An automatic anode dye addition management and monitoring system

Abstract

The present invention discloses an automatic dye addition management and monitoring system for anodes, which relates to the technical field of dye monitoring. Based on the data of the anodic surface oxidation reaction, it analyzes the influence of bubbles on the current, obtains the change in current density, can timely detect the polarization phenomenon and issue a warning signal, thus effectively reducing the coating quality problems caused by electrode polarization and improving the qualified rate of products. The prediction and analysis module constructs a current fluctuation coefficient Dbxs by analyzing the current fluctuation and the surface state of the workpiece, combined with the dynamic changes of the electrolyte solution, and then calculates the consumption rate and predicted concentration of the dye. Through this module, the system can predict the usage of the dye in advance, further avoid excessive or insufficient dye addition, save costs and maintain dyeing uniformity. The dye control module can intelligently judge the consumption of the dye according to the result of the prediction and analysis module and automatically issue a dye replenishment instruction. Through this module, the automation and precise control of dye replenishment are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of dye monitoring, and particularly to an automatic anode dye addition management and monitoring system. Background Art

[0002] The automatic anode dye addition management and monitoring system belongs to the fields of industrial automation and electrochemical surface treatment. Especially in the control and optimization of anodizing and electroplating processes, this field is widely used in industries such as metal processing, surface protection, and decorative treatment, involving the use of electrochemical reactions to form protective or decorative oxide films or coatings on the surfaces of metal workpieces. Anodizing is a commonly used technology for surface treatment of metals (especially aluminum and its alloys), which improves the corrosion resistance, hardness, and appearance of metals by forming an oxide film on the anode surface. During the anodizing process, the addition of dyes is crucial for achieving precise coloring and aesthetic effects.

[0003] In traditional anodizing processes, the anodizing process relies on manual or semi-automatic methods to monitor and manage changes in electrolyte solutions, surface states of workpieces, and dye concentrations. Such methods often have problems such as reaction lag and insufficient control accuracy, resulting in large fluctuations in dye concentrations and difficulty in uniformly controlling the thickness and dyeing effects of coatings or oxide layers. In addition, the generation of bubbles and electrode polarization phenomena are difficult to analyze in real time, and current fluctuations may affect the formation of oxide films and dyeing effects. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides an automatic anode dye addition management and monitoring system, which solves the problems in the above background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: An automatic anode dye addition management and monitoring system includes a data acquisition module, a data processing module, a polarization analysis module, a prediction analysis module, and a dye control module;

[0006] The data acquisition module is used to pre-install several groups of monitoring devices in the anodizing tank, and in real time monitor the dynamic change data of the electrolyte solution in the anodizing tank, the surface state data of related workpieces, and the related oxidation reaction data on the anode surface according to the several groups of monitoring devices;

[0007] The data processing module is used to preprocess the dynamic change data of the electrolyte solution in the anodizing tank, the surface state data of related workpieces, and the related oxidation reaction data on the anode surface, and perform linear normalization processing on the preprocessed data so that the range of the preprocessed data falls within [0,1];

[0008] The polarization analysis module is used to analyze the influence of bubble generation on current during anodic oxidation based on relevant oxidation reaction data on the anode surface, so as to obtain the current density Dmd under different bubble states. Based on the numerical value of the current density Dmd, it preliminarily judges whether the electrode is polarized. If so, it sends out an instruction for analyzing current fluctuation;

[0009] The prediction analysis module is used to, after receiving the instruction for analyzing current fluctuation, combine relevant workpiece surface state data to calculate the plating uniformity factor Gbyz, and combine the dynamic change data of the electrolyte solution in the anodic oxidation tank to construct the current fluctuation coefficient Dbxs. At the same time, according to the fluctuation situation of the current, it obtains the dye consumption rate Rhs(t), and combines with the trained prediction model to estimate the predicted dye concentration value Rghs(t+Δt);

[0010] The dye control module is used to judge whether to send out a dye replenishment instruction according to the predicted dye concentration value Rghs(t+Δt) obtained in the prediction analysis module.

[0011] Preferably, the data acquisition module includes a deployment unit, a first monitoring unit, a second monitoring unit and a third monitoring unit;

[0012] The deployment unit is used to deploy several groups of monitoring devices inside the anodic oxidation tank, and several groups of monitoring devices include a laser profilometer, a 3D scanner, a Hall effect current sensor, an X-ray fluorescence plating thickness gauge, a laser displacement sensor, a temperature sensor and a spectrophotometer;

[0013] The first monitoring unit is used to use the monitoring devices to monitor the dynamic change data of the electrolyte solution in the anodic oxidation tank in real time. The dynamic change data of the electrolyte solution in the anodic oxidation tank includes the electrode offset value Djpz, the dye concentration Rghs, the total surface area Zbmj of the electrode, the temperature Dwd of the electrolyte solution and the total volume Rtj of the electrolyte solution in the anodic oxidation tank at each time period;

[0014] The second monitoring unit is used to use the monitoring devices to monitor the relevant workpiece surface state data in real time. The relevant workpiece surface state data includes the plating thickness Hdz of each part of the workpiece surface, and through a statistical algorithm, it calculates the standard deviation Hdz of the plating thickness σ and the average thickness Hdz of the plating avg ;

[0015] The third monitoring unit is used to use the monitoring devices to monitor the relevant oxidation reaction data on the anode surface in real time. The relevant oxidation reaction data includes the current density Dlz without bubble coverage, the maximum current density Dlz without bubble coverage max and the electrode surface area Dbmj covered by bubbles.

