Multi-parameter regulation and control method and system for thermal insulation plate production and medium

Abstract

The invention discloses a multi-parameter regulation and control method and system for heat insulation plate production and a medium, and relates to the technical field of plate production. The method comprises the following steps: according to a heat insulation plate production process, decomposing influence parameters of each stage of material mixing-foaming-curing, and fitting an influence relationship between each influence parameter and a response target parameter; configuring the regulation and control priority of each influence parameter in each stage; identifying the interaction of each influence parameter, and obtaining a conflict parameter combination and an enhancement parameter combination; and performing global search according to the regulation and control priority of each influence parameter in each stage, the conflict parameter combination and the enhanced parameter combination to obtain a regulation and control strategy of each parameter in each stage. The technical problem that the production efficiency and the product quality are limited due to the fact that parameter regulation and control in each stage in the heat insulation plate production process are not accurate in the prior art is solved, the parameter regulation and control strategy in each stage is optimized by recognizing the interaction effect of each influence parameter, and the technical effect of improving the production efficiency and the product quality is achieved.

Description

Technical Field

[0001] This invention relates to the field of panel manufacturing technology, specifically to a multi-parameter control method, system, and medium for the production of thermal insulation panels. Background Technology

[0002] Thermal insulation panels, as a highly efficient thermal insulation material, can effectively reduce energy consumption and improve the energy efficiency of buildings. However, the production process of thermal insulation panels involves numerous process parameters, and these parameters have complex interactions at different production stages. Therefore, accurately controlling the production parameters at each stage becomes a key factor affecting production efficiency and product quality. Currently, traditional production methods mainly rely on manual experience to adjust parameters, but this method often struggles to cope with complex situations involving multiple variables and factors, leading to unstable product quality and low production efficiency. Summary of the Invention

[0003] This application provides a multi-parameter control method, system, and medium for the production of thermal insulation panels, which solves the technical problem in the prior art where the inaccurate control of parameters at each stage of the thermal insulation panel production process leads to limited production efficiency and product quality.

[0004] The first aspect of this application provides a multi-parameter control method for the production of thermal insulation boards, the method comprising: According to the production process of thermal insulation boards, the influencing parameters of each stage of material mixing, foaming, and curing are decomposed, and the influence relationship between each influencing parameter and the target response parameter is fitted. Based on the influence relationship, the control priority of each influencing parameter in each stage is configured. The interaction of each influencing parameter is identified using a grey relational analysis algorithm to obtain conflicting parameter combinations and enhancing parameter combinations. Taking the production target parameter of the thermal insulation board as the target evaluation value, a global search is performed according to the control priority of each influencing parameter, conflicting parameter combinations, and enhancing parameter combinations in each stage to obtain the control strategy of each parameter in each stage. The evaluation results of the control strategy of each parameter in each stage meet the target evaluation value.

[0005] A second aspect of this application provides a multi-parameter control system for the production of thermal insulation panels, the system comprising: The module includes a fitting module, which decomposes the influencing parameters of each stage (mixing, foaming, and curing) according to the thermal insulation board production process, and fits the influence relationship between each influencing parameter and the target response parameter. A configuration module is used to configure the control priority of each influencing parameter in each stage based on the influence relationship. An identification module uses a grey relational algorithm to identify the interaction of each influencing parameter, obtaining conflicting parameter combinations and enhancing parameter combinations. A search module uses the production target parameters of the thermal insulation board as the target evaluation value, and performs a global search based on the control priority, conflicting parameter combinations, and enhancing parameter combinations of each influencing parameter in each stage to obtain the control strategy for each parameter in each stage. The evaluation results of the control strategy for each parameter in each stage satisfy the target evaluation value.

[0006] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the multi-parameter control method for the production of thermal insulation panels provided in this application.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, following the thermal insulation board production process, the influencing parameters of each stage—material mixing, foaming, and curing—are decomposed, and the influence relationship between each influencing parameter and the target response parameter is fitted. Next, based on the influence relationship, the control priority of each influencing parameter in each stage is configured. Then, a grey relational analysis algorithm is used to identify the interactions of each influencing parameter, obtaining conflicting parameter combinations and enhancing parameter combinations. Finally, using the production target parameters of the thermal insulation board as the target evaluation value, a global search is performed based on the control priority of each influencing parameter in each stage, conflicting parameter combinations, and enhancing parameter combinations to obtain the control strategies for each parameter in each stage. The evaluation results of the control strategies for each parameter in each stage satisfy the target evaluation value. This solves the technical problem in the prior art where inaccurate parameter control at each stage of thermal insulation board production leads to limited production efficiency and product quality. By identifying the interactions of each influencing parameter and optimizing the parameter control strategies at each stage, the technical effect of improving production efficiency and product quality is achieved. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of a multi-parameter control method for the production of thermal insulation boards provided in an embodiment of this application; Figure 2This is a schematic diagram of a multi-parameter control system for the production of thermal insulation boards provided in an embodiment of this application.

