Heat temperature control method and system for compression wheel of pe packaging line and storage medium

Abstract

The application relates to the technical field of intelligent temperature control, and discloses a pressure roller heating temperature control method and system of a PE packaging line and a storage medium, the method comprising the following steps: taking process variables and environmental variables in high-dimensional time sequence data as nodes and taking dynamic causal relationships as edges to construct a dynamic causal structure diagram of the packaging line; taking the pressure roller temperature as a target node, screening a causal influence relationship to obtain a local network, tracing a key path to obtain a precursor variable; mapping a dynamic behavior mode of the precursor variable to generate a pressure roller temperature feedforward compensation strategy; analyzing the feedforward compensation strategy and a real-time state vector of the precursor variable to obtain a predictive compensation amount; based on the predictive compensation amount, a pressure roller temperature control instruction is cooperatively decided, and a comprehensive control instruction is generated; according to the execution effect of the comprehensive control instruction and topological consistency, the strategy applicability is judged, and a reconstruction trigger signal is obtained; and the application can improve the pressure roller temperature control operation efficiency of the PE packaging line.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent temperature control, and in particular to a pressure roller heating temperature control method and system for a PE packaging line and a storage medium. BACKGROUND

[0002] The PE packaging line plays a key role in plastic packaging industrial production, and the control of the heating temperature of the pressure roller directly affects the sealing strength, appearance quality and production efficiency of the packaged product. The traditional control method usually adopts a feedback-based PID control mechanism to maintain temperature stability by monitoring the pressure roller temperature in real time and adjusting the power of the heating device. In addition, some advanced control strategies introduce multivariable adjustment and adaptive algorithms to cope with disturbances in the production line operation. However, these methods rely on the linear relationship between local variables and do not fully consider the complex dynamic relationship between process variables and environmental variables in high-dimensional time series data, resulting in insufficient control models in dealing with nonlinear and time-delay disturbances.

[0003] In the prior art, there are two main problems with the pressure roller temperature control method: first, the dynamic causal relationship between process variables and environmental variables has not been systematically modeled, so the control strategy cannot accurately capture the time delay characteristics and influence paths of multivariable interaction, resulting in a disconnect between compensation actions and actual disturbances; second, there is a lack of a feedforward compensation mechanism based on the causal topology, so that the control command relies only on historical data and real-time feedback, making it difficult to predict changes in dynamic behavior patterns, resulting in system response lag and stability decline. Therefore, how to improve the efficiency of the pressure roller temperature control of the PE packaging line has become a problem to be solved. SUMMARY

[0004] The present application provides a pressure roller heating temperature control method and system for a PE packaging line.

[0005] In a first aspect, the present application provides a pressure roller heating temperature control method for a PE packaging line, comprising:

[0006] S1, constructing a dynamic causal structure diagram of the packaging line by taking process variables and environmental variables in a high-dimensional time series data set as nodes and taking dynamic causal relationships between the process variables and the environmental variables as edges;

[0007] S2, filtering the causal influence relationship of the dynamic causal structure diagram based on the pressure roller temperature as the target node to obtain a local causal network of the pressure roller temperature, and tracing back the key causal paths in the local causal network to obtain the precursor variables of the pressure roller temperature;

[0008] S3, performing rule mapping on the dynamic behavior patterns in the precursor variables to obtain a feedforward compensation strategy for the pressure roller temperature;

[0009] S4, feedforward manipulation variable analysis is performed on the real-time state vector in the precursor variable and the feedforward compensation strategy to obtain a predictive compensation amount of the compression roller temperature;

[0010] S5, based on the predictive compensation amount, a cooperative decision is made on the control instruction of the compression roller temperature to obtain a comprehensive control instruction of the compression roller temperature;

[0011] S6, based on the execution effect of the comprehensive control instruction and the topological consistency of the dynamic causal structure diagram, a stability determination is made on the applicability of the feedforward compensation strategy to obtain a reconstruction trigger signal of the feedforward compensation strategy.

[0012] In a preferred embodiment, the dynamic causal structure diagram of the packaging line is constructed by taking the process variables and the environmental variables in the high-dimensional time series data set as nodes, and taking the dynamic causal relationship between the process variables and the environmental variables as edges, comprising:

[0013] Obtaining original time series data of the packaging line, and performing data coordination on the original time series data to obtain high-dimensional time series data of the packaging line;

[0014] Dividing the working condition variables in the high-dimensional time series data according to a preset variable function classification rule to obtain a process variable group and an environmental variable group of the packaging line;

[0015] Nodeing the process variable group and the environmental variable group to obtain a node set of the packaging line;

[0016] Performing time lag correlation analysis on the variable interaction in the node set to obtain a dynamic correlation measure between the process variables and the environmental variables;

[0017] Performing causal orientation inference on the dynamic correlation measure to obtain a directed edge set of the packaging line;

[0018] Topologically reconstructing the node set and the directed edge set to obtain a dynamic causal structure diagram of the packaging line.

[0019] In a preferred embodiment, the dynamic causal structure diagram is subjected to causal influence relationship screening based on the compression roller temperature as a target node to obtain a local causal network of the compression roller temperature, and the key causal path in the local causal network is traced back to obtain a precursor variable of the compression roller temperature, comprising:

[0020] Taking the compression roller temperature as a target node, direct causal edge extraction is performed on the dynamic causal structure diagram to obtain a direct association set of the compression roller temperature;

[0021] In the dynamic causal structure diagram, multi-stage causal backtracking is performed from the end nodes of the causal edges in the direct association set to obtain an indirect causal path cluster of the compression wheel temperature;

[0022] Taking the direct association set as a point and the indirect causal path cluster as an edge, a complete causal network of the compression wheel temperature is constructed;

[0023] Path strength quantification is performed on each causal path in the complete causal network to obtain a causal influence weight of the complete causal network;

[0024] Based on the causal influence weight, path significance of all paths in the complete causal network is screened to obtain a key causal path of the compression wheel temperature;

[0025] Variable tracing is performed on the key causal path to obtain a precursor variable of the compression wheel temperature.

[0026] In a preferred embodiment, the rule mapping of the dynamic behavior pattern in the precursor variable obtains a feedforward compensation strategy of the compression wheel temperature, including:

[0027] According to the experience rule of the packaging line historical optimal control process, a basic compensation rule of the compression wheel temperature is obtained;

[0028] Dynamic evolution trend tracking is performed on the precursor variable to obtain a behavior trajectory sequence of the precursor variable;

[0029] Pattern features of the behavior trajectory sequence are mined to obtain a significant feature of the dynamic behavior pattern;

[0030] The significant feature is matched and mapped with the basic compensation rule to obtain a candidate compensation rule of the compression wheel temperature;

[0031] Multi-objective optimization decision is performed on the candidate compensation rule to obtain a feedforward compensation strategy of the compression wheel temperature.