[0016] Preferably, the data processing module includes a preprocessing unit and a normalization unit;

[0017] The preprocessing unit is used to detect and remove outliers and duplicate values in the dynamic change data of the electrolyte solution in the anodizing tank, the surface state data of related workpieces, and the related oxidation reaction data on the anode surface, and fill in the missing data points by interpolation to generate a data set in the tank;

[0018] The normalization unit is used to normalize the information with different dimensions in the data set in the tank so that it is within the same range, and extract features from the information in the data set in the tank.

[0019] Preferably, the polarization analysis module includes a preliminary analysis unit and a judgment unit;

[0020] The preliminary analysis unit is used to analyze the influence of the generation of bubbles on the current during the anodizing process based on the related oxidation reaction data on the anode surface, so as to obtain the current density Dmd under different bubble states. The specific method for obtaining it is as follows:

[0021]

[0022] In the formula, Dlz max represents the maximum current density when there is no bubble coverage, Dbmj represents the electrode surface area covered by bubbles, Zbmj represents the total surface area of the electrode, represents the bubble coverage rate.

[0023] Preferably, the judgment unit is used to preset a density threshold, and by comparing and analyzing the current density Dmd under the corresponding bubble state with the density threshold, to preliminarily judge whether the electrode is polarized. The specific judgment content is as follows:

[0024] If the current density Dmd under the corresponding bubble state exceeds the density threshold, it will be preliminarily judged that the electrode has a polarization risk at this time, and an instruction for current fluctuation analysis will be sent outwards;

[0025] If the current density Dmd under the corresponding bubble state does not exceed the density threshold, it will be preliminarily judged that the electrode has no polarization risk at this time.

[0026] Preferably, the prediction analysis module includes a coating analysis unit, a fluctuation analysis unit and a prediction unit;

[0027] The coating analysis unit is used to calculate the coating uniformity factor Gbyz in combination with the surface state data of related workpieces after receiving the current fluctuation analysis instruction. The specific method for obtaining it is as follows:

[0028]

[0029] In the formula, Hdz σ is the standard deviation of the coating thickness, indicating the degree of fluctuation of the coating thickness; Hdz avg represents the average thickness of the coating.

[0030] Preferably, the fluctuation analysis unit is used to construct a current fluctuation coefficient Dbxs after linear normalization according to the dynamic change data of the electrolyte solution in the anodic oxidation tank and in combination with the coating uniformity factor Gbyz. The current fluctuation coefficient Dbxs is specifically obtained through the following formula:

[0031]

[0032] In the formula, Djpz represents the electrode offset value, Dwd represents the temperature of the electrolyte solution, α and β are both weight values, and the specific values of α and β are set by the user according to the situation. C represents a correction constant.

[0033] Preferably, the prediction unit is used to calculate and obtain the dye consumption rate Rhs(t) according to the fluctuation of the current, and specifically obtain it in the following manner:

[0034]

[0035] In the formula, Dlz(t) represents the current value at the current moment, a1 and a2 are both weight values, DWd(t) represents the temperature value of the current liquid, DWd(t0) represents the standard temperature value, and e represents the Euler number, and the value is approximately 2.71828.

[0036] Preferably, an initial model is constructed using convolutional neural network technology, and the initial model is trained and tested with the information in the data set in the tank, and the trained initial model is used as the state recognition model. The feature information in the state recognition model is respectively obtained, and the obtained feature information is used to train and test the state recognition model. In combination with the current fluctuation analysis instruction sent out by the system, the trained state recognition model is used as the prediction model. The prediction model estimates the predicted dye concentration value Rghs(t+Δt) after training, and specifically obtains it in the following manner:

[0037]

[0038] In the formula, Rghs(t) represents the dye concentration at the current moment, Rhs(t) represents the dye consumption rate, Dbxs represents the current fluctuation coefficient, and Δt represents the time interval.

[0039] Preferably, the dye control module compares the predicted dye concentration value Rghs(t+Δt) obtained from the prediction analysis module with the target concentration range Mnd to determine whether to issue a dye replenishment instruction. The specific content is as follows:

[0040] When the predicted dye concentration value Rghs(t+Δt) falls within the target concentration range Mnd, no dye replenishment instruction will be issued externally at this time;

[0041] When the predicted dye concentration value Rghs(t+Δt) does not fall within the target concentration range Mnd, a dye replenishment instruction will be issued externally at this time. According to the dye replenishment instruction, the dye replenishment pump will be automatically started, and the dye will be injected into the anodic oxidation tank according to the dye replenishment amount Rbz. Among them, the dye replenishment amount Rbz is obtained through the following formula: Rbz = ΔRghs * Rtj; where ΔRghs represents the difference between the predicted dye concentration value and the intermediate value within the target range, and Rtj represents the total volume of the electrolyte solution in the anodic oxidation tank.

