Data-driven intelligent control method and system for the forming of toilet paper cores

Abstract

The present invention relates to an intelligent control method and system for the forming of toilet paper cores based on data driving, comprising the following steps S1: acquiring production process parameters and equipment operation status data and performing preprocessing; S2: constructing a mapping model of process quality and parameter data of production based on SVR; S3: predicting the quality of the process based on the mapping model and obtaining optimized control parameters based on a multi-objective optimization algorithm; S4: pushing the optimized control parameters to an intelligent control system and implementing closed-loop control by using a fuzzy PID control algorithm; S5: dynamically feeding back the actually collected real-time output process data to the modeling link to form a complete closed-loop feedback mechanism. The present invention can dynamically respond to environmental changes and process disturbances during the production process, so as to achieve the purposes of improving product quality, enhancing production efficiency and reducing resource consumption.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control, and particularly to an intelligent control method and system for the forming of toilet paper cores based on data driving. Background Art

[0002] With the rapid growth of the market demand in the toilet paper industry and the continuous improvement of product quality requirements, the traditional production method for core forming faces many challenges, such as low production efficiency, poor product quality stability, and a high dependence on the experience of operators. The traditional control method mainly adjusts fixed parameters and lacks accurate control over the relationship between process parameters and finished product quality in the actual production process, resulting in difficulty in real-time correction of production deviations caused by material fluctuations, equipment performance attenuation, or environmental changes, thereby increasing the scrap rate and production cost.

[0003] In recent years, the rapid development in the field of industrial control, especially the wide application of data-driven technologies, has provided new solutions for solving the complex process control problems in the forming of toilet paper cores. Summary of the Invention

[0004] To solve the above problems, the purpose of the present invention is to provide an intelligent control method for the forming of toilet paper cores based on data driving, which can dynamically respond to environmental changes and process disturbances during production, so as to improve product quality, increase production efficiency, and reduce resource consumption.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] The intelligent control method for the forming of toilet paper cores based on data driving includes the following steps:

[0007] S1: Obtain production process parameters and equipment operation status data, and perform preprocessing;

[0008] S2: Based on the preprocessed data, use the data-driven modeling method to construct a mapping model of the process quality and parameter data of production based on SVR;

[0009] S3: Based on the mapping model, perform quality prediction on the process, and obtain optimized control parameters based on the multi-objective optimization algorithm;

[0010] S4: Push the optimized control parameters to the intelligent control system, and through the comparison between the real-time collected data and the modeling prediction results, use the fuzzy PID control algorithm to dynamically adjust the influencing variables of tension, speed, and humidity to achieve closed-loop control;

[0011] S5: Dynamically feedback the actually produced process data collected in real time to the modeling link to form a complete closed-loop feedback mechanism.

[0012] Further, obtain the production process parameters and equipment operating status, specifically: use strain gauge type tension sensors, installed on both sides where the winding drum contacts the paper, to obtain the tension data of the paper during the winding process; use Hall effect encoders, installed at the end of the core drum shaft, to measure the rotational speed data of the servo motor; use digital humidity sensors, arranged in the area affected by environmental humidity and on one side of the paper surface, to obtain the moisture content of the paper and environmental humidity data; use thin-film pressure sensors, arranged in the pressing components of the winding drum, to monitor the pressing force data in real time; arrange triaxial vibration acceleration sensors on the rotating parts of the equipment to monitor the vibration amplitude and frequency data; and through temperature sensors, monitor the equipment temperature data in real time.

[0013] Further, perform preprocessing, specifically as follows: use low-pass filtering to smooth the high-frequency noise in the tension and pressure data; for the humidity and rotational speed data, use Kalman filtering to optimize the dynamic changes; use time series linear interpolation to fill in the missing values in the rotational speed and tension data; use mean filling, and use the mean of the historical window as the filling for the vibration and temperature data; finally, perform normalization processing on each data.

