Fireproof base material preparation process control optimization method and system

Abstract

The invention discloses a fireproof base material preparation process control optimization method and system, and relates to the technical field of fireproof base material preparation. The method includes the steps of information obtaining, wherein past preparation information, feedback address information and user requirements are obtained, and the past preparation information includes past preparation parameters and past product performance. The corresponding preparation parameters are generated according to the performance requirements of the user through the set performance feedback model, the optimal preparation parameters meeting the requirements of the user are selected from the parameters through the set cost adding method and the optimal selection method, and the final parameters are obtained. The corresponding preparation parameters are generated for the user according to the performance requirement and the cost requirement provided by the user, the method is suitable for different scenes needing cost and performance control, when the fireproof base material is prepared through the final parameters, the final parameters are optimized in real time through a judgment optimization method, the optimized parameters are obtained, and the fireproof base material is prepared. The fireproof base material is prepared by optimizing parameters so as to ensure that the prepared fireproof base material meets user requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of fireproof substrate preparation, and in particular to a fireproof substrate preparation process control optimization method and system. Background Art

[0002] Fireproof substrates refer to materials used in construction, interior decoration, or other applications that can effectively prevent the spread of flames or have certain fire resistance. In the construction industry, the demand for economical fireproof substrates is increasing, and manufacturers are faced with the challenge of controlling production costs. When preparing fireproof substrates, it is necessary to ensure that fireproof performance is met while minimizing raw material and production costs.

[0003] Patent publication number CN118732630A discloses a method and system for optimizing nanofilm preparation processes. The system includes: constructing a publicly encrypted dataset, partitioning the optimization space, evaluating parameters and extracting key parameters through dimensionality reduction using a trusted processing terminal; obtaining a label space number, defining a fitness function, and iteratively optimizing. This system constructs a solution space for production control and feedback optimization of the nanofilm process, resolving the technical issue of poor uniformity in the resulting films due to the difficulty in precisely controlling process parameters in nanofilm preparation. By collecting and analyzing parameters, key process parameters are determined, minimizing computational effort while ensuring optimal results. This results in a more accurate optimization process. Real-time monitoring using linked sensors ensures precise execution of process parameters, optimizing the preparation process, and improving the uniformity of the resulting films.

[0004] The preparation process optimization methods based on the above and similar principles focus on obtaining the influence between process parameters and product performance in the process of optimizing the preparation process of an article, and adjusting the process parameters according to the influence to improve the quality and efficiency of article preparation. However, in scenarios where production costs need to be controlled, the preparation process optimization methods based on the above and similar principles cannot well prepare articles with the best quality under the production costs according to the production costs. That is, the preparation process optimization methods based on the above and similar principles cannot well consider multiple demand factors. In actual use, their application scope will be narrow, which is not conducive to optimizing the preparation process according to demand factors. Therefore, the present invention is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for optimizing the control of the preparation process of a fireproof substrate, so as to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for optimizing the control of a fireproof substrate preparation process, the method comprising:

[0007] Information acquisition: obtaining past preparation information, feedback address information and user needs. Past preparation information includes past preparation parameters and past product performance;

[0008] Information processing: User requirements include performance requirements and cost requirements. Based on the performance requirements, pre-selected parameters are obtained through the performance feedback model.

[0009] Control parameter generation: Add cost information to pre-selected parameters through cost addition method to obtain pre-selected costs, extract pre-selected parameters whose pre-selected costs meet cost requirements to obtain several target parameters, and further select target parameters based on the target parameters through optimization method to obtain final parameters;

[0010] Control parameter optimization: Prepare the fireproof substrate based on the final parameters, and optimize the final parameters in real time by judging the optimization method to obtain the optimized parameters;

[0011] Control parameter output: Preparation of fireproof substrate based on optimized parameters;

[0012] Matching output: Based on user needs, the matching method is used to match the appropriate preparation parameters for the user to obtain the output results, which include the final parameters;

[0013] The judgment optimization method includes: real-time monitoring of whether there is a deviation in the actual operating parameters of the fire-proof substrate prepared by the final parameters to obtain a monitoring result; when the monitoring result feedback shows that there is a deviation in the actual operating parameters of the fire-proof substrate prepared by the final parameters, entering a control optimization state; establishing a time range based on the preparation start time and the deviation discovery time; obtaining the preparation operation process in the time range to obtain a paragraph parameter; obtaining first result information and second result information through an information generation method based on the paragraph parameter and pre-selected parameters; ending the control optimization state based on the first result information and the second result information; the first result information is the optimization parameter; the second result information is the feedback information; and the feedback information is sent to the user based on the feedback address information.

