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

Abstract

The application discloses a multi-parameter regulation 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 material mixing-foaming-curing stages, and fitting the influence relationship between the influence parameters and response target parameters; configuring the regulation priority of each influence parameter in each stage; identifying the interaction of each influence parameter to obtain conflict parameter combinations and enhanced parameter combinations; and performing global search according to the regulation priority of each influence parameter in each stage, the conflict parameter combinations and the enhanced parameter combinations to obtain parameter regulation strategies in each stage.The technical problem that the parameter regulation in each stage of the heat insulation plate production process is not accurate in the prior art, which limits the production efficiency and product quality, is solved, the interaction of each influence parameter is identified to optimize the parameter regulation strategy in each stage, and the technical effect of improving the production efficiency and product quality is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of plate production, in particular to a multi-parameter control method, system and medium for the production of thermal insulation plates. BACKGROUND

[0002] As a kind of efficient thermal insulation material, thermal insulation plates can effectively reduce energy consumption and improve the energy-saving effect of buildings. However, in the production process of thermal insulation plates, due to the large number of process parameters involved and the complex mutual influence between these parameters in different production stages, how to accurately control the production parameters of each stage becomes a key factor affecting production efficiency and product quality. At present, the traditional production method mainly relies on manual experience to adjust parameters, but this method often fails to cope with complex situations with multiple variables and multiple factors, resulting in unstable product quality and low production efficiency. SUMMARY

[0003] The present application provides a multi-parameter control method, system and medium for the production of thermal insulation plates, which solves the technical problem of inaccurate parameter control in each stage of the production process of thermal insulation plates in the prior art, which limits production efficiency and product quality.

[0004] In a first aspect, the present application provides a multi-parameter control method for the production of thermal insulation plates, which comprises:

[0005] According to the production process of thermal insulation plates, the influence parameters of each stage of material mixing, foaming and curing are decomposed, and the influence relationship between each influence parameter and the response target parameter is fitted. Based on the influence relationship, the control priority of each influence parameter in each stage is configured. The gray correlation degree algorithm is used to identify the interaction of each influence parameter to obtain the conflict parameter combination and the enhanced parameter combination. The production target parameter of the thermal insulation plate is taken as the target evaluation value, and the global search is performed according to the control priority of each influence parameter in each stage, the conflict parameter combination and the enhanced parameter combination to obtain the parameter control strategy of each stage, wherein the evaluation result of each parameter control strategy of each stage meets the target evaluation value.

[0006] In a second aspect, the present application provides a multi-parameter control system for the production of thermal insulation plates, which comprises:

[0007] The fitting module is configured to decompose influence parameters of material mixing-foaming-curing stages according to the production process of the thermal insulation board and fit influence relations between the influence parameters and response target parameters; the configuration module is configured to configure control priorities of the influence parameters in the stages based on the influence relations; the identification module is configured to identify interactions of the influence parameters by using a grey correlation degree algorithm to obtain conflict parameter combinations and enhanced parameter combinations; and the search module is configured to perform global search according to the control priorities of the influence parameters in the stages, the conflict parameter combinations and the enhanced parameter combinations, with the production target parameters of the thermal insulation board as a target evaluation value, to obtain parameter control strategies of the stages, wherein evaluation results of the parameter control strategies of the stages satisfy the target evaluation value.

[0008] In a third aspect, the present application provides a computer readable storage medium storing a computer program, which, when executed by a processor, implements the multi-parameter control method for thermal insulation board production provided by the present application.

[0009] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0010] First, influence parameters of material mixing-foaming-curing stages are decomposed according to the production process of the thermal insulation board, and influence relations between the influence parameters and response target parameters are fitted. Then, control priorities of the influence parameters in the stages are configured based on the influence relations. Then, interactions of the influence parameters are identified by using a grey correlation degree algorithm to obtain conflict parameter combinations and enhanced parameter combinations. Finally, global search is performed according to the control priorities of the influence parameters in the stages, the conflict parameter combinations and the enhanced parameter combinations, with the production target parameters of the thermal insulation board as a target evaluation value, to obtain parameter control strategies of the stages, wherein evaluation results of the parameter control strategies of the stages satisfy the target evaluation value. The technical problem that parameter control in stages of the thermal insulation board production process is not accurate in the prior art, resulting in limited production efficiency and product quality, is solved. By identifying interactions of the influence parameters, parameter control strategies in the stages are optimized, and the technical effect of improving production efficiency and product quality is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0012] Figure 1 A flowchart of the multi-parameter control method for thermal insulation board production provided by the embodiments of the present application is shown in the figure.

