Acrylic filament one-way filament feeding tension cooperative control system and acrylic filament one-way filament feeding tension cooperative control method

Abstract

The invention relates to the technical field of program control, in particular to a one-way filament feeding tension cooperative control system and method for acrylic filaments. The yarn feeding tension cooperative control of the acrylic filament in the molecular orientation stretching process through the multiple sets of rollers along the one-way path comprises the steps that first data of the key position of the one-way yarn feeding path and the running speed of the multiple sets of rollers are obtained; a dynamic feature control model is constructed to analyze the first data and the operation speed, and a preliminary control instruction is generated; compensating and adjusting the stretching predicted value according to the control deviation; the wire feeding process is adjusted according to the preliminary control instruction, and second data and a second running speed are obtained; a distributed cooperative control model is constructed to analyze the preliminary control instruction, and a control adjustment strategy is generated based on global tension distribution balance and key section tension gradient stability; and on the basis of low-delay information interaction, controlling a second operation speed according to the control adjustment strategy, and obtaining a globally optimized and coordinated speed control instruction.

Description

Technical Field

[0001] The present invention relates to the technical field of program control, and in particular to a coordinated control system and method for one-way feeding tension of acrylic filaments. Background Art

[0002] In continuous feeding processes, precise parameter control is crucial to ensuring processing quality, especially in unidirectional feeding applications. Unidirectional feeding processes require the material to be continuously fed in a single direction and are widely used in processing links such as stretching and winding. During this process, maintaining parameter stability is crucial to preventing uneven performance. However, the material's sensitivity to external stress and its high elongation characteristics make precise control of processing parameters a technical challenge. Improper parameter settings, such as being too high or too low, can negatively impact material properties and process results. In multi-stage or complex feeding paths, traditional single-point control methods have difficulty achieving parameter coordination across all links, resulting in insufficient processing consistency. In addition, the processing process has strict requirements on the system's response speed, requiring real-time monitoring and dynamic adjustment of relevant parameters to cope with process changes. In existing technologies, some equipment relies on a single feedback mechanism for parameter control. Although this is acceptable in basic applications, it has limitations in achieving multi-point coordinated control and rapid response. This control method is not effective in complex processing scenarios, especially in processes with extremely high requirements for continuity and parameter stability, where quality issues frequently occur. Existing technologies lack an effective multi-point collaborative control mechanism and cannot meet the requirements of modern processing technology for high precision and high stability.

[0003] Therefore, a coordinated control system and method for the unidirectional feeding tension of acrylic filaments is proposed. Summary of the Invention

[0004] The object of the present invention is to provide a one-way wire feeding tension collaborative control system and method for acrylic filaments, and the collaborative control of the wire feeding tension of acrylic filaments during molecular orientation stretching along a one-way path through multiple groups of rollers includes: obtaining first data of key positions of the one-way wire feeding path and the running speeds of multiple groups of rollers; constructing a dynamic characteristic control model to analyze the first data and the running speed, and generate preliminary control instructions; compensating and adjusting the stretching prediction value according to the control deviation; adjusting the wire feeding process according to the preliminary control instructions to obtain second data and a second running speed; constructing a distributed collaborative control model to analyze the preliminary control instructions, and generating a control adjustment strategy based on the global tension distribution balance and the stability of the tension gradient of the key section; based on low-latency information interaction, controlling the second running speed according to the control adjustment strategy to obtain a globally optimized and coordinated speed control instruction.

[0005] To achieve the above object, the present invention provides the following technical solutions: A unidirectional feeding tension coordinated control system for acrylic filaments, which coordinates the feeding tension of acrylic filaments during molecular orientation stretching along a unidirectional path through multiple roller groups, includes: A data acquisition unit for acquiring first data of key positions of a one-way wire feeding path and running speeds of multiple groups of rollers in real time; An initial control instruction acquisition unit constructs a dynamic feature control model to analyze the first data and the operating speed to generate a preliminary control instruction; the preliminary control instruction includes a control deviation, a stretch prediction value, and a first operating speed; the stretch prediction value is compensated and adjusted based on the control deviation; and the wire feeding process is adjusted based on the preliminary control instruction to obtain second data and a second operating speed. A control adjustment strategy generation unit constructs a distributed collaborative control model to analyze the second data and the second operating speed, and generates a control adjustment strategy based on the global tension distribution balance and the key section tension gradient stability; The global optimization coordination instruction generation unit controls the second operating speed based on the low-latency information interaction between multiple groups of rollers according to the control adjustment strategy to obtain the global optimization and coordinated speed control instructions.