[0014] Furthermore, the information generation method includes: judging whether there are parameters consistent with the paragraph parameters in the pre-selected parameters to obtain a judgment result; when the judgment result feedback is that there are parameters consistent with the paragraph parameters in the pre-selected parameters, extracting the parameters consistent with the paragraph parameters in the pre-selected parameters to obtain optimized parameters, and the optimized parameters are first result information; when the judgment result feedback is that there are no parameters consistent with the paragraph parameters in the pre-selected parameters, integrating the monitoring results and the paragraph parameters to obtain feedback information, and the feedback information is second result information.

[0015] Furthermore, the method for establishing the performance feedback model includes:

[0016] Data acquisition and processing: Obtain parameters used for model training through data acquisition methods to obtain derived parameters and derived properties, integrate derived parameters with previous preparation parameters to obtain preliminary parameters, integrate derived properties with previous product properties to obtain preliminary properties, establish correlation between preliminary parameters and preliminary properties, preprocess preliminary parameters and preliminary properties, and integrate the preprocessed preliminary parameters and preliminary properties to obtain training data;

[0017] Model selection and training: Select a deep learning model as the model matrix, import the training data into the model matrix for training to obtain the initial model;

[0018] Model adjustment and output: Preset test parameters and test performance, import the test parameters into the initial model to obtain test results, compare the test results with the test performance to obtain comparative results, and optimize and adjust the initial model based on the comparative results to obtain a performance feedback model.

[0019] Furthermore, the data acquisition method includes: presetting standard parameters and fixed values, obtaining the performance of the fire-resistant substrate prepared by the standard parameters to obtain a reference performance, increasing and decreasing a single data item by a fixed value based on the standard parameters to obtain a first derivative parameter, increasing and decreasing multiple data items by a fixed value based on the standard parameters to obtain a second derivative parameter, integrating the first derivative parameter and the second derivative parameter to obtain a derivative parameter, traversing past preparation information based on the derivative parameter to find whether there are past preparation parameters corresponding to the derivative parameter to obtain a traversal result, when the traversal result feedback shows that there are past preparation parameters corresponding to the derivative parameter in the past preparation information, extracting the past product performance of the past preparation parameter based on the traversal result to obtain the first derivative performance, eliminating the parameters corresponding to the first derivative performance in the derivative parameters to obtain the eliminated derivative parameters, obtaining the performance of the fire-resistant substrate prepared by the eliminated derivative parameter to obtain the second derivative performance, and integrating the first derivative performance and the second derivative performance to obtain the derivative performance.

[0020] Furthermore, the cost addition method includes: splitting previous preparation parameters to obtain several basic parameter items, obtaining the operating costs of the basic parameter items to obtain cost results, establishing an association relationship between the basic parameter items and the cost results, establishing an information directory for storing the basic parameter items and cost results, splitting pre-selected parameters to obtain cost parameter items, traversing the information directory based on the cost parameter items to select the storage parameter items closest to the cost parameter items to obtain matching parameter items, extracting the cost results of the matching parameter items in the information directory based on the association relationship to obtain the estimated cost of the cost parameters, and integrating the estimated costs of all cost parameters in the pre-selected parameters to obtain the pre-selected cost.

[0021] Furthermore, the preferred method includes: judging the number of target parameters to obtain a quantity result; when the quantity result feedback indicates that the number of target parameters is multiple, monitoring whether the user has efficiency requirements; when the user has efficiency requirements, obtaining efficiency influencing factors; sorting the target parameters based on the number of efficiency influencing factors to obtain a sorting result; based on the sorting result, selecting the target parameter with the least efficiency influencing factors to obtain the final parameter; when the user does not have efficiency requirements, selecting the target parameter with the lowest pre-selected cost to obtain the final parameter.

[0022] Furthermore, the matching method includes: obtaining performance information of a fire-resistant substrate prepared by optimizing parameters to obtain target performance, integrating target performance, optimization parameters and cost requirements to obtain target information, establishing a repository for storing target information, traversing the repository based on user requirements to search for target performance and cost requirements corresponding to user requirements to obtain search results, and when the search result feedback indicates that target performance and cost requirements corresponding to user requirements exist in the repository, extracting the optimization parameters of the target performance and cost requirements corresponding to user requirements in the repository to obtain final parameters.