[0032] In a preferred embodiment, feedforward manipulated variable analysis is performed on the feedforward compensation strategy and a real-time state vector in the precursor variable to obtain a predictive compensation amount of the compression wheel temperature, including:

[0033] Rule deconstruction is performed on the feedforward compensation strategy to obtain a control rule segment of the feedforward compensation strategy;

[0034] Based on the control rule segment, variable selection is performed on the real-time state vector in the precursor variable to obtain a key variable subset of the real-time state vector;

[0035] bias recognition is performed on the key variable subset to obtain a real-time bias value of the key variable subset;

[0036] The real-time bias value and the control rule segment are dynamically weighted and fused to obtain a predictive compensation amount of the compression wheel temperature.

[0037] In a preferred embodiment, the real-time bias value and the control rule segment are dynamically weighted and fused to obtain a predictive compensation amount of the compression wheel temperature, wherein the calculation formula of the predictive compensation amount is specifically as follows:

[0038] ;

[0039] In the formula, is the predictive compensation amount, is the total number of precursor variables included in the key variable subset, is a dynamic weight coefficient of the th precursor variable, is a real-time bias value of the th precursor variable, is an absolute amplitude of the real-time bias value, is a time constant of the th precursor variable, is a differential gain coefficient, denotes a time differential operation on the expression in the parentheses, is an exponential function.

[0040] In a preferred embodiment, based on the predictive compensation amount, a cooperative decision is made on the control instruction of the compression wheel temperature to obtain a comprehensive control instruction of the compression wheel temperature, including:

[0041] The predictive compensation amount is distributed and discretized to obtain an influence degree distribution of the compression wheel temperature;

[0042] Based on the influence degree distribution, a multi-objective weight distribution is performed on the control instruction of the compression wheel temperature to obtain a weighted decision benchmark of the compression wheel temperature;

[0043] Based on the weighted decision benchmark, a multi-objective trade-off is performed on the control instruction of the compression wheel temperature to obtain a trade-off control instruction of the compression wheel temperature;

[0044] According to the dynamic running margin of the packaging line, the instruction stability of the trade-off control instruction is evaluated to obtain an enhanced instruction of the compression wheel temperature;

[0045] The enhanced instruction and a real-time feedback control instruction of the compression wheel temperature are instruction fusion optimized to obtain a comprehensive control instruction of the compression wheel temperature.

[0046] In a preferred embodiment, the stability of the applicability of the feedforward compensation strategy is determined based on the consistency of the execution effect of the comprehensive control instruction and the topology of the dynamic causal structure diagram, and a reconstruction trigger signal of the feedforward compensation strategy is obtained, comprising:

[0047] The comprehensive control instruction is applied to the packaging line to extract the control efficiency of the packaging line,

[0048] The operating characteristics of the compression wheel temperature are obtained;

[0049] Based on the dynamic causal structure diagram, the operating characteristics are analyzed for causal topology coupling to obtain a causal consistency coefficient of the feedforward compensation strategy;

[0050] Based on the causal consistency coefficient, a strategy efficiency determination of the feedforward compensation strategy is performed to obtain an applicability decision result of the feedforward compensation strategy;

[0051] Based on the applicability decision result, the stability state of the feedforward compensation strategy is determined to obtain a reconstruction trigger signal of the feedforward compensation strategy.

[0052] In order to solve the above problems, the application also provides a compression wheel heating temperature control system of a PE packaging line, comprising:

[0053] A dynamic causal structure diagram construction module is configured to construct a dynamic causal structure diagram of a packaging line by taking process variables and environmental variables in a high-dimensional time series data set as nodes, and taking dynamic causal relationships between the process variables and the environmental variables as edges;

[0054] A causal screening and precursor variable acquisition module is configured to screen a causal influence relationship of the dynamic causal structure diagram based on a compression wheel temperature as a target node, to obtain a local causal network of the compression wheel temperature, and to trace a key causal path in the local causal network to obtain a precursor variable of the compression wheel temperature;

[0055] A feedforward compensation strategy generation module is configured to perform rule mapping on a dynamic behavior pattern in the precursor variable to obtain a feedforward compensation strategy of the compression wheel temperature;

[0056] A predictive compensation amount analysis module is configured to perform feedforward manipulated variable analysis on the feedforward compensation strategy and a real-time state vector in the precursor variable to obtain a predictive compensation amount of the compression wheel temperature;

[0057] A comprehensive control instruction decision module is configured to perform collaborative decision on a control instruction of the compression wheel temperature based on the predictive compensation amount to obtain a comprehensive control instruction of the compression wheel temperature;

[0058] The compensation strategy stability determination module is configured to determine the stability of the applicability of the feedforward compensation strategy based on the execution effect of the comprehensive control instruction and the topological consistency of the dynamic causal structure diagram, and obtain a reconstruction trigger signal of the feedforward compensation strategy.

[0059] Compared with the prior art, the present application has the following beneficial effects:

[0060] 1. The present application accurately identifies the precursor variables and their behavior patterns that affect the temperature of the compression roller by constructing a dynamic causal structure diagram and systematically analyzing the time delay correlation and causal path between process variables and environmental variables. The feedforward compensation strategy generated based on this can predict disturbance trends and analyze the predictive compensation amount, thereby significantly improving the timeliness and accuracy of temperature control and overcoming the response lag problem caused by ignoring variable dynamic interaction in traditional methods.

[0061] 2. The present application has a comprehensive control instruction cooperative decision-making and strategy applicability determination mechanism, which can dynamically evaluate the control effect and the consistency of the causal topology, and trigger strategy reconstruction accordingly. This mechanism ensures that the feedforward compensation strategy always matches the real-time state of the production line, effectively avoids control failure caused by changes in working conditions, and improves the stability and self-adaptive ability of the system in complex operating environments. BRIEF DESCRIPTION OF DRAWINGS

[0062] In the following, the present disclosure will be described in more detail based on embodiments and with reference to the accompanying drawings:

[0063] Figure 1 A work flow diagram of the compression roller heating temperature control method of the PE packaging line according to the first embodiment of the present application is shown;

[0064] Figure 2 A functional module diagram of the compression roller heating temperature control system of the PE packaging line according to the second embodiment of the present application is shown. DETAILED DESCRIPTION

[0065] In order for those skilled in the art to better understand the technical solutions of the present disclosure, and to fully understand and implement the implementation process of the present disclosure in which the technical means is applied to solve the technical problems and achieve the corresponding technical effects, the technical solutions in the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, not all. The embodiments of the present disclosure and the features of the embodiments can be combined with each other without conflict, and the technical solutions formed thereby are within the protection scope of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor shall be within the scope of protection of the present disclosure.

