Polyester fiber yarn multi-device collaborative control system using PLC controller

Abstract

The present invention discloses a polyester fiber yarn multi-device collaborative control system using a PLC controller, which belongs to the field of equipment collaborative control, and includes: a relationship establishment module, which is used to establish a collaborative relationship between a guide wire, a drafting machine, and a winder; a parameter monitoring module, which is used to monitor the operating parameters of the equipment in real time by deploying sensors on the collaborative equipment, and synchronously extract the control parameters of the PLC controller; a parameter fitting module, which is used to perform parameter linkage fitting on the real-time operating parameters of the equipment and the PLC control parameters with the collaborative relationship as a constraint condition to obtain the fitting degree; a control deployment module, which is used to determine the collaborative operating parameters of the collaborative equipment and its corresponding matching PLC control parameters, and perform production control deployment. This application solves the technical problem of low precision and efficiency of collaborative control of multiple devices in the polyester fiber yarn production process in the prior art, and achieves the technical effect of improving the precision and efficiency of collaborative control of multiple devices in the polyester fiber yarn production process.

Description

Technical Field

[0001] The invention relates to the field of equipment collaborative control, and in particular to a polyester fiber yarn multi-equipment collaborative control system using a PLC controller. Background Art

[0002] The production process of polyester fiber yarn involves the coordinated work of multiple devices, including guide wires, drafting machines, winders, etc. These devices need to work together to ensure the stability of production and product quality. In the prior art, although PLC controllers are used to control polyester fiber yarn production equipment, the prior art lacks effective establishment and management of the coordinated relationship between equipment, as well as real-time monitoring and optimization of equipment operating parameters and PLC control parameters, resulting in the inability to achieve optimal coordinated operation between equipment, resulting in low accuracy and efficiency of coordinated control of multiple equipment in the polyester fiber yarn production process. Summary of the invention

[0003] The present application aims to solve the technical problems of low precision and efficiency of multi-device collaborative control in the polyester fiber production process in the prior art by providing a polyester fiber multi-device collaborative control system using a PLC controller.

[0004] The present application discloses a polyester fiber yarn multi-device collaborative control system using a PLC controller, including: a relationship establishment module, used to establish a collaborative relationship among a guide wire, a drawing machine, and a winder, including a process delay time relationship, a collaborative parameter relationship, and a collaborative parameter fault tolerance threshold; a parameter monitoring module, used to monitor the operating parameters of the equipment in real time by deploying sensors on the collaborative equipment, and to simultaneously extract the control parameters of the PLC controller; a parameter fitting module, used to perform parameter linkage fitting on the real-time operating parameters of the equipment and the PLC control parameters with the collaborative relationship as a constraint condition to obtain a fit; a control deployment module, used to determine the collaborative operating parameters of the collaborative equipment and their corresponding matching PLC control parameters according to the fit, the matching PLC control parameters are the PLC control parameters with the highest search fit, and the matching PLC control parameters are used to perform production control deployment.

[0005] The present application discloses a method for collaborative control of multiple devices of polyester fiber yarns using a PLC controller, including: establishing a collaborative relationship among a guide wire, a drawing machine, and a winder, including a process delay time relationship, a collaborative parameter relationship, and a collaborative parameter fault tolerance threshold; real-time monitoring of the operating parameters of the equipment by deploying sensors on the collaborative equipment, and synchronously extracting the control parameters of the PLC controller; using the collaborative relationship as a constraint condition, performing parameter linkage fitting on the real-time operating parameters of the equipment and the PLC control parameters to obtain a fitting degree; based on the fitting degree, determining the collaborative operating parameters of the collaborative equipment and their corresponding matching PLC control parameters, the matching PLC control parameters are the PLC control parameters that are searched for the highest fitting degree, and using the matching PLC control parameters to perform production control deployment.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By using the relationship building module to establish the collaborative relationship between the wire guide, drawing machine, and winder, including the process delay time relationship, collaborative parameter relationship, and collaborative parameter fault tolerance threshold, effective management of the collaborative relationship between devices is achieved, providing a basis for subsequent parameter monitoring and optimization; sensors are deployed on the collaborative equipment through the parameter monitoring module to monitor the operating parameters of the equipment in real time, and the control parameters of the PLC controller are extracted simultaneously, so as to realize real-time grasp of the operating status and control status of the equipment, and provide data support for parameter fitting; the parameter fitting module 13 uses the collaborative relationship as a constraint condition to perform parameter linkage fitting on the real-time operating parameters of the equipment and the PLC control parameters, and obtains The degree of fit is obtained, and the optimal equipment collaborative operation parameters and PLC control parameters are determined, providing a basis for control deployment; the control deployment module 14 determines the collaborative operation parameters of the collaborative equipment and their corresponding matching PLC control parameters according to the degree of fit, and the matching PLC control parameters are the PLC control parameters with the highest searched degree of fit. The matching PLC control parameters are used for production control deployment, realizing the technical solution of applying the optimal parameters in production control, solving the technical problems of low precision and efficiency of collaborative control of multiple equipment in the production process of polyester fiber yarn in the prior art, and achieving the technical effect of improving the precision and efficiency of collaborative control of multiple equipment in the production process of polyester fiber yarn.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A structural schematic diagram of a polyester fiber yarn multi-device collaborative control system using a PLC controller is provided for the embodiment of the present application;

[0010] Figure 2 A flow chart of obtaining the degree of fit in a polyester fiber multi-device collaborative control system using a PLC controller is provided for an embodiment of the present application.

[0011] Explanation of the reference numerals: relationship building module 11 , parameter monitoring module 12 , parameter fitting module 13 , control deployment module 14 . DETAILED DESCRIPTION

[0012] The overall idea of ​​the technical solution provided by this application is as follows:

[0013] The embodiment of the present application provides a polyester fiber yarn multi-device collaborative control system using a PLC controller. First, a collaborative relationship between devices is established through a relationship establishment module, including a process delay time relationship, a collaborative parameter relationship, and a fault tolerance threshold, to provide a basis for subsequent parameter monitoring and optimization. Secondly, the parameter monitoring module monitors the equipment operating parameters and PLC control parameters in real time, grasps the equipment operation and control status, and provides data support for parameter fitting. Then, the parameter fitting module uses the collaborative relationship as a constraint condition to perform parameter linkage fitting to determine the optimal equipment collaborative operation parameters and PLC control parameters. Afterwards, the control deployment module applies the optimal parameters to production control based on the degree of fit, thereby improving the accuracy and efficiency of equipment collaborative control.