[0023] A fireproof base material preparation process control optimization system uses the above-mentioned fireproof base material preparation process control optimization method.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The fire-resistant substrate preparation process control optimization method and system generates corresponding preparation parameters according to the user's performance requirements through a set performance feedback model, then assigns cost information to the parameters through a set cost addition method, and selects the optimal preparation parameters that meet the user's requirements through a set optimization method to obtain final parameters. The present invention generates corresponding preparation parameters for the user based on the performance requirements and cost requirements provided by the user, which is convenient for use in different scenarios where cost and performance need to be controlled. When the fire-resistant substrate is prepared through the final parameters, the final parameters are optimized in real time through the set judgment optimization method to obtain optimized parameters, and the fire-resistant substrate is prepared through the optimized parameters to ensure that the prepared fire-resistant substrate meets the user's requirements.

[0026] At the same time, the matching output stage is run first, and the output result also includes no final parameters. When the output result is no final parameters, the final parameters are generated through the information processing and control parameter generation stage. The set matching method can directly match the user's needs according to historical data to obtain the final result that meets the user's needs, so as to reduce the system occupancy and improve the overall operation efficiency of the method, and improve the efficiency of generating the final parameters. The process of obtaining the judgment result by judging whether there are parameters consistent with the paragraph parameters in the pre-selected parameters can be further refined. First, it can be judged whether there are parameters consistent with the paragraph parameters in the target parameters. When there are no parameters in the target parameters, the scope is expanded to the selected parameters. Through this process, the cost factor can be fully considered first, and the product performance can be considered secondly to ensure that the product meets user needs as much as possible.

[0027] At the same time, the cost addition method that is set can provide cost information display for the pre-selected parameters, so as to facilitate the selection of preparation parameters that better meet user needs, which is conducive to reducing preparation costs. By setting the optimization method, when there are multiple target parameters, the target parameters with the highest efficiency are selected to obtain the final parameters, so that the final parameters can have the advantages of high efficiency and low cost while meeting user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the main process structure of the present invention;

[0029] Figure 2 Schematic diagram of the matching method structure of the present invention;

[0030] Figure 3 A schematic diagram of the structure of the performance feedback model of the present invention;

[0031] Figure 4 This is a schematic diagram of the cost addition method of the present invention;

[0032] Figure 5 This is a structural diagram of the information receiving port of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0034] As the market continues to improve the performance of fireproof materials, optimizing the preparation process can quickly respond to these changes and meet customer needs. By optimizing the preparation process of fireproof substrates, not only can product performance and production efficiency be improved, but also costs can be reduced. Optimizing the preparation process is an important measure to enhance corporate competitiveness and achieve sustainable development.

[0035] like Figure 1-Figure 5 As shown, the present invention provides a technical solution: a method for optimizing the control of a fireproof substrate preparation process, comprising:

[0036] Information acquisition: obtaining past preparation information, feedback address information and user needs. Past preparation information includes past preparation parameters and past product performance;

[0037] It should be noted that previous preparation information is obtained from the work log of historical generation of fire-resistant substrates, previous preparation parameters are the overall parameters of previously produced fire-resistant substrates, previous product performance is the performance of previously produced fire-resistant substrates, feedback address information is the address to which information is sent to the user, which can be a mobile phone number and email address, etc. User demand is the user's demand for the production of fire-resistant substrates, which is directly obtained through the user.

[0038] Example 1:

[0039] The fireproof substrate preparation process control optimization method is used in the fireproof substrate preparation plant with intelligent production line to optimize the preparation of fireproof substrate according to user needs. When preparing the fireproof substrate, it is necessary to first select raw materials, including polyolefins, polyvinyl chloride (PVC), polyester, etc., and also require fire retardants, including aluminum hydroxide, phosphates, halogen compounds, etc. At the same time, the formula ratio is selected according to the user's fire resistance performance requirements, that is, the ratio of substrate to fire retardant, for example: polyvinyl chloride (PVC): 80%; aluminum hydroxide: 15%; other additives: 5%. Under normal circumstances, the mixing temperature of the fireproof substrate preparation process parameters is usually between 160°C-180°C, depending on the thermal stability of the material, the mixing time is about 15-30 minutes to ensure uniform dispersion, and the pressure used in the molding process is 10MPa-20 MPa, the molding temperature and time are usually set to 160°C-200°C and 2-5 minutes to ensure the curing of the product. Some fire-retardant substrates require heat treatment with a temperature range of 180°C-220°C and a time of 30-60 minutes. After preparation, a combustion performance test is required. The combustion performance test is carried out according to national or industry standards (such as UL, ASTM, etc.) to evaluate the fireproof effect. At the same time, mechanical performance tests are carried out to evaluate indicators such as tensile strength and impact resistance. Through double evaluation, the performance information of the fire-retardant substrate can be obtained, such as Figure 5As shown, an information receiving port is established to receive user demands and send feedback information, and the feedback address information is obtained through the address where the user sends the demands.