[0042] The present invention provides an anode automatic dye addition management and monitoring system, which has the following beneficial effects:

[0043] (1) Through several groups of monitoring devices in the data acquisition module, the dynamic changes of the electrolyte solution, the surface state of the workpiece, and the anodic oxidation reaction on the anode surface are monitored in real time, providing high-precision data support for subsequent analysis. In this way, the key changes during the anodic oxidation process can be grasped in real time, reducing the error of human intervention. Through the polarization analysis module, based on the anodic oxidation reaction data on the anode surface, the influence of bubbles on the current is analyzed to obtain the change in current density, and the polarization phenomenon can be detected in time and a warning signal can be issued. In this way, the coating quality problems caused by electrode polarization can be effectively reduced, and the product qualification rate can be improved. The prediction analysis module analyzes the current fluctuation and the surface state of the workpiece, combines the dynamic changes of the electrolyte solution, constructs the current fluctuation coefficient Dbxs, and then calculates the consumption rate and predicted concentration of the dye. Through this module, the system can predict the dye usage in advance, further avoiding excessive or insufficient dye addition, saving costs and maintaining dyeing uniformity. According to the results of the prediction analysis module, the dye control module can intelligently judge the dye consumption situation and automatically issue a dye replenishment instruction. Through this module, the automation and precise control of dye replenishment are realized, reducing dye waste and uneven dyeing. In short, through the collaborative work of multiple modules, the system further realizes the precise monitoring of the anodic oxidation process and the automatic management of dyes, not only improving production efficiency, reducing human intervention, but also improving the finished product quality and the economic benefits of dye use.

[0044] (2) Through the preliminary analysis unit, the system can analyze the influence of different bubble states on the current based on the relevant oxidation reaction data on the anode surface, especially the influence of bubble coverage on the current density. By calculating the ratio of the bubble-covered surface area to the total surface area of the electrode, the current density under different states can be accurately estimated, providing data support for subsequent judgment of the polarization state of the electrode. The judgment unit sets a threshold for the current density. By comparing the current density under different bubble states with the preset threshold, it can timely judge whether there is a polarization risk on the anode surface, thus realizing the automation and intelligence of polarization detection, further avoiding the deficiency of relying on manual judgment in the traditional method, and improving the control accuracy in the anodic oxidation process.

[0045] (3) The prediction unit analyzes the consumption rate of the dye during the anodic oxidation process by calculating the dye consumption rate. By combining the temperature and current fluctuations with the dye consumption, the system can dynamically adjust the dye addition rate, further avoiding dye waste and ensuring the uniformity and consistency of dyeing. The system uses the convolutional neural network (CNN) technology to build an initial model and trains and tests it using the data set in the anodic oxidation tank. Through the initial model after multiple trainings, the system can effectively extract the key feature information in the process and accurately identify different states in the anodic oxidation process. Combining with the current fluctuation analysis instruction, the system uses the trained initial model as the state recognition model for further optimization prediction. Through the training and testing of the state recognition model, the system can build an accurate prediction model. This prediction model can estimate the predicted concentration of the dye in real time according to the current fluctuation situation and relevant data. Through this intelligent prediction, the system can predict the dye consumption in advance and add the dye in time according to the actual needs. This data-based dye management method makes the entire anodic oxidation and dyeing process more automated and intelligent, and further reduces the necessity of manual intervention. Description of the Drawings

[0046] Figure 1 It is a block diagram of an automatic dye addition management and monitoring system for an anode of the present invention. Detailed Embodiments

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] Embodiment 1

[0049] Please refer to Figure 1, the present invention provides an automatic anode dye addition management and monitoring system, including a data acquisition module, a data processing module, a polarization analysis module, a prediction analysis module, and a dye control module;

[0050] The data acquisition module is used to pre-install several groups of monitoring devices in the anodic oxidation tank, and based on the several groups of monitoring devices, it monitors the dynamic change data of the electrolyte solution in the anodic oxidation tank, the surface state data of related workpieces, and the related oxidation reaction data on the anode surface in real time;

[0051] The data processing module is used to preprocess the dynamic change data of the electrolyte solution in the anodic oxidation tank, the surface state data of related workpieces, and the related oxidation reaction data on the anode surface, and perform linear normalization processing on the preprocessed data to make the range of the preprocessed data fall within [0, 1];

[0052] The polarization analysis module is used to analyze the influence of the generation of bubbles on the current during the anodic oxidation process based on the related oxidation reaction data on the anode surface, so as to obtain the current density Dmd under different bubble states. Based on the value of the current density Dmd, it preliminarily judges whether the electrode is polarized. If so, it sends out a current fluctuation analysis instruction;

[0053] The prediction analysis module is used to, after receiving the current fluctuation analysis instruction, combine the surface state data of related workpieces to calculate the coating uniformity factor Gbyz, combine the dynamic change data of the electrolyte solution in the anodic oxidation tank to construct the current fluctuation coefficient Dbxs, and at the same time, according to the fluctuation situation of the current, obtain the dye consumption rate Rhs(t), and combine with the trained prediction model to estimate the predicted dye concentration value Rghs(t + Δt);

[0054] The dye control module is used to judge whether to issue a dye replenishment instruction according to the predicted dye concentration value Rghs(t + Δt) obtained in the prediction analysis module.