[0010] Figure labeling: Fitting module 11, Configuration module 12, Recognition module 13, Search module 14. Detailed Implementation

[0011] This application solves the technical problem in the prior art that the inaccurate parameter control at each stage of the thermal insulation board production process leads to limited production efficiency and product quality by providing a multi-parameter control method, system and medium for thermal insulation board production.

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0013] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0014] Example 1, as Figure 1 As shown, this application provides a multi-parameter control method for the production of thermal insulation boards, wherein the method includes: According to the production process of thermal insulation boards, the influencing parameters of each stage of material mixing, foaming and curing are decomposed, and the influence relationship between each influencing parameter and the target response parameter is fitted.

[0015] Based on the production process of thermal insulation boards, the production process is divided into three main stages, including material mixing, foaming and curing. Each stage involves multiple process parameters, which together affect the product.

[0016] The influencing parameters of the material mixing stage include raw material ratio, mixing time, mixing speed, and mixing temperature; the influencing parameters of the foaming stage include foaming agent type, foaming agent dosage, foaming temperature, foaming time, and foaming pressure; and the influencing parameters of the curing stage include curing temperature, curing time, and curing pressure.

[0017] By collecting and analyzing experimental data, and combining statistical methods such as regression analysis and machine learning, the relationship between the influencing parameters at each stage and the final product performance (such as density, thermal conductivity, and strength) is fitted. Through fitting, the influence relationship between each influencing parameter and the target response parameter is determined. For example, using a neural network model, raw material ratios and mixing process parameters are used as input layer neurons, and board performance indicators are used as output layer neurons. A large amount of production data is used for training to obtain the nonlinear mapping relationship between each parameter and the target response parameter.

[0018] Furthermore, fitting the influence relationship between each influencing parameter and the target response parameter includes: The performance parameters of the thermal insulation board are obtained and used as the top-level target parameters. The process target parameters of each stage of material mixing, foaming, and curing are analyzed and used as the second-level target parameters. The process parameters of each stage of material mixing, foaming, and curing are decomposed, and the process parameters of each stage are set as influencing parameters and used as the bottom-level influencing factors. Using experimental sample data, the influence relationship is fitted layer by layer from the top-level target parameters to the bottom-level influencing factors to construct an influence relationship tree.

[0019] Preferably, the performance parameters of the insulation board include its thermal conductivity, density, and strength, which are defined as top-level target parameters. For different stages in the insulation board production process—material mixing, foaming, and curing—the process target parameters for each stage are analyzed. In the material mixing stage, the process target parameters include material uniformity and initial porosity; in the foaming stage, the process target parameters include porosity, foaming uniformity, and preliminary insulation performance; in the curing stage, the process target parameters include insulation performance (thermal conductivity), compressive strength, and dimensional stability. These process target parameters for each stage are used as secondary target parameters. The process parameters for each stage are decomposed and set as influencing parameters, and these influencing parameters are set as bottom-level influencing factors.

[0020] By conducting multiple sets of experiments to cover different parameter combinations, multiple sets of experimental sample data are obtained. Using the experimental sample data, machine learning methods are employed to fit the hierarchical influence relationship from the top-level target parameter to the bottom-level influencing factors, and an influence relationship tree is established. The influence relationship tree is connected by arrows between each node, showing the causal relationship between the top-level target parameter and the bottom-level influencing factors.

[0021] Furthermore, constructing an influence relationship tree includes: A tree structure is constructed using the top-level target parameter as the root node, the second-level target parameter as the intermediate node, and the bottom-level influencing factor as the leaf node. The causal relationship between each node is fitted according to the experimental sample data, and the relationship is represented by connecting branches. The connecting branches have arrows and numerical labels, where the arrow labels indicate the causal influence direction of the cause parameter to the result parameter, and the numerical labels indicate the numerical value of the degree of influence.

[0022] Specifically, a hierarchical tree structure is constructed using top-level target parameters as the root node, second-level target parameters as intermediate nodes, and bottom-level influencing factors as leaf nodes. In this tree structure, the root node represents the final performance target parameters of the insulation board, such as thermal conductivity, density, and strength; the intermediate nodes represent the process target parameters at each stage; and the leaf nodes represent the various process parameters.