[0014] After introducing the basic principles of the present application, the non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the drawings in the specification.

[0015] like Figure 1 As shown, the embodiment of the present application provides a polyester fiber yarn multi-device collaborative control system using a PLC controller, the system comprising:

[0016] The relationship establishment module 11 is used to establish the coordination relationship among the guide wire, the drawing machine and the coiling machine, including the process delay time relationship, the coordination parameter relationship and the coordination parameter fault tolerance threshold.

[0017] Specifically, first, a collaborative relationship is established between the three devices of the guide wire, the drawing machine, and the winder through the relationship establishment module 11, including the process delay time relationship, the collaborative parameter relationship, and the collaborative parameter fault tolerance threshold. Among them, the guide wire, the drawing machine, and the winder are continuous process equipment, which are interconnected in the form of an assembly line. During the production process, the molten fiber passes through the guide wire and directly enters the drawing machine for stretching, and the stretched fiber is then sent to the winder for winding. The continuous operation mode can ensure production efficiency and improve the consistency and uniformity of the fiber. The operating speed and parameters of each device need to be coordinated to achieve seamless connection and optimal production effect.

[0018] The process delay time relationship refers to the time interaction and influence of different equipment in the production process. Since the production of polyester fiber yarn is a continuous process, the fiber yarn will pass through the guide wire, drawing machine and winder in sequence. Therefore, the operating status and parameter changes of each device will have an impact on the downstream equipment, but this impact has a certain time delay. The relationship establishment module 11 sets a time window for each device, records its operating status and the impact on other devices, and analyzes the relationship between the equipment operation frequency and the time window, so as to identify the interaction points between the equipment and determine the process delay time relationship.

[0019] The collaborative parameter relationship refers to the key operating parameters that influence and relate to each other among different devices. The relationship establishment module 11 first identifies the key operating parameters of each device, distinguishes the same parameters and the different parameters, and then uses the historical experimental data to perform correlation analysis, screens out the collaborative parameter relationships of the same parameters and the different parameters, and combines them to form a complete collaborative parameter relationship, which shows the mutual constraints and influences of the parameters between devices, and is an important basis for realizing the collaborative control of multiple devices.

[0020] The collaborative parameter fault tolerance threshold refers to the maximum range in which the key parameters are allowed to deviate from the standard value when the equipment is operating in collaboration. The relationship establishment module 11 collects normal operation data and abnormal case data, analyzes the differences and changes in key parameters, and determines the collaborative parameter fault tolerance threshold in combination with the equipment status change node. The threshold is the difference between the parameter value corresponding to the leading unit time of the data position and the standard parameter value, indicating the parameter deviation range that the equipment can tolerate in collaborative operation, which helps to promptly discover and handle abnormal situations and ensure production stability.

[0021] The relationship building module 11 establishes the process delay time relationship, the collaborative parameter relationship and the collaborative parameter fault tolerance threshold, which lays a solid foundation for the collaborative control of multiple devices of polyester fiber yarn, thereby effectively guiding the coordinated operation of multiple devices and improving production efficiency and product quality.

[0022] The parameter monitoring module 12 is used to monitor the operating parameters of the equipment in real time by deploying sensors on the collaborative equipment, and to synchronously extract the control parameters of the PLC controller.

[0023] Specifically, in order to realize real-time monitoring of equipment operating parameters, the parameter monitoring module 12 deploys sensors on the collaborative equipment, including temperature sensors, pressure sensors, speed sensors, etc., and selects appropriate sensor types according to the key parameters of different equipment. The sensors collect the equipment's operating data in real time, such as temperature, pressure, speed, etc., and transmit these data to the parameter monitoring module 12. Through real-time monitoring by sensors, the parameter monitoring module 12 accurately grasps the actual operating status of the equipment, providing a reliable data basis for subsequent parameter analysis and optimization.

[0024] In addition to monitoring the operating parameters of the equipment, the parameter monitoring module 12 simultaneously extracts the control parameters of the PLC controller. The PLC controller is the core component of the multi-device collaborative control system and is responsible for controlling and regulating the operation of the equipment. Through the communication interface connection with the PLC controller, the parameter monitoring module 12 obtains the control instructions and parameter settings of the PLC controller in real time, such as the target temperature, pressure, speed, etc. of the equipment. The purpose of synchronously extracting the control parameters is to compare and analyze the actual operating status of the equipment with the control instructions to evaluate the effectiveness and accuracy of the control.

[0025] Through the real-time monitoring and synchronous extraction functions of the parameter monitoring module 12, the operating status and control parameters of the collaborative equipment can be fully understood, providing data support for subsequent parameter fitting and optimization. The real-time monitoring and synchronous extraction mechanism ensures that the actual operating information and control instructions of the equipment can be obtained in a timely manner, realizing dynamic tracking and adjustment of the production process, and improving the accuracy and response speed of control.

[0026] The parameter fitting module 13 is used to perform parameter linkage fitting on the real-time operation parameters of the equipment and the PLC control parameters with the collaborative relationship as a constraint condition to obtain a fitting degree.

[0027] Specifically, the parameter fitting module 13 uses the collaborative relationship determined by the relationship establishment module 11 as a constraint condition, including the process delay time relationship, the collaborative parameter relationship and the collaborative parameter fault tolerance threshold. These collaborative relationships define the time interaction, parameter association and fault tolerance between devices, and provide the necessary boundary conditions and evaluation criteria for parameter fitting. Subsequently, based on the constraints, the parameter fitting module 13 performs parameter linkage fitting on the real-time operating parameters of the equipment and the PLC control parameters. The real-time operating parameters of the equipment come from the data collected in real time by the parameter monitoring module 12 through sensors, reflecting the actual operating status of the equipment. The PLC control parameters are the control instructions and parameter settings extracted synchronously by the parameter monitoring module 12, representing the current control strategy. The purpose of parameter linkage fitting is to find a set of optimal control parameter combinations so that they best match the real-time operating parameters of the equipment while satisfying the constraints of the collaborative relationship.