[0006] Preferably, a tension sensor array is arranged along the acrylic filament feeding path, and the tension sensor array is set at the entrance section, tension mutation section, stretching roller group and winding pre-tensioning section of the wire feeding path to collect real-time data of each section of acrylic filament respectively; the tension amplitude change rate is obtained based on the real-time data, and the key position of the unidirectional wire feeding path is determined, specifically, the tension fluctuation amplitude difference rate between two adjacent sensors is calculated. When the tension fluctuation amplitude difference rate exceeds a preset threshold, it is determined to be a key position, and the tension data collected by the sensor corresponding to the key position is used as the first data.

[0007] Preferably, the dynamic feature control model includes a data preprocessing layer, a feature extraction layer, a prediction modeling layer and a control decision layer: The data preprocessing layer performs normalization processing, outlier detection and correction on the first data and the running speed; The feature extraction layer uses a wavelet transform decomposition method to extract time-frequency domain features from the processed first data, and performs dimensionality reduction processing through a principal component analysis method to generate a reduced-dimensional feature vector; The prediction modeling layer generates a tensile prediction value by analyzing the dimension-reduced feature vector, wherein the tensile prediction value includes a tension prediction value at each key position; The control decision layer calculates the control deviation by comparing the deviation between the actual tension and the tension prediction value, and compensates and adjusts the tension prediction value. According to the adjusted tension prediction value, the tension-speed nonlinear mapping model is used to obtain the first operating speed and generate an initial control instruction.

[0008] Preferably, the tension-speed nonlinear mapping model constructs a dual-input single-output nonlinear regression model based on historical production data, the input variables are the adjusted tensile prediction value and the current roller running speed, and the output variable is the speed adjustment amount; the running speed is adjusted by the speed adjustment amount to obtain the first running speed.

[0009] Preferably, the distributed collaborative control model includes a state assessment layer, a local strategy generation layer and a global collaborative optimization layer: The state evaluation layer receives the preliminary control instruction, the second data and the second operating speed, and calculates the global tension distribution balance and the key section tension gradient stability; The local strategy generation layer designs local control adjustment strategies for different tension distribution states, including steady-state control strategy, transitional state control strategy and fluctuation suppression strategy; the control adjustment strategy includes control parameters, including speed adjustment step coefficient, tension compensation coefficient, gradient smoothing factor and collaborative weight coefficient; The global collaborative optimization layer adopts the hierarchical analysis method to determine the weights of the control parameters, and combines the particle swarm optimization algorithm to dynamically find the optimal control parameters based on the local control adjustment strategies of different rollers to generate the control adjustment strategy.

[0010] Preferably, the specific process of obtaining the globally optimized coordinated speed control instruction includes: Based on the second operating speed and control adjustment strategy, a multi-objective optimization function is constructed based on the balance of global tension distribution, the smoothness of tension gradient in key sections, and the minimization of speed variation. An improved differential evolution algorithm is used to iteratively solve the multi-objective optimization function. During the iteration process, the Lagrangian constraint method is used to address the system's physical constraints, including upper and lower speed limits for each roller, speed ratios between adjacent rollers, and speed change rate constraints, to generate the optimal speed vector. Based on the optimal speed vector, a globally optimized and coordinated speed control instruction is obtained.

