Film drawing and unwinding intelligent control method and system based on real-time tension

Abstract

The invention discloses an intelligent film-drawing and unwinding control method and system based on real-time tension, and relates to the field of automatic control and intelligent manufacturing, and the method comprises the following steps: ensuring normal starting of equipment and system states through equipment self-inspection and technological parameter input; tension and speed data are collected in real time and preprocessed, and support is provided for fuzzy PID control; the parameters of the fuzzy PID controller are dynamically adjusted by calculating the tension error and the change rate of the tension error so as to adapt to different membrane material characteristics and unwinding working conditions; an improved genetic algorithm is used for optimizing parameters of a PID controller, overshoot is minimized, the adjusting time is shortened, and the robustness and the anti-interference capability of the system are improved; a closed-loop control system is constructed, and the stability of unwinding tension is ensured through real-time feedback signals; and the system state is monitored in real time in combination with an anomaly detection algorithm, and a control strategy is automatically adjusted or fault protection is performed. The control method disclosed by the invention can be widely applied to the fields of film unwinding and automatic production lines, and has a relatively high intelligent level.

Description

Technical Field

[0001] The present invention relates to the fields of automatic control and intelligent manufacturing, and particularly to an intelligent control method and system for film unwinding based on real-time tension. Background Art

[0002] With the continuous development of automation technology, film unwinding systems have been widely used in industrial production. Especially in fields such as packaging, printing, and textiles, precise control of the unwinding tension is an important link to ensure product quality. The core task of tension control is to prevent the film material from being over-tightened or loose by monitoring and adjusting the tension of the film material in real time during the unwinding process, ensuring the smoothness and efficiency of the production process. However, when facing high speeds, large loads, and complex working conditions, there are still problems with low control accuracy and stability in tension control.

[0003] Currently, when the traditional PID control algorithm is used to process the unwinding system, although it has a certain degree of adaptability, due to its fixed parameter settings and insufficient adaptability to dynamic changes, the control effect is not ideal in an environment with large tension fluctuations or strong external interference. Although fuzzy PID control can enhance the adaptability and robustness of the system through a fuzzy rule base, there are still challenges in system parameter optimization. Especially when dealing with multiple variable factors, the performance of traditional fuzzy control algorithms is difficult to meet the requirements of complex applications.

[0004] To address the above problems, the present invention provides an intelligent control method and system for film unwinding based on real-time tension, which combines variable universe fuzzy PID control with an improved genetic algorithm (IGA). This method optimizes the PID parameters by collecting tension data in real time and combining with the genetic algorithm to ensure that the system can provide high-precision control under complex working conditions. In addition, the system can dynamically adjust the control parameters according to different working conditions, enhancing the anti-interference ability against external disturbances and achieving higher unwinding accuracy and stability. Summary of the Invention

[0005] The present invention addresses the above problems by providing an intelligent control method and system for film unwinding based on real-time tension, so as to solve the problems of insufficient adaptability to dynamic changes in the prior art and unsatisfactory control effects in an environment with large tension fluctuations or strong external interference.

[0006] To solve the above technical problems, the present invention provides the following technical solution: An intelligent control method for film unwinding based on real-time tension, comprising the following steps:

[0007] Step S1, check the device status, input process parameters and select the control mode, perform self-check to ensure that the device and parameters meet the startup conditions, and if abnormal, alarm and prohibit startup;

[0008] Among them, in step S1, the following sub-steps are further included:

[0009] S1-1. Conduct equipment status monitoring through sensor self-check, actuator detection, and communication status confirmation, perform electrical connection testing and signal integrity verification to ensure accurate data acquisition;

[0010] S1-2. Input process parameters and select control modes on the HMI interface. The process parameters include: target tension value, initial unwinding speed, film thickness, width, and roll diameter; the control modes are divided into: automatic control mode and manual control mode. The system defaults to the automatic control mode, and the automatic control mode is a fuzzy PID control mode optimized based on the improved genetic algorithm (IGA), and the manual control mode is used as an alternative;

[0011] S1-3. Automatically execute the self-check program after parameter input to confirm that both the equipment status and parameter configuration meet the startup conditions; if an abnormality occurs, it will automatically alarm and prohibit startup, and can only be started after manual intervention.

