Aluminum foil surface quality intelligent control method and system

Abstract

The application relates to the technical field of capacitors, in particular to an aluminum foil surface quality intelligent control method and system, which comprises the following steps: based on continuously input spectrum data, adopting a Bayesian network model, identifying the relationship between electrode forming characteristics and quality in aluminum foil surface treatment, and adjusting the proportioning of chemical reagents and reaction time according to the model identification result, optimizing the conductivity control of the aluminum foil, and obtaining a chemical configuration optimization model. Through the combination of real-time spectrum data analysis and the Bayesian network model, the proportioning of chemical reagents and the reaction time in the aluminum foil surface treatment process are adjusted in real time, the electrochemical stability and the capacitance efficiency of the aluminum foil electrode are significantly improved, and the application has a significant advantage in improving the overall voltage resistance performance and reliability of the capacitor. Through continuous monitoring and dynamic adjustment of the aluminum foil surface oxide layer forming process, the high repeatability and uniformity of the treatment process are ensured, and the quality fluctuation in production is greatly reduced.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of capacitors, in particular to an aluminum foil surface quality intelligent control method and system. BACKGROUND

[0002] The technical field of capacitors mainly involves the design, manufacture and optimization of capacitors, which are widely used electronic components for storing and releasing electrical energy. Capacitors play a key role in many electronic devices and power systems, including filtering, energy conversion, signal coupling and decoupling applications. This field includes different types of capacitors, such as ceramic capacitors, electrolytic capacitors and thin film capacitors, each with its own specific materials and manufacturing processes. The performance of capacitors is influenced by a variety of factors, including the use of dielectric materials, electrode materials, structural design and surface treatment techniques. Among them, the surface treatment of electrodes is one of the key technologies to improve the performance of capacitors, which can affect the capacitance, voltage resistance and reliability of capacitors.

[0003] Among them, the aluminum foil surface quality intelligent control method 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 electrical conductivity and chemical stability. Through surface treatment, a layer of oxide film or other special materials can be formed on the surface of the aluminum foil to increase its surface area, improve its corrosion resistance and enhance its electrochemical stability. By treating not only the effective surface area of the aluminum foil can be increased, but also the capacitance can be increased, and its performance in high temperature and harsh environments can be improved. Therefore, this surface treatment method is crucial for the application of capacitors in the fields of power electronics, automotive electronics and renewable energy.

[0004] The existing technical means cannot respond to changes in production variables in real time, resulting in inconsistencies in the performance of electrode materials during production. The lack of real-time data analysis and feedback mechanisms makes it difficult for traditional methods to accurately control the surface quality of aluminum foil, especially in a batch production environment. The lack of control leads to fluctuations in capacitor performance. Traditional surface treatment techniques perform poorly in high temperature and harsh environments, limiting their widespread use in high-demand applications such as electric vehicles and solar panels. Not only does this affect the reliability of the product, but it also increases the cost of production and maintenance. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings of the prior art and to provide an aluminum foil surface quality intelligent control method and system.

[0006] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: an aluminum foil surface quality intelligent control method, comprising the following steps:

[0007] S1: Based on the continuously input spectrum data, the electrode formation feature and quality relationship in the aluminum foil surface treatment are identified by using the Bayesian network model, and the proportioning of chemical reagents and reaction time are adjusted according to the model identification result, the conductivity control of the aluminum foil is optimized, and a chemical configuration optimization model is obtained.

[0008] S2: Based on the chemical configuration optimization model, the spectrum data in the aluminum foil surface oxide layer production process are captured by using the spectrum sensor, the processing deviation is monitored and identified in real time, the chemical reaction condition is optimized, and a chemical reaction monitoring parameter is obtained.

[0009] S3: Based on the chemical reaction monitoring parameter, the proportioning of chemical reagents and time are reset, the aluminum foil surface treatment process is controlled, the reagent adding step is updated, and the continuity and uniformity of the treatment are maintained, and a surface treatment consistency index is obtained.

[0010] S4: Based on the surface treatment consistency index, the capacitance characteristics and corrosion resistance of the aluminum foil are detected by automatic testing, performance data collection is carried out, and the product is verified whether it meets the capacitor design requirements by comparing with the quality standard, and a performance quality qualified record is obtained.

[0011] The electrode formation feature and quality relationship identification step of the present application is improved, and the electrode formation feature and quality relationship identification step is specifically:

[0012] S111: Based on the continuously input spectrum data, noise filtering is carried out, and the formula is:

[0013]

[0014] The processed signal data is obtained , wherein, represents the spectrum data at the moment, represents the attenuation coefficient, is the upper limit of integration, and represents the end point of the time interval of signal processing, is the time interval in integration;

[0015] S112: Based on the processed signal data, the key electrode formation signal feature is extracted, and the formula is:

[0016]

[0017] The key signal feature is generated , wherein, is the processed signal data, is the sample number, is a function for the target electrode formation feature;

[0018] ​S113: Based on the key signal features, a Bayesian network model is used to identify the relationship between the features and the electrode quality, and the formula is used:

[0019]

[0020] Generate the identification result of the relationship between the electrode formation features and the quality , wherein, is the key signal feature, is the feature corresponding weight, is a nonlinear coefficient for adjusting the feature weight, is the variance of the feature, is a regularization term, is the total number of key signal features.