[0011] A method for collaboratively controlling the unidirectional feeding tension of acrylic filaments, which collaboratively controls the feeding tension of acrylic filaments during molecular orientation stretching along a unidirectional path through multiple groups of rollers, includes: Real-time acquisition of first data of key positions of a one-way wire feeding path and the running speeds of multiple sets of rollers; A dynamic feature control model is constructed to analyze the first data and the operating speed to generate a preliminary control instruction; the preliminary control instruction includes a control deviation, a stretch prediction value, and a first operating speed; the stretch prediction value is compensated and adjusted according to the control deviation; the first operating speed is obtained by adjusting the operating speed according to the stretch prediction value; the wire feeding process is adjusted according to the preliminary control instruction to obtain second data and a second operating speed; Construct a distributed collaborative control model to analyze the second data and the second operating speed, and generate a control adjustment strategy based on the global tension distribution balance and the stability of the tension gradient in the key section; Based on low-latency information interaction between multiple groups of rollers, the second operating speed is controlled according to the control adjustment strategy to obtain a globally optimized and coordinated speed control instruction.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention constructs a dynamic feature control model to perform real-time preprocessing, time-frequency domain feature extraction, and principal component dimensionality reduction on the tension data and roller running speed at key locations along the unidirectional wire feeding path. This generates a predicted tensile value and implements compensation adjustments based on the deviation between the actual tension and the predicted tension at the control decision layer. It can capture sudden changes and subtle fluctuations in tension in real time, calculate the speed adjustment amount using a tension-speed nonlinear mapping model, and achieve targeted speed control for each set of rollers. This not only makes the tension distribution of acrylic filaments more uniform during the molecular orientation stretching process, but also significantly reduces defects such as broken wires, broken ends, and inconsistent fineness caused by tension fluctuations, thereby improving the qualified rate of spinning lines and the consistency between product batches.

[0013] 2. Aiming at the problem of tension coordination among multiple groups of rollers with complex coupling, the present invention proposes a distributed collaborative control model, which includes a state evaluation layer, a local strategy generation layer, and a global collaborative optimization layer. By deploying the tension sensor array at multiple points along the path entrance, tension mutation section, stretching roller group, and winding pre-tightening section, the second data and the second operating speed are collected in real time, and the tension distribution balance and gradient stability index are calculated to evaluate the state of each key section. In the local strategy generation layer, strategies are designed based on three typical working conditions: steady state, transition state, and fluctuation suppression. The hierarchical analysis method is used at the global level to determine the weights of the control parameters, and then the particle swarm optimization algorithm is combined for dynamic optimization to generate the optimal control adjustment strategy. It effectively reduces the information interaction delay and control conflict between nodes, and ensures the stability and scalability of the system under high-speed operation.

[0014] 3. In the speed control command generation phase, the present invention constructs a multi-objective optimization function based on the second operating speed and a distributed control strategy, taking into account global tension balance, tension gradient stability, and minimization of speed variation. This function is then iteratively solved using a differential evolution algorithm. During the calculation process, physical constraints are embedded in the system using a Lagrangian constraint method, ensuring both process quality requirements and minimizing equipment energy consumption and mechanical wear. This method achieves a balanced optimization of energy consumption and efficiency while ensuring the molecular orientation stretching quality of acrylic filaments, thereby improving the overall energy efficiency and economic benefits of the production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic structural diagram of a unidirectional tension coordinated control system for acrylic filament yarn provided by the present invention; Figure 2 A schematic flow chart of a method for coordinated control of unidirectional feeding tension of acrylic filament provided by the present invention; Figure 3 A schematic diagram of the dynamic feature control model structure provided by the present invention; Figure 4 This is a schematic diagram of the distributed collaborative control model structure provided by the present invention. DETAILED DESCRIPTION

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] Example 1 See also Figures 1 to 4 The present invention provides a coordinated control system for the tension of acrylic filament unidirectional wire feeding, the overall structure of which is as follows: Figure 1 As shown. Technical solution reference Figure 2 Specifically, the coordinated control of the feeding tension of acrylic filaments during molecular orientation stretching along a unidirectional path through multiple sets of rollers includes: Real-time acquisition of first data of key positions of a one-way wire feeding path and the running speeds of multiple sets of rollers; Furthermore, a tension sensor array is arranged along the acrylic filament feeding path. The tension sensor array is set at the entrance section, tension mutation section, stretching roller group and winding pre-tensioning section of the wire feeding path to collect real-time data of each section of acrylic filament respectively; the tension amplitude change rate is obtained based on the real-time data, and the key position of the unidirectional wire feeding path is determined, specifically, the tension fluctuation amplitude difference rate between two adjacent sensors is calculated. When the tension fluctuation amplitude difference rate exceeds a preset threshold, it is determined to be a key position, and the tension data collected by the sensor corresponding to the key position is used as the first data.

[0018] In this embodiment, the present invention arranges a tension sensor array at the entrance section, tension mutation section, stretching roller group and winding pre-tensioning section along the wire feeding path, and locates key positions in real time in combination with the tension amplitude change rate analysis method. It can perform fine monitoring and rapid closed-loop adjustment of the acrylic filament feeding tension, effectively suppress tension fluctuations and oscillations, significantly reduce the wire breakage rate, and improve the fiber stretching uniformity and mechanical properties.

