A dry electrode manufacturing process control method, system, and storage medium

Abstract

The application relates to the technical field of electrode preparation, and discloses a dry-process electrode preparation process control method, a system and a storage medium. The method comprises the following steps: in the rolling forming process of a dry-process electrode material, real-time monitoring and collection of the gap data of a compression roller and the rotation angle data of a driving motor are performed, and a support vector machine algorithm is used to identify the transmission ratio change trend of the compression roller system; in combination with historical wear data, the pitch accuracy offset amount caused by wear is calculated through Kalman filtering; when the offset amount exceeds the limit, an adjustment coefficient is generated based on a simulation model, and the control accuracy is improved through feedforward compensation and feedback optimization; when the adjustment accuracy meets the process requirements, adaptive parameter sets are determined through dynamic deviation residual analysis, and a pressure roller gap is adjusted by driving an actuator; the thickness uniformity index of the electrode plate output after adjustment is monitored in real time, and finally, the thickness uniformity of the electrode plate is taken as a verification standard to form a quality closed-loop control. The application improves the quality accuracy of dry-process electrode production.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrode preparation, and in particular to a dry electrode preparation process control method, system and storage medium. BACKGROUND

[0002] With the wide application of new energy batteries, especially the increasing demand in electric vehicles and energy storage devices, the performance and production efficiency of batteries have become one of the key factors. The performance of batteries depends largely on the quality of electrode materials, and the thickness uniformity of electrode materials directly affects the charge-discharge efficiency, service life and safety of batteries. The manufacturing process of electrodes usually involves coating, pressing and other links, among which the gap control of the pressing roller is crucial to the thickness uniformity of the electrode.

[0003] In traditional dry electrode preparation technology, the adjustment of the gap of the pressing roller usually relies on manual experience or fixed preset parameters. However, with the long-time operation of the equipment, especially the wear of mechanical parts such as lead screws, the transmission ratio changes, and the traditional control method fails to effectively respond to these changes, resulting in increased electrode thickness fluctuation, affecting battery performance. Especially in high-precision electrode production, the precision and adaptability of traditional control methods often cannot meet the changing production needs. In addition, in the prior art, most equipment relies on static parameters for adjustment, lacking real-time dynamic adjustment capability. When the equipment is worn or the operating conditions change, the control strategy cannot be corrected in time, resulting in unevenness of electrode thickness in the production process. This limitation affects the stability and consistency of battery products, and further restricts the further development of the battery industry.

[0004] Therefore, how to realize real-time dynamic adjustment of the gap of the pressing roller and adapt to the changes of equipment wear and production environment is a problem to be solved in current electrode preparation technology. The present application provides an adaptive control method based on real-time data acquisition and state estimation technology, which can dynamically adjust the gap of the pressing roller according to the change of the transmission ratio and the wear of the equipment, thereby ensuring the uniformity of the electrode thickness and solving the deficiencies in the prior art. SUMMARY

[0005] To solve the above technical problems, the present application provides a dry electrode preparation process control method, system and storage medium for improving the control precision and stability of the gap of the pressing roller, and also enabling the system to adapt to time-varying factors such as equipment wear, effectively prolonging the equipment maintenance cycle and greatly improving the product qualification rate and consistency.

[0006] In a first aspect, the present application provides a dry electrode preparation process control method, which comprises:

[0007] Step S1: In the rolling forming process of the dry electrode material, the roll gap data and the rotation angle data of the driving motor are monitored and collected in real time, the collected data is classified and processed using a support vector machine algorithm, and the transmission ratio change trend of the roll system is identified;

[0008] Step S2: The wear state of the lead screw in the current roll system is evaluated by a state estimation algorithm in combination with the transmission ratio change trend and the historical wear data of the lead screw, and the pitch accuracy offset caused by wear is calculated;

[0009] Step S3: If the pitch accuracy offset exceeds a preset threshold, an adjustment coefficient for correcting the motor displacement instruction is generated based on the pitch accuracy offset, the motor angle instruction sequence is updated using the adjustment coefficient, and the updated instruction sequence is iteratively optimized through a feedback loop to improve the actual adjustment accuracy of the roll gap;

[0010] Step S4: When the adjustment accuracy meets the process requirements, the dynamic deviation residual of the system is obtained, the dynamic deviation residual is corrected and the final adaptive control parameter set is determined, and the roll gap is adjusted based on the adaptive control parameter set;

[0011] Step S5: The thickness uniformity index of the electrode plate produced after adjustment is monitored in real time, and if the deviation of the thickness uniformity from the target range exceeds the preset range, the process returns to step S1 to restart a new round of optimization cycle until the thickness uniformity index is qualified and the final control parameter is output.

[0012] In a second aspect, the present application provides a dry electrode preparation process control system, which comprises:

[0013] The collection module is configured to monitor and collect the roll gap data and the rotation angle data of the driving motor in real time during the rolling forming process of the dry electrode material, classify and process the collected data using a support vector machine algorithm, and identify the transmission ratio change trend of the roll system.