[0021] The conductivity control optimization step of the present application is specifically:

[0022] S121: Based on the model identification result, the control effect of the current conductivity is evaluated, and the ratio of the chemical reagent and the reaction time need to be adjusted to obtain an adjustment demand signal;

[0023] S122: Based on the adjustment demand signal, a new chemical reagent ratio is calculated, and the formula is used:

[0024]

[0025] Get the new chemical reagent ratio , wherein, is the adjustment coefficient, is the target ratio, is the historical deviation, which represents the difference between the past reaction and the target, is a deviation adjustment factor for balancing the adjustment amplitude, is the current chemical reagent ratio;

[0026] S123: Based on the new chemical reagent ratio, the reaction time is adjusted, and the formula is used:

[0027]

[0028] Get the optimized conductivity control configuration , wherein, and are time adjustment parameters, respectively representing the sensitivity and resistance of the adjustment, is the optimal reaction time based on simulation, is the current reaction time.

[0029] The present application improves that the spectrum data capturing step is specifically:

[0030] S211: Based on the chemical configuration optimization model, install a spectral sensor on the aluminum foil production line, align the aluminum foil surface oxidation area, and adjust the distance and angle of the sensor, using the formula:

[0031]

[0032] Get the sensor position and angle configuration, where, is the monitoring length of the sensor, is the distance from the sensor to the aluminum foil surface, is the angle between the sensor and the aluminum foil surface, and is the adjustment factor to adjust the sensitivity and response range of the sensor;

[0033] S212: Based on the monitoring length of the sensor, calibrate the spectral sensor and set the matching data acquisition frequency, using the formula:

[0034]

[0035] Get the spectral data acquisition parameters , where, is the sensor response peak, represents the acquisition time, is the midpoint of the response time, is the response rate, which determines the steepness of the response curve, is the logarithmic adjustment coefficient, which is used to optimize the dynamic range of the response;

[0036] S213: Based on the spectral data acquisition parameters, start the spectral sensor, record the reflected spectral data, and apply the formula:

[0037]

[0038] Get the real-time spectral data record , where, is the initial light intensity, is the material absorption coefficient, is the reactant concentration, is the modulation frequency, represents the noise term, represents the acquisition time.

[0039] The present application improves the identification step of the processing deviation, which is specifically:

[0040] S221: Analyze the collected spectral data using data processing technology to identify abnormalities or deviations in the spectral pattern, using the formula:

[0041]

[0042] obtain a deviation analysis result wherein, represents the th spectral data point, is the average value of the data points, is the total number of data points;

[0043] S222: based on the deviation analysis result, using a convolutional neural network, performing deviation recognition of the target type, using the formula:

[0044]

[0045] obtain a deviation severity probability wherein, is a sensitivity parameter, is a deviation threshold, is a deviation analysis result;

[0046] S223: based on the deviation severity probability, providing feedback and adjusting the production line parameters to optimize future deviations, using the formula:

[0047]

[0048] obtain the required adjustment amount wherein, and is a production adjustment coefficient, is a deviation severity probability.

[0049] The present application improves that the acquisition step of the surface treatment consistency index is specifically:

[0050] S311: based on the chemical reaction monitoring parameters, collect key monitoring parameters including pH value, temperature and reaction rate, calculate the weighted average of the reaction rate, using the formula:

[0051]

[0052] obtain a preliminary analysis log, wherein, is the weighted average reaction rate, is the reaction rate of the th measurement, is the corresponding weight, indicating the criticality of the measurement time, is the number of measurements;

[0053] S312: based on the preliminary analysis log, adjust the chemical agent ratio and time, using the formula:

[0054]

[0055] and

[0056]

[0057] get a new chemical agent ratio and time wherein, is an adjustment intensity parameter for controlling the sensitivity of the ratio adjustment, is a target reaction rate, is a weighted average reaction rate, is an original chemical agent ratio, is an original time;

[0058] S313: execute the new chemical agent ratio and time, monitor the adjustment effect, and use the formula:

[0059]

[0060] calculate the efficiency index and maintain the consistency and uniformity of the process, wherein, is a target reaction rate, is a measured reaction rate after adjustment.