[0014] Further, construct a mapping model of the production process quality and parameter data based on SVR, specifically:

[0015] The input feature vector X is the preprocessed data, X = [T, v, H e , P, Vib, T e , H w ;

[0016] Among them, T is the tension, v is the rotational speed, H e is the environmental humidity, P is the pressure, Vib is the vibration, T e is the equipment temperature, and H w is the moisture content of the paper;

[0017] The output variable is Y = [Y1, Y2, Y3];

[0018] Among them, Y1 is the thickness uniformity, Y2 is the core roundness; Y3 is the tensile strength;

[0019] The mapping model of the production process quality and parameter data constructed based on SVR is:

[0020] ;

[0021] Among them, X i is the input feature vector of the i-th sample; is the composite kernel function; is the Lagrange multiplier, indicating the corresponding Y of the input feature vector X in the model i k ​Weight of; f k (X) is the prediction model for the k-th output Y k ; b k is the bias corresponding to Y k ; m is the number of samples in the training data;

[0022] The objective optimization function is:

[0023] ;

[0024] where C is the regularization coefficient; is the model complexity term; is the model parameter corresponding to Y k ; represents the Lagrange multiplier; K is the total number of quality indicators; respectively represent the slack variables in the positive and negative directions;

[0025] And set a dynamic error tolerance in the model to handle the error range of different sample inputs:

[0026]

[0027] where is the tolerance range of the i-th training sample; is the global basic tolerance parameter; σ i is the local variance of the input parameter of the i-th training sample.

[0028] Furthermore, the composite kernel function includes the RBF kernel , the polynomial kernel and the linear kernel , specifically as follows:

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] where c is the bias term, d is the order of the polynomial, is the width of the RBF kernel; λ1, λ2, λ3 are the weight coefficients.

[0034] Furthermore, the training of the mapping model is as follows:

[0035] Initialize the weight coefficients λ1, λ2, λ3 and the kernel parameters; and initially adjust the regularization coefficient C and the global basic tolerance parameter ;

[0036] The optimization problem of support vector regression is solved through the Lagrangian dual form:

[0037] ;

[0038] where X j is the input feature vector of the j-th sample; is the Lagrange multiplier of the j-th sample;

[0039] Use the sequential minimal optimization SMO algorithm to solve the dual problem and determine the non-zero Lagrange multipliers corresponding input feature vectors X i ; is the true value of the i-th sample with respect to the k-th quality index;

[0040] Combine the obtained input feature vectors to construct the mapping model of each output Y k ;

[0041] Further, S3 is specifically:

[0042] Through the trained mapping model f k (X) , predict the quality index in real time and calculate the sensitivity of each input process parameter X l to the mapping model f k (X) : S k,l :

[0043] ;

[0044] According to the sensitivity analysis results, sort the sensitivities S of all process parameters k,l in descending order of absolute value, determine the process parameters that have the greatest impact on the quality index, and prioritize the optimization of key variables;

[0045] Set the multi-objective optimization objective function F(X):

[0046] ;

[0047] where is the expected value of the k-th target quality index; is the weight of the k-th target; R(X) is the regularization term; λ is the weight coefficient of the regularization term;

[0048] According to the multi-objective optimization objective function, use NSGA-II to generate the Pareto solution set and obtain the parameter X for the optimization solution. opt .

[0049] Furthermore, S4 is specifically as follows:

[0050] Push the parameter X obtained from the optimization solution opt to the intelligent control system as the initial setting value;

[0051] Calculate the input control error, including the error and the error change rate :

[0052] ;

[0053] ;

[0054] where is the actual expected value, and t represents time;

[0055] According to e(t) and Δe(t), dynamically update the PID parameters:

[0056] ;

[0057] ;

[0058] ;

[0059] where are the proportional, integral, and differential coefficients dynamically adjusted by the fuzzy controller respectively; is the corresponding learning rate for adaptive adjustment; is the adjustment value for the k-th objective; is the time interval;

[0060] Fuzzy PID control output:

[0061] ;

[0062] where represents the time index; represents the error corresponding to the

[0063] u(t) is the change value of the adjustment variable:

[0064] ;

[0065] where is X lAdjusted new process parameters.