[0014] The state evaluation module is configured to evaluate the wear state of the lead screw in the current roll system by a state estimation algorithm in combination with the transmission ratio change trend and the historical wear data of the lead screw, and calculate the pitch accuracy offset caused by wear.

[0015] The iterative optimization module is configured to generate an adjustment coefficient for correcting the motor displacement instruction based on the offset if the pitch accuracy offset exceeds a preset threshold, update the motor angle instruction sequence using the adjustment coefficient, and iteratively optimize the updated instruction sequence through a feedback loop to improve the actual adjustment accuracy of the roll gap.

[0016] A correction module is configured to obtain a dynamic deviation residual of the system when the adjustment accuracy meets the process requirement, correct the dynamic deviation residual, and determine a final adaptive control parameter set, and drive the actuator to adjust the nip gap based on the adaptive control parameter set.

[0017] A cycle control module is configured to monitor the thickness uniformity of the electrode plate output after adjustment in real time, and if the deviation of the thickness uniformity from the target range exceeds a preset range, return to the acquisition module to restart a new round of optimization cycle until the thickness uniformity indicator is qualified, and output the final control parameter.

[0018] The third aspect of the present application provides a computer-readable storage medium, which stores instructions, when the instructions are executed on a computer, the computer executes the above-mentioned dry electrode preparation process control method.

[0019] Compared with the prior art, the present application has at least the following advantages:

[0020] The dry electrode preparation process control method, system and storage medium provided by the present application realize intelligent and accurate regulation and control of the nip gap by constructing a complete closed-loop control chain from device state perception to product quality verification. The method first uses a support vector machine algorithm to identify the trend of real-time data of the nip gap and the motor rotation angle, which can early detect abnormal changes in the transmission ratio caused by lead screw wear, and gain valuable time for subsequent compensation control. By combining a Kalman filter algorithm to accurately estimate the lead screw wear state, the accurate pitch accuracy offset is calculated, providing a reliable quantitative basis for compensation control.

[0021] When significant wear is detected, accurate instruction adjustment coefficients are generated based on a physical simulation model, and the effects of mechanical wear on control accuracy are effectively offset by combining feedforward compensation with feedback optimization. Finally, the electrode plate thickness uniformity is used as a quality evaluation standard to form a complete closed loop from device control to product quality, ensuring that the adjustment of the control parameters can be verified in the actual product quality. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without creative labor.

[0023] Figure 1 An embodiment of a dry electrode preparation process control method in the present application is shown in the figure;

[0024] Figure 2 FIG. 1 is a schematic diagram of an embodiment of a dry electrode preparation process control system according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] The present application provides a dry electrode preparation process control method, system and storage medium. The terms "first", "second", "third", "fourth" and the like in the description and claims of the present application and the above drawings (if any) are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged, where appropriate, so that the embodiments described herein can be carried out in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprise" or "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, processes, methods, systems, products, or devices that include a series of steps or units are not necessarily limited to those clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] For ease of understanding, the specific flow of the embodiments of the present application is described below. Please refer to Figure 1 An embodiment of a dry electrode preparation process control method according to an embodiment of the present application includes:

[0027] Step S1, in the rolling forming process of the dry electrode material, the roll gap data and the rotation angle data of the driving motor are monitored and collected in real time, the collected data is classified and processed using a support vector machine algorithm, and the transmission ratio change trend of the roll system is identified.

[0028] In step S1, the roll gap data is collected in real time by a displacement sensor, and the rotation angle data of the driving motor is collected in real time by an encoder, and the collected roll gap data and rotation angle data are used as input feature vectors; a support vector machine algorithm is used to construct a classification model, the input feature vectors are classified, the classification results of the transmission ratio change trend are obtained, the transmission ratio change trend curve is fitted, and the transmission ratio change rate is calculated; if the transmission ratio change rate exceeds a preset threshold, the transmission ratio change trend is marked as an abnormal trend, otherwise it is marked as a normal trend, the key time points are extracted from the data according to the abnormal trend, the peak and valley values of the transmission ratio change trend are analyzed through the key time points, and the quantitative indicators of the transmission ratio change trend are obtained.

[0029] Specifically, dry electrode refers to the process of forming materials into electrodes by physical means such as pressure and heat without using liquid solvents. This process is commonly used in the manufacture of energy devices such as batteries and capacitors. In this process, the pressure roller is a key device that controls the thickness and density of the material through rolling. During the operation of the pressure roller system, the gap between the two rollers and the rotation angle of the drive motor are very important parameters. The gap between the two rollers determines the degree of compression of the material during rolling and directly affects the quality of the material. The rotation angle of the drive motor reflects the operation of the motor and indirectly affects the compression force of the pressure roller. Therefore, during the entire manufacturing process, sensors and encoders are needed to monitor these two data in real time.

