Aluminum foil surface quality intelligent control method and system

Abstract

The invention relates to the technical field of capacitors, in particular to an aluminum foil surface quality intelligent control method and system, and the method comprises the following steps: employing a Bayesian network model to recognize the relation between electrode formation characteristics and quality in aluminum foil surface treatment based on continuously input spectral data, and calculating the quality of the aluminum foil according to the model recognition result; and adjusting the ratio and the reaction time of the chemical agents, and optimizing the conductivity control of the aluminum foil to obtain a chemical configuration optimization model. According to the method, by combining real-time spectral data analysis and the Bayesian network model, the chemical agent ratio and the reaction time in the aluminum foil surface treatment process are adjusted in real time, and the electrochemical stability and the capacitance efficiency of the aluminum foil electrode are remarkably improved; compared with the prior art, the method has the remarkable advantages of improving the overall voltage resistance and reliability of the capacitor, high repeatability and uniformity of the treatment process are ensured through continuous monitoring and dynamic adjustment of the forming process of the aluminum foil surface oxide layer, and quality fluctuation in production is greatly reduced.

Description

Technical Field

[0001] This invention relates to the field of capacitor technology, and in particular to an intelligent control method and system for aluminum foil surface quality. Background Technology

[0002] The field of capacitor technology mainly involves the design, manufacture, and optimization of capacitors, a widely used electronic component used to store and release electrical energy. Capacitors play a crucial role in many electronic devices and power systems, including applications such as filtering, energy conversion, and signal coupling and decoupling. This field includes different types of capacitors, such as ceramic capacitors, electrolytic capacitors, and film capacitors, each with its specific materials and manufacturing processes. The performance of capacitors is affected by a variety of factors, including the dielectric material used, electrode materials, structural design, and surface treatment technology. Among these, electrode surface treatment is one of the key technologies for improving capacitor performance, affecting the capacitor's capacitance, withstand voltage, and reliability.

[0003] Among them, the intelligent control method for aluminum foil surface quality is a specific surface engineering technology used to improve the performance of aluminum foil as a capacitor electrode. Aluminum foil is often used as an electrode material for electrolytic capacitors due to its good conductivity and chemical stability. Through surface treatment, an oxide film or other special materials can be formed on the surface of aluminum foil to increase its surface area, improve its corrosion resistance and enhance its electrochemical stability. This treatment not only increases the effective surface area of ​​aluminum foil but also increases its capacitance and improves its performance in high temperature and harsh environments. Therefore, this surface treatment method is crucial for the application of capacitors in fields such as power electronics, automotive electronics and renewable energy.

[0004] Existing technologies cannot respond to changes in production variables in real time, leading to inconsistencies in the performance of electrode materials during the production process. The lack of real-time data analysis and feedback mechanisms makes it difficult to accurately control the surface quality of aluminum foil using traditional methods. In particular, in batch production environments, insufficient control leads to fluctuations in capacitor performance. Traditional surface treatment technologies experience performance degradation in high-temperature and harsh environments, limiting their widespread use in demanding applications such as electric vehicles and solar panels. This not only affects product reliability but also increases production and maintenance costs. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and to propose an intelligent control method and system for aluminum foil surface quality.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent control method for aluminum foil surface quality, comprising the following steps: S1: Based on continuously input spectral data, a Bayesian network model is used to identify the electrode formation characteristics and quality relationship in aluminum foil surface treatment. Based on the model identification results, the ratio of chemical agents and reaction time are adjusted to optimize the conductivity control of aluminum foil and obtain a chemical configuration optimization model. S2: Based on the chemical configuration optimization model, a spectral sensor is used to capture spectral data during the formation of the oxide layer on the aluminum foil surface, monitor and identify processing deviations in real time, optimize chemical reaction conditions, and obtain chemical reaction monitoring parameters. S3: Based on the chemical reaction monitoring parameters, reset the chemical reagent ratio and time, control the aluminum foil surface treatment process, update the reagent addition steps, and maintain the continuity and uniformity of the treatment to obtain the surface treatment consistency index. S4: Based on the surface treatment consistency index, the capacitance characteristics and corrosion resistance of the aluminum foil are detected through automated testing, performance data is collected, and compared with quality standards to verify whether the product meets the capacitor design requirements and obtain a performance quality qualification record.