[0066] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0067] Embodiment one

[0068] Figure 1 The flowchart of the PE packaging line roller heating temperature control method provided by the embodiment of the present disclosure is shown in the figure. As shown in the figure, a smart device control method comprises: Figure 1

[0069] S1, taking the process variables and environmental variables in the high-dimensional time series data set as nodes, and taking the dynamic causal relationship between the process variables and the environmental variables as edges, to construct a dynamic causal structure diagram of the packaging line;

[0070] In the embodiment of the present application, the dynamic causal structure diagram of the packaging line is constructed by taking the process variables and environmental variables in the high-dimensional time series data set as nodes, and taking the dynamic causal relationship between the process variables and the environmental variables as edges, comprising:

[0071] Obtain the original time series data of the packaging line, and perform data coordination on the original time series data to obtain the high-dimensional time series data of the packaging line;

[0072] Divide the working condition variables in the high-dimensional time series data according to the preset variable function classification rule to obtain the process variable group and the environmental variable group of the packaging line;

[0073] Node the process variable group and the environmental variable group to obtain the node set of the packaging line;

[0074] Perform time lag correlation analysis on the variable interaction in the node set to obtain the dynamic correlation measure between the process variables and the environmental variables;

[0075] Perform causal orientation inference on the dynamic correlation measure to obtain the directed edge set of the packaging line;

[0076] Topological reconstruction is performed on the node set and the directed edge set to obtain the dynamic causal structure diagram of the packaging line.

[0077] ​Collect various types of original record data generated by the PE packaging line during actual production operation, which covers key information of the entire process of the packaging line operation, including but not limited to the running speed of the pinch roller, the output power of the heating device, the transmission speed of the material, the real-time temperature feedback of the heating area, the equipment running current, etc. Carry out systematic analysis of the collected original time series data, check the abnormal fluctuation values and invalid records in the data through professional verification means, fill in the missing items in the data collection process according to the time series change rule and the characteristics of the adjacent valid data, unify the record format and time sampling scale of all data, ensure that different types of data are synchronized and aligned in the time dimension, and finally form high-dimensional time series data covering key parameters of the packaging line operation and reliable data quality.

[0078] Based on the working principle of the PE packaging line, the production process requirements and the actual control requirements, a clear and executable variable function classification standard is developed, which clearly defines the functional attributes and classification basis of different variables. Based on this pre-set classification standard, all operating variables contained in the high-dimensional time series data are identified and classified one by one. The variables that directly participate in the production operation process of the packaging line and can be adjusted through device control are classified as process variable group, such as pinch roller speed, heating device power, material supply speed, etc. The external variables that affect the running state of the packaging line but are not directly controlled by the production process are classified as environmental variable group, such as temperature, humidity, power grid voltage fluctuation in the workshop, etc. Through such classification operation, the process variable group and the environmental variable group of the packaging line are obtained respectively.

[0079] For the classified process variable group and environmental variable group, each variable is independently identified and defined in detail, and each variable is given a unique identification information, which clearly defines the specific physical meaning, data acquisition range, numerical change rule and other characteristics represented by each variable. Each variable is converted into an independent basic unit that can be used for network structure analysis, which is a node. All identified and defined process variable nodes and environmental variable nodes together constitute the node set of the packaging line.

[0080] Deeply analyze the interaction process of the variables corresponding to each node in the node set during the operation of the packaging line, and focus on the time delay characteristics of the mutual influence between different variables. By continuously tracking the numerical changes of the variables, the time interval between the occurrence of a variable change and the response change of another related variable is calculated, and the strength of this influence is quantified, such as analyzing how long it takes for the heating temperature of the pressure roller to change after the environmental temperature rises, and how much the temperature changes. Through such analysis, the quantification results that can fully reflect the correlation strength, time delay and other key characteristics between variables are obtained, which are the dynamic correlation metrics between process variables and environmental variables.

[0081] Based on the dynamic correlation metric results obtained, the production operation logic, process flow and actual interaction rules between variables of the PE packaging line are combined to determine the direction of the influence relationship between variables. It is clear to distinguish which variable change is the cause of other variable changes, and which variable change is the result of being affected by other variables, and to determine the specific direction of the causal relationship between variables. Each pair of variables with a causal relationship is represented by an edge with a clear direction, with the starting end of the edge corresponding to the cause variable node and the terminating end of the edge corresponding to the result variable node. All such edges with directions are integrated together to form a directed edge set of the packaging line.

[0082] According to the causal relationship direction clearly defined in the directed edge set, each node in the node set is connected in order through the corresponding directed edge. In the connection process, the hierarchical relationship between variables is fully considered to ensure that the variable nodes at the front end of the causal chain are correctly directed to the subsequent variable nodes affected by them through the directed edge, and a network structure that can fully and clearly reflect the dynamic causal relationship between all variables is constructed. Through such topological integration and reconstruction operations, the dynamic causal structure diagram of the PE packaging line is finally formed.

[0083] The beneficial effects are that the original time series data is complete, accurate and consistent, providing a reliable data foundation for subsequent causal relationship construction, avoiding the interference of poor data on the analysis results, realizing accurate classification of working condition variables, clearly defining variable function attributes, avoiding analysis confusion caused by variable mixing, laying a clear foundation for node processing and causal analysis, converting variables into independent and identifiable node units, forming an ordered node set, providing a carrier for the construction of the correlation relationship network between variables, facilitating the intuitive representation of variable interaction, capturing the time lag characteristics and strength differences between variables, avoiding the correlation judgment deviation caused by ignoring the time lag, providing accurate basis for accurately inferring causal relationships, clearly defining the causal relationship direction between variables, avoiding misjudgment of correlation and causality or confusion of direction, forming a directed edge set to provide core edge structure support for the dynamic causal structure diagram, integrating nodes and directed edges into an intuitive dynamic causal structure diagram, clearly showing the causal path and hierarchical relationship between variables, and improving efficiency and accuracy for subsequent screening of key paths and tracing of precursor variables.

[0084] S2, based on the temperature of the compression roller as a target node, performing causal influence relationship screening on the dynamic causal structure diagram to obtain a local causal network of the temperature of the compression roller, and tracing a key causal path in the local causal network to obtain a precursor variable of the temperature of the compression roller;

[0085] In the embodiment of the application, the screening of the dynamic causal structure diagram based on the temperature of the compression roller as a target node to obtain a local causal network of the temperature of the compression roller, and tracing a key causal path in the local causal network to obtain a precursor variable of the temperature of the compression roller, comprises:

[0086] extracting a direct causal edge from the dynamic causal structure diagram with the temperature of the compression roller as a target node to obtain a direct association set of the temperature of the compression roller;

[0087] In the dynamic causal structure diagram, performing multi-order causal backtracking from the end nodes of the causal edges in the direct association set as a starting point to obtain an indirect causal path cluster of the temperature of the compression roller;

[0088] Taking the direct association set as a point and the indirect causal path cluster as an edge to construct a complete causal network of the temperature of the compression roller;

[0089] Quantifying the path strength of each causal path in the complete causal network to obtain a causal influence weight of the complete causal network;

[0090] Based on the causal influence weight, screening the path significance of all paths in the complete causal network to obtain a key causal path of the temperature of the compression roller;

[0091] Performing variable tracing on the key causal path to obtain a precursor variable of the temperature of the compression roller.

[0092] The core positioning of the temperature of the compression roller in the dynamic causal structure diagram is determined, and the temperature of the compression roller is taken as a target object that needs to be analyzed and affected. All causal connection relationships in the dynamic causal structure diagram are comprehensively sorted out, and it is judged whether the end point of each causal connection is consistent with the node corresponding to the temperature of the compression roller. All causal connections with the end point being exactly the node of the temperature of the compression roller are screened out, and these screened causal connections jointly constitute the direct association set of the temperature of the compression roller.