[0030] The present application first collects the pressure roller gap data in real time through a high-precision displacement sensor, for example, 10 data points per second, forming a pressure roller gap sequence, and simultaneously collects the rotation angle data of the drive motor shaft through the encoder installed on it, obtaining an angle sequence. The gap sequence and the angle sequence are combined into an input feature vector. The real-time input feature vector is input into a pre-trained classification model. The model is generated based on the support vector machine algorithm, and the training data is the historical data accumulated during the long-term operation of the pressure roller system. The samples in these historical data have been labeled as "stable", "rising" or "falling" trend state categories by expert knowledge or process results. The classification model learns from these labeled samples and builds a classification boundary that can distinguish different transmission ratio states. The classification model processes the real-time input feature vector and outputs the classification result of the current transmission ratio change trend, such as "stable", "rising" and "falling". The classification results at a series of time points are converted into corresponding numerical sequences, for example, mapped to numerical values 0, +1 and -1 respectively. After smoothing the numerical sequence to suppress transient fluctuations, the least squares method is used for curve fitting to generate a smooth transmission ratio change trend curve. The slope of the fitted curve is calculated to obtain the transmission ratio change rate, which quantifies the severity of the transmission ratio state change.

[0031] The calculated change rate is compared with a preset threshold, for example, the threshold is set to 0.05 units / second, if the rate exceeds the threshold, it is determined that the current is in an abnormal trend and an alarm is triggered, otherwise it is marked as a normal trend, once a certain trend is marked as abnormal, key time points are automatically extracted from the original data sequence corresponding to the abnormal trend, these time points are usually the moments when the peak and valley of the transmission ratio occur, by analyzing the transmission ratio peak and valley corresponding to these key time points, the quantitative indicators of the transmission ratio change trend such as the fluctuation amplitude and the fluctuation period are calculated, these accurate quantitative indicators provide indispensable decision basis for evaluating the severity of mechanical wear, diagnosing potential fault sources and triggering subsequent adaptive compensation control, thereby realizing the closed loop from state perception to intelligent diagnosis.

[0032] Step S2, in combination with the transmission ratio change trend and the historical wear data of the lead screw, the wear state of the lead screw in the current compression roller system is evaluated through a state estimation algorithm, and the pitch accuracy offset caused by wear is calculated.

[0033] Among them, step S2 includes: querying the historical operation log according to the transmission ratio change trend, extracting the lead screw wear related indicators matching the trend, including the wear rate and the cumulative wear amount; initializing the state vector and the covariance matrix of the Kalman filter, taking the lead screw wear related indicators as the observation value, using the Kalman filtering algorithm for iterative state estimation, calculating the state prediction value and updating the prediction covariance matrix; performing a measurement update step, calculating the Kalman gain, and fusing the observation value and the state prediction value to obtain the posterior state estimation value, and determining the final pitch accuracy offset based on the posterior state estimation value.

[0034] Specifically, in the rolling forming process of dry electrode material, as the equipment is used for a long time, the mechanical parts such as compression roller and lead screw will be worn, which will cause the control accuracy of electrode thickness to decrease, and further affect the battery performance and stability, therefore, the wear of the equipment must be state estimated to provide basis for subsequent accurate compensation.

[0035] Specifically, according to the identified abnormal trend of the transmission ratio, the historical operation log database is queried to extract the lead screw wear-related indicators corresponding to the past records with similar characteristics to the current abnormal mode, mainly including the wear rate (wear amount per unit time) and the cumulative wear amount. These indicators, as direct observations reflecting the health status of the lead screw, are input into the state estimation process. Then, the Kalman filtering algorithm is used for state estimation. First, the state vector and covariance matrix of the filter are initialized, wherein the state vector contains the estimated lead screw wear state variables, and the covariance matrix quantifies the uncertainty of the initial state estimation. Next, the algorithm enters the iterative estimation loop, which includes two core steps: prediction and update. In the prediction step, the algorithm calculates the state prediction value at the current time based on the physical model describing the lead screw wear dynamics, such as a linear model considering the average wear rate, and simultaneously updates the prediction covariance matrix to reflect the newly added uncertainty due to model imperfections and process noise. Subsequently, in the measurement update step, the algorithm calculates the Kalman gain, which is a dynamic weight used to optimally balance the credibility between the prediction value and the current observation. Using this gain, the latest observation, i.e., the wear rate and cumulative wear amount extracted from the historical log, is fused with the state prediction value to generate a new, more accurate posterior state estimation value, and the posterior estimation covariance matrix is updated accordingly. This "prediction-update" process continues to iterate with new data, allowing the state estimation to converge to the true value through continuous correction. Finally, based on the optimized posterior state estimation value output by the Kalman filter, the pitch accuracy offset caused by lead screw wear is calculated. This offset is an accurate physical quantity representing the deviation between the actual lead screw transmission accuracy and the ideal value, providing a crucial input for generating high-precision compensation instructions in the subsequent process.

[0036] The above technical solution combines data-driven historical experience (observations) with physics-based prediction models, effectively overcoming the limitations of relying solely on models or observations. It can still achieve high-precision and robust estimation of the lead screw wear state under sensor noise and device operation fluctuation interference, thereby laying a solid foundation for ensuring the thickness uniformity of the electrode plate from the root cause.