[0007] The present invention is improved in that the identification step of the relationship between electrode formation characteristics and quality is specifically as follows: S111: Noise filtering is performed based on continuously input spectral data, using the following formula:

[0008] The processed signal data ,in, express Spectral data at time [time] Indicates the attenuation coefficient. The upper limit of integration represents the end point of the time interval for signal processing. The time interval in the integral; S112: Based on the processed signal data, extract key electrode forming signal features using the following formula:

[0009] Generate key signal features ,in, It is the processed signal data. It is the sample size. It is a function that targets the characteristics of electrode formation; S113: Based on the aforementioned key signal features, a Bayesian network model is used to identify the relationship between the features and electrode quality, using the formula:

[0010] Identification results of the relationship between electrode formation characteristics and quality ,in, These are key signal characteristics. It is a feature The corresponding weights It is a non-linear coefficient that adjusts the feature weights. It is the variance of the features. It is a regularization term. It is the total number of key signal features.

[0011] The present invention is improved in that the optimization steps for conductivity control are specifically as follows: S121: Based on the model identification results, evaluate the control effect of the current conductivity, determine the ratio of chemical reagents and reaction time that need to be adjusted, and obtain the adjustment demand signal; S122: Based on the aforementioned adjustment demand signal, calculate the new chemical reagent ratio using the formula:

[0012] Obtaining new chemical reagent ratios ,in, It is an adjustment factor. It is the target ratio. It is the historical bias, representing the difference between past responses and the target. It is the deviation adjustment factor, used to adjust the magnitude of the balance. This is the current chemical reagent ratio; S123: Based on the aforementioned new chemical reagent ratio, the reaction time is adjusted using the following formula:

[0013] Optimized conductivity control configuration obtained ,in, and These are time adjustment parameters, representing the sensitivity and resistance of the adjustment, respectively. It is based on the optimal reaction time derived from simulation. This is the current reaction time.

[0014] The present invention is improved in that the step of capturing the spectral data specifically includes: S211: Based on the aforementioned chemical configuration optimization model, install a spectral sensor on the aluminum foil production line, align it with the oxide zone on the aluminum foil surface, and adjust the distance and angle of the sensor using the formula:

[0015] The sensor position and angle configuration are obtained, where, It is the sensor's monitoring length. It is the distance from the sensor to the surface of the aluminum foil. It is the angle between the sensor and the surface of the aluminum foil. and It is an adjustment factor that regulates the sensor's sensitivity and response range; S212: Based on the monitoring length of the sensor, calibrate the spectral sensor and set a matching data acquisition frequency using the formula:

[0016] Obtain spectral data acquisition parameters ,in, It is the peak value of the sensor response. Indicates the time of data collection. It is the midpoint of the response time. The response rate determines the steepness of the response curve. It is a logarithmic adjustment factor used to optimize the dynamic range of the response; S213: Based on the aforementioned spectral data acquisition parameters, activate the spectral sensor, record the reflectance spectral data, and apply the formula:

[0017] Obtain real-time spectral data recording ,in, It is the initial light intensity. It is the material absorption coefficient. It is the concentration of reactants. It is the modulation frequency. Indicates the noise term. Indicates the time of data collection.

[0018] The present invention is improved in that the step of identifying the processing deviation is specifically as follows: S221: Analyze the acquired spectral data using data processing techniques to identify anomalies or deviations in the spectral modes, using the following formula:

[0019] Obtain the deviation analysis results ,in, Indicates the first 1 spectral data point, It is the average of the data points. It represents the total number of data points; S222: Based on the aforementioned deviation analysis results, a convolutional neural network is used to identify the deviation of the target type, using the following formula:

[0020] Obtain the probability of the severity of the bias ,in, It is a sensitivity parameter. It is the deviation threshold. This is the result of the deviation analysis; S223: Based on the severity probability of the deviation, provide feedback and adjust production line parameters to optimize future deviations, using the formula:

[0021] Obtain the required adjustment amount ,in, and It is a production adjustment factor. It represents the probability of the severity of the deviation.

[0022] The present invention is improved in that the step of obtaining the surface treatment consistency index is specifically as follows: S311: Based on the aforementioned chemical reaction monitoring parameters, collect key monitoring parameters, including pH value, temperature, and reaction rate, and calculate the weighted average of the reaction rates using the formula:

[0023] Preliminary analysis logs were obtained, in which... It is a weighted average reaction rate. It is the first The reaction rate was measured once. These are the corresponding weights, representing the criticality of the measurement moment. It refers to the number of measurements; S312: Based on the preliminary analysis log, adjust the chemical reagent ratios and timing using the following formula:

[0024] and

[0025] Obtain new chemical reagent ratios and time ,in, It adjusts the strength parameter to control the sensitivity of the proportion adjustment. It is the target reaction rate. It is the weighted average reaction rate. It is the original chemical reagent ratio. It is the original time; S313: Execute the new chemical reagent ratio and time, monitor the adjustment effect, and use the following formula:

[0026] Computational efficiency index And maintain the consistency and uniformity of the processing, wherein, It is the target reaction rate. It is the reaction rate measured after adjustment.