[0066] Further, S5 is specifically as follows:

[0067] Collect the current actual process parameter X real and the actual quality index Y real Compare with the model prediction value to calculate the error :

[0068] ;

[0069] Collect new real-time production data and merge it into the training set :

[0070] ;

[0071] where D old is the historical data set;

[0072] Update the SVR model:

[0073] ;

[0074] where m new is the number of data in the merged training set; argmin represents finding the parameter that minimizes the function;

[0075] Regularly adjust the fuzzy rule base and PID weights, update the optimal solution, and form a complete self-learning and feedback closed loop.

[0076] A data-driven intelligent control system for the forming of toilet paper cores includes a processor, a memory, and a computer program stored on the memory. When the processor executes the computer program, it specifically executes the steps in the above-mentioned data-driven intelligent control method for the forming of toilet paper cores.

[0077] The present invention has the following beneficial effects:

[0078] 1. The present invention can dynamically respond to environmental changes and process disturbances during the production process, so as to achieve the purpose of improving product quality, increasing production efficiency, and reducing resource consumption;

[0079] 2. By strengthening multi-objective prediction, introducing a composite kernel, and dynamically adjusting the error tolerance, the model will be significantly improved in non-linear modeling ability and generalization ability, and at the same time, the complex relationship between each process parameter and the quality index is easier to analyze and capture;

[0080] 3. Based on the fuzzy PID algorithm, the present invention dynamically adjusts and optimizes parameters, can respond to changes in equipment operation or external environment in real time, ensures the stability and reliability of the process, and compares the quality index data collected in real time with the model prediction value, calculates the error and optimizes the parameter settings, truly realizing end-to-end closed-loop control. Description of the Drawings

[0081] Figure 1 It is a flowchart of the method of the present invention. Detailed Embodiment

[0082] The following further describes the present invention in detail with reference to the drawings and specific embodiments:

[0083] Refer to Figure 1 In this embodiment, an intelligent control method for the forming of toilet paper cores based on data driving is provided, including the following steps:

[0084] S1: Obtain production process parameters and equipment operation status data, and perform preprocessing;

[0085] S2: Based on the preprocessed data, use the data-driven modeling method to construct a mapping model between the process quality and parameter data of production based on SVR;

[0086] S3: Based on the mapping model, perform quality prediction on the process, and obtain optimized control parameters based on the multi-objective optimization algorithm;

[0087] S4: Push the optimized control parameters to the intelligent control system, and through the comparison of the real-time collected data and the modeling prediction results, use the fuzzy PID control algorithm to dynamically adjust the influencing variables of tension, speed, and humidity to achieve closed-loop control;

[0088] S5: Dynamically feedback the actually produced process data collected in real time to the modeling link to form a complete closed-loop feedback mechanism.

[0089] In this embodiment, to obtain the production process parameters and equipment operation status, specifically: strain gauge type tension sensors are used and installed on both sides where the winding drum contacts the paper to obtain the tension data of the paper during winding; Hall effect encoders are used and installed at the end of the core drum shaft to measure the rotational speed data of the servo motor; digital humidity sensors (capacitive type) are used and arranged in the area affected by environmental humidity and on one side of the paper surface to obtain the moisture content of the paper and the environmental humidity data; thin-film pressure sensors are used and arranged on the pressing components of the winding drum to monitor the pressing force data in real time; triaxial vibration acceleration sensors are arranged on the rotating parts of the equipment to monitor the vibration amplitude and frequency data; the equipment temperature data is monitored in real time through temperature sensors.

[0090] In this embodiment, the preprocessing is as follows: low-pass filtering is adopted to smooth the high-frequency noise in the tension and pressure data; for the humidity and rotational speed data, Kalman filtering is used to optimize the dynamic changes; time series linear interpolation is adopted to fill in the missing values of the rotational speed and tension data; mean filling is adopted, and the mean value of the historical window is used as the filling for the vibration and temperature data; finally, normalization processing is performed on each data item.