[0037] Step S3, if the pitch accuracy offset exceeds the preset threshold, an adjustment coefficient for modifying the motor displacement instruction is generated based on the pitch accuracy offset, the adjustment coefficient is used to update the motor angle instruction sequence, and the updated instruction sequence is iteratively optimized through a feedback loop to improve the actual adjustment accuracy of the press roll gap.

[0038] The step S3 of generating the adjustment coefficient for correcting the motor displacement instruction based on the pitch precision offset includes: if the pitch precision offset exceeds a preset threshold, inputting the pitch precision offset to an analog model, calculating the meshing fluctuation amplitude caused by the pitch precision offset based on the analog model, including the fluctuation frequency and the amplitude peak value; fitting the displacement corresponding relationship curve according to the meshing fluctuation amplitude, determining the reciprocal of the curve slope as the preliminary value of the adjustment coefficient, and calibrating the preliminary value by using an optimization algorithm to obtain a refined adjustment coefficient; and verifying the accuracy of the displacement corresponding relationship by using the refined adjustment coefficient, and outputting the adjustment coefficient if the accuracy is higher than a preset threshold.

[0039] Specifically, when the calculated pitch precision offset exceeds a preset safety threshold such as 0.01 mm, it indicates that the screw wear has a substantial impact on the transmission precision, and compensation control must be started. To solve the problem of inaccurate control of the press roller gap caused by mechanical wear, the application generates an accurate instruction correction coefficient by establishing a method combining physical simulation and optimization algorithm, and realizes the feedforward compensation of the motor displacement instruction.

[0040] Specifically, an analog model representing the dynamic characteristics of the press roller transmission system is constructed, which can be simplified as a spring-mass-damper system, where the spring stiffness is equivalent to the transmission system stiffness, the mass block is equivalent to the press roller inertia, and the damping coefficient is equivalent to the system friction characteristics. The model simulates the dynamic response of the system under different wear states by adjusting its physical parameters; the calculated pitch precision offset is input into the analog model as a key input parameter, and the meshing fluctuation dynamic response caused by the specific offset is calculated by running the model, and the output includes two key indicators of fluctuation frequency and amplitude peak value, where the fluctuation frequency reflects the periodic characteristics of transmission instability, and the amplitude peak value directly quantifies the maximum deviation of the gap fluctuation. Subsequently, based on the data point set output by the analog model, a mapping relationship from the theoretical displacement instruction to the fluctuation amplitude peak value is established, and a displacement corresponding relationship curve is fitted by using the least square method, the slope of the curve in the current process setting working interval is calculated, and the reciprocal of the curve slope is taken as the preliminary value of the adjustment coefficient, which is essentially a compensation factor for pre-scaling the motor displacement instruction. Then, the gradient descent optimization algorithm is used to calibrate the preliminary value of the adjustment coefficient to obtain a refined adjustment coefficient, and the specific calibration process is described later. Finally, the refined adjustment coefficient is verified in reverse: the corrected displacement instruction is input into the analog model again, and if the fluctuation amplitude peak value calculated after optimization is reduced by more than a preset threshold, it is determined that the accuracy of the displacement corresponding relationship meets the preset requirements, and the refined adjustment coefficient is finally output to the motor control system.

[0041] After the refining adjustment coefficient is output to the motor control system, the system immediately starts the instruction updating and closed-loop optimization process to ensure continuous and accurate control of the press roll gap, specifically, the refining adjustment coefficient is multiplied by each instruction value in the original motor angle instruction sequence to generate a set of pre-compensated updated motor angle instruction sequence, then the updated instruction sequence is input into a real-time feedback control loop, which first drives the servo actuator to act according to the instruction, and at the same time, the actual press roll gap data is collected synchronously through a high-precision displacement sensor, the real-time deviation between the actual output value and the expected output value set by the process is immediately calculated, the deviation signal comprehensively reflects the residual error of the feedforward compensation and any unmodeled dynamic disturbance, based on this deviation, an incremental PID control algorithm is used to online iteratively fine-tune the instruction sequence parameters, and the residual error and unmodeled disturbance are corrected cycle by cycle, when the gap deviation of continuous multiple cycles is stabilized within the preset tolerance range, it is determined that the system converges, this process significantly improves the actual adjustment accuracy and robustness of the press roll gap through the fusion of feedforward compensation and feedback optimization.

[0042] The above technical solution realizes accurate conversion from wear quantification to instruction compensation through the combination of physical modeling and optimization algorithm, which not only overcomes the poor adaptability of traditional fixed parameter compensation, but also generates the optimal compensation strategy according to the specific wear condition, providing key technical support for improving the actual adjustment accuracy of the press roll gap.

[0043] Among them, the refining adjustment coefficient is obtained by calibrating the preliminary value using an optimization algorithm, including: taking the preliminary value as the initial point, taking the minimization of the mesh fluctuation amplitude as the objective function, and using the gradient descent method for iterative search, in each iteration, the gradient of the objective function with respect to the adjustment coefficient is calculated and the adjustment coefficient is updated in the opposite direction of the gradient, when the change of the objective function is less than the convergence threshold or the maximum number of iterations is reached, the iteration is stopped, and the optimal solution at this time is taken as the refining adjustment coefficient.