[0027] The present invention is improved in that the detection steps for capacitance characteristics and corrosion resistance are specifically as follows: S411: Based on the surface treatment consistency index, the capacitance characteristics of the aluminum foil are measured using an LCR meter, employing the formula:

[0028] Obtain capacitance characteristic data ,in, It is the dielectric constant, which represents the material's ability to respond to an electric field. The area between the capacitor plates affects the capacitance. It is the distance between the boards; S412: Salt spray testing is performed on aluminum foil to simulate a corrosive environment, using the formula:

[0029] Obtain corrosion resistance data ,in, It is a change in quality. It is the area between the capacitor plates. It is the exposure time. It is a material property coefficient, representing the material's sensitivity to corrosion rate. It is the baseline offset, used to adjust for the effects of errors or environmental changes.

[0030] The present invention is improved in that the step of comparing with the quality standard is specifically as follows: S421: Standardize the collected performance data using the following formula:

[0031] Obtain the normalized dataset ,in, These are the original test data. It is the minimum value in the dataset. It is the maximum value in the dataset. It is a constant; S422: Based on the normalized dataset, compare it with the quality standard using the formula:

[0032] in, It is a normalized dataset. This corresponds to the quality standard value. These are coefficients used to adjust the sensitivity of the comparison. This represents the probability value of whether the data meets the standard.

[0033] An intelligent control system for aluminum foil surface quality, the system comprising: The spectral data analysis module analyzes the electrode formation characteristics and quality relationship in aluminum foil surface treatment based on continuously input spectral data, adjusts the ratio of chemical agents and reaction time, and optimizes the conductivity control parameters using a Bayesian network model to obtain a chemical configuration optimization model. Based on the chemical configuration optimization model, the chemical configuration optimization module uses a spectral sensor to capture spectral data during the formation of the oxide layer on the aluminum foil surface, monitors the chemical reaction conditions, and obtains chemical reaction monitoring parameters. Based on the chemical reaction monitoring parameters, the chemical reaction monitoring module resets the chemical reagent ratio and time, controls the aluminum foil surface treatment process, updates the reagent addition steps, maintains the continuity and uniformity of the treatment, and obtains the surface treatment consistency index. Based on the surface treatment consistency index, the chemical control module uses automated testing to detect the capacitance characteristics and corrosion resistance of the aluminum foil, collects performance data, and obtains performance evaluation results. Based on the performance evaluation results, the quality verification module collects performance data of the aluminum foil after surface treatment, verifies the capacitance characteristics and corrosion resistance standards of the aluminum foil, determines product quality, and generates a performance quality qualification record.

[0034] Compared with the prior art, the advantages and positive effects of the present invention are as follows: In this invention, by combining real-time spectral data analysis and Bayesian network models, the chemical reagent ratio and reaction time in the aluminum foil surface treatment process can be adjusted in real time, significantly improving the electrochemical stability and capacitance efficiency of the aluminum foil electrodes. In particular, it has significant advantages in improving the overall withstand voltage performance and reliability of capacitors. Through continuous monitoring and dynamic adjustment of the aluminum foil surface oxide layer formation process, the high repeatability and uniformity of the processing process are ensured, greatly reducing quality fluctuations in production. Automated testing and data collection functions further ensure full-process monitoring from production to quality control, effectively reducing errors and improving production efficiency and product consistency. Attached Figure Description

[0035] Figure 1 The present invention provides a flowchart of an intelligent control method for aluminum foil surface quality; Figure 2 This invention proposes a flowchart for identifying the relationship between electrode formation characteristics and quality in an intelligent control method for aluminum foil surface quality. Figure 3 An optimized flowchart for conductivity control in an intelligent control method for aluminum foil surface quality is proposed in this invention. Figure 4 This invention provides a flowchart for capturing spectral data in an intelligent control method for aluminum foil surface quality. Figure 5 This invention proposes a flowchart for identifying deviations in an intelligent control method for aluminum foil surface quality. Figure 6 This invention provides a flowchart for obtaining surface treatment consistency indicators in an intelligent control method for aluminum foil surface quality. Figure 7 This invention provides a flowchart for the detection of capacitance characteristics and corrosion resistance in an intelligent control method for aluminum foil surface quality. Figure 8 This invention provides a flowchart for comparing the surface quality of aluminum foil with a quality standard in an intelligent control method for aluminum foil surface quality. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0037] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0038] Example 1: Please refer to Figure 1 This invention provides a technical solution: an intelligent control method for aluminum foil surface quality, comprising the following steps: S1: Based on continuously input spectral data, a Bayesian network model is used to identify the electrode formation characteristics and quality relationship in aluminum foil surface treatment. Based on the model identification results, the ratio of chemical agents and reaction time are adjusted to optimize the conductivity control of aluminum foil and obtain a chemical configuration optimization model. S2: Based on the chemical configuration optimization model, a spectral sensor is used to capture spectral data during the formation of the oxide layer on the aluminum foil surface, monitor and identify processing deviations in real time, optimize chemical reaction conditions, and obtain chemical reaction monitoring parameters. S3: Based on chemical reaction monitoring parameters, the ratio and time of chemical agents are reset to control the aluminum foil surface treatment process, update the agent addition steps, and maintain the continuity and uniformity of the treatment to obtain surface treatment consistency indicators. S4: Based on the surface treatment consistency index, the capacitance characteristics and corrosion resistance of aluminum foil are detected through automated testing. Performance data is collected and compared with quality standards to verify whether the product meets the capacitor design requirements and obtain a performance quality qualification record.