[0012] Step S2. Real-time collect tension and speed data, calculate the error and the rate of change of the error to provide real-time data support for fuzzy PID control;

[0013] Among them, in step S2, the following sub-steps are further included:

[0014] S2-1. Real-time monitor the film tension through a tension sensor, output a digital signal to the controller, and the data sampling frequency is higher than the system dynamic response frequency to ensure real-time performance; use an encoder to real-time monitor the rotation speed of the unwinding roller and the change in film displacement, and dynamically calculate the film linear speed in combination with the roll diameter;

[0015] S2-2. Filter the collected tension and speed data, use Kalman filtering to eliminate noise and outliers, and calculate the error between the actual tension and the set tension and the rate of change of the error, specifically as shown in formulas (1)-(2):

[0016] E(t) = T set - T actual Formula (1)

[0017]

[0018] Among them, E(t) is the real-time tension error, T set is the set tension, T actual is the actual tension; ΔE is the rate of change of the tension error; the error and the rate of change of the error are used as input variables of the fuzzy PID controller to drive subsequent adaptive control.

[0019] Step S3: Adjust the parameters of the fuzzy PID controller by calculating the tension error and change rate to dynamically adapt to different film materials and unwind conditions;

[0020] Among them, in step S3, the following sub-steps are further included:

[0021] S3-1: Based on empirical knowledge and experimental data, construct a fuzzy rule base, specifically as follows:

[0022] If the tension is too large and the error increases rapidly, quickly reduce the unwind speed;

[0023] If the tension is too small and the error changes slowly, moderately increase the unwind speed;

[0024] If the tension fluctuates greatly and the error is small, maintain the current speed to avoid over-adjustment;

[0025] If the tension approaches the set value and the error continues to decrease, gradually reduce the unwind speed to achieve a smooth end;

[0026] If the tension changes violently and the error increases, increase the response speed and moderately increase the adjustment amplitude;

[0027] S3-2: Design a variable universe fuzzy controller. Adopt the variable universe strategy to dynamically adjust the input and output universes of the fuzzy controller according to the system error:

[0028] When the tension fluctuates violently, expand the universe range to improve the response speed;

[0029] When the system tends to be stable, narrow the universe range to reduce overshoot and jitter;

[0030] S3-3: The fuzzy controller dynamically adjusts the PID parameters according to the real-time error and error change rate, specifically as shown in equations (3)-(5):

[0031] K p =K p0 +ΔK p (E,ΔE) Equation (3)

[0032] K i =K i0 +ΔK i (E,ΔE) Equation (4)

[0033] K d =K d0 +ΔK d (E,ΔE) Equation (5)

[0034] Among them, K p ,K i ,K d are the real-time proportional, integral, and differential coefficients respectively, K p0, K i0 , K d0 are the initial ratio, integral, and differential coefficients respectively, and ΔK p (E, ΔE), ΔK i (E, ΔE), ΔK d (E, ΔE) are the dynamic quantities of the proportional, integral, and differential coefficients respectively.

[0035] Step S4: Use the genetic algorithm to optimize the fuzzy PID control parameters, minimize overshoot, settling time, and steady-state error, and improve the global optimization ability and anti-interference ability of the system;

[0036] Among them, in step S4, the following sub-steps are also included:

[0037] S4-1: Define the optimization objective of the fuzzy PID controller, and the optimization objective is specifically as follows:

[0038] Minimize the overshoot. By optimizing the proportional coefficient of the controller, reduce the amplitude by which the system exceeds the set value during the response process, and improve the stability of the system;

[0039] Shorten the settling time. By adjusting the integral coefficient and differential coefficient, ensure that the system can quickly return to the steady state and reduce the response time of the system;

[0040] Reduce the steady-state error. By optimizing the parameters of the PID controller, especially the proportional and integral coefficients, reduce the residual error of the system in the steady state;

[0041] Improve the robustness of the system. Ensure that the system can operate stably under different working conditions and has strong anti-interference ability;

[0042] S4-2: Construct a fitness function according to the optimization objective, and use the genetic algorithm to optimize the parameters of the fuzzy PID controller. The fitness function comprehensively considers the following performance indicators, specifically as shown in Equation (6):

[0043] F = w1·Overshoot + w2·Settling Time + w3·Steady-state Error

[0044] Equation (6)

[0045] Among them, w1, w2, and w3 are weight coefficients, Overshoot is the overshoot, Settling Time is the settling time, and Steady-state Error is the steady-state error;

[0046] S4-3: Optimize the parameters of the fuzzy PID controller through the genetic algorithm (IGA), and the specific process is as follows:

[0047] Population initialization: Randomly generate a set of PID parameters as the initial population, where each individual represents a set of controller parameters;

[0048] Fitness evaluation: Evaluate each individual according to the fitness function defined in step S4-2, and calculate its control performance under the current working conditions, including overshoot, adjustment time, and steady-state error;

[0049] Selection operation: Adopt the tournament selection strategy to select individuals with higher fitness to enter the next generation, ensuring the inheritance of excellent individuals;

[0050] Crossover operation: Use the simulated binary crossover operator to combine the PID parameters of two parent individuals to generate new offspring individuals, enhancing the diversity of the solution space;

[0051] Mutation operation: Introduce an adaptive mutation mechanism to dynamically adjust the mutation probability based on the individual fitness, in order to avoid premature convergence and explore more possible solution spaces;

[0052] Elite retention strategy: Retain the best individual of the previous generation to ensure that the best solution of each generation is directly passed to the next generation, preventing the loss of excellent solutions;

[0053] Iteration and convergence: After multiple generations of iteration, the population gradually converges to the optimal solution, obtaining the best PID parameter combination;

[0054] Parameter application: Apply the optimized optimal PID parameters to the fuzzy PID controller and adjust the unwinding tension in real time to ensure that the system can maintain high-precision control under complex working conditions.