[0040] Information processing: User requirements include performance requirements and cost requirements. Based on the performance requirements, pre-selected parameters are obtained through the performance feedback model.

[0041] It should be noted that user needs include performance requirements and cost requirements. The performance requirement is the performance of the finished fireproof substrate, and the cost requirement is the cost of making the fireproof substrate, which can be specifically the cost of a single or a batch. The set performance feedback model generates pre-selected parameters for the user based on the user's performance requirements. The number of pre-selected parameters is single or multiple. Preparing the fireproof substrate through the pre-selected parameters will obtain a fireproof substrate that meets the performance requirements.

[0042] Example 2:

[0043] Past preparation information is collected through factory logs and used as training data to establish a performance feedback model. A deep neural network architecture is selected, and multiple rounds of iterative training are performed using the training data to reduce the value of the loss function. The initial model is tested with performance requirements, and the accuracy of the model is evaluated. It is then iteratively optimized based on performance feedback and the model structure is adjusted. Through repeated testing and optimization, a stable and reliable model is eventually created that can effectively output preparation parameters according to performance requirements, assist in actual application development and testing, establish an information receiving port for receiving information sent by users, identify and classify the information sent by users, and specifically divide it into performance requirements and cost requirements. The performance requirements are imported into the established performance feedback model to obtain pre-selected parameters corresponding to the performance requirements.

[0044] Control parameter generation: Add cost information to pre-selected parameters through cost addition method to obtain pre-selected costs, extract pre-selected parameters whose pre-selected costs meet cost requirements to obtain several target parameters, and further select target parameters based on the target parameters through optimization method to obtain final parameters;

[0045] It should be noted that the cost information is added to the pre-selected parameters through the set cost adding method to obtain the pre-selected cost of the pre-selected parameters. According to the comparison between the pre-selected cost and the cost requirement, the pre-selected parameters that meet the cost requirement are selected to obtain the target parameters. The number of target parameters is single or multiple. The optimal parameter is selected from multiple target parameters through the optimization method to obtain the final parameter.

[0046] Real-time example 3:

[0047] Extract existing preparation parameters (such as formula, process conditions, etc.) from historical preparation records, split these parameters into several basic parameter items, such as: raw material ratio (basic parameter item 1), production time (basic parameter item 2), equipment operating time (basic parameter item 3), obtain the operating costs of the basic parameter items, collect data and perform cost analysis on each basic parameter item, and obtain the operating costs of each item, such as: raw material purchase cost, equipment operating cost and labor cost. Example results: The cost of basic parameter item 1 (raw material ratio) is 100 yuan; the cost of basic parameter item 2 (production time) is 50 yuan; the cost of basic parameter item 3 (equipment operating time) is 30 yuan.

[0048] Control parameter optimization: Prepare the fireproof substrate based on the final parameters, and optimize the final parameters in real time by judging the optimization method to obtain the optimized parameters;

[0049] Control parameter output: Preparation of fireproof substrate based on optimized parameters;

[0050] It should be noted that the fire-resistant substrate is prepared using the final parameters, and the final parameters are optimized in real time by the set judgment optimization method to obtain the optimized parameters. The fire-resistant substrate is prepared using the optimized parameters to ensure that the prepared fire-resistant substrate meets user needs.

[0051] Matching output: Based on user needs, the matching method is used to match the appropriate preparation parameters for the user to obtain the output results, which include the final parameters;

[0052] It should be noted that the final parameters obtained in the matching output stage and the control parameter generation stage are both subject to real-time optimization. The matching output stage and the control parameter generation stage will only produce one final parameter. The matching output stage is run first, and the output result also includes no final parameter. When the output result is no final parameter, the final parameter is generated through the information processing and control parameter generation stages. The set matching method can be used to directly match the user's needs based on historical data to obtain a final result that meets the user's needs, so as to reduce system occupancy and improve the overall operating efficiency of the method, thereby improving the efficiency of generating the final parameters.