[0039] The chemical configuration optimization model includes reagent ratio information, time adjustment sensitivity, and quality control indicators. Chemical reaction monitoring parameters include spectral deviation threshold, real-time monitoring frequency, and abnormal handling indicators. Surface treatment consistency indicators include surface smoothness information, process repeatability, and quality consistency rating. Performance quality qualification records include capacitance efficiency measurement, corrosion resistance level, and qualification standard matching degree.

[0040] Please see Figure 2 The specific steps for identifying the relationship between electrode formation characteristics and quality are as follows: S111: Noise filtering is performed based on continuously input spectral data, using the following formula:

[0041] The processed signal data ,in, express Spectral data at time [time] Indicates the attenuation coefficient. The upper limit of integration represents the end point of the time interval for signal processing. For the infinitesimal time interval in the integral; S112: Based on the processed signal data, extract key electrode-forming signal features using the following formula:

[0042] Generate key signal features ,in, It is the processed signal data. It is the sample size. It is a function that targets the characteristics of electrode formation; S113: Based on key signal features, a Bayesian network model is used to identify the relationship between features and electrode quality, using the formula:

[0043] Identification results of the relationship between electrode formation characteristics and quality ,in, These are key signal characteristics. It is a feature The corresponding weights It is a non-linear coefficient that adjusts the feature weights. It is the variance of the features. It is a regularization term to avoid the denominator being zero. It is the total number of key signal features.

[0044] Assumption (Spectral intensity is 10 units). , Second.

[0045] calculate :

[0046] Calculate the integral (using the basic integration rule):

[0047] Assumption ,but:

[0048] The value 39.4 represents the total signal strength after attenuation.

[0049] Assumption , (The simplified characteristic function is time t). .

[0050] calculate :

[0051]

[0052]

[0053] The value 118.2 represents the sum of the weighted signal characteristics.

[0054] Assumption , , , , , .

[0055] calculate :

[0056] Calculate the denominator:

[0057] Then:

[0058] A value of 345.67 indicates the identification result of the relationship between electrode formation characteristics and quality; the higher the value, the better the quality.

[0059] Please see Figure 3 The optimization steps for conductivity control are as follows: S121: Based on the model identification results, evaluate the control effect of the current conductivity, determine the ratio of chemical reagents and reaction time that need to be adjusted, and obtain the adjustment demand signal; S122: Based on the adjusted demand signal, calculate the new chemical reagent ratio using the following formula:

[0060] Obtaining new chemical reagent ratios ,in, It is an adjustment factor. It is the target ratio. It is the historical bias, representing the difference between past responses and the target. It is the deviation adjustment factor, used to adjust the magnitude of the balance. This is the current chemical reagent ratio; S123: Based on the new chemical reagent ratio, the reaction time is adjusted using the following formula:

[0061] Optimized conductivity control configuration obtained ,in, and These are time adjustment parameters, representing the sensitivity and resistance of the adjustment, respectively. It is based on the optimal reaction time derived from simulation. This is the current reaction time.

[0062] Suppose we have the following data: ; ; ; ; .

[0063] Calculation process: calculate ; Calculate the deviation ratio ; Final calculation .

[0064] Calculations show that, in order to get closer to the target ratio, the current ratio of chemical reagents needs to be increased by 0.25 units.

[0065] Suppose we have the following data: ; ; Set to 120 minutes; Set to 100 minutes.

[0066] Calculation process: Calculate the time difference minute; Calculation time adjustment ratio ; Final calculation minute.

[0067] Calculations show that the reaction time needs to be increased by 8 minutes to achieve optimal reaction conditions.