[0061] The invention improves that the detection steps of the capacitance characteristics and corrosion resistance are specifically:

[0062] S411: based on the surface treatment consistency index, measure the capacitance characteristics of the aluminum foil using an LCR meter, and use the formula:

[0063]

[0064] get capacitance characteristic data wherein, is the dielectric constant, indicating the response ability of the material to the electric field, is the area between the capacitor plates, affecting the size of the capacitance, is the distance between the plates;

[0065] S412: conduct a salt spray test on the aluminum foil and simulate a corrosion environment, and use the formula:

[0066]

[0067] get corrosion resistance data wherein, is the change in mass, is the area between the capacitor plates, is the exposure time, is the material characteristic coefficient, indicating the corrosion rate sensitivity of the material, is a baseline offset used to adjust for error or environmental variation effects.

[0068] The application is improved, and the step of comparing with the quality standard is specifically:

[0069] S421: standardizing the collected performance data using the formula:

[0070]

[0071] to obtain a normalized data set wherein, is the original test data, is the minimum value in the data set, is the maximum value in the data set, is a constant;

[0072] S422: comparing with the quality standard based on the normalized data set using the formula:

[0073]

[0074] wherein, is the normalized data set, is the corresponding quality standard value, is a coefficient used to adjust the sensitivity of the comparison, represents a probability value indicating whether the data meets the standard.

[0075] An aluminum foil surface quality intelligent control system, the system comprising:

[0076] The spectral data analysis module analyzes the relationship between the electrode formation characteristics in the aluminum foil surface treatment and the quality based on the continuously input spectral data, adjusts the proportioning of the chemical reagents and the reaction time, optimizes the conductivity control parameters using a Bayesian network model, and obtains a chemical configuration optimization model;

[0077] The chemical configuration optimization module uses a spectral sensor to capture spectral data in the process of generating an aluminum foil surface oxide layer based on the chemical configuration optimization model, monitors the chemical reaction conditions, and obtains chemical reaction monitoring parameters;

[0078] The chemical reaction monitoring module resets the proportioning of the chemical reagents and the time based on the chemical reaction monitoring parameters, controls the aluminum foil surface treatment process, updates the reagent dosing steps, maintains the continuity and uniformity of the treatment, and obtains a surface treatment consistency index;

[0079] The chemical regulation module detects the capacitance characteristics and corrosion resistance of the aluminum foil through automated testing based on the surface treatment consistency index, collects performance data, and obtains performance evaluation results;

[0080] The quality verification module collects performance data of the aluminum foil after surface treatment based on the performance evaluation result, verifies the capacitance characteristics and corrosion resistance standards of the aluminum foil, determines the product quality, and generates a performance quality qualified record.

[0081] Compared with the prior art, the advantages and positive effects of the present application are that:

[0082] In the present application, by combining real-time spectral data analysis and Bayesian network model, the chemical agent ratio and reaction time in the aluminum foil surface treatment process are adjusted in real time, which significantly improves the electrochemical stability and capacitance efficiency of the aluminum foil electrode, especially in improving the overall voltage resistance performance and reliability of the capacitor. Through continuous monitoring and dynamic adjustment of the formation process of the aluminum foil surface oxide layer, the high repeatability and uniformity of the treatment process are ensured, the quality fluctuation in production is greatly reduced, the automatic testing and data collection function further ensures the whole process monitoring from production to quality control, effectively reduces the error, and improves the production efficiency and product consistency. BRIEF DESCRIPTION OF DRAWINGS

[0083] Figure 1 A flowchart of an aluminum foil surface quality intelligent control method is proposed for the present application;

[0084] Figure 2 A recognition flowchart of the relationship between electrode formation characteristics and quality in an aluminum foil surface quality intelligent control method is proposed for the present application;

[0085] Figure 3 An optimization flowchart of conductivity control in an aluminum foil surface quality intelligent control method is proposed for the present application;

[0086] Figure 4 A spectral data capture flowchart in an aluminum foil surface quality intelligent control method is proposed for the present application;

[0087] Figure 5 A recognition flowchart of treatment deviation in an aluminum foil surface quality intelligent control method is proposed for the present application;

[0088] Figure 6 A flowchart of obtaining surface treatment consistency indicators in an aluminum foil surface quality intelligent control method is proposed for the present application;

[0089] Figure 7 A detection flowchart of capacitance characteristics and corrosion resistance in an aluminum foil surface quality intelligent control method is proposed for the present application;

[0090] Figure 8 A flowchart of comparing with quality standards in an aluminum foil surface quality intelligent control method is proposed for the present application. DETAILED DESCRIPTION

[0091] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0092] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0093] Embodiment one: please refer to Figure 1 The present application provides a technical solution: an aluminum foil surface quality intelligent control method, comprising the following steps:

[0094] S1: Based on the continuously input spectrum data, a Bayesian network model is used to identify the relationship between the electrode formation characteristics in the aluminum foil surface treatment and the quality, and according to the model identification result, the proportioning of chemical reagents and the reaction time are adjusted, the conductivity control of the aluminum foil is optimized, and a chemical configuration optimization model is obtained;