[0028] The parameter fitting module 13 uses an optimization algorithm to perform parameter linkage fitting. First, the production target parameters of polyester fiber yarn are determined based on the parameter relationship between the real-time operating parameters of the equipment and the production target. Then, with maintaining the production target parameters as the optimization target and the synergistic relationship as the constraint condition, the optimization space is constructed using optimization methods such as genetic algorithms. Through iterative search and evaluation, the parameter fitting module 13 finds the optimal combination of equipment operating parameters in the optimization space. After that, with the optimal equipment operating parameters as the target, the PLC control parameters are fitted, and the degree of fit is calculated based on the deviation between the fitting results and the optimal equipment operating parameters. The fit quantifies the degree of match between the PLC control parameters and the optimal equipment operating parameters. The higher the degree of fit, the more consistent the control strategy is with the actual needs of the equipment.

[0029] Through the parameter linkage fitting of the parameter fitting module 13, under the constraint of the collaborative relationship, the control strategy is adaptively adjusted to match the real-time operating status of the equipment, thereby realizing collaborative optimization control of multiple devices, improving production efficiency and ensuring product quality.

[0030] The control deployment module 14 is used to determine the collaborative operation parameters of the collaborative equipment and their corresponding matching PLC control parameters according to the fit degree, wherein the matching PLC control parameters are the PLC control parameters with the highest search fit degree, and the matching PLC control parameters are used for production control deployment.

[0031] Specifically, the control deployment module 14 first extracts the parameter combination with the highest degree of fit from the output results of the parameter fitting module 13, which includes two parts: one part is the optimal collaborative operation parameters of the collaborative equipment, that is, the equipment operation state and process parameters that optimize the production performance under the constraints of the equipment collaborative relationship; the other part is the PLC control parameters that match the optimal collaborative operation parameters, that is, the control instructions and setting values ​​that enable the equipment to achieve the optimal collaborative operation state. By searching for the parameter combination with the highest degree of fit, the control deployment module 14 ensures that the selected operation parameters and control parameters can meet the requirements of equipment collaborative optimization to the greatest extent.

[0032] After obtaining the optimal collaborative operation parameters and matching PLC control parameters, the control deployment module 14 sends the PLC control parameters to the PLC controller to guide it to adjust and control the operation of the equipment. The PLC controller generates corresponding control instructions based on the received control parameters, and directly acts on the polyester fiber production equipment through control devices such as actuators to adjust the operating state and process conditions of the equipment to achieve the target state specified by the optimal collaborative operation parameters. During the production control deployment process, the control deployment module 14 continuously monitors the real-time operating parameters of the equipment through the parameter monitoring module 12, and compares them with the optimal collaborative operation parameters. If it is found that the actual operating parameters deviate from the optimal target value and exceed the collaborative parameter fault tolerance threshold, the control deployment module 14 will adjust the PLC control parameters in time, and maintain the equipment operating state within the range of the optimal collaborative operation parameters through feedback control. Through the mechanism of real-time monitoring and dynamic adjustment, it is ensured that the production process is carried out smoothly and efficiently under the guidance of the optimal control strategy, and the accuracy and stability of multi-device collaborative control are improved.

[0033] The optimization results are converted into actual control behaviors through the control deployment module 14, which realizes the coordinated optimization of operating parameters and control parameters, and ensures the high efficiency and reliability of the coordinated control of multiple devices of polyester fiber yarns.

[0034] Furthermore, the embodiment of the present application also includes:

[0035] Set a time window for each device, such as guide wire, drawing machine and coiler, to record the operating status and its impact on other devices;

[0036] Monitor the operating frequency of each device;

[0037] The relationship between the operating frequency and the time window is analyzed through a timing diagram, the interaction points of different devices in the production process are identified, and the process delay time relationship between each device is determined.

[0038] In a feasible implementation, first, the relationship establishment module 11 sets an independent time window for the guide wire, the drawing machine, and the winder. Each time window is used to record the operating status of the corresponding equipment within a certain time range, as well as the impact of the change in the operating status of the equipment on other equipment. Through the time window, the dynamic change process of the equipment operating status can be captured, and the timing association between the equipment can be established. While setting the time window, the operating frequency of each device is monitored. The operating frequency reflects the rate and rhythm of the equipment state change, and is an important indicator for analyzing the interaction relationship between devices. By tracking the operating frequency of the guide wire, the drawing machine, and the winder in real time, the time characteristics of the operation of each device can be grasped.

[0039] After obtaining the time window records and operation frequency data of the equipment, the timing diagram analysis method is comprehensively used to study the relationship between the operation frequency and the time window. The timing diagram can intuitively show the changing trend of the equipment status over time, as well as the interaction process of different equipment in the time dimension. By analyzing the changing law of the operation frequency in the timing diagram and combining the state impact information recorded in the time window, the key interaction points of the guide wire, drawing machine, and winder in the production process are identified, that is, the time node when the state change of one device has a significant impact on another device. Then, based on the identified key interaction points, the process delay time relationship between the guide wire, drawing machine, and winder is further determined. The process delay time refers to the time difference between the state change of a certain device and the impact on another device after a certain time delay. By calculating the time interval between the key interaction points and considering factors such as material transfer and signal transmission between equipment, the process delay time values ​​between each device are obtained, forming a complete process delay time relationship.

[0040] By determining the process delay time relationship, an important time constraint condition is provided for the coordinated control of multiple devices. By using this relationship, the interaction process between devices can be predicted and controlled to achieve synchronization and coordination of device state changes. For example, when the state of the wire guide device changes, the control parameters of the drafting machine and the winder are adjusted in advance according to the process delay time relationship so that they respond after the corresponding delay time to ensure the continuity and stability of production.