[0053] Example 4:

[0054] A repository is established for real-time storage of optimization parameters and the performance of fire-resistant substrates prepared with the optimized parameters. During use, the performance requirements in the information receiving port are first imported into the repository, and similarity matching is performed in the repository. When there is performance in the repository that has a 100% similarity match with the performance requirements, the corresponding optimization parameters in the repository are extracted as parameters for preparing the fire-resistant substrate. When there is no performance in the repository that has a 100% similarity match with the performance requirements, the corresponding preparation parameters are obtained through the performance feedback model, and the final parameters of this preparation and the performance of the prepared fire-resistant substrate are stored in the repository to form a closed loop.

[0055] The judgment optimization method includes: real-time monitoring of whether there is a deviation in the actual operating parameters of the fire-resistant substrate prepared by the final parameters to obtain a monitoring result; when the monitoring result feedback shows that there is a deviation in the actual operating parameters of the fire-resistant substrate prepared by the final parameters, the control optimization state is entered; a time range is established based on the preparation start time and the deviation discovery time, the preparation operation process in the time range is obtained to obtain the paragraph parameters; based on the paragraph parameters and the pre-selected parameters, the first result information and the second result information are obtained through the information generation method; the control optimization state is ended based on the first result information and the second result information; the first result information is the optimization parameter, and the second result information is the feedback information; the feedback information is sent to the user based on the feedback address information.

[0056] It should be noted that when the final parameters are actually used to prepare the fire-resistant substrate, input errors or input disorders may occur. The set judgment optimization method is used to monitor factors that may cause deviations in the production of the fire-resistant substrate, that is, the actual operating parameters of the fire-resistant substrate are prepared using the final parameters. When there is a deviation in the actual operating parameters, that is, there is a difference between the actual operating parameters and the final parameters, a time range is established. The time range is the preparation start time and the paragraph time when the deviation event occurs. The paragraph parameters are the actual operating parameters within the time range. The paragraph parameters are corrected by the information generation method to obtain first result information and second result information. When the paragraph parameters can be corrected, the first result information is generated. When the paragraph parameters cannot be corrected, the second result information is generated and the second result information is fed back to the user, who decides whether to continue preparing the fire-resistant substrate. The set judgment optimization method can be used to compare the actual operating parameters for preparing the fire-resistant substrate with the final parameters, and find differences. When there are differences, the parameters within the time range are extracted, and the parameters are corrected by the set information generation method to ensure in real time that the actually produced fire-resistant substrate meets user needs, which is conducive to improving product quality.

[0057] The information generation method includes: judging whether there are parameters consistent with the paragraph parameters in the pre-selected parameters to obtain a judgment result; when the judgment result feedback is that there are parameters consistent with the paragraph parameters in the pre-selected parameters, extracting the parameters consistent with the paragraph parameters in the pre-selected parameters to obtain optimized parameters, and the optimized parameters are first result information; when the judgment result feedback is that there are no parameters consistent with the paragraph parameters in the pre-selected parameters, integrating the monitoring results and the paragraph parameters to obtain feedback information, and the feedback information is second result information.

[0058] It should be noted that the process of obtaining the judgment result by judging whether there are parameters consistent with the paragraph parameters in the pre-selected parameters can be further refined. First, it can be judged whether there are parameters consistent with the paragraph parameters in the target parameters. When there are no parameters in the target parameters, the scope is expanded to the selected parameters. Through this process, the cost factor can be fully considered first, and the product performance can be considered secondly to ensure that the product meets the user needs as much as possible. When there are no parameters consistent with the paragraph parameters in the pre-selected parameters, feedback information is generated and fed back to the user, and the user decides whether to continue production.

[0059] like Figure 3 As shown in FIG, the method for establishing the performance feedback model includes:

[0060] Data acquisition and processing: Obtain parameters used for model training through data acquisition methods to obtain derived parameters and derived properties, integrate derived parameters with previous preparation parameters to obtain preliminary parameters, integrate derived properties with previous product properties to obtain preliminary properties, establish correlation between preliminary parameters and preliminary properties, preprocess preliminary parameters and preliminary properties, and integrate the preprocessed preliminary parameters and preliminary properties to obtain training data;

[0061] It should be noted that in the data acquisition and processing stage, the parameters used for model training can be obtained by setting the data acquisition method to obtain derived parameters and derived performance. By establishing correlation, it is convenient to input corresponding parameters and performance when conducting model training. The process of preprocessing the preliminary parameters and preliminary performance includes data cleaning, deduplication and format unification to improve the neatness of the training data. At the same time, previous preparation parameters and previous product performance are also included in the training data to improve the accuracy of model training.