[0044] Specifically, after obtaining the preliminary adjustment coefficient based on the physical model, in order to further improve the compensation accuracy and overcome the errors caused by model simplification, the application adopts an optimization algorithm based on gradient descent to fine-tune the coefficient. This process takes the preliminary adjustment coefficient as the starting point for optimization, and through systematic iterative search, it finds the refined coefficient value that can most effectively suppress the mesh fluctuation. Specifically, regarding the gradient descent optimization process, first, take the preliminary adjustment coefficient as the initial point for iterative search. In each iteration, the algorithm calculates the target function value corresponding to the current adjustment coefficient through forward simulation, and then calculates the gradient of the target function with respect to the adjustment coefficient through automatic differentiation or finite difference method. This gradient vector indicates the steepest growth direction of the target function in the parameter space. To minimize the target function, the algorithm updates the adjustment coefficient in the opposite direction of the gradient, and the update step is controlled by a preset learning rate parameter. This iterative process continues until the change in the target function value between two consecutive iterations is less than a preset convergence threshold (such as 0.001), or the number of iterations reaches the maximum limit. At this time, the obtained adjustment coefficient is the refined adjustment coefficient.

[0045] In step S3, the updated instruction sequence is iteratively optimized through the feedback loop, including: multiplying the adjustment coefficient by the original motor angle instruction sequence to generate an updated motor angle instruction sequence, inputting the updated instruction sequence into the feedback loop, driving the actuator and collecting the actual nip gap as the actual output, calculating the deviation between the actual output and the expected output, iteratively adjusting the parameters in the motor angle instruction sequence based on the deviation, until the deviation converges within a preset range.

[0046] Specifically, after obtaining the preliminary adjustment coefficient based on the simulation model, in order to overcome the influence of model simplification and parameter errors, the application adopts a closed-loop feedback mechanism to iteratively optimize the motor angle instruction sequence online. This process combines feedforward compensation with feedback correction, dynamically corrects the control instruction through continuous comparison of actual output and expected target, to ensure that the system converges to the optimal state.

[0047] Specifically, the refined adjustment coefficient is multiplied by the original motor angle instruction sequence to generate an updated instruction sequence that has been pre-compensated. This sequence controls the actuator through the servo driver to complete the preliminary adjustment of the nip gap. At the same time, the system starts the feedback optimization process, and the displacement sensor installed on the nip roller group collects actual gap data at a sampling frequency of 10 kHz in real time. These data are processed through digital filtering and used as the actual output value of the system. The actual output is compared with the expected target value set by the process in real time, and a deviation signal reflecting the control accuracy is calculated. This deviation value not only includes the residual error of the feedforward compensation, but also covers the influence of various unmodeled disturbances.

[0048] Based on the deviation signal, the system adopts an improved incremental PID control algorithm to correct the instruction sequence online. The control mechanism of the algorithm is that: the proportional term quickly responds to the change of the deviation, the integral term eliminates the steady-state error, and the differential term suppresses the overshoot phenomenon. The three work together to make the output deviation gradually converge along the negative gradient direction of the error surface. To ensure the stability and robustness of the control system, the embodiment also introduces a parameter adaptive mechanism. The mechanism dynamically adjusts the PID control parameters by monitoring the system response characteristics in real time, such as automatically reducing the proportional gain when the detection response is too fast, and appropriately increasing the integral coefficient when there is a persistent deviation. At the same time, the system also sets a safety guarantee strategy. When abnormal fluctuations or excessive overshoot are detected, it automatically switches to a conservative control mode. The convergence state is determined by monitoring the statistical characteristics of the output deviation in real time. When the output deviation of multiple consecutive control periods remains within the preset range, and the root mean square value of the deviation is less than the preset threshold, it is determined that the system has reached stable convergence. This closed-loop optimization mechanism of "instruction execution-output measurement-deviation calculation-parameter correction" enables the control system to have online self-correction and adaptive adjustment capabilities, and ultimately realizes real-time and accurate control of the roll gap of the current production task, making the adjustment accuracy stable and meeting the process requirements.

[0049] Step S4, when the adjustment accuracy meets the process requirements, obtain the dynamic deviation residual of the system, correct the dynamic deviation residual, and determine the final adaptive control parameter set. Based on the adaptive control parameter set, drive the actuator to adjust the roll gap.

[0050] In step S4, the dynamic deviation residual is corrected and the final adaptive control parameter set is determined, including: when the adjustment accuracy meets the process requirements, the dynamic deviation residual value is obtained from the system output; a residual correction model is constructed through a compensation mechanism, the dynamic deviation residual value is input into the correction model for correction calculation, and the corrected residual value is output; based on the corrected residual value, the adaptive control parameter set is obtained, including the gain and time constant of the control system; the stability of the adaptive control parameter set is verified, if the stability index is higher than the preset threshold, the adaptive control parameter set is confirmed to be effective, and is output as the final adaptive control parameter set.