[0095] S2: Based on the chemical configuration optimization model, a spectrum sensor is used to capture the spectrum data in the process of generating the aluminum foil surface oxide layer, to monitor and identify the processing deviation in real time, to optimize the chemical reaction conditions, and to obtain chemical reaction monitoring parameters;

[0096] S3: Based on the chemical reaction monitoring parameters, the proportioning of chemical reagents and the time are reset, the aluminum foil surface treatment process is controlled, the reagent adding step is updated, and the continuity and uniformity of the treatment are maintained, and a surface treatment consistency index is obtained;

[0097] S4: Based on the surface treatment consistency index, the capacitance characteristics and corrosion resistance of the aluminum foil are detected through automatic testing, performance data collection is carried out, and the performance data are compared with the quality standard to verify whether the product meets the capacitor design requirements, and a performance quality qualified record is obtained.

[0098] The chemical configuration optimization model includes reagent proportioning information, time adjustment sensitivity and quality control index, the chemical reaction monitoring parameters include spectrum deviation threshold, real-time monitoring frequency and abnormal processing identifier, the surface treatment consistency index includes surface smoothness information, treatment process repeatability and quality consistency rating, and the performance quality qualified record includes capacitance efficiency determination, corrosion resistance grade and qualified standard matching degree.

[0099] Referring to Figure 2 The identification of the electrode formation feature and quality relationship is specifically as follows:

[0100] S111: Based on the continuously input spectral data, noise filtering is performed, and the formula is as follows:

[0101]

[0102] The processed signal data is obtained , wherein, represents the spectral data at the moment, represents the decay coefficient, is an integral upper limit, representing the end point of the time interval of signal processing, is a small time interval in the integral; S112: Based on the processed signal data, key electrode formation signal features are extracted, and the formula is as follows:

[0103]

[0104] The key signal features are generated

[0105] , wherein, is the processed signal data, is the number of samples, is a function for the target electrode formation feature; S113: Based on the key signal features, a Bayesian network model is used to identify the relationship between the features and the electrode quality, and the formula is as follows:

[0106]

[0107] The identification result of the electrode formation feature and quality relationship is generated

[0108] , wherein, is the key signal feature, is the feature corresponding weight, is a nonlinear coefficient for adjusting the feature weight, is the variance of the feature, is a regularization term to avoid a zero denominator, is the total number of key signal features. Suppose

[0109] the spectral intensity is 10 units, , seconds.

[0110] Calculation :

[0111] ​

[0112] The integral is calculated (using basic integration rules):

[0113]

[0114] Assume , then:

[0115]

[0116] The value 39.4 represents the total signal strength after attenuation processing.

[0117] Assume , The characteristic function is simplified as time t, .

[0118] The calculation :

[0119]

[0120]

[0121]

[0122] The value 118.2 represents the weighted signal characteristic sum.

[0123] Assume , , , , , .

[0124] The calculation :

[0125]

[0126] The denominator is calculated:

[0127]

[0128] Then:

[0129]

[0130] The value 345.67 represents the identification result of the electrode formation characteristics and quality relationship, and the higher the value, the better the quality.

[0131] Please refer to Figure 3 , the optimization steps of conductivity control are as follows:

[0132] S121: Based on the model recognition result, evaluate the control effect of the current conductivity, determine the need to adjust the chemical agent ratio and reaction time, and obtain the adjustment demand signal;

[0133] S122: Based on the adjustment demand signal, calculate the new chemical agent ratio, using the formula:

[0134]

[0135] Get new chemical agent ratio , wherein, is the adjustment coefficient, is the target ratio, is the historical deviation, indicating the difference between the past reaction and the target, is the deviation adjustment factor, used to balance the adjustment amplitude, is the current chemical agent ratio;

[0136] S123: Based on the new chemical agent ratio, adjust the reaction time, using the formula:

[0137]

[0138] Get the optimized conductivity control configuration , wherein, and are time adjustment parameters, representing the sensitivity and resistance of adjustment respectively, is the optimal reaction time based on simulation, is the current reaction time.

[0139] Assume the following data:

[0140] ;

[0141] ;

[0142] ;

[0143] ;

[0144] .

[0145] Calculation process:

[0146] Calculate ;

[0147] Calculate the deviation ratio ;

[0148] Finally, calculate .

[0149] 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.

[0150] Suppose we have the following data:

[0151] ;

[0152] ;

[0153] Set to 120 minutes;

[0154] Set to 100 minutes.

[0155] Calculation process:

[0156] Calculate the time difference minute;

[0157] Calculation time adjustment ratio ;

[0158] Final calculation minute.