[0055] During the operation of this system, by installing several groups of monitoring devices in the anodic oxidation tank, the system can collect relevant data of the electrolyte solution, workpiece surface, and anode surface in real time. After processing these data, the system can accurately master the electrolyte state, workpiece surface changes, and oxidation reaction dynamics during the anodic oxidation process, ensuring that the process operates under relatively optimal conditions and effectively avoiding the delays and errors caused by manual monitoring. Through the data acquisition module, the system can monitor the dynamic changes of the electrolyte solution in the anodic oxidation tank, the state data of the workpiece surface, and the oxidation reaction data of the anode surface in real time. This multi-level data acquisition ensures the system's comprehensive understanding of the anodic oxidation process, making the monitoring of the entire process more accurate and further avoiding the problem of lag in the reaction to process state changes in traditional systems. The data processing module normalizes all data to a set range through linear normalization, effectively solving the deviation problem caused by different data dimensions. This data preprocessing technology improves the accuracy of the subsequent analysis module and the overall calculation efficiency of the system, ensuring the unity and consistency between different data sources. Through the polarization analysis module, the system can analyze the influence of bubble generation on the current based on the oxidation reaction data of the anode surface and obtain the current density under different bubble states in real time. Through the fluctuation of the current density, the system can quickly determine whether the electrode is polarized. Once a polarization risk occurs, the system will automatically issue a current fluctuation analysis instruction, further avoiding the process instability caused by polarization and helping to adjust the current in a timely manner to ensure the quality of the oxide film. The prediction analysis module analyzes the uniformity of the coating by calculating the coating uniformity factor Gbyz and combining it with the current fluctuation coefficient. In addition, the system can accurately predict the consumption rate of the dye based on the current fluctuation and estimate the future dye concentration through the trained prediction model. This prediction ability further improves the automation level of the system, ensures the maximization of the dye usage efficiency, and reduces the waste of the dye at the same time. The dye control module makes a judgment based on the predicted dye concentration value and intelligently decides whether to issue a dye replenishment instruction. This automated dye management method effectively avoids the situation of untimely or excessive dye replenishment in traditional manual operations, ensures process stability, and improves the consistency of the dyeing effect and production efficiency. In summary, through the integration of functions such as real-time monitoring, data preprocessing, polarization analysis, and intelligent prediction, this system further improves the automated management level of the anodic oxidation process, ensures the uniformity of the coating, the accurate use of the dye, and the current stability, reduces the uncertainties and wastes in the process as much as possible, and thus improves the production efficiency and product quality.

[0056] Example 2

[0057] Please refer to Figure 1 , specifically: The data acquisition module includes a deployment unit, a first monitoring unit, a second monitoring unit, and a third monitoring unit;

[0058] The deployment unit is used to deploy several groups of monitoring devices inside the anodizing tank, and the several groups of monitoring devices include a laser profiler, a three-dimensional scanner, a Hall effect current sensor, an X-ray fluorescence coating thickness gauge, a laser displacement sensor, a temperature sensor, and a spectrophotometer;

[0059] The first monitoring unit is used to use the monitoring devices to monitor the dynamic change data of the electrolyte solution in the anodizing tank in real time. The dynamic change data of the electrolyte solution in the anodizing tank includes the electrode offset value Djpz, the dye concentration Rghs, the total surface area Zbmj of the electrode, the temperature Dwd of the electrolyte solution, and the total volume Rtj of the electrolyte solution in the anodizing tank at each time period;

[0060] The second monitoring unit is used to use the monitoring devices to monitor the surface state data of the relevant workpiece in real time. The surface state data of the relevant workpiece includes the coating thickness Hdz of each part of the workpiece surface, and through statistical algorithms, the standard deviation Hdz of the coating thickness and the average thickness Hdz of the coating are calculated respectively; σ and the average thickness Hdz of the coating; avg ;

[0061] The third monitoring unit is used to use the monitoring devices to monitor the relevant oxidation reaction data on the anode surface in real time. The relevant oxidation reaction data includes the current density Dlz when there is no bubble coverage, the maximum current density Dlz when there is no bubble coverage, and the electrode surface area Dbmj covered by bubbles. max and the electrode surface area Dbmj covered by bubbles.

[0062] The data processing module includes a preprocessing unit and a standardization unit;

[0063] The preprocessing unit is used to detect and remove outliers and duplicate values in the dynamic change data of the electrolyte solution in the anodizing tank, the surface state data of the relevant workpiece, and the relevant oxidation reaction data on the anode surface, and fill in the missing data points by interpolation to generate a data set in the tank. Among them, the filling method of missing values, such as using the average value, interpolation method or regression model to fill in the missing values. Among them, in the data cleaning process, it is often necessary to detect and remove outliers. For example, the Z-score method can be used to detect outliers;

[0064] The standardization unit is used to normalize the information with different dimensions in the data set in the tank so that it is within the same range to prevent the magnitude of some features from being too large or too small from causing deviation to the model. For example, the magnitudes of current and temperature are different, and standardization can make them comparable on the same scale, and feature extraction is performed on the information in the data set in the tank. Feature extraction can capture dynamic features by calculating the change rate of variables.

[0065] In this embodiment, the first, second, and third monitoring units deployed in the data acquisition module monitor data in multiple dimensions such as the dynamic changes of the electrolyte solution, the surface state of the workpiece, and the anodic oxidation reaction in real time. By monitoring key parameters such as the electrode offset value, dye concentration, coating thickness on the workpiece surface, and the bubble coverage on the anode surface in the anodic oxidation tank, it provides a full-range dynamic monitoring of the anodic oxidation process. In particular, the real-time statistics of the standard deviation and average value of the coating thickness help detect the coating uniformity on the workpiece surface, improving the control ability of the final coating quality. The preprocessing unit in the data processing module detects and removes outliers and duplicate values, effectively avoiding the influence of noise data on the system, thereby ensuring the accuracy of the monitoring data. For example, the Z-score method can be used to efficiently identify and process outliers. At the same time, the interpolation method or regression model is used to fill in the missing data points, ensuring the continuity and integrity of the data and providing a complete data set for subsequent data analysis. The standardization unit normalizes data with different dimensions, preventing model bias caused by differences in the magnitude of eigenvalue. This is particularly important. Data with different dimensions such as current density and temperature can be compared on a unified scale, effectively improving the accuracy and performance of the model. In addition, through feature extraction, such as the calculation of the variable change rate, the system can effectively capture the dynamic characteristics under different working conditions in the anodic oxidation process, which helps to understand the changes in the electrolyte solution and the coating on the workpiece surface more deeply, thereby optimizing the dye management strategy. Through data cleaning, normalization, and feature extraction, the system can more accurately predict the dye consumption rate, and then realize the automated and precise management of dye addition. This not only reduces the waste of dyes but also ensures the dyeing uniformity in the anodic oxidation process, further improving the product quality. In summary, through the efficient cooperation of the data acquisition and processing modules, this method further realizes the comprehensive monitoring of the anodic oxidation process, improves the accuracy and consistency of the data, reduces misjudgments caused by abnormal data, significantly optimizes the intelligent management of dye consumption prediction and addition, and improves the production efficiency and quality control ability of the anodic oxidation process.