[0023] After the tree structure is constructed, the causal relationships between nodes are fitted using experimental sample data to determine how each process parameter affects the final performance indicators. Specifically, these relationships are represented by connecting branches, where each branch connects two nodes, representing a causal influence from one node to another. Arrows on the branches indicate the direction of the causal relationship; the starting point of the arrow indicates the causal parameter, and the ending point indicates the result parameter, clearly showing the influence path between parameters. Furthermore, the numerical labels next to the arrows indicate the degree of influence of each branch, i.e., the strength of the influence of that parameter on another parameter, typically represented by correlation coefficients or influence metrics obtained from experimental data analysis.

[0024] Based on the aforementioned influence relationships, the control priority of each influence parameter in each stage is configured.

[0025] Optionally, based on the constructed influence relationship tree, the influence degree of each influence parameter on the final product performance (i.e., the top-level target parameter) can be analyzed. By evaluating the weight of each node in the influence relationship tree, the relative importance of each influence parameter in each process stage can be determined. Parameters with a greater influence degree should be given a higher control priority, while parameters with a smaller influence degree can have their control priority appropriately reduced.

[0026] The degree of influence can be assessed by fitting experimental data, specifically by calculating the contribution of each parameter to the target performance parameter. In particular, methods such as correlation analysis, regression models, or grey relational analysis can be used to quantify the strength of the relationship between each influencing parameter and the target parameter.

[0027] The grey relational analysis algorithm is used to identify the interaction of various influencing parameters and obtain conflicting parameter combinations and enhancing parameter combinations.

[0028] The grey relational analysis algorithm is used to identify the interactions of various influencing parameters. By calculating the correlation coefficients between parameters, it is determined which parameter combinations are conflicting (i.e., simultaneous adjustments would adversely affect product performance) and which parameter combinations have a reinforcing effect (i.e., synergistic adjustments can improve product performance). For example, it was found that simultaneously increasing the foaming temperature and curing temperature within a specific range can significantly enhance the thermal insulation performance of the board, forming a reinforcing parameter combination; while improper combinations of certain raw material ratios and stirring speeds can lead to a decline in product quality, constituting conflicting parameter combinations.

[0029] Furthermore, the grey relational analysis algorithm is used to identify the interactions of various influencing parameters, obtaining conflicting parameter combinations and enhancing parameter combinations, including: The experimental sample data is cleaned and standardized, covering different parameter combinations. Sample data whose performance parameters meet preset requirements are selected from the experimental sample data to construct a reference sequence. Data sequences for each influencing parameter are extracted from the experimental sample data to construct independent comparison sequences for each influencing parameter. For each influencing parameter, the absolute difference sequence between the comparison sequence and the reference sequence is calculated, and the maximum and minimum differences are determined. Based on the maximum and minimum differences, the correlation coefficient between the influencing parameter and the target performance parameter is calculated using the grey relational degree formula. Based on the correlation coefficients of each influencing parameter, conflicting parameter combinations and enhancing parameter combinations are determined, where conflicting parameter combinations are parameter combinations with the same correlation direction for the same target performance parameter, and enhancing parameter combinations are parameter combinations with opposite correlation directions for the same target performance parameter.

[0030] Specifically, the experimental sample data is cleaned and standardized to ensure data quality and consistency, and to eliminate differences between different parameter units. Sample data whose performance parameters meet the preset requirements are selected from the processed experimental sample data. These sample data will be used as reference sequences to measure the differences between other samples and the target performance. Data sequences of each influencing parameter are extracted from the experimental sample data, and independent comparison sequences of each influencing parameter are constructed. These sequences represent the changing trend of each process parameter under different conditions.

[0031] By calculating the grey relational degree between the reference sequence and each comparison sequence, the correlation between each influencing parameter and the target performance parameter is obtained. Specifically, firstly, the absolute difference sequences between the reference sequence and each comparison sequence are calculated, and the maximum and minimum values ​​of these differences are determined. Using these maximum and minimum differences, the grey relational degree coefficient between each influencing parameter and the target performance parameter is calculated using the grey relational degree formula. The grey relational degree coefficient typically ranges from 0 to 1; a larger value indicates a stronger correlation between the two sequences, while a smaller value indicates a weaker correlation. Based on the grey relational degree coefficient, influencing parameters can be divided into two categories: conflicting parameter combinations and reinforcing parameter combinations. Conflicting parameter combinations refer to parameter combinations that have the same directional correlation with the same target performance parameter; these parameters may cancel each other out or have adverse effects during production. Reinforcing parameter combinations refer to parameter combinations that have opposite directional correlations with the same target performance parameter; the regulation of these parameters can cooperate to jointly improve the target performance.