[0091] In this embodiment, a mapping model of the process quality and parameter data for production is constructed based on SVR, specifically as follows:

[0092] The input feature vector X is the preprocessed data, X = [T, v, H e , P, Vib, T e , H w ;

[0093] where T is the tension, v is the rotational speed, H e is the environmental humidity, P is the pressure, Vib is the vibration, T e is the equipment temperature, H w is the moisture content of the paper;

[0094] The output variables are Y = [Y1, Y2, Y3];

[0095] where Y1 is the thickness uniformity; Y2 is the core roundness; Y3 is the tensile strength;

[0096] The mapping model of the process quality and parameter data for production constructed based on SVR is:

[0097] ;

[0098] where X i is the input feature vector of the i-th sample; is the composite kernel function; is the Lagrange multiplier, representing the weight of the corresponding Y i for the input feature vector X in the model; f k (X) is the prediction model for the k-th output Y k ; b k is the bias corresponding to Y k ; m is the number of samples in the training data; k The objective optimization function is:

[0099] where C is the regularization coefficient;

[0100]

[0101] is the model complexity term; is the corresponding Y fork Model parameters; Denote Lagrange multipliers; K is the total number of quality indicators; Denote slack variables in the positive and negative directions respectively;

[0102] And set a dynamic error tolerance in the model to handle the error range of different sample inputs:

[0103]

[0104] Where, Is the tolerance range of the i-th training sample; Is the global basic tolerance parameter; Is the local variance of the input parameters of the i-th training sample.

[0105] In this embodiment, the composite kernel function Includes the RBF kernel , polynomial kernel And linear kernel , specifically as follows:

[0106] ;

[0107] ;

[0108] ;

[0109] ;

[0110] Where, c is the bias term, d is the order of the polynomial, Is the width of the RBF kernel; λ1, λ2, λ3 are weight coefficients.

[0111] In this embodiment, the training of the mapping model is as follows:

[0112] Initialize the weight coefficients λ1, λ2, λ3 and kernel parameters (such as γ of RBF, d, c of polynomial kernel); and initially adjust the regularization coefficient C and the global basic tolerance parameter ;

[0113] The optimization problem of support vector regression is solved by the Lagrangian dual form:

[0114] ;

[0115] Where, X j Is the input feature vector of the j-th sample; Is the Lagrange multiplier of the j-th sample;

[0116] Solve the dual problem using the Sequential Minimal Optimization (SMO) algorithm to determine the non - zero Lagrange multipliers The corresponding input feature vector X i ; is the true value of the i - th sample with respect to the k - th quality index;

[0117] Combine the obtained input feature vectors to construct each output Y k mapping model.

[0118] In this embodiment, S3 is specifically:

[0119] Through the trained mapping model f k (X) , predict the quality index in real - time, and calculate the sensitivity of each input process parameter X l to the mapping model f k (X) sensitivity S k,l :

[0120] ;

[0121] Based on the sensitivity analysis results, sort the sensitivities S of all process parameters k,l in descending order of absolute value, determine the process parameters that have the greatest impact on the quality index, and prioritize optimizing the key variables;

[0122] Set the multi - objective optimization objective function F(X):

[0123] ;

[0124] where, is the expected value of the k - th target quality index; R(X) is the regularization term; λ is the weight coefficient of the regularization term;

[0125] According to the multi - objective optimization objective function, use NSGA - II to generate the Pareto solution set and obtain the optimized parameter X opt .

[0126] In this embodiment, S4 is specifically:

[0127] Push the optimized parameter X opt to the intelligent control system as the initial set value;

[0128] Calculate the input control error, including the error and the error change rate :

[0129] ;

[0130] ;

[0131] Among them, is the actual expected value, and t represents time;

[0132] Dynamically update the PID parameters according to e(t) and Δe(t):

[0133] ;

[0134] ;

[0135] ;

[0136] Among them, are the proportional, integral, and differential coefficients dynamically adjusted by the fuzzy controller respectively; is the corresponding learning rate for adaptive adjustment; is the adjustment value for the k-th target; is the time interval;

[0137] Fuzzy PID control output:

[0138] ;

[0139] Among them, represents the time index; represents the error corresponding to the time;

[0140] u(t) is the change value of the adjustment variable (such as tension, speed, or humidity):

[0141] ;

[0142] Among them, is X l the new adjusted process parameter .