[0066] Example 3

[0067] Please refer to Figure 1 , specifically: The polarization analysis module includes a preliminary analysis unit and a judgment unit;

[0068] The preliminary analysis unit is used to analyze the influence of bubble generation on the current during the anodic oxidation process based on the relevant oxidation reaction data on the anode surface, so as to obtain the current density Dmd under different bubble states. Specifically, it is obtained in the following way:

[0069]

[0070] In the formula, Dlz maxis expressed as the maximum current density without bubble coverage, Dbmj is expressed as the surface area of the electrode covered by bubbles, and Zbmj is expressed as the total surface area of the electrode. is expressed as the bubble coverage rate.

[0071] The above-mentioned surface area Dbmj of the electrode covered by bubbles can detect the surface profile through a laser profiler and estimate the bubble coverage rate by analyzing the surface changes.

[0072] The total surface area Zbmj of the electrode can scan the surface shape of the electrode through a 3D scanner to obtain the total surface area.

[0073] The current density Dlz can be monitored and calculated by a Hall effect current sensor and a shunt resistor.

[0074] The judgment unit is used to preset a density threshold and perform a comparison and analysis by comparing the current density Dmd in the corresponding bubble state with the density threshold to preliminarily judge whether the electrode is polarized. The specific judgment content is as follows:

[0075] If the current density Dmd in the corresponding bubble state exceeds the density threshold, it will be preliminarily judged that the electrode has a polarization risk at this time, and a current fluctuation analysis instruction will be sent outwards.

[0076] If the current density Dmd in the corresponding bubble state does not exceed the density threshold, it will be preliminarily judged that the electrode has no polarization risk at this time.

[0077] In this embodiment, based on the oxidation reaction data of the anode surface, the preliminary analysis unit of the polarization analysis module uses the bubble coverage condition of the electrode to calculate the current density Dmd under different bubble states through a formula. This analysis method combines the surface area of the electrode covered by bubbles with the total surface area of the electrode, accurately reflecting the influence of bubbles on the current distribution. This precise calculation method can provide reliable basic data for subsequent polarization judgment, helping to reduce the influence of abnormal current fluctuations during anodic oxidation. By comparing the difference between the current density Dmd under different bubble states and the threshold value preset by the judgment unit in real time, the system can dynamically monitor whether the electrode has a polarization risk. When the current density exceeds the set threshold value, the system can timely issue an instruction for current fluctuation analysis. This automatic judgment mechanism further reduces the error and time delay of manual detection, ensuring the real-time and accuracy of the anodic oxidation process. When the current density Dmd exceeds the density threshold value, the system can preliminarily judge that the electrode has a polarization risk and quickly issue a warning signal. Through this mechanism, the occurrence of polarization can be effectively prevented, further avoiding problems such as current instability, uneven coating, or anode damage caused by electrode polarization, thereby improving the service life of the electrode and the product quality during the production process. The judgment unit provides an automatic polarization risk analysis and control function, which can not only judge the polarization state of the electrode according to real-time data but also take corresponding measures in a timely manner. This automatic risk control system reduces the need for manual intervention, ensures the stability and consistency of the anodic oxidation process, and greatly improves the automation level of the process. By combining the change of the current density under different bubble states with the set density threshold value, the system can predict the polarization trend of the electrode in advance. Compared with the traditional manual monitoring method, the system can identify abnormal changes in the current density earlier, helping to take preventive measures before the actual occurrence of polarization risk, thereby reducing production stagnation or product defects caused by polarization and improving the overall production efficiency. In short, this method realizes the precise analysis of the current density and the real-time monitoring of the polarization risk through the preliminary analysis unit and the judgment unit of the polarization analysis module, not only improving the safety and stability of the anodic oxidation process but also reducing production failures caused by polarization phenomena, improving the finished product quality and production efficiency.

[0078] Example 4

[0079] Please refer to Figure 1 , specifically: The prediction analysis module includes a coating analysis unit, a fluctuation analysis unit, and a prediction unit;

[0080] The coating analysis unit is used to calculate the coating uniformity factor Gbyz after receiving the current fluctuation analysis instruction, in combination with relevant workpiece surface state data, and is specifically obtained in the following manner:

[0081]

[0082] In the formula, Hdz σ is the standard deviation of the coating thickness, indicating the degree of fluctuation of the coating thickness; Hdz avg represents the average thickness of the coating.

[0083] The coating thickness Hdz of each part of the workpiece surface mentioned above can be measured by an X-ray fluorescence coating thickness gauge, an eddy current coating thickness gauge, and a laser rangefinder.