[0062] Model selection and training: Select a deep learning model as the model matrix, import the training data into the model matrix for training to obtain the initial model;

[0063] It should be noted that the model matrix is ​​a deep learning model, which can be specifically a neural network and support vector machine. The initial model can be obtained by importing the training data into the model matrix for the model to learn. In the specific training process, a single corresponding item in the training data can be randomly selected or a single corresponding item in the training data can be selected in a targeted manner to input into the training data.

[0064] Model adjustment and output: Preset test parameters and test performance, import the test parameters into the initial model to obtain test results, compare the test results with the test performance to obtain comparative results, and optimize and adjust the initial model based on the comparative results to obtain a performance feedback model.

[0065] It should be noted that the test parameters are parameters with the same format as the prepared parameters in the training data, and the test performance is the performance consistent with the prepared performance in the training data. The test results are obtained by importing the test parameters into the initial model. The test results are performance information. The comparison results are obtained by comparing the test results and the test performance. According to the comparison results, the initial model is optimized and adjusted to obtain a performance feedback model. The specific optimization and adjustment process includes adjusting the learning rate, regularization terms, etc., trying different neural network layers, number of nodes or activation functions, increasing the diversity of the data set, and using technologies such as data flipping and cropping.

[0066] The data acquisition method includes: presetting standard parameters and fixed values, obtaining the performance of a fire-resistant substrate prepared by the standard parameters to obtain a reference performance, increasing and decreasing a single data item by a fixed value based on the standard parameters to obtain a first derivative parameter, increasing and decreasing multiple data items by a fixed value based on the standard parameters to obtain a second derivative parameter, integrating the first derivative parameter and the second derivative parameter to obtain a derivative parameter, traversing past preparation information based on the derivative parameter to find whether there are past preparation parameters corresponding to the derivative parameter to obtain a traversal result, when the traversal result feedback indicates that there are past preparation parameters corresponding to the derivative parameter in the past preparation information, extracting the past product performance of the past preparation parameter based on the traversal result to obtain a first derivative performance, eliminating the parameter corresponding to the first derivative performance in the derivative parameter to obtain the eliminated derivative parameter, obtaining the performance of the fire-resistant substrate prepared by the eliminated derivative parameter to obtain a second derivative performance, and integrating the first derivative performance and the second derivative performance to obtain a derivative performance.

[0067] It should be noted that the standard parameters can be intermediate parameters. The smaller the fixed value, the smaller the gap between adjacent derived parameters. The standard parameters and fixed values ​​are preset according to actual use needs. The standard parameters are preparation mixing temperature: 160°C, mixing time: 15 minutes, pressure: 10MPa, extrusion temperature: 160°C, cooling time: 2 minutes, heat treatment temperature is 180°C, heat treatment time is 30 minutes. The fixed values ​​are formulated according to the units of the standard parameters. For example, the fixed values ​​are: preparation mixing temperature: 1°C, mixing time: 1 minute, pressure: 1MPa, extrusion temperature Degree: 2°C, cooling time: 1 minute, heat treatment temperature is 2°C, heat treatment time is 1 minute, the process of obtaining the reference performance by preparing the performance of the fire-resistant substrate through standard parameters and the process of obtaining the second derivative performance by preparing the performance of the fire-resistant substrate through the eliminated derivative parameters can be obtained through experiments. The more specific training data, the higher the accuracy of the subsequent model, but the process of obtaining performance is more cumbersome. At the same time, the less training data, the lower the accuracy of the subsequent model, but the process of obtaining performance is relatively streamlined. The specific derivative performance and the number of derivative parameters are determined according to actual usage requirements.

[0068] like Figure 4 As shown, the cost adding method includes: splitting the previous preparation parameters to obtain several basic parameter items, obtaining the operating cost of the basic parameter items to obtain the cost result, establishing the association relationship between the basic parameter items and the cost result, establishing an information directory for storing the basic parameter items and the cost results, splitting the pre-selected parameters to obtain the cost parameter items, traversing the information directory based on the cost parameter items to select the storage parameter items closest to the cost parameter items to obtain the matching parameter items, extracting the cost results of the matching parameter items in the information directory based on the association relationship to obtain the estimated cost of the cost parameters, and integrating the estimated costs of all cost parameters in the pre-selected parameters to obtain the pre-selected cost.