[0019] A dynamic feature control model is constructed to analyze the first data and the operating speed to generate a preliminary control instruction; the preliminary control instruction includes a control deviation, a stretch prediction value, and a first operating speed; the stretch prediction value is compensated and adjusted according to the control deviation; the first operating speed is obtained by adjusting the operating speed according to the stretch prediction value; the wire feeding process is adjusted according to the preliminary control instruction to obtain second data and a second operating speed; Furthermore, the dynamic feature control model refers to Figure 3 , including data preprocessing layer, feature extraction layer, prediction modeling layer and control decision layer: The data preprocessing layer performs normalization processing, outlier detection and correction on the first data and the running speed; The feature extraction layer uses a wavelet transform decomposition method to extract time-frequency domain features from the processed first data, and performs dimensionality reduction processing through a principal component analysis method to generate a reduced-dimensional feature vector; The prediction modeling layer generates a tensile prediction value by analyzing the dimension-reduced feature vector, wherein the tensile prediction value includes a tension prediction value at each key position; The control decision layer calculates the control deviation by comparing the deviation between the actual tension and the tension prediction value, and compensates and adjusts the tension prediction value. According to the adjusted tension prediction value, the tension-speed nonlinear mapping model is used to obtain the first operating speed and generate an initial control instruction.

[0020] In this embodiment, the present invention constructs a dynamic feature control model, conducts in-depth analysis and prediction of real-time tension data and roller speed information, can generate more accurate initial control instructions and adaptively compensate and adjust during operation, realize forward-looking prediction and closed-loop optimization of acrylic filament stretching tension, effectively suppress tension fluctuations and oscillations, reduce wire breakage and rework rates, improve fiber stretching uniformity and mechanical properties, and at the same time realize intelligent system operation and energy consumption optimization, greatly improving production efficiency and product quality.

[0021] Furthermore, the tension-speed nonlinear mapping model constructs a dual-input single-output nonlinear regression model based on historical production data, the input variables are the adjusted tensile prediction value and the current roller operating speed, and the output variable is the speed adjustment amount; the operating speed is adjusted by the speed adjustment amount to obtain the first operating speed.

[0022] In this embodiment, the tension-speed nonlinear mapping model of the present invention constructs a dual-input single-output regression model based on historical production data, with the compensated stretching prediction value and the current roller speed as input, and fine-tunes the roller speed through the predicted speed adjustment amount to achieve precise control that quickly responds to tension requirements, significantly suppress oscillation, reduce wire breakage rate and rework rate, improve filament stretching uniformity and mechanical properties, and optimize energy consumption and production efficiency.

[0023] Construct a distributed collaborative control model to analyze the second data and the second operating speed, and generate a control adjustment strategy based on the global tension distribution balance and the stability of the tension gradient in the key section; Furthermore, the distributed collaborative control model refers to Figure 4 , including the state evaluation layer, the local strategy generation layer and the global collaborative optimization layer: The state evaluation layer receives the preliminary control instruction, the second data and the second operating speed, and calculates the global tension distribution balance and the key section tension gradient stability; The local strategy generation layer designs local control adjustment strategies for different tension distribution states, including steady-state control strategy, transitional state control strategy and fluctuation suppression strategy; the control adjustment strategy includes control parameters, including speed adjustment step coefficient, tension compensation coefficient, gradient smoothing factor and collaborative weight coefficient; The global collaborative optimization layer adopts the hierarchical analysis method to determine the weights of the control parameters, and combines the particle swarm optimization algorithm to dynamically find the optimal control parameters based on the local control adjustment strategies of different rollers to generate the control adjustment strategy.

[0024] In this embodiment, the constructed distributed collaborative control model quantitatively analyzes the real-time tension distribution balance and tension gradient stability through the state assessment layer, combines the steady-state, transitional state, and fluctuation suppression control schemes in the local strategy generation layer, and uses the hierarchical analysis method and particle swarm optimization algorithm in the global collaborative optimization layer to dynamically determine the speed adjustment step size, tension compensation coefficient, gradient smoothing factor, and collaborative weight coefficient, achieving an organic synergy between the global balance of tension distribution and local gradient stability among multiple roller groups. It can not only adapt to tension disturbances under different production conditions and quickly suppress oscillations and mutations, but also realize online optimization and updating of optimal control parameters for the entire line, further reducing the breakage rate and rework rate, improving the uniformity of filament stretching, mechanical properties, and production yield, and significantly enhancing production stability and economic benefits.