[0032] Conflicting parameter combinations, such as increasing foaming temperature and decreasing foaming pressure, will increase porosity but worsen pore size distribution. Conversely, reinforcing parameter combinations, such as increasing stirring speed and increasing filler ratio, will increase the uniformity and strength of the board.

[0033] Furthermore, obtaining conflicting parameter combinations and enhanced parameter combinations, and then including: The conflicting parameter combinations and the enhancing parameter combinations are fitted into the influence relationship tree. The influence relationship tree is labeled with arrow symbols according to the conflicting parameter combinations and the enhancing parameter combinations. The arrow symbols include positive and negative signs. Positive signs indicate that the parameters are conflicting parameter combinations, and negative signs indicate that the parameters are enhancing parameter combinations.

[0034] After obtaining the conflict parameter combinations and enhancement parameter combinations, these combinations need to be fitted into the constructed influence relationship tree. Specifically: the influence relationship tree is labeled according to the conflict parameter combinations and enhancement parameter combinations; for each conflict parameter combination, a positive sign is marked on the connecting branch in the influence relationship tree to indicate that there is a conflict relationship between these parameters; for enhancement parameter combinations, a negative sign is marked on the connecting branch in the influence relationship tree to indicate that there is an enhancement relationship between these parameters.

[0035] By symbolically labeling these conflicting and enhancing parameter combinations in the influence relationship tree, the interactions between various process parameters can be more intuitively displayed, providing clear guidance for subsequent production control. The arrows labeled with positive and negative signs help clarify the synergistic or antagonistic relationships between the influencing parameters, thus providing a basis for developing more precise control strategies, avoiding conflicts, optimizing enhancements, and ultimately improving production efficiency and product quality.

[0036] Using the production target parameters of the thermal insulation board as the target evaluation value, a global search is performed based on the control priority of each influencing parameter, the combination of conflicting parameters, and the combination of enhancing parameters in each stage to obtain the control strategy for each parameter in each stage. The evaluation results of the control strategy for each parameter in each stage satisfy the target evaluation value.

[0037] Using the production target parameters of thermal insulation panels (such as achieving a specific thermal insulation coefficient and compressive strength not lower than a certain standard) as the target evaluation values, and combining the control priorities of parameters at each stage, conflicting parameter combinations, and enhancing parameter combinations, global search algorithms such as genetic algorithms and particle swarm optimization algorithms are used to efficiently search within the parameter space to obtain the optimal control strategy for each parameter at each stage. Through multiple iterative optimizations, it is ensured that the evaluation results of the parameter control strategies at each stage meet the target evaluation values, thereby achieving optimal product performance.

[0038] Furthermore, using the production target parameters of the thermal insulation board as the target evaluation value, a global search is conducted based on the control priority of each influencing parameter in each stage, the combination of conflicting parameters, and the combination of enhancing parameters to obtain the control strategies for each parameter in each stage, including: Using the production target parameters of the thermal insulation board as constraints, a first search path is established by performing a priority maximum path search based on the influence relationship tree. Based on the node relationships in the influence relationship tree, the branch parameters of the first search path are searched and adjusted. The target is evaluated based on the causal influence relationship of the control priority, conflict parameter combination, and enhancement parameter combination to obtain the optimal path with the maximum target evaluation value and the shortest path. Based on the optimal path, the control strategies for each parameter at each stage are obtained.

[0039] Specifically, using the production target parameters of the thermal insulation board as constraints, a priority-maximizing path search is conducted based on the constructed influence relationship tree to establish a first search path. The goal of this first search path is to find the control scheme that best matches the production target parameters, prioritizing the adjustment of the process parameters with the greatest influence. Based on the node relationships in the influence relationship tree, the branch parameters of the established first search path are searched and adjusted. By analyzing the relationships between nodes and considering the causal relationships between the control priorities of each influencing parameter, conflicting parameter combinations, and enhancing parameter combinations, a target evaluation is performed. Then, by gradually adjusting each node in the path, the optimal path with the maximum target evaluation value and the shortest path is obtained. The maximum target evaluation value means that the final production result is closest to the set production target, while the shortest path indicates achieving the best effect within a limited number of adjustment steps, thereby improving production efficiency. Finally, based on the obtained optimal path, specific parameter control strategies for each stage are determined. These strategies ensure optimal coordination of the control priorities and interactions of each influencing parameter, achieving global optimization in the production process and thus meeting the requirements of the thermal insulation board production target parameters.