[0055] Step S5, construct a closed-loop control system, adjust the control signal through real-time feedback, and adopt double-loop control to ensure tension stability and adapt to different working condition changes;

[0056] Among them, in step S5, the following sub-steps are also included:

[0057] S5-1, closed-loop control system construction: Use the actual tension as the feedback signal to form a closed-loop control structure, and compare the error with the target tension in real time;

[0058] S5-2, real-time feedback adjustment mechanism: Based on the real-time collected data, the system automatically adjusts the control output signal, dynamically adjusts the speed of the servo motor and the unwinding tension to ensure the minimum error;

[0059] S5-3, introduce double-loop control, the inner loop is for fast-response tension adjustment; the outer loop is for long-term stable control of the film position and speed;

[0060] S5-4, Adaptive control adjustment. During the closed-loop feedback process, the system automatically adjusts the fuzzy rules and PID parameters according to different working conditions, ensuring that the system can maintain high-performance operation in various environments.

[0061] Step S6, Real-time monitor the system parameters, combine the anomaly detection algorithm to automatically adjust the control strategy, correct minor anomalies, and automatically protect the equipment safety for serious anomalies.

[0062] Among them, in step S6, the following sub-steps are also included:

[0063] S6-1, Anomaly status monitoring. Real-time monitor the key parameters of the system. The key parameters include tension, speed, and displacement. Set the threshold range to detect whether there is an over-limit phenomenon; identify common anomalies, including film material breakage, sudden tension change, sensor failure, and motor overload;

[0064] S6-2, Anomaly detection algorithm. Combine the convolutional neural network CNN deep learning algorithm and the support vector machine. Identify potential anomalies in the tension fluctuation through the trained model. Analyze the collected data in real time according to the machine learning algorithm model, identify normal and abnormal states, and respond quickly to improve the detection accuracy and processing speed;

[0065] S6-3, Adaptive correction mechanism. For minor anomalies, the system automatically adjusts the control strategy, including adjusting the PID parameters and changing the control mode to achieve adaptive correction; for serious anomalies, the system automatically switches to the safe mode and performs emergency shutdown if necessary to protect the equipment and products;

[0066] S6-4, Alarm and fault handling. When an anomaly is detected, the system automatically records the anomaly data and sends an alarm signal to prompt the operator to intervene; the system supports remote fault diagnosis and automatic recovery functions, reducing the fault shutdown time and improving the system availability.

[0067] An intelligent control system for film unwinding based on real-time tension, including:

[0068] Data acquisition module, data processing module, control module, feedback and monitoring module, and user interface;

[0069] The data acquisition module includes: a tension sensor, an encoder, a temperature sensor, and a displacement sensor, which are used to collect the film material tension, speed, temperature, and displacement data in real time and transmit them to the data processing module;

[0070] The data processing module includes: a real-time data processing unit, a fuzzy PID controller, a genetic algorithm optimization unit, and an anomaly detection unit, which are responsible for data preprocessing, tension control, parameter optimization, and fault detection;

[0071] The control module includes: a PLC controller and a servo driver, which are used to receive the control signals output by the data processing module and adjust the speed and tension of the unwinding motor;

[0072] The feedback and monitoring module includes: a closed-loop control feedback loop, a remote monitoring interface, and an alarm system, which are used to monitor the unwinding tension in real time and automatically adjust the control strategy or give a fault alarm when an abnormality occurs;

[0073] The user interface includes an HMI, which is used for users to set and adjust process parameters, select control modes, and monitor the system status.

[0074] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0075] The present invention combines variable universe fuzzy PID control and an improved genetic algorithm (IGA). By dynamically adjusting the PID control parameters, it can effectively reduce the tension fluctuation and overshoot phenomenon, ensure the stability of the tension during the unwinding process, and achieve more precise tension control.

[0076] The present invention optimizes the PID control parameters by introducing a genetic algorithm, which improves the robustness of the system under complex working conditions; when facing changes in film material types, speed fluctuations, and external disturbances, it can automatically adjust the control parameters, maintain high-precision tension control, and avoid the sensitivity of traditional control methods to external disturbances.