[0013] Figure 2 A multi-parameter control system structure diagram for the production of thermal insulation board is provided for the embodiments of the present application.

[0014] Legend: fitting module 11, configuration module 12, identification module 13, search module 14. DETAILED DESCRIPTION

[0015] The present application provides a multi-parameter control method, system and medium for the production of thermal insulation board, which solves the technical problem of inaccurate parameter control in each stage of the production process of thermal insulation board in the prior art, resulting in limited production efficiency and product quality.

[0016] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0017] It should be noted that the terms "include" and "have" are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units need not be limited to those clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0018] Embodiment one, as shown, the present application provides a multi-parameter control method for the production of thermal insulation board, wherein the method comprises: Figure 1 According to the production process of thermal insulation board, the influence parameters of each stage of material mixing, foaming and curing are decomposed, and the influence relationship between each influence parameter and the response target parameter is fitted.

[0019] Based on the production process of thermal insulation board, the production process is divided into three main stages, including material mixing, foaming and curing, each stage involves multiple process parameters, which jointly affect the product.

[0020] The influence parameters of the material mixing stage include raw material ratio, mixing time, mixing speed, mixing temperature, etc.; the influence parameters of the foaming stage include foaming agent type, foaming agent amount, foaming temperature, foaming time, foaming pressure, etc.; the influence parameters of the curing stage include curing temperature, curing time, curing pressure, etc.

[0021]

[0022] ​Through experimental data collection and analysis, combined with regression analysis, machine learning and other statistical methods, the relationship between the influencing parameters of each stage and the performance of the final product (such as density, thermal conductivity, strength, etc.) is fitted; through fitting, the influence relationship between each influencing parameter and the response target parameter is determined. For example, through a neural network model, the raw material ratio and mixing process parameters are taken as input layer neurons, and the plate performance indicators are taken 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 response target parameter.

[0023] Further, fitting the influence relationship between each influencing parameter and the response target parameter includes:

[0024] Obtain the performance parameters of the thermal insulation plate, and take the performance parameters as the top-level target parameters; analyze the process target parameters of the material mixing, foaming and curing stages, and take the process target parameters of each stage as the secondary target parameters; decompose the process parameters of the material mixing, foaming and curing stages, set the process parameters of each stage as the influencing parameters, and take the influencing parameters as the bottom-level influencing factors; use experimental sample data to perform influence relationship fitting layer by layer from the top-level target parameters to the bottom-level influencing factors, and construct an influence relationship tree.

[0025] Preferably, the performance parameters of the thermal insulation plate include the thermal conductivity, density, strength, etc. of the thermal insulation plate, and the performance parameters of the thermal insulation plate are defined as the top-level target parameters. For different stages in the production process of the thermal insulation plate, i.e. the material mixing, foaming and curing stages, the process target parameters of each stage are analyzed, in the material mixing stage, the process target parameters include material uniformity, initial porosity, etc.; in the foaming stage, the process target parameters include porosity, foaming uniformity, preliminary thermal insulation performance, etc.; in the curing stage, the process target parameters include thermal insulation performance (thermal conductivity), compressive strength, dimensional stability, etc.; these stage process target parameters are taken as secondary target parameters. The process parameters of each stage are decomposed and set as influencing parameters, and these influencing parameters are set as bottom-level influencing factors.

[0026] A plurality of experiments are performed to cover different parameter combinations, thereby obtaining a plurality of experimental sample data; using experimental sample data, machine learning methods are used to fit the layer-by-layer influence relationship from the top-level target parameters to the bottom-level influencing factors, and an influence relationship tree is established. The influence relationship tree shows the causal relationship between the top-level target parameters and the bottom-level influencing factors through the arrow connections between the nodes.

[0027] Further, constructing the influence relationship tree includes:

[0028] The top layer target parameter is taken as a root node, the secondary target parameter is taken as an intermediate node, and the bottom layer influence factor is taken as a leaf node to construct a tree structure. A causal influence relationship between nodes is fitted according to the experimental sample data, and the relationship is represented by connecting branches, which have arrows and numerical annotations. The arrow annotations represent the causal influence direction of the cause parameter to the result parameter, and the numerical annotations represent the numerical value of the influence degree.