[0040] Furthermore, the branch parameters of the first search path are adjusted, and the target is evaluated based on the causal relationship between the control priority, conflict parameter combination, and enhancement parameter combination to obtain the optimal path with the maximum target evaluation value and the shortest path, including: The target parameters are decomposed according to the production target parameters to construct an objective function. Based on the node relationships in the influence relationship tree, the relationship between each node in the first search path and its neighboring nodes is analyzed. According to the causal influence relationship of the control priority of neighboring nodes, conflict parameter combinations, or enhancement parameter combinations, the adjustment strategy is evaluated through the objective function. When the evaluation value of the node exceeds the original node in the first search path, the path node is replaced. The search and adjustment of all nodes are completed in sequence to obtain candidate target paths. The candidate target paths are paths that meet the target evaluation value requirements. When there are multiple candidate target paths, the path optimization is performed with the shortest path length as the objective to obtain the optimal path.

[0041] Specifically, when adjusting the branch parameters of the first search path, the target parameters are decomposed based on the production target parameters, and an objective function is constructed. This objective function quantifies the relationship between the production target parameters and various process parameters, enabling effective target evaluation during the search process. Based on the node relationships in the influence relationship tree, each node in the first search path is analyzed, and its relationship with adjacent nodes is evaluated. These relationships include the control priority of adjacent nodes, the causal influence of conflicting parameter combinations, and enhancing parameter combinations. The objective function evaluates these relationships to assess the adjustment strategy and determine the adjustment effect of each node in the current path. When the evaluation value of the adjusted node exceeds the evaluation value of the original path node, the path node is replaced, i.e., a better node is selected, and the search and adjustment of all nodes are completed sequentially. After completing the search and adjustment of all nodes, multiple candidate target paths are generated. Each candidate path represents a possible parameter adjustment scheme, and the target evaluation value of each path meets the requirements of the production target parameters. When multiple candidate target paths exist, the path with the shortest path length (i.e., the number of adjustment steps) is selected as the optimal path by evaluating the path length.

[0042] Furthermore, obtaining the control strategies for each parameter at each stage also includes: Based on the parameter control strategies for each stage, the tracking and evaluation rules for each production process parameter are analyzed; the production process of the thermal insulation board is monitored in real time based on the tracking and evaluation rules; when the real-time tracking and monitoring data does not meet the preset requirements, adaptive adjustments are made based on the difference in tracking parameters and the influence relationship between each influencing parameter and the response target parameter.

[0043] After obtaining the control strategies for each parameter at each stage, the tracking and evaluation rules for each production process parameter are analyzed based on the control strategies for each stage and parameter. These tracking and evaluation rules are used to guide how each process parameter is monitored and evaluated in real time during the production process, so as to ensure that each parameter in the production process can always be maintained within the set optimal range, thereby ensuring the quality of the final product.

[0044] The tracking and evaluation rules for each process parameter include setting a target range or ideal value as the ideal working range for that parameter, and defining the tolerance range. The tolerance range is determined based on product quality requirements, production equipment capabilities, and material characteristics. Data exceeding this range will trigger subsequent adjustment or warning mechanisms. Furthermore, the tracking and evaluation rules also include defining the frequency of data acquisition and monitoring to ensure timely detection and response to deviations. When real-time monitoring data deviates from the set tolerance range of the target parameter, a predetermined response mechanism is immediately triggered, which may include alarms or automatic activation of control mechanisms to correct the parameter. Simultaneously, the tracking and evaluation rules also include dynamic evaluation and correction strategies. Based on real-time monitoring data, the deviation of each parameter is evaluated, and correction strategies are formulated according to the priority of each parameter and its relationship with the target performance parameter.

[0045] Based on tracking and evaluation rules, the production process of thermal insulation panels will be monitored in real time. A real-time data acquisition system will continuously monitor changes in various influencing parameters during production and compare the collected real-time data with preset standards or targets to assess whether the production process meets the established requirements. When the real-time monitoring data does not meet the preset requirements, adaptive adjustments will be made based on the differences in the tracking parameters and the influence relationships between each influencing parameter and the response target parameter. Specifically, the system will adjust relevant process parameters based on the differences detected in real time and the interactions of parameters in the influence relationship tree.