[0084] The fluctuation analysis unit is used to construct a current fluctuation coefficient Dbxs after linear normalization according to the dynamic change data of the electrolyte solution in the anodic oxidation tank and in combination with the coating uniformity factor Gbyz. The current fluctuation coefficient Dbxs is specifically obtained through the following formula:

[0085]

[0086] In the formula, Djpz represents the electrode offset value, Dwd represents the temperature of the electrolyte solution, both α and β are weight values, and the specific values of α and β are set by the user according to the situation. C represents a correction constant.

[0087] The above-mentioned electrode offset value Djpz can be monitored by a laser displacement sensor for the displacement or offset state of the electrode during the process;

[0088] The temperature Dwd of the electrolyte solution can be monitored and obtained by a temperature sensor.

[0089] In this embodiment, through the coating analysis unit, the system can calculate the uniformity factor Gbyz of the coating and evaluate the uniformity of the coating by combining the workpiece surface state data after receiving the current fluctuation analysis instruction. Through this formula, the uniformity of the coating can be intuitively evaluated. The fluctuation analysis unit constructs the current fluctuation coefficient Dbxs through linear normalization based on the dynamic change data of the electrolyte solution in the anodic oxidation tank and in combination with the coating uniformity factor Gbyz. Through this formula, the system can accurately reflect the influence of the state of the electrolyte solution on the current fluctuation. This analysis method can not only capture the current fluctuation situation, but also set weights according to the actual working conditions, providing a more personalized and adaptable prediction. By constructing the current fluctuation coefficient Dbxs and combining the coating uniformity factor and the dynamic change data of the electrolyte solution, the system realizes the accurate prediction and control of the current fluctuation. This method not only improves the prediction accuracy of the current fluctuation, but also can adjust the current parameters through advance analysis to avoid the influence of excessive current fluctuation on anodic oxidation and coating uniformity. Through the collaborative work of the coating analysis and fluctuation analysis units in the prediction analysis module, the system can quickly respond and adjust the process parameters when detecting current fluctuations, realizing the automatic control and optimization in the anodic oxidation process, reducing manual intervention, and improving the production stability and efficiency. In short, through the application of the prediction analysis module, this method not only realizes the accurate evaluation of the coating uniformity, but also further optimizes the anodic oxidation process through the prediction and control of the current fluctuation coefficient, improves the quality and production efficiency of the finished product, and provides a flexible and customizable control means for users.

[0090] Example 5

[0091] Please refer to Figure 1 , specifically: The prediction unit is used to calculate and obtain the dye consumption rate Rhs(t) according to the current fluctuation situation, and is specifically obtained in the following manner:

[0092]

[0093] In the formula, Dlz(t) represents the current value at the current moment, both a1 and a2 are weight values, DWd(t) represents the temperature value of the current liquid, DWd(t0) represents the standard temperature value, and e represents the Euler number, with a value of approximately 2.71828.

[0094] The above current value can be monitored and obtained through a current sensor, a shunt resistor, and a current transmitter;

[0095] Construct an initial model using convolutional neural network technology, train and test the initial model with the information in the in-tank data set, and use the trained initial model as the state recognition model. Respectively obtain the feature information in the state recognition model, and use the obtained feature information to train and test the state recognition model. Combine the current fluctuation analysis instruction sent by the system, and use the trained state recognition model as the prediction model. After training, the prediction model estimates the predicted dye concentration value Rghs(t+Δt), which is specifically obtained in the following manner:

[0096]

[0097] In the formula, Rghs(t) represents the dye concentration at the current moment, Rhs(t) represents the dye consumption rate, Dbxs represents the current fluctuation coefficient, and Δt represents the time interval.

[0098] The above-mentioned dye concentration Rghs can be obtained by monitoring with a spectrophotometer and an on-line colorimeter.

[0099] In this embodiment, through the prediction unit, the system calculates the consumption rate of the dye according to the current fluctuation. This formula can accurately capture the influence of current fluctuation and liquid temperature on dye consumption. By setting the weight value, the system can flexibly adjust the influence weights of current and temperature to achieve real-time monitoring of the dye consumption rate, thereby optimizing the dye replenishment decision. The prediction unit uses the convolutional neural network (CNN) technology to build an initial model and trains and tests the model using the information in the in-tank data set. This deep learning technology can capture complex non-linear relationships, effectively identify different state information in the anodic oxidation tank, and improve the system's self-learning ability and prediction accuracy. The feature information of the in-tank data is extracted through the convolutional neural network and used to train and optimize the state recognition model. The optimization of the state recognition model can better capture the influence of current fluctuation and temperature change on dye consumption, providing more accurate feature inputs for the subsequent prediction model. This process maximally improves the system's learning and adaptation ability to enable it to cope with complex process environment changes. The trained state recognition model is used as the prediction model to predict the dye concentration value. Through this formula, the system can dynamically predict the change of the dye concentration. Combining the current fluctuation coefficient and the consumption rate, the system can accurately estimate the dye consumption trend. This real-time prediction ability can help the system predict the dye usage status in advance, avoid the situation of insufficient or excessive dye addition, and ensure the stability of the process. In summary, through the accurate calculation of current fluctuation and dye consumption rate in the prediction unit and combining the deep learning technology of the convolutional neural network, this method realizes the dynamic prediction and management of the dye concentration. The system can adjust the dye replenishment amount in real time, improve the automation and intelligence level of production, further reduce dye waste, and ensure the high efficiency and high quality of the anodic oxidation process.