[0029] Specifically, a tree structure with clear levels is constructed by taking the top layer target parameter as a root node, the secondary target parameter as an intermediate node, and the bottom layer influence factor as a leaf node. In the tree structure, the root node represents the final performance target parameter of the thermal insulation board, such as thermal conductivity, density, strength, etc. The intermediate node represents the process target parameter at each stage, and the leaf node represents each process parameter.

[0030] After the tree structure is constructed, the causal influence relationship between nodes is fitted according to the experimental sample data to determine how each process parameter affects the final performance index. Specifically, these relationships are represented by connecting branches, where each branch connects two nodes to represent the causal influence from one node to another. The arrow on the branch is annotated with the direction of the causal relationship, and the starting point of the arrow indicates the cause parameter, and the end point of the arrow indicates the result parameter. The arrow direction clearly shows the influence path between parameters. In addition, the numerical annotation beside the arrow represents the influence degree of each branch, that is, the influence strength of the parameter on another parameter, which is usually represented by the correlation coefficient or influence metric value obtained by experimental data analysis.

[0031] Based on the influence relationship, the control priority of each influence parameter in each stage is configured.

[0032] Optionally, according to the constructed influence relationship tree, the influence degree of each influence parameter on the final product performance (i.e., the top layer target parameter) is 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 greater influence degree should be given higher control priority, and parameters with smaller influence degree can appropriately reduce their control priority.

[0033] The evaluation of the influence degree can be obtained by fitting experimental data, which specifically includes calculating the contribution of each parameter to the target performance parameter. Specifically, methods such as correlation analysis, regression model, or grey correlation analysis can be used to quantify the relationship strength between each influence parameter and the target parameter.

[0034] The grey correlation degree algorithm is used to identify the interaction of each influence parameter to obtain the conflict parameter combination and the enhanced parameter combination.

[0035] The interaction of each influencing parameter is identified by using the grey correlation degree algorithm. By calculating the correlation degree coefficient between parameters, it is determined which parameter combination has a conflict (i.e. will have an adverse effect on product performance when adjusted at the same time) and which parameter combination has an enhancing effect (i.e. can improve product performance when adjusted cooperatively). For example, it is found that when the foaming temperature and the curing temperature are simultaneously increased within a certain range, the thermal insulation performance of the plate material can be significantly enhanced, forming an enhancing parameter combination; and the improper combination of some raw material ratios and stirring speeds will lead to a decline in product quality, constituting a conflict parameter combination.

[0036] Further, the interaction of each influencing parameter is identified by using the grey correlation degree algorithm to obtain the conflict parameter combination and the enhancing parameter combination, including:

[0037] The experimental sample data is cleaned and standardized, wherein the experimental sample data covers different parameter combinations; sample data whose performance parameters meet the preset requirements is selected from the experimental sample data to construct a reference sequence; data sequences of each influencing parameter are extracted from the experimental sample data to construct comparison sequences independent of each influencing parameter; for each influencing parameter, the absolute difference sequence between the comparison sequence and the reference sequence is calculated to determine the maximum difference and the minimum difference in the absolute difference; the correlation coefficient between the influencing parameter and the target performance parameter is calculated by the grey correlation degree formula according to the maximum difference and the minimum difference; and the conflict parameter combination and the enhancing parameter combination are determined according to the correlation coefficients of each influencing parameter, wherein the conflict parameter combination is a parameter combination with the same correlation direction for the same target performance parameter, and the enhancing parameter combination is a parameter combination with opposite correlation directions for the same target performance parameter.

[0038] Specifically, the experimental sample data is cleaned and standardized to ensure the quality and consistency of the data and eliminate the differences between different parameter dimensions; sample data whose performance parameters meet the preset requirements is selected from the processed experimental sample data, and these sample data will be used as the reference sequence to measure the difference between other samples and the target performance; data sequences of each influencing parameter are extracted from the experimental sample data to construct comparison sequences independent of each influencing parameter, and these sequences represent the variation trend of each process parameter under different conditions.