[0159] Calculations show that the reaction time needs to be increased by 8 minutes to achieve optimal reaction conditions.

[0160] Please see Figure 4 The specific steps for capturing spectral data are as follows:

[0161] 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:

[0162]

[0163] 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;

[0164] S212: Based on the sensor's monitoring length, calibrate the spectral sensor and set a matching data acquisition frequency using the formula:

[0165]

[0166] Obtain spectral data acquisition parameters ,in, It is the peak value of the sensor response. denotes the acquisition time, is the response time midpoint, specifying the time point at the center of the response curve, is the response rate, determining the steepness of the response curve, is the logarithmic adjustment factor, used to optimize the dynamic range of the response;

[0167] S213: Based on the spectral data acquisition parameters, start the spectral sensor, record the reflectance spectral data, apply the formula:

[0168]

[0169] get real-time spectral data record where, is the initial light intensity, is the material absorption coefficient, is the reactant concentration, is the modulation frequency, denotes the noise term, denotes the acquisition time.

[0170] Assume the following data:

[0171] Assume 2 meters;

[0172] Assume 45°;

[0173] ;

[0174] .

[0175] Calculation process:

[0176] Calculate as the tangent value of the angle between the aluminum foil surface and the incident light, assuming , then ;

[0177] Calculate ;

[0178] Finally 2.2 meters.

[0179] The result indicates that the effective monitoring length of the sensor is 2.2 meters, taking into account the basic geometric settings and fine-tuning factors.

[0180] Assume the following data:

[0181] Assume 100;

[0182] t = 5 seconds;

[0183] Assume 3 seconds;

[0184] Assume 1 second;

[0185] Assume 0.5.

[0186] Calculation procedure:

[0187] Calculation ;

[0188] Calculation denominator ;

[0189] Calculation ;

[0190] Final .

[0191] The result reflects the response of the spectral sensor over a given time, including the basic response and the enhanced response adjusted by the logarithmic term.

[0192] Assume the following data:

[0193] Assume 500;

[0194] Assume 0.05;

[0195] Assume the value changes over time seconds, ;

[0196] Assume rad / s;

[0197] Assume the random value is within a range of 5 units.

[0198] Calculation procedure:

[0199] Calculation ;

[0200] Calculation (because is a periodic point of the sine function);

[0201] Final .

[0202] The calculation shows that the light intensity at a specific time point is mainly controlled by the noise term, as the periodicity of the sine function results in a zero main signal.

[0203] Please refer to Figure 5 , the identification step for handling bias is as follows:

[0204] S221: Analyze the collected spectral data using data processing techniques to identify anomalies or deviations in the spectral pattern, using the formula:

[0205]

[0206] Obtain the deviation analysis result where, represents the th spectral data point, is the average value of the data points, is the total number of data points;

[0207] S222: Based on the deviation analysis result, use a convolutional neural network to identify the type of deviation, using the formula:

[0208]

[0209] Obtain the deviation severity probability where, is the sensitivity parameter, is the deviation threshold, is the deviation analysis result;

[0210] S223: Based on the deviation severity probability, provide feedback and adjust the production line parameters to optimize future deviations, using the formula:

[0211]

[0212] Obtain the required adjustment amount where, and are production adjustment coefficients, is the deviation severity probability.

[0213] Assume the following data:

[0214] Spectral data points ;

[0215]

[0216]

[0217] .

[0218] Calculation process:

[0219] Calculate the square of the difference between each data point and the average value:

[0220]

[0221] ​

[0222]

[0223]

[0224]

[0225] Sum of logarithms:

[0226]

[0227] Calculate the square root:

[0228]

[0229] The standard deviation of the data quantifies the dispersion of the spectral data and is approximately 3.16.

[0230] Suppose we have the following data:

[0231] ;

[0232] ;

[0233] .

[0234] Calculation process:

[0235] calculate ;

[0236] Calculation of the index:

[0237]

[0238] Calculate the probability:

[0239]

[0240] This indicates that the probability of discovering this bias is approximately 53.4%, suggesting a high likelihood of a significant bias.

[0241] Assume the following:

[0242] It is 5;

[0243] =1;

[0244] .

[0245] Calculation process:

[0246] Calculation ratio:

[0247]

[0248] The adjustment amount is calculated as:

[0249]

[0250] The required adjustment amount for adjusting the production line to reduce future deviations is 6.73.