[0069] It should be noted that the basic parameter item is a single parameter item in the previous preparation parameters, such as mixing temperature, pressure, heat treatment temperature, etc. The cost result is the cost generated by the operation of the parameter item, which can be obtained by obtaining the electricity bill for a quarter or stage and the average number of fireproof materials. By establishing a correlation between the basic parameters and the cost results, it is convenient to subsequently match and extract the corresponding cost results. By splitting the pre-selected parameters and matching the cost parameter items with the corresponding basic parameter items in the information directory, the matching parameter items are obtained. The estimated costs of all matching parameter items are integrated to obtain the pre-selected cost. The pre-selected cost can be a specific number or a range number, which needs to be determined according to actual usage. When the pre-selected cost is a specific number, the amount of calculation data required is large. When the pre-selected cost is a range number, the amount of calculation data required is small. The cost addition method that is set can provide cost information display for the pre-selected parameters, so as to facilitate the selection of preparation parameters that better meet user needs and help reduce preparation costs.

[0070] like Figure 1 As shown, the preferred method includes: judging the number of target parameters to obtain a quantity result; when the quantity result feedback indicates that the number of target parameters is multiple, monitoring whether the user has efficiency requirements; when the user has efficiency requirements, obtaining efficiency influencing factors; sorting the target parameters based on the number of efficiency influencing factors to obtain a sorting result; based on the sorting result, selecting the target parameter with the least efficiency influencing factors to obtain the final parameter; when the user does not have efficiency requirements, selecting the target parameter with the lowest pre-selection cost to obtain the final parameter.

[0071] It should be noted that the efficiency influencing factors are the factors that have a greater impact on the preparation efficiency in the process. They can be obtained during actual use or based on past historical information. By setting the optimization method, when there are multiple target parameters, the target parameters with the highest efficiency are selected to obtain the final parameters. This can ensure that the final parameters have the advantages of high efficiency and low cost while meeting user needs.

[0072] like Figure 2 As shown, the matching method includes: obtaining performance information of a fire-resistant substrate prepared by optimizing parameters to obtain target performance, integrating target performance, optimization parameters and cost requirements to obtain target information, establishing a repository for storing target information, traversing the repository based on user requirements to search for target performance and cost requirements corresponding to user requirements to obtain search results, and when the search result feedback indicates that the target performance and cost requirements corresponding to the user requirements exist in the repository, extracting the optimization parameters of the target performance and cost requirements corresponding to the user requirements in the repository to obtain final parameters.

[0073] It should be noted that through the set matching method, the target performance, optimization parameters and cost requirements are continuously collected to obtain the target information as a reference. When obtaining user needs in the future, it is first matched in the repository, and the decision on whether to perform information processing and parameter processing is made based on the matching results, which is conducive to improving the overall operation efficiency of the method and improving the user experience.

[0074] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is limited by the accompanying embodiments and their equivalents.

Claims

1. A method for optimizing the control of a fireproof substrate preparation process, characterized in that: The method comprises: Information acquisition: obtaining past preparation information, feedback address information and user needs. Past preparation information includes past preparation parameters and past product performance; Information processing: User requirements include performance requirements and cost requirements. Based on the performance requirements, pre-selected parameters are obtained through the performance feedback model. Control parameter generation: Add cost information to pre-selected parameters through cost addition method to obtain pre-selected costs, extract pre-selected parameters whose pre-selected costs meet cost requirements to obtain several target parameters, and further select target parameters based on the target parameters through optimization method to obtain final parameters; Control parameter optimization: Prepare the fireproof substrate based on the final parameters, and optimize the final parameters in real time by judging the optimization method to obtain the optimized parameters; Control parameter output: Preparation of fireproof substrate based on optimized parameters; Matching output: Based on user needs, the matching method is used to match the appropriate preparation parameters for the user to obtain the output results, which include the final parameters; The judgment optimization method includes: real-time monitoring of whether there is a deviation in the actual operating parameters of the fire-proof substrate prepared by the final parameters to obtain a monitoring result; when the monitoring result feedback shows that there is a deviation in the actual operating parameters of the fire-proof substrate prepared by the final parameters, entering a control optimization state; establishing a time range based on the preparation start time and the deviation discovery time; obtaining the preparation operation process in the time range to obtain a paragraph parameter; obtaining first result information and second result information through an information generation method based on the paragraph parameter and pre-selected parameters; ending the control optimization state based on the first result information and the second result information; the first result information is the optimization parameter; the second result information is the feedback information; and the feedback information is sent to the user based on the feedback address information.