[0093] In the completed dynamic causal structure diagram, the end nodes of each causal connection in the direct correlation set are accurately identified first, and these end nodes are the front nodes directly acting on the roller temperature node. Taking each end node as the initial search point, the search work is carried out along the reverse direction of the causal connection, and the first level front nodes and the corresponding causal connections that can directly affect the end node are found out first, and then the first level front nodes are taken as the new starting point to continue to find the second level front nodes and the corresponding causal connections that can affect them in the reverse direction. According to this way, the level number of backtracking is reasonably set combined with the actual running conditions of the packaging line and the close degree of association between data, and all the causal paths obtained through multi-level reverse search are collected to form the indirect causal path cluster of the roller temperature.

[0094] The nodes involved in each causal connection in the direct correlation set are taken as the core support points for building the network. Each causal path in the indirect causal path cluster is taken as the link between the core nodes and the indirectly affected nodes, and the core nodes and the corresponding indirectly affected nodes are connected in order according to the actual causal direction relationship of each path, while the original connection relationship between the direct correlation nodes remains unchanged. Through such a combination mode, a complete causal network of the roller temperature is finally formed, which has clear structure and covers direct and indirect influence relationships.

[0095] Combined with the historical running data of the packaging line, the control accuracy requirements of the roller temperature and the actual close degree of association between variables, an evaluation standard system including key dimensions such as correlation frequency, influence amplitude and duration is established. For each causal path in the complete causal network, its specific performance in each evaluation dimension is analyzed one by one, and the corresponding weight proportion is given according to the importance of each evaluation dimension, and then the specific numerical value corresponding to each causal path is obtained through comprehensive calculation. This value is the causal influence weight of the causal path, which directly reflects the influence strength of the path on the roller temperature.

[0096] Combined with the actual production needs of the packaging line, the priority of the roller temperature control and the historical control experience, a reasonable screening limit value is comprehensively determined, which can effectively distinguish the paths with greater influence on the roller temperature and the paths with smaller influence. The causal influence weight of each causal path in the complete causal network is compared with the set screening limit value one by one, and the causal paths with weight values greater than or equal to the screening limit value are selected out. These selected paths are the key causal paths that have significant influence on the roller temperature, and the specific structure and associated node information of each key causal path are recorded in detail.

[0097] For each filtered key causal path, starting from the pressure roller temperature target node, following the reverse causal direction of the path, each node on the path is searched one by one, including directly associated variables and indirectly associated variables through multiple stages, ensuring that no variable on the path is missed. All variables involved in the key causal path are collected comprehensively, and duplicate variables are removed. These collected and de-duplicated variables are the precursor variables that can directly or indirectly affect the pressure roller temperature, and the specific position of each precursor variable in the key causal path and the association with other variables are recorded.

[0098] The beneficial effects are that the direct impact elements of the pressure roller temperature are quickly focused, irrelevant causal connection interference is excluded, the causal relationship screening efficiency is improved, a precise foundation is laid for subsequent analysis, potential paths indirectly affecting the pressure roller temperature are fully excavated, important indirect factors are avoided, the pressure roller temperature influence factor analysis is more complete, direct and indirect influence factors are integrated, a structured complete causal network is constructed, the systematization and orderliness of the pressure roller temperature influence factor analysis are improved, abstract causal effects are converted into comparable numerical values, objective and accurate basis is provided for key causal path screening, the scientificity and accuracy of screening are improved, the key path that plays a leading role in the pressure roller temperature is accurately focused, secondary path interference is excluded, subsequent workload is reduced, the accuracy and efficiency of influence factor analysis are improved, all key precursor variables affecting the pressure roller temperature are accurately locked, explicit basis is provided for formulating a feedforward compensation strategy, and the pertinence and effectiveness of pressure roller temperature control are improved.

[0099] S3, performing rule mapping on the dynamic behavior mode of the precursor variable to obtain a feedforward compensation strategy of the pressure roller temperature;

[0100] In the embodiment of the present application, the rule mapping on the dynamic behavior mode of the precursor variable to obtain the feedforward compensation strategy of the pressure roller temperature comprises:

[0101] According to the experience rule of the packaging line historical optimal control process, a basic compensation rule of the pressure roller temperature is obtained;

[0102] Tracking the dynamic evolution trend of the precursor variable to obtain a behavior trajectory sequence of the precursor variable;

[0103] Mining the pattern features of the behavior trajectory sequence to obtain significant features of the dynamic behavior mode;

[0104] Matching and mapping the significant features with the basic compensation rule to obtain a candidate compensation rule of the pressure roller temperature;

[0105] Multi-objective optimization decision is made on the candidate compensation rule to obtain the feedforward compensation strategy of the pressure roller temperature.

[0106] The judgment criteria of the historical optimal control process of the packaging line are defined, and the operation period with the minimum range of the pressure roller temperature fluctuation and the highest level of the packaging product qualification rate is selected as the historical optimal control process. The data in these periods are comprehensively collected, including the pressure roller temperature adjustment parameters, the environmental conditions at that time, the packaging line operation load, the working state of the related components, and other information. The repeatedly appearing control logic and operation specification in the collected information are refined, and these effective logic and specification verified by practice are the experience rules of the historical optimal control process. The experience rules are classified and integrated according to the control scene, the influencing factors, and other dimensions to form a set of pressure roller temperature basic compensation rules with universality and practicality, which provide the initial basis for the construction of the subsequent compensation strategy.

[0107] For the determined pressure roller temperature precursor variables, a reasonable collection time interval is set to ensure that the changes of the variables can be captured in time. According to the set interval, the real-time values of each precursor variable are continuously collected, and the time nodes corresponding to the values are recorded. During the collection process, the change trend of each precursor variable value is closely observed, including different states such as value rising, falling, and keeping stable, as well as the speed of change. The values of each precursor variable at different time nodes and the corresponding change states are arranged in sequence according to the time sequence to form a complete and continuous precursor variable behavior trajectory sequence, which fully presents the dynamic change process of the precursor variable.

[0108] The formed precursor variable behavior trajectory sequence is analyzed in depth, and the change amplitude of the variable value in the sequence is focused on, i.e. the difference between the values at adjacent time nodes; the change frequency, i.e. the number of times the value changes significantly; the duration, i.e. the length of time the variable remains in a certain change trend or stable state; and the time law and value characteristics of the peak and valley. By comparing the trajectory sequences in different time periods and different scenes, those features that have a significant impact on the change of the pressure roller temperature, repeatedly appear in multiple runs, or have a very representative change trend are selected. These selected features with key influence are the significant features of the dynamic behavior mode.

[0109] First, the basic compensation rules are disassembled, and the core adaptation conditions of each basic compensation rule, such as the applicable scene, the trigger condition, and the corresponding adjustment method, are clarified. The dynamic behavior mode significant features refined before are compared and analyzed with the adaptation conditions of each basic compensation rule one by one to determine whether the significant features meet the applicable scene and trigger requirements of a basic compensation rule. For those basic compensation rules with high adaptation conditions and significant features, they are selected out. These selected basic compensation rules that match the current precursor variable behavior mode form the candidate compensation rules of the pressure roller temperature.