[0039] By calculating the grey correlation degree between the reference sequence and each comparison sequence, the correlation degree between each influence parameter and the target performance parameter is obtained. Specifically, first, the absolute difference sequence between the reference sequence and each comparison sequence is calculated, and the maximum and minimum values of these differences are determined; by using the maximum and minimum difference values, the grey correlation degree coefficient between each influence parameter and the target performance parameter is calculated using the grey correlation degree formula, and the numerical range of the grey correlation degree coefficient is usually 0 to 1, and the larger the value, the stronger the correlation between the two sequences, and the smaller the value, the weaker the correlation. According to the grey correlation degree coefficient, the influence parameters can be divided into two categories: conflict parameter combination and enhancement parameter combination; conflict parameter combination refers to those parameter combinations that have the same direction of association on the same target performance parameter, and these parameters may cancel each other out or have an adverse effect in the production process; while the enhancement parameter combination refers to those parameter combinations that have opposite directions of association on the same target performance parameter, and the regulation between these parameters can cooperate with each other to improve the target performance.

[0040] Conflict parameter combinations, such as increasing the foaming temperature and reducing the foaming pressure, will cause the porosity to rise but the pore size distribution to deteriorate. Enhancement parameter combinations, such as increasing the stirring speed and increasing the filler ratio, will cause the uniformity and strength of the board to rise.

[0041] Further, obtaining the conflict parameter combination and the enhancement parameter combination further comprises:

[0042] Fitting the conflict parameter combination and the enhancement parameter combination into the influence relationship tree, wherein the influence relationship tree is annotated with arrow symbols according to the conflict parameter combination and the enhancement parameter combination, and the arrow symbols include positive signs and negative signs, and the positive signs represent conflict parameter combinations between parameters, and the negative signs represent enhancement parameter combinations between parameters.

[0043] After obtaining the conflict parameter combination and the enhancement parameter combination, these combinations need to be fitted into the influence relationship tree that has been constructed. Specifically, the influence relationship tree is annotated according to the conflict parameter combination and the enhancement parameter combination; for each conflict parameter combination, a positive sign is annotated on the connecting branches in the influence relationship tree, indicating that there is a conflict relationship between these parameters; for the enhancement parameter combination, a negative sign is annotated on the connecting branches in the influence relationship tree, indicating that there is an enhancement relationship between these parameters.

[0044] By annotating these conflict and enhancement parameter combinations with symbols in the influence relationship tree, the interaction between process parameters can be more intuitively displayed, and clear guidance can be provided for subsequent production regulation. The arrows annotated with positive and negative signs help to clarify the synergistic or antagonistic relationship between influence parameters, thereby providing a basis for formulating more accurate regulation strategies, avoiding conflicts, optimizing enhancements, and ultimately improving the efficiency of the production process and the quality of the product.

[0045] The production target parameters of the thermal insulation board are taken as the target evaluation value, global search is performed according to the control priority of each influencing parameter in each stage, the conflict parameter combination and the enhanced parameter combination, and the control strategies of each parameter in each stage are obtained, wherein the evaluation results of the control strategies of each parameter in each stage meet the target evaluation value.

[0046] The production target parameters of the thermal insulation board are taken as the target evaluation value, global search is performed according to the control priority of each influencing parameter in each stage, the conflict parameter combination and the enhanced parameter combination, and the control strategies of each parameter in each stage are obtained, wherein the evaluation results of the control strategies of each parameter in each stage meet the target evaluation value.

[0047] Further, the production target parameters of the thermal insulation board are taken as the target evaluation value, global search is performed according to the control priority of each influencing parameter in each stage, the conflict parameter combination and the enhanced parameter combination, and the control strategies of each parameter in each stage are obtained, including:

[0048] The production target parameters of the thermal insulation board are taken as the constraint condition, the priority maximum path search is performed according to the influence relationship tree, the first search path is established, the branch and stem parameter search adjustment is performed on the first search path based on the node relationship in the influence relationship tree, the target evaluation is performed according to the causal influence relationship of the control priority, the conflict parameter combination and the enhanced parameter combination, the optimal path with the maximum target evaluation value and the shortest path is obtained, and the control strategies of each parameter in each stage are obtained according to the optimal path.

[0049] Specifically, the production target parameters of the thermal insulation board are taken as constraint conditions, the first search path is established by performing a priority maximum path search according to the constructed influence relationship tree, and the target of the first search path search is to find a regulation and control scheme that is most consistent with the production target parameters, and the process parameters with the greatest influence are preferentially selected for adjustment. On the basis of the node relationship of the influence relationship tree, the branch and trunk parameters of the established first search path are searched and adjusted. By analyzing the relationship between nodes, combining the regulation and control priority of each influence parameter, and the causal influence relationship of the conflict parameter combination and the enhancement parameter combination, target evaluation is performed. At this time, by gradually adjusting each node in the path, the optimal path with the maximum target evaluation value and the shortest path is obtained, wherein the maximum target evaluation value means that the final production result is closest to the set production target, and the shortest path means that the best effect is achieved in a limited adjustment step, thereby improving the production efficiency. Finally, according to the obtained optimal path, the specific parameter regulation and control strategies of each stage are determined, which realizes the global optimization in the production process by ensuring the optimal coordination of the regulation and control priority and interaction of each influence parameter, thereby meeting the requirements of the thermal insulation board production target parameters.