[0025] Based on low-latency information interaction between multiple groups of rollers, the second operating speed is controlled according to the control adjustment strategy to obtain a globally optimized and coordinated speed control instruction; Furthermore, the specific process of obtaining the globally optimized coordinated speed control instruction includes: Based on the second operating speed and control adjustment strategy, a multi-objective optimization function is constructed based on the balance of global tension distribution, the smoothness of tension gradient in key sections, and the minimization of speed variation. An improved differential evolution algorithm is used to iteratively solve the multi-objective optimization function. During the iteration process, the Lagrangian constraint method is used to address the system's physical constraints, including upper and lower speed limits for each roller, speed ratios between adjacent rollers, and speed change rate constraints, to generate the optimal speed vector. Based on the optimal speed vector, a globally optimized and coordinated speed control instruction is obtained.

[0026] In this embodiment, low-latency information interaction between multiple groups of rollers and an improved differential evolution algorithm are utilized, and multi-objective optimization is used to take into account tension balance, gradient smoothness, and minimization of speed changes. In combination with Lagrangian constraints, real-time constraints are imposed on the upper and lower limits of roller speed, speed ratio, and change rate. This can generate globally optimal and coordinated speed control instructions, achieve rapid suppression and uniform distribution of tension fluctuations, and significantly improve production stability and fiber quality.

[0027] The present invention achieves refined tension monitoring by placing tension sensor arrays at key locations along the acrylic filament feeding path and combining them with real-time positioning of the tension amplitude change rate. A dynamic feature control model based on data preprocessing, wavelet decomposition, and principal component analysis is introduced to conduct in-depth analysis and prediction of tension and roller speed information, generating initial control instructions for adaptive compensation. A tension-speed nonlinear mapping model constructed based on historical data enables forward-looking fine-tuning of roller speed. Furthermore, a distributed collaborative control model dynamically coordinates local strategies with global optimization, employing an improved differential evolution algorithm and Lagrangian constrained multi-objective optimization to generate globally optimal speed control instructions that balance tension distribution, gradient stability, and minimized speed variation. The system can suppress tension fluctuations and oscillations in real time and with low latency, significantly reducing filament breakage and rework rates, improving filament stretching uniformity and mechanical properties, and enhancing production line stability, yield rate, and economic benefits.

[0028] Example 2 The system is used to achieve coordinated control of wire feeding tension during the molecular orientation stretching of acrylic filaments through multiple sets of rollers along a unidirectional path. It specifically includes: a data acquisition unit, an initial control instruction acquisition unit, a control adjustment strategy generation unit and a global optimization coordination instruction generation unit.

[0029] The data acquisition unit is used to obtain the first data of the key positions of the one-way wire feeding path and the running speed of multiple groups of rollers in real time. In modern acrylic fiber production lines, the molecular orientation stretching of the raw silk through multiple groups of rollers is a key process to improve the strength and elasticity of acrylic filaments. The accuracy of tension control directly affects product quality and production efficiency. In this embodiment, the data acquisition unit is arranged along the acrylic filament feeding path using a tension sensor array. The tension sensor array is arranged at the entrance section, tension mutation section, stretching roller group and winding pre-tightening section of the wire feeding path to collect real-time data of each section of acrylic filament respectively; based on the real-time data, the tension amplitude change rate is obtained, and the key position of the one-way wire feeding path is determined, specifically, the tension fluctuation amplitude difference rate between two adjacent sensors is calculated. The specific calculation formula is for any two adjacent sensors. and , calculate them in the time window The tension fluctuation amplitudes are and , tension fluctuation amplitude difference rate for: ; in, For any two adjacent sensors and Tension fluctuation amplitude, is the maximum tension fluctuation amplitude difference; When the tension fluctuation amplitude difference rate exceeds a preset threshold, it is determined to be a key position, and the tension data collected by the sensor corresponding to the key position is used as the first data.