[0041] Furthermore, the implementation of this application also includes:

[0042] Identify the key operating parameters of each device including guide wire, drawing machine and coiler, and determine the same parameters and different parameters;

[0043] Through historical experimental data, correlation analysis is performed with the same parameters to determine feedback correlation and screen the synergistic parameter relationship of the same parameters;

[0044] Based on the historical experimental data, feedback correlation analysis is performed with the difference parameter as the target to screen the synergistic parameter relationship of the difference parameter;

[0045] The collaborative parameter relationship of the same parameter is combined with the collaborative parameter relationship of the different parameter to obtain the collaborative parameter relationship.

[0046] In a feasible implementation, the relationship establishment module 11 identifies key operating parameters of the equipment and uses data analysis methods to determine the collaborative relationship between the same parameters and the different parameters to form a complete collaborative parameter relationship.

[0047] Specifically, the relationship establishment module 11 first performs parameter analysis on the three devices of the guide wire, the drawing machine, and the winder to identify the key operating parameters of each device. Key operating parameters refer to control variables that have an important impact on the operating state and performance of the device, such as temperature, speed, tension, etc. By comparing and analyzing the key operating parameters of each device, the relationship establishment module 11 divides them into two categories: the same parameters and the difference parameters. The same parameters refer to operating parameters that exist in different devices and have similar effects, while the difference parameters are operating parameters that are unique to a certain device or have obvious differences from other devices. On the basis of parameter identification and classification, the relationship establishment module 11 uses historical experimental data to carry out correlation analysis between parameters. For the same parameter, its feedback correlation between different devices is studied, that is, the impact of the change of the parameter in one device on the parameter of the same name in another device. By calculating indicators such as correlation coefficients and mutual information, the relationship establishment module 11 quantifies the correlation strength between the same parameters, and selects strongly correlated parameter pairs based on the correlation significance to form a collaborative parameter relationship of the same parameters. For the difference parameters, a similar correlation analysis method is used, but the analysis target is the feedback correlation between the difference parameters and the parameters in other devices. By exploring the impact of the difference parameter changes on the operating status of other equipment, the significant correlation between the difference parameters and other parameters is identified, and they are screened as the collaborative parameter relationship of the difference parameters. After that, the collaborative parameter relationship of the same parameters is combined with the collaborative parameter relationship of the difference parameters to form a complete collaborative parameter relationship, which comprehensively describes the parameter interaction and influence mechanism between the guide wire, drawing machine, and winder, and provides key parameter constraints for the collaborative control of multiple devices.

[0048] By establishing a collaborative parameter relationship, when adjusting the operating parameters of a certain device, the relevant parameters of other devices are automatically considered and coordinated to achieve parameter matching and optimization between devices. For example, when the drafting speed of the wire guide device changes, the drafting ratio of the drafting machine and the winding tension of the winder are adjusted accordingly according to the collaborative parameter relationship to ensure that the operating parameters of each device are always in the best ratio state, providing a solid foundation for realizing the collaborative optimization control of parameters among multiple devices.

[0049] Furthermore, the embodiment of the present application also includes:

[0050] Collect normal operation data and abnormal case data, and integrate the normal operation data and abnormal case data, including timestamps, device status, and key parameter values;

[0051] Analyze the key parameter differences between the normal operation data and the abnormal case data, and search for abnormal parameter changes;

[0052] According to the timestamp of the abnormal parameter change, the temporal continuity of the normal operation data and the abnormal parameters is determined. Based on the change node of the device state, it is projected to the data position in the abnormal parameter change to determine the collaborative parameter fault tolerance threshold. The collaborative parameter fault tolerance threshold is the difference between the parameter value corresponding to the preceding unit time of the data position and the standard parameter value.

[0053] In a feasible implementation, first, the normal operation data of the polyester fiber production line in normal operation and the abnormal case data under abnormal conditions are collected. Among them, the normal operation data reflects the operation characteristics of the equipment in a stable and optimized state, while the abnormal case data records the parameter changes when the equipment fails, has quality problems and other abnormal conditions. In order to facilitate subsequent analysis, the collected data are integrated and standardized, and key information dimensions are extracted, including the timestamp of the data, the equipment operation status and the values ​​of key parameters. Among them, the timestamp is used to record the specific time of data collection, which provides a basis for the time series analysis of events; the equipment status identifies whether the equipment is in normal operation or abnormal state at that moment; and the key parameter value quantifies the specific process conditions of the equipment operation. On the basis of data integration, the normal operation data and the abnormal case data are compared and analyzed, and the difference between the key parameters in the two data sets is paid attention to. By calculating the change amount of the key parameters in the abnormal data relative to the normal data, the deviation degree of the parameters under abnormal conditions is quantified. At the same time, through the search algorithm, the key threshold of the abnormal parameter change is identified, that is, the critical point at which the equipment state will change significantly when the parameter shifts to a certain extent, and the abnormal parameter change amount is obtained.

[0054] After that, the timing relationship between abnormal parameter changes and equipment status changes is further revealed, and the normal operation data and abnormal parameter changes are aligned and analyzed for continuity using timestamp information. By matching the timestamp of abnormal parameter changes with the time series of normal operation data, the specific time node at which the abnormal parameter changes occur during normal operation is determined. Then, combined with the equipment status data, the key nodes at which the equipment status changes are identified, and mapped and compared with the time nodes of abnormal parameter changes. Through timing analysis, the key data position in the abnormal parameter change is determined, that is, the parameter change threshold point before the equipment status is about to change. For this key data position, the parameter mean within the preceding unit time (such as the previous minute) is extracted, and compared with the standard value of the corresponding parameter, and the difference between the two is calculated. This difference is the collaborative parameter fault tolerance threshold, which represents the maximum allowable deviation of the key parameter within the normal range.

[0055] By introducing the collaborative parameter fault tolerance threshold, an important fault tolerance mechanism is provided for the collaborative control of multiple devices. In actual production, even if the collaborative relationship between devices is optimized, slight fluctuations and deviations of parameters are inevitable. The collaborative parameter fault tolerance threshold provides a safe range for parameter deviations, allowing the system to tolerate parameter fluctuations to a certain extent, avoid overly frequent control adjustments, and improve control stability.