[0046] In summary, the embodiments of this application have at least the following technical effects: First, following the thermal insulation board production process, the influencing parameters of each stage—material mixing, foaming, and curing—are decomposed, and the influence relationship between each influencing parameter and the target response parameter is fitted. Next, based on the influence relationship, the control priority of each influencing parameter in each stage is configured. Then, a grey relational analysis algorithm is used to identify the interactions of each influencing parameter, obtaining conflicting parameter combinations and enhancing parameter combinations. Finally, using the production target parameters of the thermal insulation board as the target evaluation value, a global search is performed based on the control priority of each influencing parameter in each stage, conflicting parameter combinations, and enhancing parameter combinations to obtain the control strategies for each parameter in each stage. The evaluation results of the control strategies for each parameter in each stage satisfy the target evaluation value. This solves the technical problem in the prior art where inaccurate parameter control at each stage of thermal insulation board production leads to limited production efficiency and product quality. By identifying the interactions of each influencing parameter and optimizing the parameter control strategies at each stage, the technical effect of improving production efficiency and product quality is achieved.

[0047] Example 2, based on the same inventive concept as the multi-parameter control method for the production of thermal insulation boards in the foregoing examples, such as... Figure 2 As shown, this application provides a multi-parameter control system for the production of thermal insulation panels, wherein the system includes: Fitting module 11 is used to decompose the influence parameters of each stage of material mixing-foaming-curing according to the thermal insulation board production process, and fit the influence relationship between each influence parameter and the response target parameter; configuration module 12 is used to configure the control priority of each influence parameter in each stage based on the influence relationship; identification module 13 is used to identify the interaction of each influence parameter using a grey relational algorithm to obtain conflict parameter combinations and enhancement parameter combinations; search module 14 is used to perform a global search based on the production target parameter of the thermal insulation board as the target evaluation value, according to the control priority of each influence parameter in each stage, conflict parameter combinations, and enhancement parameter combinations, to obtain the control strategy of each parameter in each stage, wherein the evaluation result of the control strategy of each parameter in each stage satisfies the target evaluation value.

[0048] Furthermore, the search module 14 is used to perform the following method: Based on the parameter control strategies for each stage, the tracking and evaluation rules for each production process parameter are analyzed; the production process of the thermal insulation board is monitored in real time based on the tracking and evaluation rules; when the real-time tracking and monitoring data does not meet the preset requirements, adaptive adjustments are made based on the difference in tracking parameters and the influence relationship between each influencing parameter and the response target parameter.

[0049] Furthermore, the fitting module 11 is used to perform the following method: The performance parameters of the thermal insulation board are obtained and used as the top-level target parameters. The process target parameters of each stage of material mixing, foaming, and curing are analyzed and used as the second-level target parameters. The process parameters of each stage of material mixing, foaming, and curing are decomposed, and the process parameters of each stage are set as influencing parameters and used as the bottom-level influencing factors. Using experimental sample data, the influence relationship is fitted layer by layer from the top-level target parameters to the bottom-level influencing factors to construct an influence relationship tree.

[0050] Furthermore, the fitting module 11 is used to perform the following method: A tree structure is constructed using the top-level target parameter as the root node, the second-level target parameter as the intermediate node, and the bottom-level influencing factor as the leaf node. The causal relationship between each node is fitted according to the experimental sample data, and the relationship is represented by connecting branches. The connecting branches have arrows and numerical labels, where the arrow labels indicate the causal influence direction of the cause parameter to the result parameter, and the numerical labels indicate the numerical value of the degree of influence.

[0051] Furthermore, the identification module 13 is used to perform the following method: The experimental sample data is cleaned and standardized, covering different parameter combinations. Sample data whose performance parameters meet preset requirements are selected from the experimental sample data to construct a reference sequence. Data sequences for each influencing parameter are extracted from the experimental sample data to construct independent comparison sequences for each influencing parameter. For each influencing parameter, the absolute difference sequence between the comparison sequence and the reference sequence is calculated, and the maximum and minimum differences are determined. Based on the maximum and minimum differences, the correlation coefficient between the influencing parameter and the target performance parameter is calculated using the grey relational degree formula. Based on the correlation coefficients of each influencing parameter, conflicting parameter combinations and enhancing parameter combinations are determined, where conflicting parameter combinations are parameter combinations with the same correlation direction for the same target performance parameter, and enhancing parameter combinations are parameter combinations with opposite correlation directions for the same target performance parameter.