[0100] Embodiment 6

[0101] Please refer to Figure 1 , specifically: The dye control module compares the predicted dye concentration value Rghs(t + Δt) obtained from the prediction and analysis module with the target concentration range Mnd to determine whether to issue a dye replenishment instruction. The specific content is as follows:

[0102] If the predicted dye concentration value Rghs(t + Δt) falls within the target concentration range Mnd, no dye replenishment instruction will be issued outward at this time;

[0103] When the predicted dye concentration value Rghs(t+Δt) does not fall within the target concentration range Mnd, a dye replenishment instruction will be sent out at this time. According to the dye replenishment instruction, the dye replenishment pump will be automatically started, and the dye will be injected into the anodic oxidation tank according to the dye replenishment amount Rbz. Among them, the dye replenishment amount Rbz is obtained through the following formula: Rbz = ΔRghs * Rtj; where ΔRghs represents the difference between the predicted dye concentration value and the intermediate value within the target range, and Rtj represents the total volume of the electrolyte solution in the anodic oxidation tank; and the system will automatically stop after the replenishment pump reaches the required amount of dye to avoid over-supplementation.

[0104] In this embodiment, by comparing the predicted dye concentration value obtained by the prediction and analysis module with the pre-set target concentration range, the system can accurately judge whether the current dye concentration needs to be adjusted. If the predicted concentration value is within the target range, the system will not issue a dye replenishment instruction, further avoiding unnecessary dye replenishment, reducing dye waste and operation frequency, and effectively improving the efficiency of the system. When the predicted dye concentration value exceeds the target concentration range, the system will automatically issue a dye replenishment instruction and achieve automatic replenishment by starting the dye replenishment pump. The replenishment process is completely controlled by the system, and accurate dye addition can be carried out according to real-time requirements, further reducing the need for manual intervention, while ensuring the continuity and stability of the dyeing process. Through the predicted dye concentration value Rghs(t+Δt), the required dye replenishment amount can be accurately calculated according to the predicted demand, further avoiding over-addition. Through the calculation of the concentration difference, the system can quickly respond to concentration fluctuations, ensure the accuracy and timeliness of dye replenishment, and ensure the consistency of the dyeing effect. During the dye replenishment process, through the real-time control of the replenishment pump, when the replenishment amount reaches the required amount of dye, the system will automatically stop the operation of the replenishment pump to avoid over-injection of dye. This function not only reduces dye waste, but also avoids the possible impact of excessive dye on the anodic oxidation tank and process quality, improving the safety and economic benefits of the entire system. By integrating dye prediction, replenishment instruction, replenishment amount calculation and pump control into the same automated process, the system realizes fully automated dye management. At the same time, the intelligent judgment mechanism of the system can reduce unnecessary replenishment operations, further reducing energy consumption and production costs.

[0105] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An anode automatic dye addition management and monitoring system, characterized in that: It includes data acquisition module, data processing module, polarization analysis module, prediction analysis module and dye control module; The data acquisition module is used to install several groups of monitoring equipment in the anodizing tank in advance, and monitor the dynamic change data of the electrolyte solution in the anodizing tank, the surface state data of the relevant workpiece and the relevant oxidation reaction data of the anode surface in real time according to the several groups of monitoring equipment; The data processing module is used to pre-process the dynamic change data of the electrolyte solution in the anodizing tank, the relevant workpiece surface state data and the relevant oxidation reaction data of the anode surface, and perform linear normalization processing on the pre-processed data so that the pre-processed data range falls within [0,1]; The polarization analysis module is used to analyze the influence of bubble generation on current during the anodic oxidation process based on the relevant oxidation reaction data on the anode surface, so as to obtain the current density Dmd under different bubble states, and preliminarily judge whether the electrode is polarized based on the current density Dmd value, and if so, issue a current fluctuation analysis instruction to the outside; The prediction and analysis module is used to calculate the coating uniformity factor Gbyz in combination with the relevant workpiece surface state data after receiving the current fluctuation analysis instruction, and to construct the current fluctuation coefficient Dbxs in combination with the dynamic change data of the electrolyte solution in the anodizing tank, and to obtain the dye consumption rate Rhs(t) according to the current fluctuation, and to estimate the dye predicted concentration value Rghs(t+Δt) in combination with the trained prediction model; The dye control module is used to determine whether to issue a dye replenishment instruction based on the dye predicted concentration value Rghs(t+Δt) obtained in the prediction analysis module.

2. The anode automatic dye addition management and monitoring system according to claim 1 is characterized by: The data acquisition module includes a deployment unit, a first monitoring unit, a second monitoring unit and a third monitoring unit; The deployment unit is used to deploy several groups of monitoring equipment in the anodizing tank, wherein the several groups of monitoring equipment include a laser profiler, a three-dimensional scanner, a Hall effect current sensor, an X-ray fluorescence coating thickness meter, a laser displacement sensor, a temperature sensor and a spectrophotometer; The first monitoring unit is used to monitor the dynamic change data of the electrolyte solution in the anodizing tank in real time using the monitoring equipment, and the dynamic change data of the electrolyte solution in the anodizing tank includes the electrode offset value Djpz, the dye concentration Rghs, the total surface area Zbmj of the electrode, the temperature Dwd of the electrolyte solution and the total volume Rtj of the electrolyte solution in the anodizing tank in each time period; The second monitoring unit is used to monitor the relevant workpiece surface status data in real time using the monitoring equipment. The relevant workpiece surface status data includes the coating thickness Hdz of each part of the workpiece surface, and calculates the standard deviation Hdz of the coating thickness respectively through a statistical algorithm. σ And the average thickness of the coating Hdz avg ; The third monitoring unit is used to monitor the relevant oxidation reaction data of the anode surface in real time using the monitoring device, and the relevant oxidation reaction data includes the current density Dlz when there is no bubble coverage, the maximum current density Dlz when there is no bubble coverage max And the electrode surface area covered by bubbles Dbmj.