[0251] See Figure 6 for the steps to obtain the surface treatment consistency index:

[0252] S311: Collect key monitoring parameters including pH, temperature, and reaction rate based on chemical reaction monitoring parameters, calculate the weighted average of reaction rate using the formula:

[0253]

[0254] Obtain the preliminary analysis log, where, is the weighted average reaction rate, is the reaction rate of the th measurement, is the corresponding weight indicating the criticality of the measurement time, is the number of measurements;

[0255] S312: Adjust the chemical agent ratio and time based on the preliminary analysis log, using the formula:

[0256]

[0257] and

[0258]

[0259] Obtain the new chemical agent ratio and time , where, is the adjustment intensity parameter for controlling the sensitivity of the ratio adjustment, is the target reaction rate, is the weighted average reaction rate, is the original chemical agent ratio, is the original time;

[0260] S313: Execute the new chemical agent ratio and time, monitor the adjustment effect, using the formula:

[0261]

[0262] Calculate the efficiency index and maintain consistency and uniformity in the process, is the target reaction rate, is the adjusted measured reaction rate.

[0263] Assuming there are 3 measurements, reaction rates of 2, 4 and 6, the corresponding weights are 1, 2 and 3 respectively.

[0264] The weighted average reaction rate is calculated as follows:

[0265]

[0266] Indicating that the average reaction rate is 4.67 when the importance of the measurements is taken into account.

[0267] Suppose there are the following data:

[0268] 100ml;

[0269] 60min;

[0270] 5;

[0271] 4.67;

[0272] 0.5.

[0273] Calculation process:

[0274]

[0275]

[0276] Indicating that in order to achieve the target reaction rate, the dosage ratio should be slightly reduced to 98.5ml, and the time adjusted to 58 minutes.

[0277] Suppose the actual measured reaction rate after adjustment is 4.9, calculated as follows:

[0278]

[0279] Indicating that the adjusted actual efficiency is close to the target efficiency, reaching 98%.

[0280] Please refer to Figure 7 , the detection steps of the capacitance characteristics and corrosion resistance are as follows:

[0281] S411: Measure the capacitance properties of the aluminum foil using LCR meter based on surface treatment consistency index, using formula:

[0282]

[0283] Get capacitance property data Where, is the dielectric constant, representing the material's response ability to electric field, is the area between the capacitor plates, affecting the size of the capacitance, is the distance between the plates, reducing the distance can increase the capacitance value;

[0284] S412: Perform salt spray test on aluminum foil and simulate corrosion environment, using formula:

[0285]

[0286] Get corrosion resistance data Where, is the mass change, is the area between the capacitor plates, is the exposure time, is the material property coefficient, representing the material's corrosion rate sensitivity, is the baseline offset, used to adjust errors or environmental changes.

[0287] Assumptions:

[0288] Assume the dielectric constant of aluminum foil is F / m (value in vacuum);

[0289] Size is ;

[0290] Assume the distance is .

[0291] Calculation process:

[0292] Assuming the use of the above parameter values, The calculation is as follows:

[0293]

[0294] Indicates that under given conditions, the capacitance of aluminum foil is 88.5 pF.

[0295] Assumptions:

[0296] Assume 0.05 day;

[0297] Assume 0.001 day;

[0298] Assume the mass change before and after corrosion is 0.02g;

[0299] Assume ;

[0300] Assume 1 day.

[0301] Using the above parameters, the corrosion rate is calculated as follows:

[0302]

[0303] This means that under the given conditions, the corrosion rate of the material is 0.101g / / day.

[0304] Please refer to Figure 8 , the steps of comparing with the quality standard are as follows:

[0305] S421: Standardize the collected performance data using the formula:

[0306]

[0307] Get the normalized data set , where, is the original test data, is the minimum value in the data set, is the maximum value in the data set, is a constant to ensure that the denominator is not zero;

[0308] S422: Based on the normalized data set, compare with the quality standard using the formula:

[0309]

[0310] where, is the normalized data set, is the corresponding quality standard value, is a coefficient used to adjust the sensitivity of the comparison, represents the probability value of whether the data meets the standard.

[0311] Assume the data is as follows:

[0312] ;

[0313] ;

[0314] ;

[0315] is set to .

[0316] The minimum and maximum values are calculated:

[0317]

[0318] For , the normalized result is:

[0319]

[0320] Assume the data as follows:

[0321] The quality standard value is assumed to be 0.3 (representing the qualified standard for capacitance and corrosion resistance);

[0322] Assume .

[0323] The calculation process is:

[0324] Use

[0325] Apply the comparison formula:

[0326]

[0327] There is a 58.2% probability that the capacitance characteristics and corrosion resistance meet the quality standards.