[0068] Please see Figure 4 The specific steps for capturing spectral data are as follows: S211: Based on a chemical configuration optimization model, a spectral sensor is installed on the aluminum foil production line, aligned with the oxide zone on the aluminum foil surface, and the distance and angle of the sensor are adjusted using the following formula:

[0069] The sensor position and angle configuration are obtained, where, It is the sensor's monitoring length. It is the distance from the sensor to the surface of the aluminum foil. It is the angle between the sensor and the surface of the aluminum foil. and It is an adjustment factor that regulates the sensor's sensitivity and response range; S212: Based on the sensor's monitoring length, calibrate the spectral sensor and set a matching data acquisition frequency using the formula:

[0070] Obtain spectral data acquisition parameters ,in, It is the peak value of the sensor response. Indicates the time of data collection. It is the midpoint of the response time, specifying the time point at the center of the response curve. The response rate determines the steepness of the response curve. It is a logarithmic adjustment factor used to optimize the dynamic range of the response; S213: Based on the spectral data acquisition parameters, activate the spectral sensor, record the reflectance spectral data, and apply the formula:

[0071] Obtain real-time spectral data recording ,in, It is the initial light intensity. It is the material absorption coefficient. It is the concentration of reactants. It is the modulation frequency. Indicates the noise term. Indicates the time of data collection.

[0072] Suppose we have the following data: Assume it is 2 meters; Assuming it's 45°; ; .

[0073] Calculation process: calculate Let be the tangent of the angle between the aluminum foil surfaces, assuming ,but ; calculate ; final rice.

[0074] The results indicate that the effective monitoring length of the sensor is 2.2 meters, taking into account the basic geometry and fine-tuning factors.

[0075] Suppose we have the following data: Assume it is 100; t = 5 seconds; Assume it's 3 seconds; It takes 1 second; Let's assume it's 0.5.

[0076] Calculation process: calculate ; Calculate the denominator ; calculate ; final .

[0077] The results reflect the response of the spectral sensor over a given time period, including the basic response and the enhanced response adjusted by the logarithmic term.

[0078] Suppose we have the following data: It is 500; It is 0.05; Assuming over time Changes in seconds ; Assuming rad / s; Assume the random value is within the range of 5 units.

[0079] Calculation process: calculate ; calculate (because (It is a periodic point of the sine function). final .

[0080] The calculations show that the light intensity at a specific time point is mainly controlled by the noise term, because the periodicity of the sine function causes the main signal to be zero.

[0081] Please see Figure 5 The specific steps for identifying and handling deviations are as follows: S221: Analyze the acquired spectral data using data processing techniques to identify anomalies or deviations in the spectral modes, using the following formula:

[0082] Obtain the deviation analysis results ,in, Indicates the first 1 spectral data point, It is the average of the data points. It represents the total number of data points; S222: Based on the deviation analysis results, a convolutional neural network is used to identify the deviation of the target type, using the following formula:

[0083] Obtain the probability of the severity of the bias ,in, It is a sensitivity parameter. It is the deviation threshold. This is the result of the deviation analysis; S223: Based on the probability of deviation severity, provide feedback and adjust production line parameters to optimize future deviations, using the formula:

[0084] Obtain the required adjustment amount ,in, and It is a production adjustment factor. It represents the probability of the severity of the deviation.

[0085] Suppose we have the following data: Spectral data points ; for:

[0086] .

[0087] Calculation process: Calculate the square of the difference between each data point and the mean:

[0088]

[0089]

[0090]

[0091]

[0092] Sum of logarithms:

[0093] Calculate the square root:

[0094] The standard deviation of the data quantifies the dispersion of the spectral data and is approximately 3.16.

[0095] Suppose we have the following data: ; ; .

[0096] Calculation process: calculate ; Calculation of the index:

[0097] Calculate the probability:

[0098] This indicates that the probability of discovering this bias is approximately 53.4%, suggesting a high likelihood of a significant bias.

[0099] Assume the following: It is 5; =1; .

[0100] Calculation process: Calculation ratio:

[0101] Calculate the adjustment amount:

[0102] This indicates the required adjustment amount, used to adjust the production line to reduce future deviations; the adjustment amount is 6.73.

[0103] Please see Figure 6 The specific steps for obtaining the surface treatment consistency index are as follows: S311: Based on chemical reaction monitoring parameters, key monitoring parameters are collected, including pH value, temperature, and reaction rate. A weighted average of the reaction rates is calculated using the formula:

[0104] Preliminary analysis logs were obtained, in which... It is a weighted average reaction rate. It is the first The reaction rate was measured once. These are the corresponding weights, representing the criticality of the measurement moment. It refers to the number of measurements; S312: Based on the preliminary analysis log, adjust the chemical reagent ratios and timing, using the following formula:

[0105] and

[0106] Obtain new chemical reagent ratios and time ,in, It adjusts the strength parameter to control the sensitivity of the proportion adjustment. It is the target reaction rate. It is the weighted average reaction rate. It is the original chemical reagent ratio. It is the original time; S313: Implement the new chemical reagent ratios and timing, monitor the adjustment effects, and use the following formula:

[0107] Computational efficiency index And maintain the consistency and uniformity of the processing, wherein, It is the target reaction rate. It is the reaction rate measured after adjustment.