2. The method for controlling and optimizing the preparation process of a fireproof substrate according to claim 1, wherein: The information generation method includes: judging whether there are parameters consistent with the paragraph parameters in the pre-selected parameters to obtain a judgment result; when the judgment result feedback is that there are parameters consistent with the paragraph parameters in the pre-selected parameters, extracting the parameters consistent with the paragraph parameters in the pre-selected parameters to obtain optimized parameters, and the optimized parameters are first result information; when the judgment result feedback is that there are no parameters consistent with the paragraph parameters in the pre-selected parameters, integrating the monitoring results and the paragraph parameters to obtain feedback information, and the feedback information is second result information.

3. The method for controlling and optimizing a fireproof substrate preparation process according to claim 1, wherein: The method for establishing the performance feedback model includes: Data acquisition and processing: Obtain parameters used for model training through data acquisition methods to obtain derived parameters and derived properties, integrate derived parameters with previous preparation parameters to obtain preliminary parameters, integrate derived properties with previous product properties to obtain preliminary properties, establish correlation between preliminary parameters and preliminary properties, preprocess preliminary parameters and preliminary properties, and integrate the preprocessed preliminary parameters and preliminary properties to obtain training data; Model selection and training: Select a deep learning model as the model matrix, import the training data into the model matrix for training to obtain the initial model; Model adjustment and output: Preset test parameters and test performance, import the test parameters into the initial model to obtain test results, compare the test results with the test performance to obtain comparative results, and optimize and adjust the initial model based on the comparative results to obtain a performance feedback model.

4. The method for controlling and optimizing the preparation process of a fireproof substrate according to claim 3, wherein: The data acquisition method includes: presetting standard parameters and fixed values, obtaining the performance of a fire-resistant substrate prepared using the standard parameters to obtain a reference performance, increasing and decreasing a single data item by a fixed value based on the standard parameters to obtain a first derived parameter, increasing and decreasing multiple data items by a fixed value based on the standard parameters to obtain a second derived parameter, integrating the first derived parameter and the second derived parameter to obtain a derived parameter, traversing past preparation information based on the derived parameters to find whether there are past preparation parameters corresponding to the derived parameters to obtain a traversal result, when the traversal result feedback indicates that there are past preparation parameters corresponding to the derived parameters in the past preparation information, extracting past product performance of the past preparation parameters based on the traversal result to obtain a first derived performance, eliminating the parameters corresponding to the first derived performance in the derived parameters to obtain the eliminated derived parameters, obtaining the performance of the fire-resistant substrate prepared using the eliminated derived parameters to obtain a second derived performance, and integrating the first derived performance and the second derived performance to obtain a derived performance.

5. The method for controlling and optimizing the preparation process of a fireproof substrate according to claim 1, wherein: The cost adding method includes: splitting previous preparation parameters to obtain several basic parameter items, obtaining the operating costs of the basic parameter items to obtain cost results, establishing an association relationship between the basic parameter items and the cost results, establishing an information directory for storing the basic parameter items and the cost results, splitting pre-selected parameters to obtain cost parameter items, traversing the information directory based on the cost parameter items to select the storage parameter items closest to the cost parameter items to obtain matching parameter items, extracting the cost results of the matching parameter items in the information directory based on the association relationship to obtain the estimated cost of the cost parameters, and integrating the estimated costs of all cost parameters in the pre-selected parameters to obtain the pre-selected cost.

6. The method for controlling and optimizing a fireproof substrate preparation process according to claim 1, wherein: The preferred method includes: judging the number of target parameters to obtain a quantity result; when the quantity result feedback indicates that the number of target parameters is multiple, monitoring whether the user has efficiency requirements; when the user has efficiency requirements, obtaining efficiency influencing factors; sorting the target parameters based on the number of efficiency influencing factors to obtain a sorting result; based on the sorting result, selecting the target parameter with the least efficiency influencing factors to obtain the final parameter; when the user does not have efficiency requirements, selecting the target parameter with the lowest pre-selected cost to obtain the final parameter.

7. The method for controlling and optimizing a fireproof substrate preparation process according to claim 1, wherein: The matching method includes: obtaining performance information of a fire-resistant substrate prepared by optimizing parameters to obtain target performance, integrating the target performance, optimization parameters, and cost requirements to obtain target information, establishing a repository for storing the target information, traversing the repository based on user requirements to search for target performance and cost requirements corresponding to the user requirements to obtain search results, and when the search result feedback indicates that the target performance and cost requirements corresponding to the user requirements exist in the repository, extracting the optimization parameters of the target performance and cost requirements corresponding to the user requirements in the repository to obtain final parameters.

8. A fireproof substrate preparation process control optimization system, characterized by: A fireproof substrate preparation process control optimization method according to any one of claims 1 to 7 is used.

Images