[0030] The initial control instruction acquisition unit is used to construct a dynamic feature control model to analyze the first data and the operating speed and generate a preliminary control instruction. The preliminary control instruction includes a control deviation, a stretching prediction value and a first operating speed; the stretching prediction value is compensated and adjusted according to the control deviation; the wire feeding process is adjusted according to the preliminary control instruction to obtain the second data and the second operating speed; Figure 3 As shown in the figure, the dynamic feature control model includes a data preprocessing layer, a feature extraction layer, a predictive modeling layer, and a control decision layer, forming a complete closed-loop system from data to control.

[0031] The data preprocessing layer normalizes the first data and the running speed, detects and corrects outliers, and uses the sliding window method to smooth the original signal with a window size of 20 sampling points. Normalization uses the min-max standardization method to scale each data to the [0,1] interval; outlier detection uses The data points that deviate from the mean by more than 3 standard deviations are considered as outliers and corrected by linear interpolation.

[0032] The feature extraction layer uses wavelet transform decomposition to extract time-frequency domain features from the processed first data. These features include time-domain and frequency-domain characteristic parameters such as mean, variance, peak value, spectral energy distribution, and rate of change, forming a feature vector. The wavelet transform uses the db4 wavelet basis function with a three-level decomposition order to obtain signal components and their energy distribution across different frequency bands. Principal component analysis is then used to reduce the dimensionality of the feature vectors, retaining those with a cumulative contribution exceeding 95%. This significantly reduces the dimensionality of the feature space while retaining key information, generating a reduced-dimensional feature vector.

[0033] The predictive modeling layer is based on a long short-term memory network structure. The input layer contains the dimensionality-reduced feature vector output by the feature extraction layer. The hidden layer contains 64 LSTM units and 32 fully connected neurons. The output layer generates stretch prediction values, including the tension prediction values of each key position in the next 0.5 seconds.

[0034] The control decision layer calculates the control deviation by comparing the actual tension with the target tension and uses an adaptive fuzzy PID controller to compensate for the predicted tension. Fuzzy control rules are designed based on the tension error and its rate of change, and the output is the PID parameter adjustment. After the compensation adjustment is completed, the initial operating speed is calculated based on the adjusted predicted tension value using a tension-speed nonlinear mapping model, providing the initial control command for the operating speed of multiple roller groups.

[0035] The tension-speed nonlinear mapping model builds a double-input single-output nonlinear regression model based on historical production data. The input variable is the adjusted tensile prediction value. and the current roller speed , the output variable is the speed regulation . Through the speed adjustment Current running speed Adjust to get the first running speed .

[0036] The specific process of adjusting the wire feeding process according to the preliminary control instruction to obtain the second data and the second operating speed includes: first, sending the first operating speed to the frequency conversion control unit of each roller driver through the field bus, and each frequency conversion control unit adjusts the rotation speed of the roller according to the received instruction; then implementing a control adjustment for a predetermined time, and the predetermined time is set to 2 to 5 seconds according to the system response characteristics; during the adjustment process, using the tension sensor array to monitor the tension changes at each key position in real time, and record them as the second data; at the same time, the actual operating speed of each group of rollers after adjustment is collected through the encoder and recorded as the second operating speed.

[0037] The control adjustment strategy generation unit is used to build a distributed collaborative control model to analyze the preliminary control instructions and generate a control adjustment strategy based on the global tension distribution balance and the key section tension gradient stability. Figure 4 As shown in Figure 3, the distributed collaborative control model includes a state evaluation layer, a strategy generation layer, and a collaborative optimization layer.

[0038] The distributed collaborative control model includes a state assessment layer, a local strategy generation layer, and a global coordination layer: The state evaluation layer receives the preliminary control instruction, the second data, and the second operating speed, and calculates the global tension distribution balance and the key section tension gradient stability; wherein the tension distribution balance index is the root mean square error between the actual tension value and the tension prediction value at each key position, and the tension gradient stability index is the standard deviation of the tension change rate between adjacent key positions; The local strategy generation layer is based on an improved model predictive control algorithm and designs a control adjustment strategy library for different tension distribution states, including three basic control modes: steady-state control strategy, transitional control strategy, and fluctuation suppression strategy. Each mode contains multiple control parameter sets. The control parameters include the speed adjustment step coefficient , tension compensation coefficient , gradient smoothing factor and synergy weight coefficient Under the steady-state control strategy, the parameters are conservatively selected. The value is small, and the focus is on maintaining system stability; under the transition state control strategy, A larger value improves the system response speed; under the fluctuation suppression strategy, and The larger the value, the more emphasis is placed on suppressing tension fluctuations.