[0108] Assuming there are 3 measurements, the reaction rate The weights are 2, 4, and 6 respectively. They are 1, 2, and 3 respectively.

[0109] Then the weighted average reaction rate The calculation is as follows:

[0110] This indicates that, taking into account the importance of measurement, the average reaction rate is 4.67.

[0111] Suppose we have the following data: 100ml; For 60 minutes; It is 5; It is 4.67; It is 0.5.

[0112] Calculation process:

[0113]

[0114] This indicates that in order to achieve the target reaction rate, the reagent ratio should be slightly reduced to 98.5 ml, and the time adjusted to 58 minutes.

[0115] Assuming the actual measured reaction rate after adjustment The value is 4.9, calculated as follows:

[0116] This indicates that the adjusted actual efficiency is close to the target efficiency, reaching 98%.

[0117] Please see Figure 7 The specific testing steps for capacitance characteristics and corrosion resistance are as follows: S411: Based on the surface treatment consistency index, the capacitance characteristics of the aluminum foil are measured using an LCR meter, employing the formula:

[0118] Obtain capacitance characteristic data ,in, It is the dielectric constant, which represents the material's ability to respond to an electric field. The area between the capacitor plates affects the capacitance. It refers to the distance between the boards; reducing the distance can increase the capacitance value. S412: Salt spray testing is performed on aluminum foil to simulate a corrosive environment, using the formula:

[0119] Obtain corrosion resistance data ,in, It is a change in quality. It is the area between the capacitor plates. It is the exposure time. It is a material property coefficient, representing the material's sensitivity to corrosion rate. It is the baseline offset, used to adjust for the effects of errors or environmental changes.

[0120] Assume the following: Assume the dielectric constant of the aluminum foil is F / m (value in vacuum); Size is ; Assume the distance is .

[0121] Calculation process: Assuming the above parameter values ​​are used, The calculation is as follows:

[0122] This indicates that, under given conditions, the capacitance of the aluminum foil is 88.5pF.

[0123] Assume the following: Assume it is 0.05 day; Assume it is 0.001 day; Assume the mass change before and after corrosion is 0.02g; Assuming ; Let's assume it's 1 day.

[0124] Using the above parameters, the corrosion rate is calculated as follows:

[0125] This means that under given conditions, the corrosion rate of the material is 0.101 g / L. / day.

[0126] Please see Figure 8 The specific steps for comparing with the quality standard are as follows: S421: Standardize the collected performance data using the following formula:

[0127] Obtain the normalized dataset ,in, These are the original test data. It is the minimum value in the dataset. It is the maximum value in the dataset. It is a constant, ensuring that the denominator is not zero; S422: Based on a normalized dataset, compare with quality standards using the following formula:

[0128] in, It is a normalized dataset. This corresponds to the quality standard value. These are coefficients used to adjust the sensitivity of the comparison. This represents the probability value of whether the data meets the standard.

[0129] Assume the data is as follows: ; ; ; Set as .

[0130] Calculate the minimum and maximum values:

[0131] for The normalization result is:

[0132] Assume the data is as follows: The quality standard value is assumed to be 0.3 (representing the pass / fail standard for capacitance and corrosion resistance). Assumption .

[0133] Calculation process: use

[0134] Application of the comparison formula:

[0135] This indicates that there is a 58.2% probability that the capacitor characteristics and corrosion resistance meet the quality standards.

[0136] An intelligent control system for aluminum foil surface quality, the system comprising: The spectral data analysis module analyzes the electrode formation characteristics and quality relationship in aluminum foil surface treatment based on continuously input spectral data, adjusts the ratio of chemical agents and reaction time, and optimizes the conductivity control parameters using a Bayesian network model to obtain a chemical configuration optimization model. The chemical configuration optimization module is based on a chemical configuration optimization model. It uses a spectral sensor to capture spectral data during the formation of the oxide layer on the aluminum foil surface, monitors the chemical reaction conditions, and obtains chemical reaction monitoring parameters. Based on the chemical reaction monitoring parameters, the chemical reaction monitoring module resets the chemical reagent ratio and time, controls the aluminum foil surface treatment process, updates the reagent addition steps, maintains the continuity and uniformity of the treatment, and obtains the surface treatment consistency index. Based on the surface treatment consistency index, the chemical control module uses automated testing to detect the capacitance characteristics and corrosion resistance of aluminum foil, collect performance data, and obtain performance evaluation results. Based on the performance evaluation results, the quality verification module collects performance data of aluminum foil after surface treatment, verifies the capacitance characteristics and corrosion resistance standards of the aluminum foil, determines product quality, and generates performance quality qualification records.