[0056] Further, such as Figure 2 As shown, the embodiment of the present application also includes:

[0057] Establishing a parameter relationship between the real-time operating parameters of the equipment and the production target, matching the parameter relationship with the real-time operating parameters of the equipment, and determining the production target parameters of the polyester fiber yarn;

[0058] Taking maintaining the production target parameters as the goal, taking the synergistic relationship as the constraint condition, and taking the genetic algorithm as the search execution rule, an optimization space is constructed, and the optimal equipment operation parameters are determined through iterative optimization of the optimization space;

[0059] Taking the optimal equipment operating parameters as the target, parameter linkage fitting is performed on the PLC control parameters, and the fitting degree is obtained according to the execution consistency of the PLC control parameters on the optimal equipment operating parameters.

[0060] In a preferred embodiment, the parameter fitting module 13 first establishes a parameter relationship between the real-time operating parameters of the equipment and the production target. The parameter relationship is based on production process knowledge and historical data, and depicts the mapping relationship between the equipment operating status and production indicators such as product quality and output. By collecting the equipment operating parameters in real time and substituting them into the parameter relationship for calculation, the production target parameters under the current production state can be dynamically determined, such as the key quality indicators such as the linear density, strength, and elongation at break of the fiber. After clarifying the production target parameters, the parameter fitting module 13 takes maintaining the target parameters as the optimization target and the synergistic relationship between the equipment as the constraint condition to construct the parameter optimization space. The optimization space is a multidimensional parameter search domain, in which each dimension represents an equipment operating parameter. By encoding the equipment operating parameters as chromosomes, the parameter fitting module 13 converts the optimization problem into a genetic optimization problem. In the optimization space, each point represents a set of equipment operating parameter combinations, and its fitness is determined by the closeness of the combination to the production target parameters. At the same time, the synergistic relationship constraint ensures that all feasible solutions meet the synergy requirements between equipment, such as process delay time, synergistic parameter relationship, etc.

[0061] In order to search for the optimal solution in the optimization space, the parameter fitting module 13 uses a genetic algorithm as the search execution rule. First, an initial population is formed by randomly generating a set of initial equipment operation parameter combinations. Then, for each individual in the population, its fitness is evaluated, that is, the difference between it and the production target parameters is calculated. According to the fitness, a selection operator is used to preferentially select individuals with high fitness from the current population, and these individuals are combined and disturbed by crossover and mutation operators to generate new equipment operation parameter combinations to form the next generation population. By iteratively repeating the above process, the population continues to evolve and gradually approaches the optimal solution until a preset termination condition is reached, such as an upper limit on the number of iterations or a fitness threshold. At this time, the equipment operation parameter combination corresponding to the individual with the highest fitness is the optimal equipment operation parameter. Based on the optimal equipment operation parameters, the parameter fitting module 13 performs parameter linkage fitting on the PLC control parameters. Specifically, taking the optimal equipment operation parameters as the target, one or more sets of PLC control parameters that match it are derived through theoretical calculations or simulation experiments. Then, by evaluating the execution consistency of each set of PLC control parameters for the optimal equipment operating parameters, that is, the accuracy and stability of the control instructions converted into the actual operating state, the fit of the PLC control parameters was obtained. The higher the fit, the better the set of PLC control parameters can achieve the optimal equipment operating parameters and the higher the fit with the production goals.

[0062] Through the parameter linkage fitting process, while ensuring equipment coordination, the optimal match between production goals and equipment operating parameters and PLC control parameters is achieved, thereby improving production efficiency and product quality.

[0063] Furthermore, the embodiment of the present application also includes:

[0064] The equipment operation parameters and PLC control parameters are respectively used as graph nodes, edges are defined according to the relationship between the control parameters, and weights are assigned to the edges to represent the influence strength, thus constructing a graph structure.

[0065] Assign a multidimensional feature vector to each graph node, identify the parameter value, standard deviation, and average value in the historical data, and use the time information and correlation strength of the historical data to add features to the edge;

[0066] Select the GNN model architecture, design the number of layers and aggregation information of the graph structure, and establish a network propagation mechanism of the graph structure so that each node can aggregate the features of its neighboring nodes and use the aggregated features to update the own features of each node;

[0067] The collected historical data sets of PLC control parameters and equipment operation parameters are used to train the GNN model and converge, and the relationship model between the PLC control parameters and equipment operation parameters is obtained;

[0068] Based on the relationship model between the PLC control parameters and the equipment operating parameters, the optimal equipment operating parameters are used as input features to perform PLC control parameter analysis and output fitting results of the PLC control parameters.

[0069] In a preferred embodiment, the parameter fitting module 13 introduces a graph neural network model when performing parameter linkage fitting of PLC control parameters, obtains a relationship model between PLC control parameters and equipment operation parameters by constructing a parameter relationship graph, node feature learning and network training, and implements optimal fitting of PLC control parameters based on the model.

[0070] Specifically, the parameter fitting module 13 first abstracts the equipment operation parameters and PLC control parameters into nodes in the graph structure. The connection relationship between the nodes, that is, the edge, is defined according to the dependency and influence relationship between the control parameters. At the same time, in order to quantify the influence strength between the parameters, a weight value is assigned to each edge. The larger the weight, the stronger the influence between the two parameters. In this way, the parameter fitting module 13 constructs a graph structure, in which the nodes represent the parameters and the edges represent the association between the parameters. After constructing the graph structure, the parameter fitting module 13 further assigns a multidimensional feature vector to each node. The feature vector contains the statistical information of the parameter in the historical data, such as the value, standard deviation, average value, etc. of the parameter. These statistical features characterize the distribution characteristics and change laws of the parameters. In addition, the time information and correlation analysis results of the historical data are used to add features to the edges between the nodes, such as the lag length, correlation coefficient, etc. These edge features reflect the dynamic association and mutual influence between the parameters.