[0328] An aluminum foil surface quality intelligent control system, the system comprises:

[0329] The spectral data analysis module analyzes the relationship between electrode formation characteristics and quality in the aluminum foil surface treatment based on continuously input spectral data, adjusts the proportioning of chemical agents and reaction time, optimizes the conductivity control parameters using the Bayesian network model, and obtains a chemical configuration optimization model;

[0330] The chemical configuration optimization module uses a spectral sensor to capture spectral data during the generation of the aluminum foil surface oxide layer based on the chemical configuration optimization model, monitors the chemical reaction conditions, and obtains chemical reaction monitoring parameters;

[0331] The chemical reaction monitoring module resets the proportioning of chemical agents and time based on the chemical reaction monitoring parameters, controls the aluminum foil surface treatment process, updates the agent dosing steps, maintains the continuity and uniformity of the treatment, and obtains a surface treatment consistency index;

[0332] The chemical regulation module detects the capacitance characteristics and corrosion resistance of the aluminum foil through automatic testing based on the surface treatment consistency index, collects performance data, and obtains performance evaluation results;

[0333] The quality verification module collects performance data of the aluminum foil after surface treatment based on the performance evaluation results, verifies the capacitance characteristics and corrosion resistance standards of the aluminum foil, determines the product quality, and generates a performance quality qualified record.

[0334] The above is only a preferred embodiment of the present application, and does not limit the form of the present application in other forms. Any skilled person in the art can use the disclosed technical content to make changes or modifications as equivalent embodiments applied to other fields. However, any simple modification, equivalent change and modification made to the above embodiments without departing from the technical solution content of the present application, according to the technical essence of the present application, still belongs to the protection scope of the technical solution of the present application.

Claims

1. An aluminum foil surface quality intelligent control method, characterized by, The method comprises the following steps: Based on the continuously input spectral data, the relationship between the electrode formation characteristics and the quality in the aluminum foil surface treatment is identified by using a Bayesian network model, and the proportioning of the chemical reagents and the reaction time are adjusted according to the model identification result, the conductivity control of the aluminum foil is optimized, and a chemical configuration optimization model is obtained; The optimization step of the conductivity control is specifically: Based on the model identification result, the control effect of the current conductivity is evaluated, the proportioning of the chemical reagents and the reaction time that need to be adjusted are determined, and an adjustment demand signal is obtained; Based on the adjustment demand signal, the new proportioning of the chemical reagents is calculated by using the formula: ； Obtaining a new chemical agent recipe wherein, is an adjustment coefficient, is a target recipe, is a historical deviation amount, indicating a difference between past reactions and the target, is a deviation adjustment factor, used to balance the magnitude of adjustment, is a current chemical agent recipe; Based on the new proportioning of the chemical reagents, the reaction time is adjusted by using the formula: ； Optimized conductivity control configuration is obtained wherein, and are time adjustment parameters, respectively representing the sensitivity and resistance of adjustment, is the optimal reaction time based on simulation, is the current reaction time; Based on the chemical reaction monitoring parameter, the proportioning of the chemical reagents and the time are reset, the aluminum foil surface treatment process is controlled, the reagent adding step is updated, and the continuity and uniformity of the treatment are maintained, and a surface treatment consistency index is obtained; Based on the surface treatment consistency index, the capacitance characteristics and the corrosion resistance of the aluminum foil are detected through automatic testing, performance data are collected, and the product is verified whether it meets the capacitor design requirements by comparing with the quality standard, and a performance quality qualified record is obtained. The identification step of the relationship between the electrode formation characteristics and the quality is specifically:

2. The aluminum foil surface quality intelligent control method according to claim 1, characterized by, Based on the continuously input spectral data, noise filtering is performed by using the formula: Based on the processed signal data, the key electrode formation signal characteristics are extracted by using the formula: ； obtaining processed signal data wherein representing spectral data at a time instant, representing an attenuation coefficient, is an upper limit of integration, representing an end point of a time interval of signal processing, is a time interval in the integration; Based on the key signal characteristics, the relationship between the characteristics and the electrode quality is identified by using a Bayesian network model by using the formula: ； Generating key signal features wherein, is the processed signal data, is the number of samples, is a function forming features for the target electrode; The capturing step of the spectral data is specifically: ； Generating electrode formation feature and quality relationship identification results wherein, is a key signal feature, is a feature a corresponding weight, is a non-linear coefficient that adjusts the feature weight, is a variance of the feature, is a regularization term, is a total number of key signal features.

3. The aluminum foil surface quality intelligent control method according to claim 1, characterized by, Based on the chemical configuration optimization model, a spectral sensor is installed on the aluminum foil production line, is aligned with the aluminum foil surface oxidation area, and the distance and angle of the sensor are adjusted by using the formula: Based on the monitoring length of the sensor, the spectral sensor is calibrated, and a matching data acquisition frequency is set by using the formula: ； The sensor position and angle configuration is obtained, wherein, is the monitoring length of the sensor, is the distance of the sensor to the aluminum foil surface, is the angle between the sensor and the aluminum foil surface, and is an adjustment factor to adjust the sensitivity and response range of the sensor; Based on the spectral data acquisition parameter, the spectral sensor is started, the reflected spectral data are recorded, and the formula is applied: ； Obtaining spectral data acquisition parameters wherein, is the sensor response peak, denotes the acquisition time, is the response time midpoint, is the response rate, determining the steepness of the response curve, is the logarithmic adjustment coefficient, used to optimize the dynamic range of the response; The identification step of the treatment deviation is specifically: ； obtaining a real-time spectral data record wherein is the initial light intensity, is the material absorption coefficient, is the reactant concentration, is the modulation frequency, denotes a noise term, denotes the acquisition time.