[0052] Furthermore, the identification module 13 is used to perform the following method: The conflicting parameter combinations and the enhancing parameter combinations are fitted into the influence relationship tree. The influence relationship tree is labeled with arrow symbols according to the conflicting parameter combinations and the enhancing parameter combinations. The arrow symbols include positive and negative signs. Positive signs indicate that the parameters are conflicting parameter combinations, and negative signs indicate that the parameters are enhancing parameter combinations.

[0053] Furthermore, the search module 14 is used to perform the following method: Using the production target parameters of the thermal insulation board as constraints, a first search path is established by performing a priority maximum path search based on the influence relationship tree. Based on the node relationships in the influence relationship tree, the branch parameters of the first search path are searched and adjusted. The target is evaluated based on the causal influence relationship of the control priority, conflict parameter combination, and enhancement parameter combination to obtain the optimal path with the maximum target evaluation value and the shortest path. Based on the optimal path, the control strategies for each parameter at each stage are obtained.

[0054] Furthermore, the search module 14 is used to perform the following method: The target parameters are decomposed according to the production target parameters to construct an objective function. Based on the node relationships in the influence relationship tree, the relationship between each node in the first search path and its neighboring nodes is analyzed. According to the causal influence relationship of the control priority of neighboring nodes, conflict parameter combinations, or enhancement parameter combinations, the adjustment strategy is evaluated through the objective function. When the evaluation value of the node exceeds the original node in the first search path, the path node is replaced. The search and adjustment of all nodes are completed in sequence to obtain candidate target paths. The candidate target paths are paths that meet the target evaluation value requirements. When there are multiple candidate target paths, the path optimization is performed with the shortest path length as the objective to obtain the optimal path.

[0055] Example 3: Based on the same inventive concept as the multi-parameter control method for the production of thermal insulation boards in the foregoing examples, this example provides a computer-readable storage medium that can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the multi-parameter control method for the production of thermal insulation boards in this application. The processor executes the software programs, instructions, and modules stored in the memory to perform various functional applications and data processing of the computer device, thereby realizing the aforementioned multi-parameter control method for the production of thermal insulation boards.

[0056] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0057] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0058] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A multi-parameter control method for the production of thermal insulation boards, characterized in that, The method includes: According to the production process of thermal insulation boards, the influencing parameters of each stage of material mixing-foaming-curing are decomposed, and the influence relationship between each influencing parameter and the target response parameter is fitted. Based on the aforementioned influence relationships, the control priority of each influence parameter in each stage is configured; The grey relational analysis algorithm is used to identify the interaction of various influencing parameters and to obtain conflicting parameter combinations and enhancing parameter combinations. Using the production target parameters of the thermal insulation board as the target evaluation value, a global search is performed based on the control priority of each influencing parameter, the combination of conflicting parameters, and the combination of enhancing parameters in each stage to obtain the control strategy of each parameter in each stage. The evaluation results of the control strategy of each parameter in each stage meet the target evaluation value. The fitting of the influence relationship between each influencing parameter and the target response parameter includes: Obtain the performance parameters of the thermal insulation board and use these parameters as the top-level target parameters; The process target parameters for each stage of the material mixing, foaming, and curing are analyzed, and the process target parameters for each stage are used as secondary target parameters. The process parameters of each stage of the material mixing, foaming, and curing are decomposed, and the process parameters of each stage are set as influencing parameters, and the influencing parameters are used as the underlying influencing factors. Using experimental sample data, the influence relationship is fitted layer by layer from the top-level target parameter to the bottom-level influence factor to construct an influence relationship tree; The construction of the influence relationship tree includes: A tree structure is constructed using the top-level target parameters as the root node, the second-level target parameters as intermediate nodes, and the bottom-level influence factors as leaf nodes. The causal relationship between nodes is fitted based on the experimental sample data, and the relationship is represented by connecting branches. The connecting branches have arrows and numerical labels, where the arrow labels indicate the causal influence direction of the cause parameter to the result parameter, and the numerical labels indicate the numerical value of the degree of influence.

2. The multi-parameter control method for the production of thermal insulation boards according to claim 1, characterized in that, The strategy for adjusting each parameter at each stage is obtained, and then it also includes: Based on the control strategies for each parameter at each stage, the tracking and evaluation rules for each production process parameter are analyzed. The production process of thermal insulation boards is monitored in real time based on the aforementioned tracking and evaluation rules. When the real-time tracking and monitoring data does not meet the preset requirements, adaptive adjustments are made based on the tracking parameter difference and the influence relationship between the various influencing parameters and the response target parameters.