[0071] In order to learn the complex relationship between parameters on the graph structure, the parameter fitting module 13 selects GNN as a modeling tool. GNN is a deep learning model based on graph structure data, which can effectively model the interaction and propagation between nodes. According to the characteristics of the graph structure, the model architecture of GNN is designed, such as the number of convolutional layers, the selection of aggregation functions, etc. By designing the network propagation mechanism, the GNN model enables each node to aggregate the feature information of its neighboring nodes and use the aggregated features to update its own feature representation. This feature propagation and update process enables the GNN model to learn high-order interactions and long-range dependencies between nodes.

[0072] After the GNN model is designed, the parameter fitting module 13 uses the collected historical data sets of PLC control parameters and equipment operation parameters to train and optimize the model. By inputting historical data into the GNN model and comparing the difference between the model output and the true value, the module uses the back propagation algorithm and the gradient descent method to continuously adjust the parameters of the model so that its output result is as close to the true value as possible. After multiple rounds of iterative training, the GNN model gradually converges, learns the complex nonlinear relationship between the PLC control parameters and the equipment operation parameters, and forms a relationship model. After obtaining the relationship model between the PLC control parameters and the equipment operation parameters, the parameter fitting module 13 uses the model to perform fitting optimization of the PLC control parameters. Specifically, the optimal equipment operation parameters are used as input features and fed into the trained GNN model. Based on the learned parameter relationship, the GNN model infers and maps the optimal equipment operation parameters, and outputs the most matching PLC control parameter combination, that is, the fitting result of the PLC control parameters. The fitting result fully considers the inherent connection and dynamic influence between the parameters, and ensures the high consistency between the PLC control parameters and the optimal equipment operation parameters.

[0073] By introducing the GNN model, the graph structure is used to represent the parameter relationship, and the deep interaction and dynamic dependency between parameters are effectively captured through node feature learning and network propagation. Based on the trained relationship model, the PLC control parameters are accurately fitted and optimized, so that the control strategy and the equipment operating status are optimally matched.

[0074] Furthermore, the implementation of this application also includes:

[0075] The formula expression for obtaining the degree of fit is: , where n is the dimension of the parameter, is the optimal device operation parameter vector, is the PLC control parameter vector, is the value of the ith PLC control parameter, is the value of the i-th optimal equipment operating parameter, is the variance of the optimal equipment operating parameters.

[0076] In a preferred embodiment, a formula for calculating parameter fit is provided to quantify the degree of match between PLC control parameters and optimal equipment operating parameters. The formula comprehensively considers the multi-dimensional characteristics of the parameters and the discrete degree of the optimal parameters, and obtains a unified and intuitive fit index through normalization. Specifically, the calculation formula for the fit is:

[0077] ;

[0078] in, Indicates the degree of fit, with a value ranging from 0 to 1. The closer the value is to 1, the better the fit between the PLC control parameters and the optimal equipment operating parameters, and the smaller the deviation between the two. n represents the dimension of the parameter, that is, the number of parameters involved in the fit calculation, such as temperature, pressure, speed and other dimensions, each of which corresponds to a specific parameter value. The introduction of parameter dimensions enables the calculation of fit to fully consider the matching of each key parameter. Represents the optimal equipment operation parameter vector, which is an n-dimensional column vector, where each element Represents the value of the i-th optimal equipment operating parameter. Represents the PLC control parameter vector, which is also an n-dimensional column vector, where each element Represents the value of the i-th PLC control parameter.

[0079] The numerator of the fitness formula is , the sum of squares of the differences between the PLC control parameters and the optimal equipment operating parameters in each dimension is calculated. The smaller the sum of squares of the differences, the closer the two sets of parameters are in each dimension, and the better the fitting effect. The denominator of the fitting formula It plays a role in normalization and standardization. It represents the variance of the optimal equipment operating parameters and reflects the degree of dispersion of the optimal parameters in each dimension. The larger the variance, the wider the range of the optimal parameter and the greater the variability of the parameter. Dividing the sum of squared differences by the variance of the optimal parameter can eliminate the influence of different parameter magnitudes and make the value of the fit fall within the range of 0 to 1. At the same time, multiplying by the parameter dimension n can balance the contribution of parameters of different dimensions to the fit and avoid the parameters of a certain dimension dominating the calculation result of the fit.

[0080] The above fit formula can be used to quantitatively evaluate the degree of match between PLC control parameters and optimal equipment operating parameters. The higher the fit, the better the optimization effect on the equipment operating status, and the more it can meet production goals and performance requirements.

[0081] In summary, the polyester fiber yarn multi-device collaborative control system using a PLC controller provided in the embodiment of the present application has the following technical effects:

[0082] The relationship establishment module is used to establish the collaborative relationship between the guide wire, drawing machine, and winder, including the process delay time relationship, collaborative parameter relationship, and collaborative parameter fault tolerance threshold, to provide a basis for collaborative control between devices, to ensure that each device can coordinate and operate according to the predetermined relationship and parameters during the control process, and to set the fault tolerance threshold to improve the robustness of the system. The parameter monitoring module is used to monitor the operating parameters of the equipment in real time by deploying sensors on the collaborative equipment, and to simultaneously extract the control parameters of the PLC controller, so as to grasp the operating status and control status of the equipment in real time, and provide real and reliable data support for subsequent parameter fitting. The parameter fitting module is used to perform parameter linkage fitting on the real-time operating parameters of the equipment and the PLC control parameters with the collaborative relationship as the constraint condition, to obtain the degree of fit, and thus find the optimal combination of equipment collaborative operating parameters and PLC control parameters, and provide a decision-making basis for control deployment. The control deployment module is used to determine the collaborative operation parameters of the collaborative equipment and their corresponding matching PLC control parameters based on the degree of fit. The matching PLC control parameters are the PLC control parameters with the highest search degree of fit. The matching PLC control parameters are used for production control deployment, and the optimized parameters are applied to actual production control to achieve efficient collaboration between equipment and improve the accuracy and efficiency of collaborative control of multiple equipment.