[0110] The pressure roller temperature feedforward compensation strategy has several clearly defined objectives, including improving the control accuracy of the pressure roller temperature, accelerating the response speed of temperature adjustment, ensuring the overall stability of the packaging line, and reducing energy consumption. For each candidate compensation rule, its performance under each objective is evaluated. For example, one rule may excel in control accuracy but have a slightly slower response speed, while another rule may have advantages in both response speed and stability. The advantages and disadvantages of each candidate compensation rule are comprehensively weighed, considering both performance under a single objective and the balance between multiple objectives. Finally, one or more candidate compensation rules that exhibit the best overall performance across multiple objectives are selected and integrated to form a pressure roller temperature feedforward compensation strategy that can meet various control requirements.

[0111] The beneficial effects are as follows: the basic compensation rules are derived from the historical optimal control experience of the packaging line, ensuring the reliability and practicality of the rules; after sorting and integration, the structure is clear and the applicable scenarios are well-defined, laying an effective foundation for subsequent matching with significant features. Continuously collecting precursor variable data at reasonable intervals can comprehensively capture its dynamic evolution process, avoiding misjudgment of behavior patterns due to missing or lagging data. The resulting behavior trajectory sequence provides continuous and systematic support for subsequent mining of pattern features. Focusing on the core information of the trajectory sequence to extract significant features can effectively eliminate irrelevant data and interference information. Clear significant features make subsequent matching with basic compensation rules more targeted, avoiding rule adaptation bias. By accurately comparing the significant features with the adaptation conditions of basic compensation rules, rules that fit the current variable behavior pattern can be selected, inapplicable rules can be eliminated, the scope of subsequent optimization decisions can be narrowed, invalid interference can be reduced, and decision-making efficiency and accuracy can be improved. Multi-objective optimization decisions take into account the requirements of control precision, response speed, and operational stability, avoiding the limitations of single-objective orientation; the integrated feedforward compensation strategy can achieve optimal balance in multiple dimensions, can cope with complex packaging line operation scenarios, and achieve efficient and precise control of pressure roller temperature.

[0112] S4. Perform feedforward manipulation variable analysis on the feedforward compensation strategy and the real-time state vector in the precursor variables to obtain the predictive compensation amount of the pressure roller temperature.

[0113] In this embodiment of the invention, the feedforward compensation strategy and the real-time state vector in the precursor variables are analyzed by feedforward manipulation variables to obtain the predictive compensation amount for the pressure roller temperature, including:

[0114] The feedforward compensation strategy is deconstructed to obtain the control rule fragments of the feedforward compensation strategy;

[0115] Based on the control rule fragment, variable selection is performed on the real-time state vector in the predecessor variables to obtain a subset of key variables of the real-time state vector.

[0116] bias recognition is performed on the key variable subset to obtain a real-time bias value of the key variable subset;

[0117] The real-time bias value and the control rule segment are dynamically weighted and fused to obtain a predictive compensation amount of the compression roller temperature.

[0118] The real-time bias value and the control rule segment are dynamically weighted and fused to obtain a predictive compensation amount of the compression roller temperature, wherein a calculation formula of the predictive compensation amount is specifically as follows:

[0119] ;

[0120] In the formula, is the predictive compensation amount, is a total number of precursor variables included in the key variable subset, is a dynamic weight coefficient of the i-th precursor variable, is a real-time bias value of the i-th precursor variable, is an absolute amplitude of the real-time bias value, is a time constant of the i-th precursor variable, is a differential gain coefficient, denotes a time differential operation on the expression in the parentheses, is an exponential function. First, the overall control logic contained in the feedforward compensation strategy is comprehensively combed, and the core content such as the temperature regulation direction involved in the strategy, the applicable operating conditions, and the sequence relationship of each regulation link is clarified. According to the differences of control targets, the differences of applicable scenes, and the specific types of adjustment actions, the complete feedforward compensation strategy is systematically split, and the originally coherent strategy is decomposed into multiple specific rule units that can be independently analyzed, applied and logically complete. These rule units formed after splitting are control rule segments. In the splitting process, it is necessary to ensure that each rule segment can clearly reflect a certain specific control logic, without missing key regulation requirements or appearing logical repetition.

[0121] First, the overall control logic contained in the feedforward compensation strategy is comprehensively combed, and the core content such as the temperature regulation direction involved in the strategy, the applicable operating conditions, and the sequence relationship of each regulation link is clarified. According to the differences of control targets, the differences of applicable scenes, and the specific types of adjustment actions, the complete feedforward compensation strategy is systematically split, and the originally coherent strategy is decomposed into multiple specific rule units that can be independently analyzed, applied and logically complete. These rule units formed after splitting are control rule segments. In the splitting process, it is necessary to ensure that each rule segment can clearly reflect a certain specific control logic, without missing key regulation requirements or appearing logical repetition.

[0122] ​​Each control rule segment is analyzed one by one to determine the temperature control requirements, adjustment targets and specific requirements for related variables corresponding to each segment. Based on these explicit requirements and requirements, all variables contained in the real-time state vector of the precursor variable are analyzed one by one. The degree of association between each variable and the corresponding control rule segment is judged, the direct influence degree and significance of the variable on the pressure roller temperature adjustment effect are evaluated, and those variables that are highly related to the control rule segment, can directly affect the pressure roller temperature adjustment and have obvious influence effect are screened out. The selected variables are integrated to form a key variable subset of the real-time state vector.

[0123] First, the historical optimal operation data of each variable in the key variable subset during the long-term stable operation of the packaging line is collected, and a stable and reasonable standard reference value is determined for each key variable based on the design standards of the packaging line and the target requirements of temperature control. The current actual operation value of each variable in the key variable subset is collected by real-time monitoring equipment, and each variable is compared and analyzed one by one with the pre-determined standard reference value. The difference between the two is accurately calculated, which is the real-time deviation value of the key variable.

[0124] The importance of each control rule segment in the overall temperature control, the priority order of its application, and the influence of each variable in the key variable subset on the pressure roller temperature are comprehensively considered, and the real-time deviation value of each key variable is assigned a corresponding weight value. This weight value is not fixed and will be adaptively adjusted according to the real-time running conditions, load changes, environmental fluctuations and other situations of the packaging line to ensure that the weight accurately reflects the influence degree of the variable and the rule under the current working condition. Then the real-time deviation value of each key variable is multiplied by the corresponding dynamic weight, and all the operation results are integrated and calculated according to the specific requirements of the control rule segment. The influence of various factors is comprehensively considered, and finally the predictive compensation amount for accurately adjusting the pressure roller temperature is obtained.