3. The multi-parameter control method for the production of thermal insulation boards according to claim 1, characterized in that, The grey relational analysis algorithm is used to identify the interactions of various influencing parameters, obtaining conflicting parameter combinations and enhancing parameter combinations, including: The experimental sample data was cleaned and standardized, and the experimental sample data covered different combinations of parameters. From the experimental sample data, sample data whose performance parameters meet the preset requirements are selected to construct a reference sequence; Extract the data sequences of each influencing parameter from the experimental sample data, and construct independent comparison sequences for each influencing parameter; For each influencing parameter, calculate the absolute difference sequence between the comparison sequence and the reference sequence, and determine the maximum and minimum differences in the absolute differences; Based on the maximum and minimum differences, the correlation coefficient between the influencing parameters and the target performance parameters is calculated using the grey relational degree formula. Based on the correlation coefficients of each influencing parameter, conflicting parameter combinations and enhancing parameter combinations are determined. The conflicting parameter combinations are parameter combinations with the same correlation direction for the same target performance parameter, and the enhancing parameter combinations are parameter combinations with opposite correlation directions for the same target performance parameter.

4. The multi-parameter control method for the production of thermal insulation boards according to claim 1, characterized in that, Obtain conflicting parameter combinations, enhance parameter combinations, and then include: The conflicting parameter combinations and the enhancing parameter combinations are fitted into the influence relationship tree. The influence relationship tree is labeled with arrow symbols according to the conflicting parameter combinations and the enhancing parameter combinations. The arrow symbols include positive and negative signs. Positive signs indicate that the parameters are conflicting parameter combinations, and negative signs indicate that the parameters are enhancing parameter combinations.

5. The multi-parameter control method for the production of thermal insulation boards according to claim 4, characterized in that, Using the production target parameters of thermal insulation boards as the target evaluation values, a global search is conducted based on the control priority of each influencing parameter in each stage, the combination of conflicting parameters, and the combination of enhancing parameters to obtain the control strategies for each parameter in each stage, including: Using the production target parameters of the thermal insulation board as constraints, a first search path is established by performing a maximum priority path search based on the influence relationship tree. Based on the node relationships in the influence relationship tree, the branch parameters of the first search path are searched and adjusted. The target is evaluated according to the causal influence relationship of the control priority, conflict parameter combination and enhancement parameter combination, and the optimal path with the maximum target evaluation value and the shortest path is obtained. Based on the optimal path, the parameter control strategies for each stage are obtained.

6. The multi-parameter control method for the production of thermal insulation boards according to claim 5, characterized in that, The first search path undergoes branch parameter search and adjustment. Based on the causal relationship between the control priority, conflict parameter combinations, and enhancement parameter combinations, a target evaluation is performed to obtain the optimal path with the highest target evaluation value and the shortest path, including: Based on the production target parameters, the target parameters are decomposed to construct the objective function; Based on the node relationships in the influence relationship tree, the relationship between each node in the first search path and its neighboring nodes is analyzed. According to the causal influence relationship of the control priority, conflict parameter combination or enhancement parameter combination of the neighboring nodes, the adjustment strategy is evaluated through the objective function. When the evaluation value of the original node in the first search path is exceeded, the path node is replaced. The search and adjustment of all nodes are completed in sequence to obtain the candidate target path. The candidate target path is the path that meets the target evaluation value requirement. When there are multiple candidate target paths, the path optimization is performed with the shortest path length as the objective to obtain the optimal path.

7. A multi-parameter control system for the production of thermal insulation panels, characterized in that, For implementing the multi-parameter control method for the production of thermal insulation panels according to any one of claims 1-6, the system comprises: The fitting module is used to decompose the influence parameters of each stage of material mixing-foaming-curing according to the thermal insulation board production process, and fit the influence relationship between each influence parameter and the response target parameter. The configuration module is used to configure the control priority of each influencing parameter in each stage based on the influencing relationship; The identification module is used to identify the interaction of various influencing parameters using the grey relational analysis algorithm, and to obtain conflicting parameter combinations and enhancing parameter combinations. The search module is used to perform a global search based on the production target parameters of the thermal insulation board as the target evaluation value, and according to the control priority of each influencing parameter, the combination of conflicting parameters, and the combination of enhancing parameters in each stage, to obtain the control strategy of each parameter in each stage. The evaluation result of the control strategy of each parameter in each stage satisfies the target evaluation value.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the multi-parameter control method for the production of thermal insulation panels as described in any one of claims 1-6.

Images