[0077] Based on the real-time acquisition of tension data, the present invention can quickly respond to changes in working conditions and automatically optimize the control parameters through a closed-loop feedback and adaptive adjustment mechanism, enabling the system to continuously maintain the best performance under different working conditions, reducing manual intervention and adjustment, and improving production efficiency.

[0078] The present invention adopts an anomaly detection algorithm based on deep learning and support vector machine (SVM), which can monitor and identify system anomalies in real time, quickly respond and correct them when a fault occurs. This intelligent fault warning mechanism effectively improves the safety and stability of the system and reduces the fault downtime. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0080] Figure 1 is the method flow chart of the present invention;

[0081] Figure 2It is the system architecture diagram of the present invention. Detailed implementation manners

[0082] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but is merely for the selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0083] Please refer to Figure 1 - Figure 2 It is a schematic diagram of an intelligent control method and system for film unwinding based on real-time tension provided by an embodiment of the present invention, including the following steps:

[0084] Step S1, check the device status, input process parameters and select a control mode, perform self-check to ensure that the device and parameters meet the startup conditions. If there is an abnormality, an alarm will be given to prohibit startup;

[0085] Among them, in step S1, the following sub-steps are further included:

[0086] S1-1, monitor the device status through sensor self-check, actuator detection and communication status confirmation, perform electrical connection tests and signal integrity verification to ensure accurate data acquisition;

[0087] S1-2, input process parameters and select a control mode on the HMI interface. The process parameters include: target tension value, initial unwinding speed, film thickness, width and roll diameter; the control modes are divided into: automatic control mode and manual control mode. The system defaults to the automatic control mode, and the automatic control mode is a fuzzy PID control mode optimized based on the improved genetic algorithm (IGA), and the manual control mode is used as an alternative;

[0088] S1-3, automatically execute the self-check program after the parameter input is completed, and confirm that both the device status and parameter configuration meet the startup conditions; if an abnormality occurs, an alarm will be automatically given and startup will be prohibited, and manual intervention is required before startup.

[0089] It should be noted that the sensor self - inspection includes: checking whether the tension sensor, encoder, and displacement sensor components are working properly to ensure error - free signal acquisition; the actuator detection includes: checking the operating status of the servo motor, driver, and unwinding mechanism to confirm no jamming and abnormal noise faults; the communication status confirmation includes: ensuring stable and reliable data communication between the PLC, HMI, and each control unit.

[0090] The target tension value is: setting an ideal tension range according to the film material type and process requirements; the initial unwinding speed is: inputting the initial unwinding speed according to production requirements; the film material characteristic parameters are: including physical parameters such as film thickness, width, and initial coil diameter.

[0091] The fuzzy PID control combines fuzzy logic and traditional PID control to handle non - linear and uncertainty problems and adapt to different working condition changes; the fuzzy controller adjusts the PID parameters according to the tension error and its change rate to dynamically optimize the control performance.

[0092] Traditional fuzzy PID parameters usually rely on empirical settings and are difficult to cope with dynamic changes under complex working conditions. Introducing IGA to optimize the parameters of the fuzzy controller, such as the proportional coefficient, integral coefficient, and differential coefficient, offline can improve the global optimization ability of the system.

[0093] Step S2, real - time collect tension and speed data, calculate the error and the error change rate, providing real - time data support for fuzzy PID control;

[0094] Among them, in step S2, the following sub - steps are also included:

[0095] S2 - 1, real - time monitor the film material tension through the tension sensor, output digital signals to the controller, and the data sampling frequency is higher than the system dynamic response frequency to ensure real - time performance; use the encoder to real - time monitor the rotation speed of the unwinding roller and the change of film material displacement, and dynamically calculate the film material linear speed in combination with the coil diameter;

[0096] S2 - 2, perform filtering processing on the collected tension and speed data, use Kalman filtering to eliminate noise and outliers, and calculate the error between the actual tension and the set tension and the error change rate, specifically as shown in equations (1) - (2):

[0097] E(t)=T set -T actual Equation (1)

[0098]

[0099] Among them, E(t) is the real - time tension error, T set is the set tension, T actualis the actual tension; ΔE is the rate of change of tension error; the error and the rate of change of error are used as the input variables of the fuzzy PID controller to drive the subsequent adaptive control.