[0039] The global collaborative optimization layer uses the hierarchical analysis method to determine the weight of each control parameter, and combines it with the particle swarm optimization algorithm to dynamically find the optimal control parameter set when the system is in different working conditions, and generates a control adjustment strategy. The specific acquisition process of the control adjustment strategy is: first calculate the deviation matrix between the current system state and the control target, then query the strategy library based on the deviation matrix to match the closest basic control mode, and then use the optimization algorithm to fine-tune the control parameters under the selected basic control mode to minimize the comprehensive performance index. ,in , is the tension distribution balance, is the tension gradient stability, is the speed control quantity, 、 and is the corresponding weight, The position and velocity update formulas of the particle swarm optimization algorithm are as follows: ; ; in, and Respectively The speed and position of each particle, is the historical optimal position of the particle, is the global optimal position, is the inertia weight, and is the learning factor of speed, and is a random number in the interval [0,1], As unit time.

[0040] The global optimization coordination command generation unit controls the second operating speed based on the control adjustment strategy based on low-latency information exchange between multiple roller groups, generating globally optimized and coordinated speed control commands. This low-latency information exchange between multiple roller groups utilizes a distributed real-time bus system to build a communication network between roller control units. This real-time bus system uses the EtherCAT industrial Ethernet protocol. Each roller control unit is equipped with an edge computing module and an integrated real-time operating system. Each roller control unit can directly transmit key status information to adjacent roller control units.

[0041] The specific process of obtaining the globally optimized coordinated speed control command includes: constructing a multi-objective optimization function based on the global tension distribution balance, the key section tension gradient stability and the minimization of speed variation based on the second operating speed and the control adjustment strategy; An improved differential evolution algorithm is used to solve the multi-objective optimization function. In this embodiment, the differential evolution algorithm population size is set to 30, the maximum number of iterations is 20, the crossover probability is 0.8, and the dynamic adjustment range of the mutation factor is [0.4, 0.9]. During each iteration, the Lagrangian constraint method is used to address the system's physical constraints, including the upper and lower speed limits of each roller, the speed ratio of adjacent rollers, and the speed change rate constraint, to generate the optimal speed vector. After the optimization solution is completed, the optimal speed vector obtained is used as the speed control instruction for global optimization coordination and is synchronously sent to each roller control unit through the real-time bus system. Each control unit accurately controls the roller speed according to the received instruction to achieve global coordinated control.

[0042] The experimental results show that the effect of the acrylic filament unidirectional wire feeding tension coordinated control system of the present invention compared with the traditional control method is shown in Table 1: Table 1 Comparison of the effects of the method of the present invention and the traditional method As can be seen from Table 1, compared with the traditional control method, the method of the present invention has significant advantages in key indicators such as tension fluctuation amplitude, response time, broken wire rate, fiber strength uniformity and batch-to-batch consistency, which verifies the effectiveness and advancement of the present invention.

[0043] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A coordinated control system for the tension of acrylic filament unidirectional wire feeding, characterized in that: Coordinated control of feed tension during molecular orientation stretching of acrylic filaments along a unidirectional path through multiple sets of rollers includes: A data acquisition unit for acquiring first data of key positions of a one-way wire feeding path and running speeds of multiple groups of rollers in real time; An initial control instruction acquisition unit constructs a dynamic feature control model to analyze the first data and the operating speed to generate a preliminary control instruction; the preliminary control instruction includes a control deviation, a stretch prediction value, and a first operating speed; the stretch prediction value is compensated and adjusted based on the control deviation; and the wire feeding process is adjusted based on the preliminary control instruction to obtain second data and a second operating speed. A control adjustment strategy generation unit constructs a distributed collaborative control model to analyze the second data and the second operating speed, and generates a control adjustment strategy based on the global tension distribution balance and the key section tension gradient stability; The global optimization coordination instruction generation unit controls the second operating speed based on the low-latency information interaction between multiple groups of rollers according to the control adjustment strategy to obtain the global optimization and coordinated speed control instructions.

2. The acrylic filament unidirectional feeding tension coordinated control system according to claim 1, characterized in that: A tension sensor array is arranged along the acrylic filament feeding path. The tension sensor array is set at the entrance section, tension mutation section, stretching roller group and winding pre-tensioning section of the wire feeding path to collect real-time data of each section of acrylic filament. The tension amplitude change rate is obtained based on the real-time data, and the key position of the unidirectional wire feeding path is determined. Specifically, the tension fluctuation amplitude difference rate between two adjacent sensors is calculated. When the tension fluctuation amplitude difference rate exceeds a preset threshold, it is determined to be a key position, and the tension data collected by the sensor corresponding to the key position is used as the first data.