[0083] Embodiment 2, based on the same inventive concept as the polyester fiber yarn multi-device coordinated control system using a PLC controller in the aforementioned embodiment, the embodiment of the present application provides a polyester fiber yarn multi-device coordinated control method using a PLC controller, the method comprising:

[0084] Establish the collaborative relationship between the wire guide, drawing machine, and coiling machine, including the process delay time relationship, collaborative parameter relationship, and collaborative parameter fault tolerance threshold;

[0085] By deploying sensors on collaborative equipment, the operating parameters of the equipment are monitored in real time, and the control parameters of the PLC controller are extracted synchronously;

[0086] Taking the collaborative relationship as a constraint condition, parameter linkage fitting is performed on the real-time operation parameters of the equipment and the PLC control parameters to obtain a fitting degree;

[0087] According to the degree of fit, the collaborative operation parameters of the collaborative equipment and their corresponding matching PLC control parameters are determined. The matching PLC control parameters are the PLC control parameters with the highest search degree of fit, and the matching PLC control parameters are used for production control deployment.

[0088] Furthermore, the embodiment of the present application also includes:

[0089] Set a time window for each device, such as guide wire, drawing machine and coiler, to record the operating status and its impact on other devices;

[0090] Monitor the operating frequency of each device;

[0091] The relationship between the operating frequency and the time window is analyzed through a timing diagram, the interaction points of different devices in the production process are identified, and the process delay time relationship between each device is determined.

[0092] Furthermore, the embodiment of the present application also includes:

[0093] Identify the key operating parameters of each device including guide wire, drawing machine and coiler, and determine the same parameters and different parameters;

[0094] Through historical experimental data, correlation analysis is performed with the same parameters to determine feedback correlation and screen the synergistic parameter relationship of the same parameters;

[0095] Based on the historical experimental data, feedback correlation analysis is performed with the difference parameter as the target to screen the synergistic parameter relationship of the difference parameter;

[0096] The collaborative parameter relationship of the same parameter is combined with the collaborative parameter relationship of the different parameter to obtain the collaborative parameter relationship.

[0097] Furthermore, the embodiment of the present application also includes:

[0098] Collect normal operation data and abnormal case data, and integrate the normal operation data and abnormal case data, including timestamps, device status, and key parameter values;

[0099] Analyze the key parameter differences between the normal operation data and the abnormal case data, and search for abnormal parameter changes;

[0100] According to the timestamp of the abnormal parameter change, the temporal continuity of the normal operation data and the abnormal parameters is determined. Based on the change node of the device state, it is projected to the data position in the abnormal parameter change to determine the collaborative parameter fault tolerance threshold. The collaborative parameter fault tolerance threshold is the difference between the parameter value corresponding to the preceding unit time of the data position and the standard parameter value.

[0101] Furthermore, the embodiment of the present application also includes:

[0102] Establishing a parameter relationship between the real-time operating parameters of the equipment and the production target, matching the parameter relationship with the real-time operating parameters of the equipment, and determining the production target parameters of the polyester fiber yarn;

[0103] Taking maintaining the production target parameters as the goal, taking the synergistic relationship as the constraint condition, and taking the genetic algorithm as the search execution rule, an optimization space is constructed, and the optimal equipment operation parameters are determined through iterative optimization of the optimization space;

[0104] Taking the optimal equipment operating parameters as the target, parameter linkage fitting is performed on the PLC control parameters, and the fitting degree is obtained according to the execution consistency of the PLC control parameters on the optimal equipment operating parameters.

[0105] Furthermore, the embodiment of the present application also includes:

[0106] The equipment operation parameters and PLC control parameters are respectively used as graph nodes, edges are defined according to the relationship between the control parameters, and weights are assigned to the edges to represent the influence strength, thus constructing a graph structure.

[0107] Assign a multidimensional feature vector to each graph node, identify the parameter value, standard deviation, and average value in the historical data, and use the time information and correlation strength of the historical data to add features to the edge;

[0108] Select the GNN model architecture, design the number of layers and aggregation information of the graph structure, and establish a network propagation mechanism of the graph structure so that each node can aggregate the features of its neighboring nodes and use the aggregated features to update the own features of each node;

[0109] The collected historical data sets of PLC control parameters and equipment operation parameters are used to train the GNN model and converge, and the relationship model between the PLC control parameters and equipment operation parameters is obtained;

[0110] Based on the relationship model between the PLC control parameters and the equipment operating parameters, the optimal equipment operating parameters are used as input features to perform PLC control parameter analysis and output fitting results of the PLC control parameters.

[0111] Furthermore, the embodiment of the present application also includes:

[0112] The formula expression for obtaining the degree of fit is: , where n is the dimension of the parameter, is the optimal device operation parameter vector, is the PLC control parameter vector, is the value of the ith PLC control parameter, is the value of the i-th optimal equipment operating parameter, is the variance of the optimal equipment operating parameters.

[0113] Any steps of the system described above may be stored as computer instructions or programs in an unlimited computer memory, and may be called and recognized by an unlimited computer processor to implement any system in the embodiments of the present application, without any unnecessary restrictions.