[0051] Specifically, after the feedback control makes the system adjustment accuracy meet the process requirements, in order to optimize the control performance of subsequent production tasks, improve the system convergence speed and establish long-term adaptive ability, the application starts an offline optimization process based on dynamic deviation residual analysis and parameter self-learning. Specifically, a dynamic deviation residual collection and analysis system is established. When it is detected that the control accuracy of the press roll gap is continuously and stably within the range of the process requirements, it is marked that the system has entered the quasi-steady state working stage. At this time, the dynamic deviation data extracted from the control system output is the small difference sequence between the actual output value and the predicted output value based on the ideal mathematical model of the control system when the control accuracy of the press roll gap meets the process requirements and the system is in the quasi-steady state working. It contains the dynamic characteristics and external disturbance information that are not represented in the model, such as periodic micro-vibration caused by transmission chain wear or low-frequency fluctuation caused by material property change.

[0052] The specific implementation of residual correction and parameter optimization is as follows: First, a residual correction model based on modern control theory is constructed. This model can identify and separate the systematic deviation component and random noise component in the residual by establishing the mapping relationship between the residual sequence and the dynamic characteristics of the system. After inputting the collected dynamic deviation residual value into the model, real-time calculation is performed through the recursive least squares algorithm to effectively filter out measurement noise and extract corrected residual values reflecting the true dynamic characteristics of the system. Based on the corrected residual values, the model reference adaptive method is used to set the controller parameters. The core idea of this step is to use the corrected residual information to back-propagate the actual dynamic characteristics of the system, and then optimize the controller parameters. By solving the Lyapunov equation, the control parameters that can make the actual system dynamic characteristics tend to the ideal reference model are calculated, including the gain parameter that determines the response speed of the system and the time constant parameter that affects the stability of the system. These parameters together constitute the adaptive control parameter set.

[0053] After obtaining the adaptive control parameter set, strict stability verification is immediately performed. This step is crucial because inappropriate parameters can cause system instability. The verification process is based on the Nyquist stability criterion. By analyzing the open-loop frequency response characteristics of the control system, the phase margin and gain margin of the system are evaluated. When the verification result shows that the stability margins of the system are all higher than the preset safety threshold, it indicates that the parameter set can ensure the stability of the system under all expected working conditions. At this time, the adaptive control parameter set is confirmed to be effective and is output as the final parameter. Finally, the system downloads the verified adaptive control parameter set to the actuator drive system. This step completes the transformation process from parameter optimization to actual application. The new parameter set adjusts the core algorithm parameters of the servo controller to achieve precise regulation of the press roll gap, enabling the control system to automatically adapt to changes in equipment characteristics and maintain long-term stable control performance.

[0054] Step S5, the thickness uniformity index of the electrode plate output after adjustment is monitored in real time, if the deviation of the thickness uniformity from the target range exceeds the preset range, return to step S1, restart a new round of optimization cycle until the thickness uniformity index is qualified, and output the final control parameter.

[0055] In step S5, the thickness uniformity index of the electrode plate output after adjustment is monitored in real time, including: generating a driving signal according to the adaptive control parameter set, inputting the actuator to adjust the press roller gap, collecting the adjusted gap data, processing the collected gap data by filtering technology, calculating the thickness uniformity index of the electrode plate based on the processed data, including uniformity variance and average thickness, if the variance of the uniformity index is lower than the preset threshold, it is confirmed that the press roller gap adjustment is effective, and the thickness uniformity index is output.

[0056] Specifically, after completing the optimization of the control system parameters, in order to establish a complete quality closed loop control, the application constructs a final verification and feedback mechanism based on the actual quality index of the product. In specific implementation, the system first performs production control based on the optimized parameters: generate accurate driving signals based on the determined adaptive control parameter set, drive the actuator to adjust the press roller gap through the servo system, this step converts the results of all the technical optimizations into specific mechanical actions, realizes the accurate control of the press roller gap, and in the adjustment process, the thickness data of the electrode plate is collected in real time through the online thickness gauge, the sampling frequency is set to meet the quality monitoring requirements of the production process, to ensure that the real changes of the thickness of the electrode plate can be completely reflected.

[0057] The following technical solution is adopted for the accurate calculation of thickness uniformity index: First, the collected raw thickness data is filtered in real time. An adaptive Kalman filter algorithm is used to effectively separate the actual thickness variation and measurement noise in the signal. This processing is crucial for subsequent accurate calculation. Based on the high-quality filtered data, key quality indicators are calculated through the following steps: The average thickness index is calculated by statistically averaging the thickness values ​​of all sampling points within a set evaluation period. This index reflects the overall thickness level of the electrode sheet and is a core parameter for evaluating whether the product meets basic specifications. The uniformity variance index is calculated by using an unbiased estimation method in statistics to weighted average the squared deviations of the thickness of each sampling point from the average thickness. This index quantitatively characterizes the uniformity of thickness distribution in spatial and temporal dimensions and is directly related to the consistency and performance stability of battery products. The calculated thickness uniformity index is rigorously compared with the process standard. When the uniformity variance is lower than the preset qualified threshold and the average thickness meets the product specification requirements, the system determines that the current control parameters are valid, outputs a thickness uniformity qualified report, and locks the current control parameters as the standardized parameters for this production process. This determination is based on rigorous statistical process control principles to ensure the scientific nature and reliability of the decision.

