obtain surface reflectance spectrum data; An infrared spectrum analyzer is used to perform molecular structure detection on the recycled plastic to obtain a degradation index DI value; A surface roughness sensor is used to perform surface line scanning measurement on the recycled plastic to obtain a surface roughness Ra value; A resistivity measuring instrument is used to perform surface point array resistivity measurement on the recycled plastic to obtain a surface polarity distribution map; A fluorescence analyzer is used to perform surface UV excitation imaging on the recycled plastic to obtain a surface impurity distribution density; The surface reflectance spectrum data, the degradation index DI value, the surface roughness Ra value, the surface polarity distribution map, and the surface impurity distribution density are standardized, and are combined to obtain the electroplating feature data set.

3. The low energy consumption electroplating method based on recycled plastic according to claim 1, wherein, The input of the electroplating feature data set into the deep neural network for processing to output the electroplating parameter prediction value set containing the pretreatment stage, the micro-etching stage, the catalytic activation stage, the initial deposition stage, and the structure regulation stage comprises: The electroplating feature data set is converted into an input matrix, which is input into a first convolutional layer of an encoder network in the deep neural network, 3×3 convolutional operation is performed on the input matrix, local features of the recycled plastic surface are extracted, and a first feature map is obtained; The first feature map is input into a second convolutional layer of the encoder network for 5×5 convolutional operation, surface feature correlation is extracted, and a second feature map is obtained; The second feature map is sequentially input into convolutional layers with 7×7, 5×5, 3×3, and 1×1 convolutional kernels, multi-scale features of the recycled plastic surface are extracted, and a latent feature vector is obtained; A nonlinear piecewise activation function is applied to elements in the potential feature vector for different degradation degree intervals to realize adaptive processing of different degradation states of the recycled plastic and obtain an optimized feature vector; The optimized feature vector is input into a corresponding five-stage decoder network in a deep neural network to output a set of electroplating parameter prediction values including pre-processing stage, micro-etching stage, catalytic activation stage, initial deposition stage and structure regulation stage, wherein the pre-processing stage includes temperature and stirring speed, the micro-etching stage includes current density and micro-etching agent concentration, the catalytic activation stage includes activator concentration and pulse frequency, the initial deposition stage includes current waveform and additive ratio, and the structure regulation stage includes temperature gradient and current density.

4. The low energy consumption electroplating method based on recycled plastic according to claim 3, wherein, Energy consumption sensitivity analysis is performed on the electroplating process of the recycled plastic based on the set of electroplating parameter prediction values to obtain energy consumption key factors and compensation coefficients for each stage, including: Based on the set of electroplating parameter prediction values, cyclic energy optimization analysis is performed, and parameter change tests are performed on the temperature and stirring speed of the pre-processing stage, the current density and micro-etching agent concentration of the micro-etching stage, the activator concentration and pulse frequency of the catalytic activation stage, the current waveform and additive ratio of the initial deposition stage, and the temperature gradient and current density of the structure regulation stage. The energy consumption change rates corresponding to each parameter are recorded, and the parameters with energy consumption change rates exceeding a preset target value are determined as energy consumption sensitive parameters to obtain energy consumption key factors for each stage. Feature extraction is performed on the degradation degree index DI value, ultraviolet aging index UV-I value, flame retardant content FR value and plasticizer content PI value in the electroplating feature data set to construct an interference feature vector. Correlation analysis is performed on the interference feature vector and the energy consumption key factors to calculate weight coefficients, and compensation coefficient calculation is performed based on the weight coefficients to obtain compensation coefficients for the energy consumption key factors.

5. The low energy consumption electroplating method based on recycled plastic according to claim 1, wherein, The first energy consumption optimization parameter sequence for each stage is calculated based on the energy consumption key factors and the compensation coefficients, including: Based on the energy consumption key factor and its compensation coefficient in the pretreatment stage, the pretreatment stage energy consumption minimization control equation is constructed Wherein E1 is the pretreatment stage energy consumption, c p is the specific heat capacity, m is the solution mass, T1(t) is the temperature, T0 is the initial temperature, V1(t) is the stirring speed, P1 is the stirring power coefficient, t1 is the pretreatment stage end time; Based on the key factors of energy consumption and its compensation coefficient of micro-etching stage, the control equation of energy consumption minimization of micro-etching stage is constructed Wherein E2 is the energy consumption of micro-etching stage, I2(t) is the current density, U2(t) is the voltage, C2(t) is the concentration of micro-etching agent, λ2 is the energy consumption equivalent coefficient of micro-etching agent consumption, t2 is the end time of micro-etching stage; Based on the key factors of energy consumption and its compensation coefficient in the catalytic activation stage, the energy consumption minimization control equation of the catalytic activation stage is constructed Wherein E3 is the energy consumption of the catalytic activation stage, C3(t) is the activator concentration, λ3 is the energy consumption equivalent coefficient of the activator, F3(t) is the pulse frequency, P3 is the pulse generator power coefficient, and t3 is the end time of the catalytic activation stage. Based on the energy consumption key factor and its compensation coefficient of the initial deposition stage, the energy consumption minimization control equation of the initial deposition stage is constructed Wherein E4 is the energy consumption of the initial deposition stage, I4(t) is the current density, U4(t) is the voltage, D4(W4) is the duty cycle function of the current waveform W4, R4(t) is the additive ratio, λ4 is the energy consumption equivalent coefficient of the additive, and t4 is the end time of the initial deposition stage. Based on the key factors of energy consumption and compensation coefficient in the structure regulation stage, the structure regulation stage energy consumption minimization control equation is constructed Wherein E5 is the energy consumption of the structure regulation stage, I5(t) is the current density, U5(t) is the voltage, G5(t) is the temperature gradient, λ5 is the energy consumption equivalent coefficient of the temperature gradient, and t5 is the end time of the structure regulation stage. The first energy consumption optimization parameter sequence for each stage in the electroplating process of the recycled plastic is obtained by solving the energy consumption minimization control equation for the five stages.