[0050] Further, the branch and trunk parameter search adjustment is performed on the first search path, the target evaluation is performed according to the causal influence relationship of the regulation and control priority, the conflict parameter combination and the enhancement parameter combination, and the optimal path with the maximum target evaluation value and the shortest path is obtained, including:

[0051] The target parameter decomposition is performed according to the production target parameters, the target function is constructed, the relationship between each node in the first search path and the adjacent node is analyzed based on the node relationship in the influence relationship tree, the adjustment strategy evaluation is performed through the target function according to the causal influence relationship of the regulation and control priority, the conflict parameter combination or the enhancement parameter combination of the adjacent node, the path node replacement is performed when the evaluation value of the original node in the first search path is exceeded, the search adjustment of all nodes is sequentially completed, the candidate target path that meets the target evaluation value requirement is obtained, and when the candidate target path is multiple, the path optimization is performed with the shortest path length as the target to obtain the optimal path.

[0052] Specifically, when performing branch parameter search adjustment on the first search path, target parameter decomposition is performed according to the production target parameters, and a target function is constructed, which is used to quantify the relationship between the production target parameters and each process parameter, so as to perform effective target evaluation in the search process. Based on the node relationship in the influence relationship tree, each node in the first search path is analyzed to evaluate the relationship between it and adjacent nodes, including the control priority of adjacent nodes, the causal influence relationship of conflict parameter combination and enhancement parameter combination. The evaluation of adjustment strategy for these relationships is performed by the target function to judge 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, that is, a better node is selected, and the search adjustment of all nodes is completed in turn. After completing the search 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 there are multiple candidate target paths, the path with the shortest length (i.e. the number of adjustment steps) is selected as the optimal path by evaluating the path length.

[0053] Further, obtaining the parameter control strategy of each stage further includes:

[0054] According to the parameter control strategy of each stage, the tracking evaluation rules of each production process parameter are analyzed; the production process of the heat insulation plate is monitored in real time based on the tracking evaluation rules; when the real-time tracking monitoring data does not meet the preset requirements, the adaptive adjustment is performed according to the tracking parameter difference combined with the influence relationship between the influence parameters and the response target parameters.

[0055] After obtaining the parameter control strategy of each stage, according to the parameter control strategy of each stage, the tracking evaluation rules of each production process parameter are analyzed, which 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 maintain in the set optimal range, thereby guaranteeing the quality of the final product.

[0056] The tracking evaluation rule of each process parameter includes setting a target range or ideal value as the ideal working interval of the parameter, defining a tolerance range, which is determined according to product quality requirements, production equipment capacity and material characteristics, and data outside this range will trigger subsequent adjustment or warning mechanism. In addition, the tracking evaluation rule also includes defining the frequency of data collection and monitoring to ensure that deviations can be found in time and responded. When the real-time monitoring data deviates from the tolerance range of the set target parameter, a predetermined response mechanism is triggered immediately, which may include alarm or automatic start of the control mechanism to correct the parameter. At the same time, the tracking evaluation rule also includes dynamic evaluation and correction strategy, which evaluates the deviation of each parameter according to real-time monitoring data, and formulates correction strategy according to the priority of each parameter and its relationship with the target performance parameter.

[0057] Based on the tracking evaluation rule, the production process of the thermal insulation board will be monitored in real time. Through the real-time data acquisition system, the changes of various influencing parameters in the production process are continuously monitored, and the collected real-time data are compared with the preset standards or targets to evaluate whether the production process meets the set requirements. When the real-time tracking monitoring data does not meet the preset requirements, adaptive adjustment is made according to the difference of the tracking parameters combined with the influence relationship between the influencing parameters and the response target parameters. Specifically, the system adjusts the related process parameters according to the differences monitored in real time combined with the interaction of each parameter in the influence relationship tree.