[0125] In the calculation formula of the predictive compensation amount is the predictive compensation amount of the pressure roller temperature to be solved, which is used for pressure roller temperature adjustment to match the actual deviation requirement, is the total number of precursor variables in the key variable subset, which comes from the previous variable selection result, is the dynamic weight coefficient of the th precursor variable, which is determined by the influence of the variable on the pressure roller temperature, the importance of the control rule and the real-time working condition, and is used to highlight the role of key factors, is the real-time deviation value of the th precursor variable, which is obtained by comparing the actual value and the standard reference value of the variable, and is the core data for compensation amount calculation, which shows the deviation direction and degree, This represents the absolute magnitude of the deviation, measuring only the magnitude of the deviation and avoiding directional interference in the calculation. For the first The time constants of the precursor variables reflect the response speed to changes in deviation and regulate the pace of change in the influence of deviation. As an exponential function, it performs non-linear adjustment on the impact of deviation, weakening the extreme effects of excessive deviation and making the compensation amount change more smoothly. This is the differential gain coefficient, used to adjust the impact of the dynamic correction on the compensation amount, and is set according to operating condition fluctuations. It is a time differential operation, calculating the rate of change of the expression within parentheses to capture the dynamic effects of operating conditions. It is in the order of variables, for each variable The results are summed to obtain the total static impact. The overall formula first calculates the total static compensation impact of each variable, then adds the dynamic correction amount, and finally obtains the predictive compensation amount, which takes into account both real-time static deviation and dynamic changes in operating conditions.

[0126] The beneficial effects are as follows: splitting the feedforward compensation strategy into control rule segments reduces redundant interference and improves the pertinence and efficiency of subsequent variable selection and deviation calculation. Key variables are selected according to control rules, and irrelevant and weakly influential variables are excluded, reducing data processing volume and avoiding interference, laying the foundation for accurate deviation calculation. Real-time deviation is obtained by comparing the actual value of the variable with the standard benchmark value, providing accurate basic data, clarifying the compensation target, avoiding insufficient or excessive compensation, dynamically adjusting weights and integrating data, so that the predictive compensation amount fits the real-time operating conditions, improving the accuracy and timeliness of compensation, and helping to stabilize the pressure roller temperature. This formula integrates the static influence and dynamic trend of key variables, balances the role of various factors, and ensures that the compensation amount calculation is scientific and accurate, closely matching the actual operating needs of the packaging line.

[0127] S5. Based on the predictive compensation amount, make collaborative decisions on the control command for the pressure roller temperature to obtain the comprehensive control command for the pressure roller temperature;

[0128] In this embodiment of the invention, the step of making collaborative decisions on the control command for the pressure roller temperature based on the predictive compensation amount to obtain a comprehensive control command for the pressure roller temperature includes:

[0129] The predictive compensation amount is discretized in a distributed manner to obtain the influence distribution of the pressure roller temperature;

[0130] Based on the influence distribution, the control command for the pressure roller temperature is weighted by multiple objectives to obtain the weighted decision criterion for the pressure roller temperature.

[0131] Based on the weighted decision criterion, the control command for the pressure roller temperature is subjected to multi-objective trade-offs to obtain the trade-off control command for the pressure roller temperature.

[0132] According to the dynamic operation margin of the packaging line, the instruction stability of the trade-off control instruction is evaluated to obtain an enhanced instruction of the compression roller temperature;

[0133] The enhanced instruction and the real-time feedback control instruction of the compression roller temperature are subjected to instruction fusion optimization to obtain a comprehensive control instruction of the compression roller temperature.

[0134] In combination with the actual operation scene of the PE packaging line compression roller, work condition intervals covering different operation states are divided, and the temperature regulation dimension corresponding to each interval is determined. The predictive compensation amount is split by work condition interval and regulation dimension one by one, so that each subdivided compensation amount accurately corresponds to a specific regulation scene, and the influence of different subdivided parts on the compression roller temperature is clearly presented to form an influence degree distribution of the compression roller temperature.

[0135] On the basis of the influence degree distribution, the core targets of the compression roller temperature control are determined, including temperature stability, regulation response, energy saving and consumption reduction, and equipment protection. According to the regulation effect of each subdivided influence, each control target is allocated with a corresponding importance degree proportion, and a higher proportion is allocated to a target with a higher influence degree to form a weighted decision benchmark for control instruction decision-making.

[0136] Various candidate control instructions of the compression roller temperature control are collected, and each candidate instruction is evaluated one by one according to the weighted decision benchmark in terms of the satisfaction degree of each control target, and the quantitative comprehensive effect is combined with the target importance degree proportion. Following the priority order, the satisfaction degree of the high proportion target is preferentially guaranteed, and the basic needs of other targets are considered, and the trade-off control instruction with the optimal comprehensive effect is screened out.

[0137] The operation state of the PE packaging line is monitored in real time, key data such as equipment load, energy supply, and component tolerance are collected, the regulation fluctuation range and load redundancy that the packaging line can withstand at present are determined, i.e. the dynamic operation margin. The trade-off control instruction is substituted into the margin for simulation analysis to determine whether there is an instability risk in the execution process, and the instruction is adjusted and optimized according to the risk point to form an enhanced instruction adapted to the operation state.

[0138] The enhanced instruction and the feedback control instruction reflecting the real-time temperature state of the compression roller are obtained, and the regulation direction, intensity, timing and other key elements of the two instructions are compared to identify the regulation conflict and repeated parts. A reasonable regulation scheme is determined for the conflict part, and the regulation intensity of the repeated part is optimized to integrate the advantages of the forward-looking of the enhanced instruction and the immediacy of the feedback instruction to form a comprehensive control instruction.

[0139] The beneficial effects include: refining the analysis of influencing factors, enabling precise matching of compensation amounts with control scenarios, avoiding control deviations, improving the pertinence and accuracy of decision-making, ensuring that weight allocation aligns with actual impacts, preventing key objectives from being overlooked, guaranteeing a scientific and reasonable decision-making benchmark, enhancing the effectiveness of control strategies, achieving a balance between multiple control objectives, avoiding the one-sidedness of single-objective-oriented commands, improving the overall quality of pressure roller temperature control, proactively mitigating operational mismatch risks, ensuring stable and safe command execution, enhancing the adaptability of commands to real-time operating conditions, improving reliability, integrating the advantages of both types of commands, compensating for the shortcomings of single commands, achieving a balance between temperature fluctuation prediction and real-time response, and improving control accuracy and efficiency.

[0140] S6. Based on the execution effect of the integrated control command and the topological consistency of the dynamic causal structure graph, the applicability of the feedforward compensation strategy is determined by stability, and the reconstruction trigger signal of the feedforward compensation strategy is obtained.

[0141] In this embodiment of the invention, the stability determination of the applicability of the feedforward compensation strategy based on the execution effect of the integrated control command and the topological consistency of the dynamic causal structure graph, to obtain the reconstruction trigger signal of the feedforward compensation strategy, includes:

[0142] The integrated control commands are applied to the packaging line to extract the control performance of the packaging line.

[0143] The operating characteristics of the pressure roller temperature are obtained;

[0144] Based on the dynamic causal structure graph, the causal topological coupling analysis of the operational characteristics is performed to obtain the causal consistency coefficient of the feedforward compensation strategy;

[0145] Based on the causal consistency coefficient, the effectiveness of the feedforward compensation strategy is determined, and the applicability of the feedforward compensation strategy is determined.

[0146] Based on the applicability decision, the stability state of the feedforward compensation strategy is determined, and the reconstruction trigger signal of the feedforward compensation strategy is obtained.