4. The aluminum foil surface quality intelligent control method according to claim 1, characterized by, The collected spectral data are analyzed by using a data processing technology, and the abnormality or deviation in the spectral mode is identified by using the formula: Based on the deviation analysis result, a convolutional neural network is used to identify the deviation type by using the formula: ； obtaining bias analysis results wherein, denotes the thspectral data point, is the average value of the data points, is the total number of data points; Based on the deviation severity probability, feedback is provided and the production line parameters are adjusted to optimize future deviations by using the formula: ； obtaining a bias severity probability wherein, is a sensitivity parameter, is a bias threshold, is a bias analysis result; The obtaining step of the surface treatment consistency index is specifically: ； obtaining the desired adjustment amount wherein, and is a production adjustment coefficient, is a deviation severity probability.

5. The aluminum foil surface quality intelligent control method according to claim 1, wherein Based on the chemical reaction monitoring parameter, the key monitoring parameters including the pH value, the temperature and the reaction rate are collected, the weighted average of the reaction rate is calculated by using the formula: Based on the preliminary analysis log, the proportioning of the chemical reagents and the time are adjusted by using the formula: ； a preliminary analysis log is obtained, wherein, is a weighted average reaction rate, is the reaction rate of the first measurement, is a corresponding weight indicating the criticality of the measurement time, is the number of measurements; And ； The new proportioning of the chemical reagents and the time are executed, and the adjustment effect is monitored by using the formula: ； a new chemical formulation is obtained and time wherein, is an adjustment strength parameter for controlling the sensitivity of the formulation adjustment, is a target reaction rate, is a weighted average reaction rate, is an original chemical formulation, is an original time; The detection step of the capacitance characteristics and the corrosion resistance is specifically: ； Computing efficiency index and maintaining consistency and uniformity of processing, wherein, is the target reaction rate, is the adjusted measured reaction rate.

6. The aluminum foil surface quality intelligent control method according to claim 1, wherein ​ Based on the surface treatment consistency index, the capacitance characteristics of the aluminum foil are measured using an LCR meter, and a formula is used: ； Obtaining capacitance characteristic data wherein, is the dielectric constant, representing the material's ability to respond to an electric field, is the area between the capacitor plates, affecting the size of the capacitance, is the distance between the plates; The aluminum foil is subjected to a salt spray test and simulated corrosion environment, and a formula is used: ； Corrosion resistance data is obtained wherein, is the change in mass, is the area between the capacitor plates, is the exposure time, is a material property coefficient representing the corrosion rate sensitivity of the material, is a baseline offset to adjust for error or environmental variation effects.

7. The aluminum foil surface quality intelligent control method according to claim 1, characterized by, The step of comparing with the quality standard is specifically: The collected performance data is standardized, and a formula is used: ； obtaining a normalized data set wherein, is the original test data, is the minimum value in the data set, is the maximum value in the data set, is a constant; Based on the normalized data set, the quality standard is compared, and a formula is used: ； wherein, is the normalized data set, is the corresponding quality standard value, is a coefficient for adjusting the sensitivity of the comparison, is a probability value indicating whether the data meets the standard.

8. An aluminum foil surface quality intelligent control system, characterized by, The aluminum foil surface quality intelligent control method according to any one of claims 1-7 is executed, and the system comprises: The spectral data analysis module analyzes the relationship between the electrode formation characteristics in the aluminum foil surface treatment and the quality based on continuously input spectral data, adjusts the proportioning of chemical agents and the reaction time, optimizes the conductivity control parameters using a Bayesian network model, and obtains a chemical configuration optimization model; The chemical configuration optimization module uses a spectral sensor to capture spectral data during the generation of the aluminum foil surface oxide layer based on the chemical configuration optimization model, monitors the chemical reaction conditions, and obtains chemical reaction monitoring parameters; The chemical reaction monitoring module resets the proportioning of chemical agents and the time based on the chemical reaction monitoring parameters, controls the aluminum foil surface treatment process, updates the agent dosing steps, maintains the continuity and uniformity of the treatment, and obtains a surface treatment consistency index; The chemical regulation module detects the capacitance characteristics and corrosion resistance of the aluminum foil through automated testing based on the surface treatment consistency index, collects performance data, and obtains performance evaluation results; The quality verification module collects performance data of the aluminum foil after surface treatment based on the performance evaluation results, verifies the capacitance characteristics and corrosion resistance standards of the aluminum foil, determines the product quality, and generates a performance quality qualified record.

Images