[0143] In this embodiment, S5 is specifically:

[0144] Collect the current actual process parameter X real and the actual quality index Y real Compare with the model prediction value and calculate the error :

[0145] ;

[0146] Collect new real-time production data , combined into a training set :

[0147] ;

[0148] Among them, D old is the historical data set;

[0149] Update the SVR model:

[0150] ;

[0151] Among them, m new is the number of data in the combined training set; argmin represents finding the parameter that minimizes the function;

[0152] Regularly adjust the fuzzy rule base and PID weights, update the optimal solution, and form a complete self-learning and feedback closed loop.

[0153] The data-driven intelligent control system for the forming of toilet paper cores includes a processor, a memory, and a computer program stored on the memory. When the processor executes the computer program, it specifically executes the steps in the above-mentioned data-driven intelligent control method for the forming of toilet paper cores.

[0154] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0155] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0156] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 in one block or multiple blocks.

[0157] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to produce a computer-implemented process, thereby providing steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 in one block or multiple blocks.

[0158] As described above, it is only a preferred embodiment of the present invention, and it is not a limitation to the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A data-driven intelligent control method for toilet paper roll core forming, characterized in that: The following steps are included S1: Obtain production process parameters and equipment operation status data, and pre-process them; S2: Based on the preprocessed data, a data-driven modeling method is used to build a mapping model between production process quality and parameter data based on SVR; S3: Based on the mapping model, the quality of the process is predicted, and the optimization control parameters are obtained based on the multi-objective optimization algorithm; S4: Push the optimized control parameters to the intelligent control system, compare the real-time collected data with the modeling prediction results, and use the fuzzy PID control algorithm to dynamically adjust the tension, speed, and humidity influencing variables to achieve closed-loop control; S5: Dynamically feed back the actual output process data collected in real time to the modeling link to form a complete closed-loop feedback mechanism; The mapping model between process quality and parameter data of production based on SVR is specifically as follows: The input feature vector X is the preprocessed data, X=[T,v,H e ,P,Vib,T e ,H w ]; Where, T is the tension, v is the speed, H e is the ambient humidity, P is the pressure, Vib is the vibration, T e is the device temperature, H w is the moisture content of paper; The output variable is Y=[Y1,Y2,Y3]; Among them, Y1 is thickness uniformity; Y2 is the roundness of the core; Y3 is the tensile strength; The mapping model between process quality and parameter data of production based on SVR is: ； Among them, X i is the input feature vector of the i-th sample; is the composite kernel function; is the Lagrange multiplier, which represents the input feature vector X in the model i The corresponding Y k The weight of k (X) is the k-th output Y k The prediction model of k For the corresponding Y k The bias of; m is the number of samples in the training data; The objective optimization function is: ； Where C is the regularization coefficient; is the model complexity term; For the corresponding Y k Model parameters of represents the Lagrange multiplier; K is the total number of quality indicators; denote the slack variables in the positive and negative directions respectively; And set a dynamic error tolerance in the model to handle the error range of different sample inputs: ； in, is the tolerance range of the i-th training sample; is the global basic tolerance parameter; σ i is the local variance of the input parameters of the ith training sample; The S3 is specifically: Through the trained mapping model f k (X) , predicting quality indicators in real time and calculating each input process parameter X l Mapping Model f k (X) Sensitivity S k,l : ； Through the sensitivity analysis results, the sensitivity S of all process parameters k,l Sort by absolute value, determine the process parameters that have the greatest impact on quality indicators, and prioritize the optimization of key variables; Set the multi-objective optimization objective function F(X): ； in, is the expected value of the kth target quality index; R(X) is the regularization term; λ is the weight coefficient of the regularization term; According to the multi-objective optimization objective function, NSGA-II is used to generate the Pareto solution set and obtain the optimized solution parameter X opt .