[0058] When the system detects that the thickness uniformity index exceeds the preset range, it will automatically trigger the quality feedback mechanism, record the current quality deviation data, and further analyze the spatiotemporal distribution characteristics of the deviation to identify abnormal patterns. This complete quality information will serve as the input for a new round of optimization cycle and be fed back to the transmission ratio trend analysis stage in step S1, restarting the complete process from state perception to parameter optimization. This closed-loop control mechanism based on the final product quality ensures that the system can continuously self-optimize and gradually approach the optimal control state.

[0059] The above describes a dry electrode fabrication process control method according to an embodiment of this application. The following describes a dry electrode fabrication process control system according to an embodiment of this application. Please refer to [link / reference]. Figure 2 One embodiment of a dry electrode fabrication process control system in this application includes:

[0060] The data acquisition module is used to monitor and acquire data on the gap between the pressure rollers and the rotation angle of the drive motor in real time during the rolling process of dry electrode materials. The acquired data is classified and processed using a support vector machine algorithm to identify the trend of transmission ratio change of the pressure roller system.

[0061] The condition assessment module is used to combine the transmission ratio change trend with the historical wear data of the lead screw, and to assess the wear condition of the lead screw in the current pressure roller system through the condition estimation algorithm, and calculate the pitch accuracy offset caused by wear.

[0062] An iterative optimization module is configured to generate an adjustment coefficient for correcting the motor displacement instruction based on the pitch accuracy offset if the pitch accuracy offset exceeds a preset threshold, update the motor angle instruction sequence by using the adjustment coefficient, and perform iterative optimization on the updated instruction sequence through a feedback loop to improve the actual adjustment accuracy of the press roll gap.

[0063] A correction module is configured to obtain a dynamic deviation residual of the system when the adjustment accuracy meets the process requirement, correct the dynamic deviation residual, and determine a final adaptive control parameter set, and drive the actuator to adjust the press roll gap based on the adaptive control parameter set.

[0064] A cycle control module is configured to monitor the thickness uniformity of the electrode plate output after adjustment in real time, and if the deviation of the thickness uniformity from the target range exceeds a preset range, return to the acquisition module to restart a new round of optimization cycle until the thickness uniformity is qualified, and output the final control parameter.

[0065] The application also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, and the computer-readable storage medium stores instructions, which, when executed on a computer, cause the computer to perform the steps of the dry-process electrode preparation process control method.

[0066] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein.

[0067] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0068] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A dry electrode preparation process control method characterized by, The method comprises: Step S1: In the rolling forming process of the dry electrode material, the roll gap data and the rotation angle data of the driving motor are monitored and collected in real time, the collected data is classified and processed using a support vector machine algorithm, and the change trend of the transmission ratio of the roll system is identified; Step S2: In combination with the change trend of the transmission ratio and the historical wear data of the lead screw, the wear state of the lead screw in the current roll system is evaluated by a state estimation algorithm, and the pitch accuracy offset caused by wear is calculated; Step S3: If the pitch accuracy offset exceeds a preset threshold, an adjustment coefficient for correcting the motor displacement instruction is generated based on the pitch accuracy offset, the adjustment coefficient is used to update the motor angle instruction sequence, and the updated instruction sequence is iteratively optimized through a feedback loop to improve the actual adjustment accuracy of the roll gap; Step S4: When the adjustment accuracy meets the process requirements, the dynamic deviation residual of the system is obtained, the dynamic deviation residual is corrected and the final adaptive control parameter set is determined, and the roll gap is adjusted based on the adaptive control parameter set; Step S5: The thickness uniformity index of the electrode plate output after adjustment is monitored in real time, and if the deviation of the thickness uniformity from the target range exceeds the preset range, the process returns to step S1 to restart a new round of optimization cycle until the thickness uniformity index is qualified and the final control parameters are output.

2. The method of claim 1, wherein, The step S1 comprises: The roll gap data is collected in real time by a displacement sensor, and the rotation angle data of the driving motor is collected in real time by an encoder, and the collected roll gap data and rotation angle data are used as input feature vectors; A classification model is constructed using a support vector machine algorithm to classify the input feature vectors, obtain the classification result of the change trend of the transmission ratio, and fit the classification result to obtain the change trend curve of the transmission ratio, and calculate the change rate of the transmission ratio; If the change rate of the transmission ratio exceeds a preset threshold, the change trend of the transmission ratio is marked as an abnormal trend, otherwise it is marked as a normal trend, the key time points are extracted from the data according to the abnormal trend, the peak and valley values of the change trend of the transmission ratio are analyzed through the key time points, and the quantitative index of the change trend of the transmission ratio is obtained.