[0100] Step S3, by calculating the tension error and the rate of change, adjust the parameters of the fuzzy PID controller to dynamically adapt to different film material characteristics and unwind conditions;

[0101] Among them, in step S3, the following sub-steps are also included:

[0102] S3-1, based on empirical knowledge and experimental data, construct a fuzzy rule base, specifically as follows:

[0103] If the tension is too large and the error increases rapidly, quickly reduce the unwind speed;

[0104] If the tension is too small and the change of error is slow, moderately increase the unwind speed;

[0105] If the tension fluctuates greatly and the error is small, keep the current speed to avoid over-adjustment;

[0106] If the tension is close to the set value and the error continues to decrease, gradually reduce the unwind speed to achieve a smooth end;

[0107] If the tension changes violently and the error increases, increase the response speed and moderately increase the adjustment amplitude;

[0108] S3-2, design of a variable universe fuzzy controller, adopt a variable universe strategy, and dynamically adjust the input and output universes of the fuzzy controller according to the system error:

[0109] When the tension fluctuates violently, expand the universe range to improve the response speed;

[0110] When the system tends to be stable, narrow the universe range to reduce overshoot and jitter;

[0111] S3-3, the fuzzy controller dynamically adjusts the PID parameters according to the real-time error and the rate of change of error, specifically as shown in equations (3)-(5):

[0112] K p =K p0 +ΔK p (E,ΔE) Equation (3)

[0113] K i =K i0 +ΔK i (E,ΔE) Equation (4)

[0114] K d =K d0 +ΔK d (E,ΔE) Equation (5)

[0115] Among them, K p , K i , K d are the real-time proportional, integral, and derivative coefficients respectively, and K p0 , K i0 , K d0 are the initial proportional, integral, and derivative coefficients respectively. ΔK p (E, ΔE), ΔK i (E, ΔE), ΔK d (E, ΔE) are the dynamic quantities of the proportional, integral, and derivative coefficients respectively.

[0116] Step S4: Use the genetic algorithm to optimize the fuzzy PID control parameters, minimize overshoot, settling time, and steady-state error, and improve the global optimization ability and anti-interference ability of the system;

[0117] Among them, in step S4, the following sub-steps are also included:

[0118] S4-1: Define the optimization objective of the fuzzy PID controller, and the optimization objective is specifically as follows:

[0119] Minimize the overshoot. By optimizing the proportional coefficient of the controller, reduce the amplitude by which the system exceeds the set value during the response process and improve the stability of the system;

[0120] Shorten the settling time. By adjusting the integral coefficient and derivative coefficient, ensure that the system can quickly return to the steady state and reduce the response time of the system;

[0121] Reduce the steady-state error. By optimizing the parameters of the PID controller, especially the proportional and integral coefficients, reduce the residual error of the system in the steady state;

[0122] Improve the robustness of the system. Ensure that the system can operate stably under different working conditions and has strong anti-interference ability;

[0123] S4-2: Construct a fitness function according to the optimization objective, and use the genetic algorithm to optimize the parameters of the fuzzy PID controller. The fitness function comprehensively considers the following performance indicators, specifically as shown in Equation (6):

[0124] F = w1·Overshoot + w2·Settling Time + w3·Steady-state Error

[0125] Equation (6)

[0126] Among them, w1, w2, and w3 are weight coefficients, Overshoot is the overshoot, Settling Time is the settling time, and Steady-state Error is the steady-state error;

[0127] S4-3. Optimize the parameters of the fuzzy PID controller through the improved genetic algorithm (IGA). The specific process is as follows:

[0128] Population initialization: Randomly generate a set of PID parameters as the initial population, where each individual represents a set of controller parameters.

[0129] Fitness evaluation: Evaluate each individual according to the fitness function defined in step S4-2, and calculate its control performance under the current working conditions, including overshoot, adjustment time, and steady-state error.

[0130] Selection operation: Adopt the tournament selection strategy to select individuals with higher fitness to enter the next generation, ensuring the inheritance of excellent individuals.

[0131] Crossover operation: Use the simulated binary crossover operator to combine the PID parameters of two parent individuals to generate new offspring individuals, enhancing the diversity of the solution space.

[0132] Mutation operation: Introduce an adaptive mutation mechanism to dynamically adjust the mutation probability according to the individual fitness, avoiding premature convergence and exploring more possible solution spaces.

[0133] Elite retention strategy: Retain the best individual of the previous generation to ensure that the best solution of each generation is directly passed to the next generation, preventing the loss of excellent solutions.

[0134] Iteration and convergence: After multiple generations of iteration, the population gradually converges to the optimal solution, obtaining the best PID parameter combination.

[0135] Parameter application: Apply the optimized optimal PID parameters to the fuzzy PID controller and adjust the unwinding tension in real time to ensure that the system can maintain high-precision control under complex working conditions.

[0136] It should be noted that the main objectives of this optimization process include minimizing overshoot, shortening the adjustment time, reducing the steady-state error, improving the system robustness, and maintaining stability under different film materials and different production conditions; the optimization steps: through operations such as population initialization, fitness evaluation, selection, crossover, and mutation in the improved genetic algorithm (IGA), continuously adjust the parameters of the fuzzy PID controller, and finally obtain the optimal parameter combination.