[0147] The packaging line control execution unit receives comprehensive control commands and adjusts the operating status of components such as the power of the pressure roller heating device and the speed of the transmission mechanism according to the commands to ensure that the commands are accurately applied to the packaging line. During execution, data such as the actual temperature of the pressure roller, the rate of temperature change, and the temperature difference change are continuously collected within a preset time to extract control effectiveness; then, this data is analyzed to determine the patterns of temperature stability and fluctuations, thus forming the operating characteristics of the pressure roller temperature.

[0148] Based on the constructed dynamic causal structure diagram, the variable correlation and close degree affecting the temperature of the compression wheel are determined according to the operation characteristics, the variable influence source corresponding to each characteristic is determined, the matching of the variable effect reflected by the characteristic and the preset causal correlation is analyzed according to the correlation relationship in the structure diagram, and the fitting degree of the variable effect reflected by the characteristic and the preset causal correlation is analyzed. The fitting degree is converted into a numerical value directly reflecting the consistency of the causal relationship of the strategy and the actual control, that is, the causal consistency coefficient.

[0149] The preset determination interval divides the value of the causal consistency coefficient into multiple level intervals, each interval corresponds to a clear strategy performance level, and the coefficient is classified into the corresponding interval. In combination with the production process of the packaging line, product quality and temperature control stability requirements, whether the strategy corresponding to the coefficient meets the temperature control requirements and can cope with variable changes is analyzed, and whether the current strategy is suitable for continued application is determined, and an applicability decision result is obtained.

[0150] Stability determination standards corresponding to different applicability decision results are formulated, stable for suitable use, critical stable for adjustment, and unstable for replacement, and the current state of the strategy is determined by comparing the standards. Whether the strategy can continue to stably control the temperature in the current and expected production cycle and whether there is a temperature out-of-control risk is analyzed. According to the determination result, a signal is generated, and no reconstruction is required if it is stable, and reconstruction is required if it is critical or unstable.

[0151] The beneficial effects are that the accuracy of the instructions is guaranteed and the performance data is comprehensive, which provides a real basis for subsequent strategy applicability determination, avoids determination deviation caused by insufficient data support, relies on the existing dynamic causal structure diagram to ensure coherent analysis logic and avoid directional deviation, quantifies the coefficient to provide a reference standard for strategy applicability determination, improves the objectivity and accuracy of the results, reduces subjective errors, combines the determination interval with the production standard to make the performance determination have rules to follow and avoid subjectivity, the decision result accurately reflects the actual value of the strategy, provides a clear basis for subsequent strategy adjustment or reconstruction, ensures the practicality of the determination, the decision result directly corresponds to the determination standard, and the stability determination is accurate; the reconstruction trigger signal accurately guides the strategy optimization, unstable strategies are processed in a timely manner, temperature control failure is avoided, and the continuity of the packaging line production and the stability of the product quality are ensured.

[0152] Embodiment Two

[0153] As shown in Figure 2 , the embodiment also provides a functional module diagram of a compression wheel heating temperature control system of a PE packaging line.

[0154] The PE packaging line pinch roller heated temperature control system 100 described in this embodiment can be installed in an electronic device. According to the functions implemented, the PE packaging line pinch roller heated temperature control system 100 can include a dynamic causal structure diagram construction module 101, a causal screening and precursor variable acquisition module 102, a feedforward compensation strategy generation module 103, a predictive compensation amount analysis module 104, and a comprehensive control instruction decision module 105, as well as a compensation strategy stability determination module 106. The modules described in the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0155] In this embodiment, the functions of each module / unit are as follows:

[0156] The dynamic causal structure diagram construction module 101 is used to construct a dynamic causal structure diagram of the packaging line by taking process variables and environmental variables in a high-dimensional time series data set as nodes, and taking dynamic causal relationships between the process variables and the environmental variables as edges.

[0157] The causal screening and precursor variable acquisition module 102 is used to screen the causal influence relationship of the dynamic causal structure diagram based on the pinch roller temperature as the target node, to obtain the local causal network of the pinch roller temperature, and to trace back the key causal path in the local causal network to obtain the precursor variable of the pinch roller temperature.

[0158] The feedforward compensation strategy generation module 103 is used to perform rule mapping on the dynamic behavior patterns in the precursor variables to obtain the feedforward compensation strategy of the pinch roller temperature.

[0159] The predictive compensation amount analysis module 104 is used to perform feedforward manipulated variable analysis on the feedforward compensation strategy and the real-time state vector in the precursor variables to obtain the predictive compensation amount of the pinch roller temperature.

[0160] The comprehensive control instruction decision module 105 is used to cooperatively decide the control instruction of the pinch roller temperature based on the predictive compensation amount to obtain the comprehensive control instruction of the pinch roller temperature.

[0161] The compensation strategy stability determination module 106 is used to determine the applicability of the feedforward compensation strategy based on the execution effect of the comprehensive control instruction and the topological consistency of the dynamic causal structure diagram to obtain a reconstruction trigger signal of the feedforward compensation strategy.

[0162] In detail, each module in the PE packaging line roller heating temperature control system 100 in the embodiments of the present application uses the same technical means as the PE packaging line roller heating temperature control method described in Embodiment One and Embodiment Two when in use, and can produce the same technical effects, which will not be described here.

[0163] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, i.e., can be located in one place or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment according to actual needs.

[0164] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0165] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0166] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (Artificial Intelligence, AI) is to use digital computers or computer-controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0167] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for controlling the heating temperature of the pressure roller in a PE packaging line, characterized in that, The method includes: S1. Using process variables and environmental variables in the high-dimensional time series dataset as nodes, and the dynamic causal relationship between the process variables and the environmental variables as edges, construct a dynamic causal structure graph of encapsulation lines. S2. Based on the pressure roller temperature as the target node, the dynamic causal structure diagram is filtered for causal influence relationships to obtain the local causal network of the pressure roller temperature, and the key causal paths in the local causal network are traced to obtain the precursor variables of the pressure roller temperature. S3. Perform rule mapping on the dynamic behavior patterns in the precursor variables to obtain the feedforward compensation strategy for the pressure roller temperature. S4. Perform feedforward manipulation variable analysis on the feedforward compensation strategy and the real-time state vector in the precursor variables to obtain the predictive compensation amount of the pressure roller temperature. S5. Based on the predictive compensation amount, make collaborative decisions on the control command for the pressure roller temperature to obtain the comprehensive control command for the pressure roller temperature; S6. Based on the execution effect of the integrated control command and the topological consistency of the dynamic causal structure graph, the applicability of the feedforward compensation strategy is determined by stability, and the reconstruction trigger signal of the feedforward compensation strategy is obtained. By performing feedforward manipulation variable analysis on the feedforward compensation strategy and the real-time state vector in the precursor variables, a predictive compensation amount for the pressure roller temperature is obtained, including: The feedforward compensation strategy is deconstructed to obtain the control rule fragments of the feedforward compensation strategy; Based on the control rule fragment, variable selection is performed on the real-time state vector in the predecessor variables to obtain a subset of key variables of the real-time state vector. Deviation identification is performed on the subset of key variables to obtain the real-time deviation value of the subset of key variables; The real-time deviation value and the control rule segment are dynamically weighted and fused to obtain the predictive compensation amount for the pressure roller temperature; The real-time deviation value and the control rule segment are dynamically weighted and fused to obtain the predictive compensation amount for the pressure roller temperature. The specific formula for calculating the predictive compensation amount is as follows: ； In the formula, The predictive compensation amount, This represents the total number of predecessor variables contained in the subset of key variables. For the first The dynamic weighting coefficients of the aforementioned precursor variables, For the first The real-time deviation values ​​of the aforementioned precursor variables. The absolute magnitude of the real-time deviation value. For the first The time constants of the aforementioned precursor variables The differential gain coefficient, This indicates that the expression within the parentheses is subjected to time differentiation. It is an exponential function.