3. The acrylic filament unidirectional feeding tension coordinated control system according to claim 1, characterized in that: The dynamic feature control model includes a data preprocessing layer, a feature extraction layer, a prediction modeling layer, and a control decision layer: The data preprocessing layer performs normalization processing, outlier detection and correction on the first data and the running speed; The feature extraction layer uses a wavelet transform decomposition method to extract time-frequency domain features from the processed first data, and performs dimensionality reduction processing through a principal component analysis method to generate a reduced-dimensional feature vector; The prediction modeling layer generates a tensile prediction value by analyzing the dimension-reduced feature vector, wherein the tensile prediction value includes a tension prediction value at each key position; The control decision layer calculates the control deviation by comparing the deviation between the actual tension and the tension prediction value, and compensates and adjusts the tension prediction value. According to the adjusted tension prediction value, the tension-speed nonlinear mapping model is used to obtain the first operating speed and generate an initial control instruction.

4. The acrylic filament unidirectional feeding tension coordinated control system according to claim 3, characterized in that: The tension-speed nonlinear mapping model constructs a dual-input single-output nonlinear regression model based on historical production data, wherein the input variables are the adjusted tensile prediction value and the current roller operating speed, and the output variable is the speed adjustment amount; the operating speed is adjusted by the speed adjustment amount to obtain a first operating speed.

5. The acrylic filament unidirectional feeding tension coordinated control system according to claim 1, characterized in that: The distributed collaborative control model includes a state assessment layer, a local strategy generation layer, and a global collaborative optimization layer: The state evaluation layer receives the preliminary control instruction, the second data and the second operating speed, and calculates the global tension distribution balance and the key section tension gradient stability; The local strategy generation layer designs local control adjustment strategies for different tension distribution states, including steady-state control strategy, transitional state control strategy and fluctuation suppression strategy; the control adjustment strategy includes control parameters, including speed adjustment step coefficient, tension compensation coefficient, gradient smoothing factor and collaborative weight coefficient; The global collaborative optimization layer adopts the hierarchical analysis method to determine the weights of the control parameters, and combines the particle swarm optimization algorithm to dynamically find the optimal control parameters based on the local control adjustment strategies of different rollers to generate the control adjustment strategy.

6. The acrylic filament unidirectional feeding tension coordinated control system according to claim 1, characterized in that: The specific process of obtaining the globally optimized coordinated speed control instructions includes: Based on the second operating speed and control adjustment strategy, a multi-objective optimization function is constructed based on the balance of global tension distribution, the smoothness of tension gradient in key sections, and the minimization of speed variation. An improved differential evolution algorithm is used to iteratively solve the multi-objective optimization function. During the iteration process, the Lagrangian constraint method is used to address the system's physical constraints, including upper and lower speed limits for each roller, speed ratios between adjacent rollers, and speed change rate constraints, to generate the optimal speed vector. Based on the optimal speed vector, a globally optimized and coordinated speed control instruction is obtained.

7. A method for coordinated control of the tension of acrylic filament unidirectional wire feeding, characterized in that: Coordinated control of feed tension during molecular orientation stretching of acrylic filaments along a unidirectional path through multiple sets of rollers includes: Real-time acquisition of first data of key positions of a one-way wire feeding path and the running speeds of multiple sets of rollers; A dynamic feature control model is constructed to analyze the first data and the operating speed to generate a preliminary control instruction; the preliminary control instruction includes a control deviation, a stretch prediction value, and a first operating speed; the stretch prediction value is compensated and adjusted according to the control deviation; the first operating speed is obtained by adjusting the operating speed according to the stretch prediction value; the wire feeding process is adjusted according to the preliminary control instruction to obtain second data and a second operating speed; Construct a distributed collaborative control model to analyze the second data and the second operating speed, and generate a control adjustment strategy based on the global tension distribution balance and the stability of the tension gradient in the key section; Based on low-latency information interaction between multiple groups of rollers, the second operating speed is controlled according to the control adjustment strategy to obtain a globally optimized and coordinated speed control instruction.

Images