2. The data-driven intelligent control method for toilet paper roll core forming according to claim 1, characterized in that: The method for obtaining the production process parameters and the equipment operation status is as follows: a strain gauge tension sensor is installed on both sides of the winding drum in contact with the paper to obtain the tension data of the paper during the winding process; a Hall effect encoder is installed on the end of the winding core drum shaft to measure the rotation speed data of the servo motor; a digital humidity sensor is arranged in the environmental humidity influence area and on one side of the paper surface to obtain the paper moisture content and environmental humidity data; a thin film pressure sensor is arranged in the clamping component of the winding drum to monitor the clamping force data in real time; a three-axis vibration accelerometer sensor is arranged on the rotating part of the equipment to monitor the vibration amplitude and frequency data; and a temperature sensor is used to monitor the equipment temperature data in real time.

3. The data-driven intelligent control method for toilet paper roll core forming according to claim 2 is characterized in that: The preprocessing is specifically as follows: low-pass filtering is used to smooth the high-frequency noise in the tension and pressure data; Kalman filtering is used to optimize the dynamic changes of humidity and speed data; time series linear interpolation is used to fill missing values ​​in the speed and tension data; mean filling is used to fill the vibration and temperature data with the mean of the historical window; and finally, each data is normalized.

4. The data-driven intelligent control method for toilet paper roll core forming according to claim 1, characterized in that: The composite kernel function Including RBF kernel , polynomial kernel and the linear kernel , as follows: ； ; ； ； Where c is the bias term, d is the order of the polynomial, is the width of the RBF kernel; λ1, λ2, λ3 are weight coefficients.

5. The data-driven intelligent control method for toilet paper roll core forming according to claim 4 is characterized in that: The training of the mapping model is as follows: Initialize weight coefficients λ1, λ2, λ3 and kernel parameters; and initially adjust regularization coefficient C and global base tolerance parameters ; The optimization problem of support vector regression is solved using the Lagrangian dual form: ； Among them, X j is the input feature vector of the jth sample; is the Lagrange multiplier of the jth sample; Solve the dual problem using the Sequential Minimal Optimization (SMO) algorithm and determine the non-zero Lagrange multipliers The corresponding input feature vector X i ; is the true value of the i-th sample regarding the k-th quality indicator; Combine the obtained input feature vector to construct each output Y k The mapping model.

6. The data-driven intelligent control method for toilet paper roll core forming according to claim 1, characterized in that: The S4 is specifically: The parameter X to be optimized opt Push to the intelligent control system as the initial setting value; Calculate the input control error, including the error and error rate of change : ； ； in, is the actual expected value, t represents time; According to e(t) and Δe(t), dynamically update PID parameters: ； ； ； in, They are the proportional, integral and differential coefficients dynamically adjusted by the fuzzy controller; is the corresponding adaptively adjusted learning rate; is the adjustment value of the kth target; is the time interval; Fuzzy PID control output: ； in, Indicates the time index; express The error corresponding to the moment; u(t) is the change in the adjustment variable: ； in, for X l The new process parameters after adjustment.

7. The data-driven intelligent control method for toilet paper roll core forming according to claim 6, characterized in that: The S5 is specifically: Collect the current actual process parameters X real and the actual quality index Y real With the model prediction value Compare and calculate the error : ； Collect new real-time production data , merged into the training set : ； Among them, D old For historical data sets; Update SVR model: ； Among them, m new is the number of training set data after merging; argmin means finding the parameter that minimizes the function; Regularly adjust the fuzzy rule base and PID weights, update the optimization solution, and form a complete self-learning and feedback closed loop.

8. A data-driven intelligent control system for toilet paper roll core forming, characterized in that: It includes a processor, a memory and a computer program stored in the memory. When the processor executes the computer program, it specifically executes the steps in the data-driven intelligent control method for toilet paper roll core forming as described in any one of claims 1 to 7.

Images