[0137] The control output signal acts on the servo motor, dynamically adjusts the proportional, integral, and differential parameters according to the real-time error, and adjusts the unwinding speed in real time to maintain the tension stable.

[0138] Step S5. Construct a closed-loop control system, adjust the control signal through real-time feedback, and adopt double closed-loop control to ensure the tension stability and adapt to different working conditions.

[0139] Among them, in step S5, the following sub-steps are also included:

[0140] S5-1. Construction of a closed-loop control system, using the actual tension as a feedback signal to form a closed-loop control structure, and comparing the error with the target tension in real time;

[0141] S5-2. Real-time feedback adjustment mechanism. Based on the real-time collected data, the system automatically adjusts the control output signal, dynamically adjusts the rotation speed of the servo motor and the unwinding tension to ensure the minimization of the error;

[0142] S5-3. Introduction of double closed-loop control. The inner loop is for rapid-response tension adjustment; the outer loop is for long-term stable control of the film position and speed;

[0143] S5-4. Adaptive control adjustment. During the closed-loop feedback process, the system automatically adjusts the fuzzy rules and PID parameters according to different working conditions changes to ensure that the system can maintain high-performance operation in various environments.

[0144] Step S6. Real-time monitoring of system parameters, automatically adjusting the control strategy in combination with the anomaly detection algorithm, correcting minor anomalies, and automatically protecting the safety of the equipment for serious anomalies.

[0145] Among them, in step S6, the following sub-steps are also included:

[0146] S6-1. Anomaly status monitoring. Real-time monitoring of key system parameters, where the key parameters include tension, speed, and displacement. Set the threshold range to detect whether there is an over-limit phenomenon; identify common anomalies, including film breakage, sudden tension change, sensor failure, and motor overload;

[0147] S6-2. Anomaly detection algorithm. Combining the convolutional neural network CNN deep learning algorithm and the support vector machine, identifying potential anomalies in the tension fluctuation through the trained model, analyzing the collected data in real time according to the machine learning algorithm model, identifying normal and abnormal states, and making a rapid response to improve the detection accuracy and processing speed;

[0148] S6-3. Adaptive correction mechanism. For minor anomalies, the system automatically adjusts the control strategy, including adjusting the PID parameters and changing the control mode to achieve adaptive correction; for serious anomalies, the system automatically switches to the safe mode and performs an emergency stop if necessary to protect the equipment and products;

[0149] S6-4. Alarm and fault handling. When an anomaly is detected, the system automatically records the anomaly data and sends an alarm signal to prompt the operator to intervene; the system supports remote fault diagnosis and automatic recovery functions to reduce the fault downtime and improve the system availability.

[0150] An intelligent control system for film unwinding based on real-time tension, comprising:

[0151] A data acquisition module, a data processing module, a control module, a feedback and monitoring module, and a user interface;

[0152] The data acquisition module includes: a tension sensor, an encoder, a temperature sensor, and a displacement sensor, which are used to collect the film tension, speed, temperature, and displacement data in real time and transmit them to the data processing module;

[0153] The data processing module includes: a real-time data processing unit, a fuzzy PID controller, a genetic algorithm optimization unit, and an anomaly detection unit, which are responsible for data preprocessing, tension control, parameter optimization, and fault detection;

[0154] The control module includes: a PLC controller and a servo driver, which are used to receive the control signals output by the data processing module and adjust the speed and tension of the unwinding motor;

[0155] The feedback and monitoring module includes: a closed-loop control feedback loop, a remote monitoring interface, and an alarm system, which are used to monitor the unwinding tension in real time and automatically adjust the control strategy or give a fault alarm when an anomaly occurs;

[0156] The user interface includes an HMI, which is used for users to set and adjust process parameters, select control modes, and monitor the system status.

[0157] The above is only the preferred embodiment of the present invention and is not used to limit the present invention. For those skilled in the art, there are various changes and modifications to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent control method for film unwinding based on real-time tension, characterized in that: The following steps are involved: Step S1, check the equipment status, input process parameters and select control mode, perform self-check to ensure that the equipment and parameters meet the startup conditions, and alarm to prohibit startup if abnormal; Step S2, real-time collection of tension and speed data, calculation of error and error change rate, and providing real-time data support for fuzzy PID control; Step S3, by calculating the tension error and the rate of change, adjusting the fuzzy PID controller parameters to dynamically adapt to different film material characteristics and unwinding conditions; Step S4, using genetic algorithm to optimize fuzzy PID control parameters, minimize overshoot, adjustment time and steady-state error, and improve the system's global optimization ability and anti-interference ability; Step S5, constructing a closed-loop control system, adjusting the control signal through real-time feedback, and using double closed-loop control to ensure tension stability and adapt to changes in different working conditions; Step S6, real-time monitoring of system parameters, automatic adjustment of control strategies in combination with anomaly detection algorithms, correction of minor anomalies, and automatic protection of equipment safety in the event of serious anomalies.