2. The method for controlling the heating temperature of the pressure rollers in a PE packaging line as described in claim 1, characterized in that, The method of constructing a dynamic causal structure graph with encapsulated lines, using process variables and environmental variables in a high-dimensional time-series dataset as nodes and the dynamic causal relationships between the process variables and environmental variables as edges, includes: The original timing data of the packaging line is obtained, and the original timing data is coordinated to obtain the high-dimensional timing data of the packaging line. Using preset variable function classification rules, the operating condition variables in the high-dimensional time series data are divided to obtain the process variable group and environmental variable group of the packaging line; The process variable group and the environment variable group are node-based to obtain the node set of the encapsulation line; Time-delay correlation analysis is performed on the interaction of variables in the node set to obtain a dynamic correlation measure between the process variables and the environmental variables; By performing causal-guided inference on the dynamic correlation metric, the directed edge set of the encapsulation line is obtained; The node set and the directed edge set are topologically reconstructed to obtain the dynamic causal structure graph of the encapsulation line.

3. The method for controlling the heating temperature of the pressure rollers in a PE packaging line as described in claim 1, characterized in that, The process involves using the pressure roller temperature as the target node, filtering causal relationships in the dynamic causal structure graph to obtain a local causal network for the pressure roller temperature, and tracing key causal paths within this local causal network to obtain the antecedent variables of the pressure roller temperature, including: Using the pressure roller temperature as the target node, direct causal edge extraction is performed on the dynamic causal structure graph to obtain the direct association set of the pressure roller temperature; In the dynamic causal structure graph, multi-order causal backtracking is performed starting from the end node of the causal edge in the direct association set to obtain the indirect causal path cluster of the pressure roller temperature; Using the directly associated set as points and the indirect causal path cluster as edges, a complete causal network for the pressure roller temperature is constructed. The path strength of each causal path in the complete causal network is quantified to obtain the causal influence weight of the complete causal network. Based on the causal influence weights, the path saliency of all paths in the complete causal network is screened to obtain the key causal path of the pressure roller temperature; By tracing the key causal path, the precursor variable of the pressure roller temperature is obtained.

4. The method for controlling the heating temperature of the pressure rollers in a PE packaging line as described in claim 1, characterized in that, The step of mapping the dynamic behavior patterns in the precursor variables to obtain the feedforward compensation strategy for the pressure roller temperature includes: Based on the empirical rules of the historical optimal control process of the packaging line, the basic compensation rules for the pressure roller temperature are obtained; The predecessor variables are dynamically evolved and their behavior trajectory sequences are obtained by tracking their dynamic evolution. By mining the pattern features of the behavioral trajectory sequence, the saliency features of the dynamic behavioral pattern are obtained; The saliency features are matched and mapped with the basic compensation rules to obtain candidate compensation rules for the pressure roller temperature; A multi-objective optimization decision is made on the candidate compensation rules to obtain the feedforward compensation strategy for the pressure roller temperature.

5. The method for controlling the heating temperature of the pressure rollers in a PE packaging line as described in claim 1, characterized in that, The step of making collaborative decisions on the control command for the pressure roller temperature based on the predictive compensation amount to obtain a comprehensive control command for the pressure roller temperature includes: The predictive compensation amount is discretized in a distributed manner to obtain the influence distribution of the pressure roller temperature; Based on the influence distribution, the control command for the pressure roller temperature is weighted by multiple objectives to obtain the weighted decision criterion for the pressure roller temperature. Based on the weighted decision criterion, the control command for the pressure roller temperature is subjected to multi-objective trade-offs to obtain the trade-off control command for the pressure roller temperature. Based on the dynamic operating margin of the packaging line, the stability of the control command after the trade-off is evaluated, and the enhanced command for the pressure roller temperature is obtained. The enhanced command and the real-time feedback control command for the pressure roller temperature are fused and optimized to obtain a comprehensive control command for the pressure roller temperature.

6. The method for controlling the heating temperature of the pressure rollers in a PE packaging line as described in claim 1, characterized in that, The applicability of the feedforward compensation strategy is determined by the stability assessment of the execution effect of the integrated control command and the topological consistency of the dynamic causal structure graph, resulting in the reconstruction trigger signal of the feedforward compensation strategy, including: The integrated control commands are applied to the packaging line to extract the control performance of the packaging line. The operating characteristics of the pressure roller temperature are obtained; Based on the dynamic causal structure graph, the causal topological coupling analysis of the operational characteristics is performed to obtain the causal consistency coefficient of the feedforward compensation strategy; Based on the causal consistency coefficient, the effectiveness of the feedforward compensation strategy is determined, and the applicability of the feedforward compensation strategy is determined. Based on the applicability decision, the stability state of the feedforward compensation strategy is determined, and the reconstruction trigger signal of the feedforward compensation strategy is obtained.

7. A pressure roller heating temperature control system for a PE packaging line, employing the pressure roller heating temperature control method for a PE packaging line as described in claim 1, characterized in that... include: The dynamic causal structure graph construction module is used to construct a dynamic causal structure graph with process variables and environmental variables in a high-dimensional time series dataset as nodes and the dynamic causal relationship between the process variables and the environmental variables as edges. The causal screening and precursor variable acquisition module is used to screen the causal influence relationship of the dynamic causal structure diagram based on the pressure roller temperature as the target node, so as to obtain the local causal network of the pressure roller temperature, and trace the key causal path in the local causal network to obtain the precursor variable of the pressure roller temperature. The feedforward compensation strategy generation module is used to perform rule mapping on the dynamic behavior patterns in the precursor variables to obtain the feedforward compensation strategy for the pressure roller temperature. The predictive compensation analysis module is used to analyze the feedforward manipulator variables of the feedforward compensation strategy and the real-time state vector in the precursor variables to obtain the predictive compensation amount of the pressure roller temperature. The integrated control command decision module is used to make collaborative decisions on the control command for the pressure roller temperature based on the predictive compensation amount, so as to obtain the integrated control command for the pressure roller temperature. The stability determination module for the compensation strategy is used to determine the applicability of the feedforward compensation strategy based on the execution effect of the integrated control command and the topological consistency of the dynamic causal structure graph, and to obtain the reconstruction trigger signal of the feedforward compensation strategy.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 6.

Images