[0137] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for intelligent control of aluminum foil surface quality, characterized in that, Includes the following steps: Based on continuously input spectral data, a Bayesian network model is used to identify the relationship between electrode formation characteristics and quality in aluminum foil surface treatment. Based on the model identification results, the ratio of chemical agents and reaction time are adjusted to optimize the conductivity control of aluminum foil, thus obtaining a chemical configuration optimization model. Based on the chemical configuration optimization model, a spectral sensor is used to capture spectral data during the formation of the oxide layer on the aluminum foil surface, monitor and identify processing deviations in real time, optimize chemical reaction conditions, and obtain chemical reaction monitoring parameters. Based on the chemical reaction monitoring parameters, the ratio and time of the chemical agents are reset, the aluminum foil surface treatment process is controlled, the agent addition steps are updated, and the continuity and uniformity of the treatment are maintained to obtain the surface treatment consistency index. Based on the surface treatment consistency index, the capacitance characteristics and corrosion resistance of the aluminum foil are detected through automated testing. Performance data is collected and compared with quality standards to verify whether the product meets the capacitor design requirements and obtain a performance quality qualification record.

2. The intelligent control method for aluminum foil surface quality according to claim 1, characterized in that, The specific steps for identifying the relationship between electrode formation characteristics and quality are as follows: Noise filtering is performed based on continuously input spectral data, using the following formula: ； The processed signal data ,in, express Spectral data at time [time] Indicates the attenuation coefficient. The upper limit of integration represents the end point of the time interval for signal processing. The time interval in the integral; Based on the processed signal data, key electrode formation signal features are extracted using the following formula: ； Generate key signal features ,in, It is the processed signal data. It is the sample size. It is a function that targets the characteristics of electrode formation; Based on the aforementioned key signal features, a Bayesian network model is used to identify the relationship between the features and electrode quality, using the formula: ； Identification results of the relationship between electrode formation characteristics and quality ,in, These are key signal characteristics. It is a feature The corresponding weights It is a non-linear coefficient that adjusts the feature weights. It is the variance of the features. It is a regularization term. It is the total number of key signal features.

3. The intelligent control method for aluminum foil surface quality according to claim 1, characterized in that, The optimization steps for conductivity control are as follows: Based on the model identification results, the control effect of the current conductivity is evaluated, the ratio of chemical reagents and reaction time that need to be adjusted are determined, and the adjustment demand signal is obtained. Based on the aforementioned adjustment demand signal, the new chemical reagent ratio is calculated using the following formula: ； Obtaining new chemical reagent ratios ,in, It is an adjustment factor. It is the target ratio. It is the historical bias, representing the difference between past responses and the target. It is the deviation adjustment factor, used to adjust the magnitude of the balance. This is the current chemical reagent ratio; Based on the new chemical reagent ratio, the reaction time is adjusted using the following formula: ； Optimized conductivity control configuration obtained ,in, and These are time adjustment parameters, representing the sensitivity and resistance of the adjustment, respectively. It is based on the optimal reaction time derived from simulation. This is the current reaction time.

4. The intelligent control method for aluminum foil surface quality according to claim 1, characterized in that, The specific steps for capturing the spectral data are as follows: Based on the aforementioned chemical configuration optimization model, a spectral sensor is installed on the aluminum foil production line, aligned with the oxide zone on the aluminum foil surface, and the distance and angle of the sensor are adjusted using the formula: ； The sensor position and angle configuration are obtained, where, It is the sensor's monitoring length. It is the distance from the sensor to the surface of the aluminum foil. It is the angle between the sensor and the surface of the aluminum foil. and It is an adjustment factor that regulates the sensor's sensitivity and response range; Based on the monitoring length of the sensor, the spectral sensor is calibrated, and a matching data acquisition frequency is set using the formula: ； Obtain spectral data acquisition parameters ,in, It is the peak value of the sensor response. Indicates the time of data collection. It is the midpoint of the response time. The response rate determines the steepness of the response curve. It is a logarithmic adjustment factor used to optimize the dynamic range of the response; Based on the aforementioned spectral data acquisition parameters, the spectral sensor is activated, reflectance spectral data is recorded, and the formula is applied: ； Obtain real-time spectral data recording ,in, It is the initial light intensity. It is the material absorption coefficient. It is the concentration of reactants. It is the modulation frequency. Indicates the noise term. Indicates the time of data collection.