[0058] In summary, the embodiments of the present application have at least the following technical effects:

[0059] First, according to the production process of the thermal insulation board, the influencing parameters of the material mixing-foaming-curing stages are decomposed, and the influence relationship between the influencing parameters and the response target parameters is fitted. Then, based on the influence relationship, the control priority of each influencing parameter in each stage is configured. Then, the gray correlation degree algorithm is used to identify the interaction of each influencing parameter to obtain the conflict parameter combination and the enhanced parameter combination. Finally, taking the production target parameter of the thermal insulation board as the target evaluation value, the global search is performed according to the control priority of each influencing parameter in each stage, the conflict parameter combination and the enhanced parameter combination to obtain the parameter control strategy of each stage, wherein the evaluation result of each parameter control strategy of each stage satisfies the target evaluation value. The technical problem that the parameter control in each stage of the production process of the thermal insulation board in the prior art is not accurate, resulting in limited production efficiency and product quality is solved. By identifying the interaction of each influencing parameter, the parameter control strategy of each stage is optimized, and the technical effect of improving the production efficiency and product quality is achieved.

[0060] Embodiment two, based on the same inventive concept as the multi-parameter control method for the production of thermal insulation boards in the foregoing embodiments, as shown in Figure 2 The present application provides a multi-parameter control system for the production of thermal insulation boards, wherein the system comprises:

[0061] The fitting module 11 is configured to decompose the influence parameters of the material mixing, foaming and curing stages in the production process of the insulation board and fit the influence relationship between the influence parameters and the response target parameters; the configuration module 12 is configured to configure the control priorities of the influence parameters in the stages based on the influence relationship; the identification module 13 is configured to identify the interaction of the influence parameters by using the grey correlation degree algorithm and obtain the conflict parameter combination and the enhanced parameter combination; and the search module 14 is configured to perform global search based on the control priorities of the influence parameters in the stages, the conflict parameter combination and the enhanced parameter combination, with the production target parameters of the insulation board as the target evaluation value, and obtain the parameter control strategies of the stages, wherein the evaluation results of the parameter control strategies of the stages meet the target evaluation value.

[0062] Further, the search module 14 is configured to perform the following method:

[0063] According to the parameter control strategies of the stages, the tracking evaluation rules of the production process parameters are analyzed; the production process of the insulation board is tracked and monitored in real time based on the tracking evaluation rules; and when the real-time tracking monitoring data does not meet the preset requirements, the tracking parameter difference is combined with the influence relationship between the influence parameters and the response target parameters for adaptive adjustment.

[0064] Further, the fitting module 11 is configured to perform the following method:

[0065] The performance parameters of the insulation board are obtained, and the performance parameters are taken as top-level target parameters; the process target parameters of the material mixing, foaming and curing stages are analyzed, and the process target parameters of the stages are taken as secondary target parameters; the process parameters of the material mixing, foaming and curing stages are decomposed, the process parameters of the stages are set as influence parameters, and the influence parameters are taken as bottom-level influence factors; and the influence relationship fitting is performed layer by layer from the top-level target parameters to the bottom-level influence factors by using the experimental sample data, and an influence relationship tree is constructed.

[0066] Further, the fitting module 11 is configured to perform the following method:

[0067] The tree structure is constructed with the top-level target parameters as root nodes, the secondary target parameters as intermediate nodes and the bottom-level influence factors as leaf nodes; the causal influence relationship between the nodes is fitted according to the experimental sample data, and the relationship is represented by connecting branches, the connecting branches have arrows and numerical annotations, wherein the arrows indicate the causal influence direction of the cause parameters to the result parameters, and the numerical annotations indicate the numerical value of the influence degree.

[0068] Further, the identification module 13 is configured to perform the following method:

[0069] The experimental sample data is cleaned and standardized, wherein the experimental sample data covers different parameter combinations; sample data satisfying a preset requirement in performance parameters is screened from the experimental sample data, and a reference sequence is constructed; data sequences of each influence parameter are extracted from the experimental sample data, and comparison sequences independent of each influence parameter are constructed; for each influence parameter, an absolute difference sequence of the comparison sequence and the reference sequence is calculated, and a maximum difference and a minimum difference in the absolute difference are determined; a correlation coefficient of the influence parameter and the target performance parameter is calculated according to the maximum difference and the minimum difference through a grey correlation degree formula; and a conflict parameter combination and an enhancement parameter combination are determined according to the correlation coefficients of the influence parameters, wherein the conflict parameter combination is a parameter combination with consistent correlation directions to the same target performance parameter, and the enhancement parameter combination is a parameter combination with opposite correlation directions to the same target performance parameter.