6. The low energy consumption electroplating method based on recycled plastic according to claim 1, wherein, Real-time monitoring of the process parameter deviation data corresponding to the electroplating process of the recycled plastic is performed, and the first energy consumption optimization parameter sequence for each stage is dynamically adjusted to obtain a second energy consumption optimization parameter sequence for each stage, including: Electrochemical impedance spectroscopy measurement device is used to perform sweep frequency measurement on the electroplating process of the recycled plastic to obtain a set of electrochemical parameters including interface capacitance, charge transfer resistance, Warburg impedance coefficient and solution resistance; An infrared thermal imaging system is used to perform temperature distribution scanning on the electroplated surface of the recycled plastic to obtain a surface temperature distribution map; An eddy current thickness detector is used to measure the electroplated surface of the recycled plastic to obtain real-time data of the plating layer thickness; The set of electrochemical parameters, the surface temperature distribution map and the real-time data of the plating layer thickness are compared and calculated with the set of electroplating parameter prediction values to obtain process parameter deviation data, and a deviation vector is constructed based on the process parameter deviation data; The online identification method is used to update the Jacobian matrix in real time, and the control parameter correction amount is calculated based on the deviation vector and the Jacobian matrix, so as to obtain the corrected control parameters of each stage; According to the corrected control parameters of each stage, the pulse frequency dynamic adjustment of the local hot spot effect, the auxiliary anode activation of the coating unevenness, and the local catalyst injection technology of the insufficient activation area are combined to obtain the second energy consumption optimization parameter sequence of each stage.

7. The low energy consumption electroplating method based on recycled plastic according to claim 6, wherein, The online identification method is used to update the Jacobian matrix in real time, and the control parameter correction amount is calculated based on the deviation vector and the Jacobian matrix, so as to obtain the corrected control parameters of each stage, including: Based on the process parameter deviation data, a parameter time sequence matrix and a target deviation matrix are constructed; The recursive least square algorithm is applied to the parameter time sequence matrix and the target deviation matrix to calculate a weight matrix and obtain a parameter sensitivity matrix; The singular value decomposition (SVD) operation is performed on the parameter sensitivity matrix, and the singular values less than a threshold τ are truncated to obtain a Jacobian matrix; The deviation vector and the Jacobian matrix are subjected to matrix multiplication to obtain an unconstrained control parameter correction amount, and a saturation function constraint is applied to the unconstrained control parameter correction amount to obtain a constrained control parameter correction amount; The constrained control parameter correction amount is added to the first energy consumption optimization parameter sequence according to each stage to obtain the corrected control parameters of each stage.

8. A low energy consumption electroplating device based on recycled plastic, characterized by, The low-energy consumption electroplating device based on recycled plastic for performing the low-energy consumption electroplating method based on recycled plastic according to any one of claims 1-7, the low-energy consumption electroplating device based on recycled plastic comprising: A collection module is configured to collect surface feature parameters of the recycled plastic to obtain an electroplating feature data set, wherein the surface feature parameters include surface reflectance spectrum data, degradation index (DI) value, surface roughness (Ra) value, surface polarity distribution map, and surface impurity distribution density. A processing module is configured to input the electroplating feature data set into a deep neural network for processing, and output an electroplating parameter prediction value set including a pretreatment stage, a micro-etching stage, a catalytic activation stage, an initial deposition stage, and a structure control stage, wherein the pretreatment stage includes temperature and stirring speed, the micro-etching stage includes current density and micro-etching agent concentration, the catalytic activation stage includes activator concentration and pulse frequency, the initial deposition stage includes current waveform and additive ratio, and the structure control stage includes temperature gradient and current density. An analysis module is configured to perform energy consumption sensitivity analysis on the electroplating process of the recycled plastic based on the electroplating parameter prediction value set to obtain energy consumption key factors and compensation coefficients of each stage. A calculation module is configured to calculate a first energy consumption optimization parameter sequence of each stage according to the energy consumption key factors and the compensation coefficients. A dynamic adjustment module is configured to monitor process parameter deviation data corresponding to the electroplating process of the recycled plastic in real time, and dynamically adjust the first energy consumption optimization parameter sequence of each stage to obtain a second energy consumption optimization parameter sequence of each stage.

9. A computer device, comprising: The computer program product comprises a memory and a processor, the memory stores a computer program capable of running on the processor, and the processor implements the low-energy-consumption electroplating method based on recycled plastic according to any one of claims 1 to 7 when running the computer program.

Images