5. The intelligent control method for aluminum foil surface quality according to claim 1, characterized in that, The specific steps for identifying the processing deviation are as follows: The collected spectral data is analyzed using data processing techniques to identify anomalies or deviations in the spectral modes, using the following formula: ； Obtain the deviation analysis results ,in, Indicates the first 1 spectral data point, It is the average value of the data points. It is the total number of data points; Based on the deviation analysis results, a convolutional neural network is used to identify the deviation of the target type, using the following formula: ； Obtain the probability of the severity of the bias ,in, It is a sensitivity parameter. It is the deviation threshold. This is the result of the deviation analysis; Based on the severity probability of the deviation, feedback is provided and production line parameters are adjusted to optimize future deviations, using the formula: ； Obtain the required adjustment amount ,in, and It is a production adjustment factor. It represents the probability of the severity of the deviation.

6. The intelligent control method for aluminum foil surface quality according to claim 1, characterized in that, The specific steps for obtaining the surface treatment consistency index are as follows: Based on the aforementioned chemical reaction monitoring parameters, key monitoring parameters, including pH value, temperature, and reaction rate, are collected. A weighted average of the reaction rates is calculated using the formula: ； Preliminary analysis logs were obtained, in which... It is a weighted average reaction rate. It is the first The reaction rate was measured once. These are the corresponding weights, representing the criticality of the measurement moment. It refers to the number of measurements; Based on the preliminary analysis log, adjust the chemical reagent ratios and timing, using the following formula: ； and ； Obtain new chemical reagent ratios and time ,in, It adjusts the strength parameter to control the sensitivity of the proportion adjustment. It is the target reaction rate. It is the weighted average reaction rate. It is the original chemical reagent ratio. It is the original time; Implement the new chemical reagent ratios and timings, monitor and adjust the effects, using the following formula: ； Computational efficiency index And maintain the consistency and uniformity of the processing, wherein, It is the target reaction rate. It is the reaction rate measured after adjustment.

7. The intelligent control method for aluminum foil surface quality according to claim 1, characterized in that, The specific steps for testing the capacitance characteristics and corrosion resistance are as follows: Based on the surface treatment consistency index, the capacitance characteristics of the aluminum foil were measured using an LCR meter, employing the formula: ； Obtain capacitance characteristic data ,in, It is the dielectric constant, which represents the material's ability to respond to an electric field. The area between the capacitor plates affects the capacitance. It is the distance between the boards; Salt spray testing was performed on the aluminum foil to simulate a corrosive environment, using the formula: ； Obtain corrosion resistance data ,in, It is a change in quality. It is the area between the capacitor plates. It is the exposure time. It is a material property coefficient, representing the material's sensitivity to corrosion rate. It is the baseline offset, used to adjust for the effects of errors or environmental changes.

8. The intelligent control method for aluminum foil surface quality according to claim 1, characterized in that, The specific steps for comparing with the quality standard are as follows: The collected performance data is standardized using the following formula: ； Obtain the normalized dataset ,in, These are the original test data. It is the minimum value in the dataset. It is the maximum value in the dataset. It is a constant; Based on the normalized dataset, a comparison is made with the quality standard using the following formula: ； in, It is a normalized dataset. This corresponds to the quality standard value. These are coefficients used to adjust the sensitivity of the comparison. This represents the probability value of whether the data meets the standard.

9. An intelligent control system for aluminum foil surface quality, characterized in that, The system, which executes the intelligent control method for aluminum foil surface quality according to any one of claims 1-8, comprises: The spectral data analysis module analyzes the electrode formation characteristics and quality relationship in aluminum foil surface treatment based on continuously input spectral data, adjusts the ratio of chemical agents and reaction time, and optimizes the conductivity control parameters using a Bayesian network model to obtain a chemical configuration optimization model. Based on the chemical configuration optimization model, the chemical configuration optimization module uses a spectral sensor to capture spectral data during the formation of the oxide layer on the aluminum foil surface, monitors the chemical reaction conditions, and obtains chemical reaction monitoring parameters. Based on the chemical reaction monitoring parameters, the chemical reaction monitoring module resets the chemical reagent ratio and time, controls the aluminum foil surface treatment process, updates the reagent addition steps, maintains the continuity and uniformity of the treatment, and obtains the surface treatment consistency index. Based on the surface treatment consistency index, the chemical control module uses automated testing to detect the capacitance characteristics and corrosion resistance of the aluminum foil, collects performance data, and obtains performance evaluation results. Based on the performance evaluation results, the quality verification module collects performance data of the aluminum foil after surface treatment, verifies the capacitance characteristics and corrosion resistance standards of the aluminum foil, determines product quality, and generates a performance quality qualification record.

Images