[0070] Further, the identification module 13 is configured to perform the following method:

[0071] The conflict parameter combination and the enhancement parameter combination are fitted into the influence relationship tree, wherein arrow symbol annotations are performed on the influence relationship tree according to the conflict parameter combination and the enhancement parameter combination, and the arrow symbol annotations include positive signs and negative signs, the positive sign indicating that the conflict parameter combination is between parameters, and the negative sign indicating that the enhancement parameter combination is between parameters.

[0072] Further, the search module 14 is configured to perform the following method:

[0073] The production target parameter of the heat insulation board is taken as a constraint condition, a first search path is established according to the influence relationship tree, branch and trunk parameter search adjustment is performed on the first search path based on the node relationship in the influence relationship tree, target evaluation is performed according to the causal influence relationship of the regulation priority, the conflict parameter combination and the enhancement parameter combination, and an optimal path with a maximum target evaluation value and a shortest path is obtained; and the regulation strategy of each parameter at each stage is obtained according to the optimal path.

[0074] Further, the search module 14 is configured to perform the following method:

[0075] According to the production target parameter, target parameter decomposition is performed to construct a target function; based on the node relationship in the influence relationship tree, the relationship between each node in the first search path and adjacent nodes is analyzed, the target function is adjusted according to the regulation priority of the adjacent nodes, the causal influence relationship of the conflict parameter combination or the enhanced parameter combination, and the path node replacement is performed when the evaluation value of the original node in the first search path is exceeded, and the search adjustment of all nodes is sequentially completed to obtain a candidate target path. The candidate target path is a path meeting the target evaluation value requirement; when the candidate target path is multiple, path optimization is performed with the shortest path length as the target to obtain the optimal path.

[0076] Embodiment three, based on the same inventive concept as the multi-parameter regulation method for the production of the heat insulation plate in the foregoing embodiments, this embodiment provides a computer readable storage medium, which can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the multi-parameter regulation method for the production of the heat insulation plate in the embodiments of the present application. The processor executes the software programs, instructions and modules stored in the memory, thereby performing various functional applications and data processing of the computer device, i.e. implementing the above-mentioned multi-parameter regulation method for the production of the heat insulation plate.

[0077] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0078] The above-mentioned only for the preferred embodiments of the present application, and does not limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0079] The present application and the accompanying drawings are only exemplary descriptions of the present application, and are considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application intends to include these modifications and changes.

Claims

1. A method of multi-parameter control for the production of thermal insulation boards, characterized by, The method comprises: According to the production process of the thermal insulation board, the influence parameters of the material mixing-foaming-curing stages are decomposed, and the influence relationship between the influence parameters and the response target parameters is fitted; Based on the influence relationship, the control priority of each influence parameter in each stage is configured; Using the grey correlation degree algorithm to identify the interaction of each influence parameter, the conflict parameter combination and the enhanced parameter combination are obtained; Taking the production target parameters of the thermal insulation board as the target evaluation value, the global search is carried out according to the control priority of each influence parameter in each stage, the conflict parameter combination and the enhanced parameter combination, and the parameter control strategy of each stage is obtained, wherein the evaluation result of the parameter control strategy of each stage meets the target evaluation value, including: Taking the production target parameters of the thermal insulation board as the constraint condition, the first search path is established by performing priority maximum path search according to the influence relationship tree; Based on the node relationship in the influence relationship tree, the branch parameter search adjustment of the first search path is carried out, the target evaluation is carried out according to the causal influence relationship of the control priority, the conflict parameter combination and the enhanced parameter combination, and the optimal path with the maximum target evaluation value and the shortest path is obtained, including: According to the production target parameters, the target parameter decomposition is carried out, and the target function is constructed; Based on the node relationship in the influence relationship tree, the relationship between each node in the first search path and the adjacent node is analyzed, the adjustment strategy evaluation is carried out through the target function according to the causal influence relationship of the control priority, the conflict parameter combination or the enhanced parameter combination of the adjacent node, the path node replacement is carried out when the evaluation value of the original node in the first search path is exceeded, and the search adjustment of all nodes is sequentially completed, to obtain a candidate target path, the candidate target path is a path meeting the target evaluation value requirement; When the candidate target path is multiple, path optimization is carried out with the shortest path length as the target, to obtain the optimal path; According to the optimal path, the parameter control strategy of each stage is obtained; Wherein, fitting the influence relationship between the influence parameters and the response target parameters comprises: Obtaining the performance parameters of the thermal insulation board, and taking the performance parameters as top-level target parameters; Analyzing the process target parameters of the material mixing, foaming and curing stages, and taking the process target parameters of each stage as secondary target parameters; Decomposing the process parameters of the material mixing, foaming and curing stages, setting the process parameters of each stage as influence parameters, and taking the influence parameters as bottom-level influence factors; Using experimental sample data, the influence relationship fitting is carried out layer by layer from the top-level target parameters to the bottom-level influence factors, and the influence relationship tree is constructed; The construction of the influence relationship tree comprises: Taking the top-level target parameters as root nodes, the secondary target parameters as intermediate nodes, and the bottom-level influence factors as leaf nodes, a tree structure is constructed; According to the experimental sample data, the causal influence relationship between the nodes is fitted, and the relationship is represented by connecting branches, the connecting branches have arrows and numerical annotations, wherein the arrow annotations represent the causal influence direction of the cause parameters to the result parameters, and the numerical annotations represent the numerical value of the influence degree. The conflict parameter combination and the enhancement parameter combination are fitted to the influence relationship tree, wherein arrow symbol marking is performed on the influence relationship tree according to the conflict parameter combination and the enhancement parameter combination, and the arrow symbol marking includes a positive sign and a negative sign, the positive sign indicating that the parameters are in conflict parameter combination, and the negative sign indicating that the parameters are in enhancement parameter combination.