2. According to claim 1, a film-pulling and unwinding intelligent control method based on real-time tension is characterized in that: Wherein step S1 also includes the following sub-steps: S1-1, monitor the equipment status through sensor self-test, actuator detection and communication status confirmation, conduct electrical connection test and signal integrity verification to ensure accurate data collection; S1-2, input process parameters and select control mode on the HMI interface. The process parameters include: target tension value, initial unwinding speed, film thickness, width and roll diameter; the control mode is divided into: automatic control mode and manual control mode. The system defaults to automatic control mode. The automatic control mode is a fuzzy PID control mode optimized based on the improved genetic algorithm (IGA). The manual control mode is an alternative. S1-3, after completing the parameter input, the self-test procedure is automatically executed to confirm that the device status and parameter configuration meet the startup conditions; If an abnormality occurs, an alarm will be automatically triggered and startup will be prohibited. It can only be started after manual intervention.

3. The intelligent control method for film unwinding based on real-time tension according to claim 1, characterized in that: Wherein step S2 also includes the following sub-steps: S2-1, monitor the film tension in real time through the tension sensor, output digital signals to the controller, and the data sampling frequency is higher than the system dynamic response frequency to ensure real-time performance; use the encoder to monitor the speed of the unwinding roller and the displacement change of the film material in real time, and calculate the linear speed of the film material in combination with the roll diameter; S2-2, filter the collected tension and speed data, use Kalman filtering to remove noise and outliers, and calculate the error between the actual tension and the set tension and the error change rate, as shown in formulas (1)-(2): E(t)=T set -T actual Formula (1) Where E(t) is the real-time tension error, T set To set the tension, T actual is the actual tension; ΔE is the tension error change rate; the error and the error change rate are used as input variables of the fuzzy PID controller to drive the subsequent adaptive control.

4. The intelligent control method for film unwinding based on real-time tension according to claim 1, characterized in that: Wherein step S3 also includes the following sub-steps: S3-1, based on empirical knowledge and experimental data, construct a fuzzy rule base, as follows: If the tension is too high and the error increases rapidly, quickly reduce the unwinding speed; If the tension is too small and the error changes slowly, increase the unwinding speed appropriately; If the tension fluctuates greatly and the error is small, maintain the current speed to avoid over-adjustment; If the tension is close to the set value and the error continues to decrease, the unwinding speed is gradually reduced to achieve a smooth ending; If the tension changes dramatically and the error increases, increase the response speed and moderately increase the adjustment range; S3-2, variable domain fuzzy controller design, adopts variable domain strategy to dynamically adjust the input and output domain of the fuzzy controller according to the system error: When the tension fluctuates violently, the domain range is expanded to improve the response speed; When the system tends to be stable, the domain range is reduced to reduce overshoot and jitter; S3-3, the fuzzy controller dynamically adjusts the PID parameters according to the real-time error and the error change rate, as shown in equations (3) to (5): K p = K p0 + ΔK p (E, ΔE) Equation (3) K i = K i0 + ΔK i (E, ΔE) Equation (4) K d = K d0 + ΔK d (E, ΔE) Equation (5) Among them, K p , K i , K d are real-time proportional, integral, and differential coefficients, respectively, K p0 , K i0 , K d0 are the initial proportional, integral, and differential coefficients, ΔK p (E, ΔE), ΔK i (E, ΔE), ΔK d (E, ΔE) are the dynamic quantities of proportional, integral and differential coefficients respectively.