[0114] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A polyester fiber multi-device collaborative control system using a PLC controller, characterized in that: include: A relationship establishment module, wherein the relationship establishment module is used to establish a collaborative relationship among the guide wire, the drawing machine, and the coiling machine, including a process delay time relationship, a collaborative parameter relationship, and a collaborative parameter fault tolerance threshold; A parameter monitoring module, which is used to monitor the operating parameters of the equipment in real time by deploying sensors on the collaborative equipment, and synchronously extract the control parameters of the PLC controller; A parameter fitting module, wherein the parameter fitting module is used to perform parameter linkage fitting on the real-time operation parameters of the equipment and the PLC control parameters with the synergistic relationship as a constraint condition to obtain a fitting degree; A control deployment module, wherein the control deployment module is used to determine the collaborative operation parameters of the collaborative equipment and the corresponding matching PLC control parameters according to the fit degree, wherein the matching PLC control parameters are the PLC control parameters with the highest search fit degree, and the matching PLC control parameters are used to perform production control deployment; The relationship building module includes the following execution steps: Set a time window for each device, such as guide wire, drawing machine and coiler, to record the operating status and its impact on other devices; Monitor the operating frequency of each device; Analyzing the relationship between the operating frequency and the time window through a timing diagram, identifying the interaction points of different devices in the production process, and determining the process delay time relationship between the devices; The relationship building module also includes the following execution steps: Identify the key operating parameters of each device including guide wire, drawing machine and coiler, and determine the same parameters and different parameters; Through historical experimental data, correlation analysis is performed with the same parameters to determine feedback correlation and screen the synergistic parameter relationship of the same parameters; Based on the historical experimental data, feedback correlation analysis is performed with the difference parameter as the target to screen the synergistic parameter relationship of the difference parameter; Combining the collaborative parameter relationship of the same parameter with the collaborative parameter relationship of the different parameter to obtain the collaborative parameter relationship; The relationship building module also includes the following execution steps: Collect normal operation data and abnormal case data, and integrate the normal operation data and abnormal case data, including timestamps, device status, and key parameter values; Analyze the key parameter differences between the normal operation data and the abnormal case data, and search for abnormal parameter changes; According to the timestamp of the abnormal parameter change, the temporal continuity of the normal operation data and the abnormal parameters is determined. Based on the change node of the device state, it is projected to the data position in the abnormal parameter change to determine the collaborative parameter fault tolerance threshold. The collaborative parameter fault tolerance threshold is the difference between the parameter value corresponding to the preceding unit time of the data position and the standard parameter value.

2. The polyester fiber yarn multi-device coordinated control system using a PLC controller as claimed in claim 1, characterized in that: The parameter fitting module includes the following execution steps: Establishing a parameter relationship between the real-time operating parameters of the equipment and the production target, matching the parameter relationship with the real-time operating parameters of the equipment, and determining the production target parameters of the polyester fiber yarn; Taking maintaining the production target parameters as the goal, taking the synergistic relationship as the constraint condition, and taking the genetic algorithm as the search execution rule, an optimization space is constructed, and the optimal equipment operation parameters are determined through iterative optimization of the optimization space; Taking the optimal equipment operating parameters as the target, parameter linkage fitting is performed on the PLC control parameters, and the fitting degree is obtained according to the execution consistency of the PLC control parameters on the optimal equipment operating parameters.

3. The polyester fiber yarn multi-device coordinated control system using a PLC controller as claimed in claim 2, characterized in that: The parameter fitting module also includes the following execution steps: The equipment operation parameters and PLC control parameters are respectively used as graph nodes, edges are defined according to the relationship between the control parameters, and weights are assigned to the edges to represent the influence strength, thus constructing a graph structure. Assign a multidimensional feature vector to each graph node, identify the parameter value, standard deviation, and average value in the historical data, and use the time information and correlation strength of the historical data to add features to the edge; Select the GNN model architecture, design the number of layers and aggregation information of the graph structure, and establish a network propagation mechanism of the graph structure so that each node can aggregate the features of its neighboring nodes and use the aggregated features to update the own features of each node; The collected historical data sets of PLC control parameters and equipment operation parameters are used to train the GNN model and converge, and the relationship model between the PLC control parameters and equipment operation parameters is obtained; Based on the relationship model between the PLC control parameters and the equipment operating parameters, the optimal equipment operating parameters are used as input features to perform PLC control parameter analysis and output fitting results of the PLC control parameters.

4. The polyester fiber yarn multi-device coordinated control system using a PLC controller as claimed in claim 2, characterized in that: The formula expression for obtaining the degree of fit is: , where n is the dimension of the parameter, is the optimal device operation parameter vector, is the PLC control parameter vector, is the value of the ith PLC control parameter, is the value of the i-th optimal equipment operating parameter, is the variance of the optimal equipment operating parameters.

5. A polyester fiber yarn multi-device collaborative control method using a PLC controller, characterized in that: include: Establish the collaborative relationship between the wire guide, drawing machine, and coiling machine, including the process delay time relationship, collaborative parameter relationship, and collaborative parameter fault tolerance threshold; By deploying sensors on collaborative equipment, the operating parameters of the equipment are monitored in real time, and the control parameters of the PLC controller are extracted synchronously; Taking the collaborative relationship as a constraint condition, parameter linkage fitting is performed on the real-time operation parameters of the equipment and the PLC control parameters to obtain a fitting degree; According to the degree of fit, determining the collaborative operation parameters of the collaborative equipment and the corresponding matching PLC control parameters, wherein the matching PLC control parameters are the PLC control parameters with the highest search degree of fit, and using the matching PLC control parameters to perform production control deployment; The method further comprises: Set a time window for each device, such as guide wire, drawing machine and coiler, to record the operating status and its impact on other devices; Monitor the operating frequency of each device; Analyzing the relationship between the operating frequency and the time window through a timing diagram, identifying the interaction points of different devices in the production process, and determining the process delay time relationship between the devices; The method further comprises: Identify the key operating parameters of each device including guide wire, drawing machine and coiler, and determine the same parameters and different parameters; Through historical experimental data, correlation analysis is performed with the same parameters to determine feedback correlation and screen the synergistic parameter relationship of the same parameters; Based on the historical experimental data, feedback correlation analysis is performed with the difference parameter as the target to screen the synergistic parameter relationship of the difference parameter; Combining the collaborative parameter relationship of the same parameter with the collaborative parameter relationship of the different parameter to obtain the collaborative parameter relationship; The method further comprises: Collect normal operation data and abnormal case data, and integrate the normal operation data and abnormal case data, including timestamps, device status, and key parameter values; Analyze the key parameter differences between the normal operation data and the abnormal case data, and search for abnormal parameter changes; According to the timestamp of the abnormal parameter change, the temporal continuity of the normal operation data and the abnormal parameters is determined. Based on the change node of the device state, it is projected to the data position in the abnormal parameter change to determine the collaborative parameter fault tolerance threshold. The collaborative parameter fault tolerance threshold is the difference between the parameter value corresponding to the preceding unit time of the data position and the standard parameter value.

Images