2. The multi-parameter regulation method for the production of thermal insulation boards according to claim 1, characterized by, After obtaining the parameter regulation strategy of each stage, the following steps are further included: According to the parameter regulation strategy of each stage, the tracking evaluation rule of each production process parameter is analyzed; Based on the tracking evaluation rule, the production process of the heat insulation plate is tracked and monitored in real time; When the real-time tracking monitoring data does not meet the preset requirement, the tracking parameter difference is combined with the influence relationship between the influence parameters and the response target parameters to perform adaptive adjustment.

3. The multi-parameter regulation method for the production of thermal insulation boards according to claim 1, characterized by the fact that, The conflict parameter combination and the enhancement parameter combination are obtained by using a grey correlation degree algorithm to identify the interaction of the influence parameters, including: The experimental sample data is cleaned and standardized, wherein the experimental sample data covers different parameter combinations; Sample data satisfying a preset requirement is selected from the experimental sample data, and a reference sequence is constructed; Data sequences of the influence parameters are extracted from the experimental sample data, and comparison sequences independent of the influence parameters are constructed; For each influence parameter, the absolute difference sequence of the comparison sequence and the reference sequence is calculated, and the maximum difference and the minimum difference in the absolute difference are determined; The correlation coefficient of the influence parameter and the target performance parameter is calculated by a grey correlation degree formula according to the maximum difference and the minimum difference; The conflict parameter combination and the enhancement parameter combination are determined according to the correlation coefficient of the influence parameter, wherein the conflict parameter combination is a parameter combination with the same direction of correlation to the same target performance parameter, and the enhancement parameter combination is a parameter combination with opposite directions of correlation to the same target performance parameter.

4. A multi-parameter control system for the production of thermal insulation boards, characterized by The system for implementing the multi-parameter regulation method for the production of the heat insulation plate according to any one of claims 1-3, the system comprising: A fitting module configured to decompose the influence parameters of the material mixing-foaming-curing stages according to the production process of the heat insulation plate, and fit the influence relationship between the influence parameters and the response target parameters; A configuration module configured to configure the regulation priority of each influence parameter in each stage based on the influence relationship; An identification module configured to use a grey correlation degree algorithm to identify the interaction of the influence parameters, and obtain the conflict parameter combination and the enhancement parameter combination; A search module configured to take the production target parameter of the heat insulation plate as a target evaluation value, and perform global search according to the regulation priority of each influence parameter in each stage, the conflict parameter combination and the enhancement parameter combination, and obtain the parameter regulation strategy of each stage, wherein the evaluation result of the parameter regulation strategy of each stage satisfies the target evaluation value.

5. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the multi-parameter regulation method for the production of the heat insulation plate according to any one of claims 1-3.

Images