3. The method of claim 1, wherein, The step S2 comprises: The historical operation log is queried according to the change trend of the transmission ratio, and the lead screw wear related indexes including the wear rate and the cumulative wear amount that match the trend are extracted; The state vector and the covariance matrix of the Kalman filter are initialized, the lead screw wear related indexes are used as observation values, the Kalman filtering algorithm is used for iterative state estimation, the state prediction value is calculated and the prediction covariance matrix is updated; A measurement update step is performed, the Kalman gain is calculated, and the observation values and the state prediction values are fused to obtain the posterior state estimation value, and the final pitch accuracy offset is determined based on the posterior state estimation value.

4. The method of claim 1, wherein, In step S3, the adjustment coefficient for correcting the motor displacement instruction is generated based on the offset, which comprises: If the pitch accuracy offset exceeds a preset threshold, the pitch accuracy offset is input to a simulation model, and a meshing fluctuation amplitude caused by the pitch accuracy offset is calculated based on the simulation model, including a fluctuation frequency and an amplitude peak value; A displacement corresponding relationship curve is fitted according to the meshing fluctuation amplitude, an inverse of a curve slope is determined as a preliminary value of an adjustment coefficient, an optimization algorithm is used to calibrate the preliminary value to obtain a refined adjustment coefficient; The accuracy of the displacement corresponding relationship is verified through the refined adjustment coefficient, and if the accuracy is higher than a preset threshold, the adjustment coefficient is output.

5. The method of claim 4, wherein, The preliminary value is calibrated by using an optimization algorithm to obtain a refined adjustment coefficient, including: The gradient descent method is used for iterative search with the preliminary value as an initial point and minimizing the meshing fluctuation amplitude as an objective function; In each iteration, the gradient of the objective function with respect to the adjustment coefficient is calculated and the adjustment coefficient is updated in the opposite direction of the gradient, and when the change of the objective function is less than a convergence threshold or the maximum number of iterations is reached, the iteration is stopped, and the optimal solution at this time is taken as the refined adjustment coefficient.

6. The method of claim 5, wherein, The updated instruction sequence is iteratively optimized through the feedback loop in step S3, including: The adjustment coefficient is multiplied by the original motor angle instruction sequence to generate an updated motor angle instruction sequence, and the updated instruction sequence is input to the feedback loop to drive the actuator and collect the actual press roll gap as the actual output; The deviation between the actual output and the expected output is calculated, and based on the deviation, the parameters in the motor angle instruction sequence are iteratively adjusted until the deviation converges within a preset range.

7. The method of claim 1, wherein, The dynamic deviation residual is corrected and the final adaptive control parameter set is determined in step S4, including: When the adjustment accuracy meets the process requirements, the dynamic deviation residual value is obtained from the system output; A residual correction model is constructed through a compensation mechanism, the dynamic deviation residual value is input into the correction model for correction calculation, and the corrected residual value is output; Based on the corrected residual value, an adaptive control parameter set is obtained, including the gain and time constant of the control system; The stability of the adaptive control parameter set is verified, and if the stability index is higher than a preset threshold, the adaptive control parameter set is confirmed to be effective as the final adaptive control parameter set.

8. The method of claim 1, wherein, The thickness uniformity index of the electrode plate output after adjustment is monitored in real time in step S5, including: A driving signal is generated according to the adaptive control parameter set, and the press roll gap is adjusted by inputting the actuator to collect the adjusted gap data; The collected gap data is processed by using a filtering technique, and the thickness uniformity index of the electrode plate is calculated based on the processed data, including the uniformity variance and the average thickness; If the variance of the uniformity index is lower than a preset threshold, it is confirmed that the press roll gap adjustment is effective, and the thickness uniformity index is output.

9. A dry electrode production process control system for implementing a dry electrode production process control method according to any one of claims 1 to 8, characterized by, The system includes: A collection module is configured to monitor and collect press roll gap data and rotation angle data of a driving motor in real time during the rolling forming process of the dry-process electrode material, and to classify and process the collected data using a support vector machine algorithm to identify the transmission ratio change trend of the press roll system. The state evaluation module is configured to combine the transmission ratio change trend and historical wear data of the lead screw, evaluate the wear state of the lead screw in the current compression roller system through a state estimation algorithm, and calculate a pitch precision offset caused by wear; The iterative optimization module is configured to, if the pitch precision offset exceeds a preset threshold, generate an adjustment coefficient for correcting a motor displacement instruction based on the offset, update a motor angle instruction sequence using the adjustment coefficient, and perform iterative optimization on the updated instruction sequence through a feedback loop to improve the actual adjustment precision of the compression roller gap; The correction module is configured to, when the adjustment precision meets process requirements, obtain a dynamic deviation residual of the system, correct the dynamic deviation residual, and determine a final adaptive control parameter set, and drive an actuator to adjust the compression roller gap based on the adaptive control parameter set; The cycle control module is configured to monitor the thickness uniformity of the output electrode in real time, and if the deviation of the thickness uniformity from a target range exceeds a preset range, return to the acquisition module to restart a new round of optimization cycle until the thickness uniformity indicator is qualified, and output the final control parameter.

10. A computer-readable storage medium having stored thereon instructions, the instructions comprising, The instructions are executed by the processor to implement the dry-process electrode preparation process control method of any one of claims 1-8.

Images