3. The anode automatic dye addition management and monitoring system according to claim 2 is characterized by: The data processing module includes a preprocessing unit and a standardization unit; The pre-processing unit is used to detect and remove abnormal values ​​and duplicate values ​​in the dynamic change data of the electrolyte solution in the anodizing tank, the relevant workpiece surface state data and the relevant oxidation reaction data of the anode surface, and fill the missing data points by interpolation to generate the in-tank data set; The standardization unit is used to normalize information of different dimensions in the in-slot data set to make them within the same range, and to extract features from the information in the in-slot data set.

4. The anode automatic dye addition management and monitoring system according to claim 3 is characterized by: The polarization analysis module includes a preliminary analysis unit and a judgment unit; The preliminary analysis unit is used to analyze the influence of the generation of bubbles on the current during the anodic oxidation process based on the relevant oxidation reaction data on the anode surface, so as to obtain the current density Dmd under different bubble states, which is specifically obtained in the following manner: Where Dlz max It is represented as the maximum current density when there is no bubble coverage, Dbmj is represented as the electrode surface area covered by bubbles, and Zbmj is represented as the total surface area of ​​the electrode. Expressed as bubble coverage.

5. The anode automatic dye addition management and monitoring system according to claim 4 is characterized by: The judgment unit is used to pre-set a density threshold, and compare and analyze the current density Dmd under the corresponding bubble state with the density threshold to preliminarily judge whether the electrode is polarized. The specific judgment content is as follows: If the current density Dmd in the corresponding bubble state exceeds the density threshold, it will be preliminarily judged that the electrode has a polarization risk and issue a current fluctuation analysis instruction; If the current density Dmd under the corresponding bubble state does not exceed the density threshold, it can be preliminarily judged that there is no polarization risk of the electrode.

6. The anode automatic dye addition management and monitoring system according to claim 3 is characterized by: The prediction and analysis module includes a coating analysis unit, a fluctuation analysis unit and a prediction unit; The coating analysis unit is used to calculate the coating uniformity factor Gbyz in combination with relevant workpiece surface state data after receiving the current fluctuation analysis instruction, which is specifically obtained in the following manner: In the formula, Hdz σ Hdz is the standard deviation of the coating thickness, indicating the degree of fluctuation of the coating thickness; avg Expressed as the average thickness of the coating.

7. The anode automatic dye addition management and monitoring system according to claim 6 is characterized by: The fluctuation analysis unit is used to construct a current fluctuation coefficient Dbxs according to the dynamic change data of the electrolyte solution in the anodizing tank and in combination with the coating uniformity factor Gbyz after linear normalization. The current fluctuation coefficient Dbxs is specifically obtained by the following formula: Wherein, Djpz represents the electrode offset value, Dwd represents the temperature of the electrolyte solution, α and β are weight values, and the specific values ​​of α and β are set by the user according to the situation, and C represents the correction constant.

8. The anode automatic dye addition management and monitoring system according to claim 7 is characterized by: The prediction unit is used to calculate and obtain the dye consumption rate Rhs(t) according to the fluctuation of the current, which is specifically obtained in the following manner: Wherein, Dlz(t) represents the current value at the current moment, a1 and a2 are weight values, DWd(t) represents the current temperature value of the liquid, DWd(t0) represents the standard temperature value, and e represents the Euler number, which is approximately 2.71828.

9. The anode automatic dye addition management and monitoring system according to claim 8, characterized in that: The initial model is constructed using convolutional neural network technology, and the initial model is trained and tested with the information in the tank data set. The trained initial model is used as the state recognition model, and the characteristic information in the state recognition model is obtained respectively. The state recognition model is trained and tested with the obtained characteristic information. Combined with the current fluctuation analysis instruction sent out by the system, the trained state recognition model is used as the prediction model. After training, the prediction model estimates the dye prediction concentration value Rghs(t+Δt), which is obtained in the following way: Where Rghs(t) represents the dye concentration at the current moment, Rhs(t) represents the dye consumption rate, Dbxs represents the current fluctuation coefficient, and Δt represents the time interval.

10. The anode automatic dye addition management and monitoring system according to claim 9, characterized in that: The dye control module compares the dye predicted concentration value Rghs(t+Δt) obtained in the prediction and analysis module with the target concentration range Mnd to determine whether to issue a dye replenishment instruction. The specific content is: If the predicted dye concentration value Rghs(t+Δt) falls within the target concentration range Mnd, no dye replenishment instruction will be issued temporarily; If the predicted dye concentration value Rghs(t+Δt) does not fall within the target concentration range Mnd, a dye replenishment instruction will be issued. According to the dye replenishment instruction, the dye replenishment pump will be automatically started to inject the dye into the anodizing tank according to the dye replenishment amount Rbz, wherein the dye replenishment amount Rbz is obtained by the following formula: Rbz=ΔRghs*Rtj; wherein ΔRghs represents the difference between the predicted dye concentration value and the middle value within the target range, and Rtj represents the total volume of the electrolyte solution in the anodizing tank.

Images