5. The intelligent control method for film unwinding based on real-time tension according to claim 1, characterized in that: Wherein step S4 also includes the following sub-steps: S4-1, define the optimization target of the fuzzy PID controller, the optimization target is as follows: Minimize overshoot, by optimizing the proportional coefficient of the controller, reduce the amplitude of the system exceeding the set value during the response process, and improve the stability of the system; Shorten the adjustment time, by adjusting the integral coefficient and differential coefficient, ensure that the system can quickly return to a steady state and reduce the system response time; Reduce steady-state error by optimizing the parameters of the PID controller, especially the proportional and integral coefficients, to reduce the residual error of the system in a stable state; Improve system robustness, ensure that the system can operate stably under different working conditions, and have strong anti-interference ability; S4-2, construct a fitness function according to the optimization target, and use the genetic algorithm to optimize the parameters of the fuzzy PID controller. The fitness function comprehensively considers the following performance indicators, as shown in formula (6): F=w1·Overshoot+w2·SettlingTime+w3·Steady-stateError Formula (6) Among them, w1, w2, w3 are weight coefficients, Overshoot is the overshoot, SettlingTime is the adjustment time, and Steady-stateError is the steady-state error; S4-3, optimize the parameters of the fuzzy PID controller through genetic algorithm (IGA), the specific process is as follows: Population initialization: randomly generate a set of PID parameters as the initial population, each individual represents a set of controller parameters; Fitness evaluation: According to the fitness function defined in step S4-2, each individual is evaluated to calculate its control performance under the current working conditions, including overshoot, adjustment time and steady-state error; Selection operation: adopt the tournament selection strategy to select individuals with higher fitness to enter the next generation, ensuring the inheritance of excellent individuals; Crossover operation: Use the simulated binary crossover operator to combine the PID parameters of two parent individuals to generate new offspring individuals and enhance the diversity of the solution space; Mutation operation: Introduce an adaptive mutation mechanism to dynamically adjust the mutation probability based on individual fitness to avoid early convergence and explore more possible solution spaces; Elite retention strategy: retain the best individuals of the previous generation to ensure that the best solution of each generation is directly passed to the next generation to prevent the loss of excellent solutions; Iteration and convergence: After multiple generations of iterations, the population gradually converges to the optimal solution and obtains the best PID parameter combination; Parameter application: The optimal PID parameters obtained through optimization are applied to the fuzzy PID controller, and the unwinding tension is adjusted in real time to ensure that the system can maintain high-precision control under complex working conditions.

6. The intelligent control method for film unwinding based on real-time tension according to claim 1, characterized in that: Wherein, in step S5, the following sub-steps are also included: S5-1, closed-loop control system construction, using actual tension as feedback signal to form a closed-loop control structure, and performing error comparison with target tension in real time; S5-2, real-time feedback adjustment mechanism, based on real-time collected data, the system automatically adjusts the control output signal, dynamically adjusts the servo motor speed and unwinding tension to ensure that the error is minimized; S5-3, introduces dual closed-loop control, the inner loop is for fast response tension adjustment; the outer loop is for long-term stable control of film position and speed; S5-4, adaptive control adjustment. During the closed-loop feedback process, the system automatically adjusts the fuzzy rules and PID parameters according to different operating conditions to ensure that the system can maintain high performance in various environments.

7. The intelligent control method for film unwinding based on real-time tension according to claim 1, characterized in that: Wherein, in step S6, the following sub-steps are also included: S6-1, abnormal state monitoring, real-time monitoring of key system parameters, including tension, speed and displacement, setting threshold ranges, detecting whether there is an over-limit phenomenon; identifying common abnormalities, including film breakage, tension mutation, sensor failure and motor overload; S6-2, anomaly detection algorithm, combines the convolutional neural network (CNN) deep learning algorithm with the support vector machine to identify potential anomalies in tension fluctuations through training models, analyzes the collected data in real time according to the machine learning algorithm model, identifies normal and abnormal states, responds quickly, and improves detection accuracy and processing speed; S6-3, adaptive correction mechanism. For minor abnormalities, the system automatically adjusts the control strategy, including adjusting PID parameters and changing the control mode, to achieve adaptive correction. For serious abnormalities, the system automatically switches to safe mode and performs emergency shutdown when necessary to protect equipment and products. S6-4, alarm and fault handling. When an abnormality is detected, the system automatically records the abnormal data and sends an alarm signal to prompt the operator to intervene. The system supports remote fault diagnosis and automatic recovery functions to reduce fault downtime and improve system availability.

8. An intelligent control system for film unwinding based on real-time tension, applied to an intelligent control method for film unwinding based on real-time tension as claimed in any one of claims 1 to 7, characterized in that: Data acquisition module, data processing module, control module, feedback and monitoring module and user interface; The data acquisition module includes: a tension sensor, an encoder, a temperature sensor and a displacement sensor, which are used to collect film material tension, speed, temperature and displacement data in real time and transmit them to the data processing module; The data processing module includes: a real-time data processing unit, a fuzzy PID controller, a genetic algorithm optimization unit and an abnormality detection unit, which are responsible for data preprocessing, tension control, parameter optimization and fault detection; The control module includes: a PLC controller and a servo driver, which are used to receive the control signal output by the data processing module and adjust the speed and tension of the unwinding motor; The feedback and monitoring module includes: a closed-loop control feedback loop, a remote monitoring interface and an alarm system, which are used to monitor the unwinding tension in real time and automatically adjust the control strategy or issue a fault alarm when an abnormality occurs; The user interface includes an HMI, which is used by the user to set and adjust process parameters, select control modes, and monitor system status.

Images