Intelligent optimization method and system for production of thermal insulation board based on characteristics of raw materials

Abstract

The present application relates to the technical field of intelligent regulation and control of industrial production, and particularly relates to a method and system for intelligent optimization of production of insulation boards based on characteristics of raw materials. The method comprises the following steps: analyzing distribution attribute characteristics of raw materials of the insulation boards based on environmental data and characteristic data of raw materials of the insulation boards, and generating distribution attribute characteristic data of the raw materials; analyzing reaction behaviors of the characteristics of the raw materials based on the distribution attribute characteristic data of the raw materials, and generating reaction behavior data of the characteristics of the raw materials; analyzing simulation evolution structural characteristics of the production of the insulation boards based on the reaction behaviors of the raw materials, and generating simulation evolution structural characteristic data of the production of the insulation boards; and designing intelligent optimization control relations of the production of the insulation boards based on the simulation evolution structural characteristic data of the production of the insulation boards, and generating an intelligent optimization control engine of the production of the insulation boards. The present application realizes targeted and efficient intelligent optimization control of the production of the insulation boards.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology in industrial production, and in particular to an intelligent optimization method and system for the production of insulation boards based on raw material characteristics. Background Technology

[0002] As a core thermal insulation material, the production quality of insulation boards directly affects the energy efficiency and safety of buildings. Large-scale, high-quality insulation board production has become a core requirement for the industry. Currently, insulation board production largely employs traditional control methods, relying heavily on operator experience to set production parameters. This lack of precise control over key influencing factors during production results in difficulties in improving production efficiency and product quality stability, and also leads to prominent problems such as excessive energy consumption and low raw material utilization. Traditional insulation board production methods are no longer suitable for the industry's development needs; large-scale, standardized, and high-quality insulation board production has become the core direction for the transformation and upgrading of the current building energy-saving materials industry. However, existing insulation board production technologies mostly rely on single-dimensional data collection for monitoring raw materials, failing to integrate production environment data with the distribution and characteristics of raw materials for comprehensive analysis. This results in a lack of precise data support for setting subsequent production parameters, hindering in-depth exploration of the reaction behavior patterns of raw material characteristics. Consequently, problems such as incomplete reactions and weak interfacial bonding are prone to occur. Furthermore, production control is mostly based on fixed parameters, lacking effective simulation and evolution analysis of the production process. This makes it impossible to simulate structural changes during the curing process of the insulation board in advance, making it difficult to avoid production defects. Consequently, insulation board products exhibit uneven pore distribution, insufficient structural strength, and substandard insulation performance, failing to meet the demands of large-scale, high-quality insulation board production. Summary of the Invention

[0003] Based on this, the present invention provides an intelligent optimization method and system for the production of insulation boards based on the characteristics of raw materials, in order to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a smart optimization method for insulation board production based on raw material characteristics includes the following steps: Step S1: Use sensor monitoring cluster equipment to monitor and process the environmental and raw material characteristics of the target area for insulation board production control, and generate environmental data and raw material characteristic data for insulation board production respectively; based on the environmental data and raw material characteristic data for insulation board production, perform raw material distribution attribute feature analysis to generate raw material distribution attribute feature data for insulation board. Step S2: Analyze the reaction behavior of the raw materials based on the distribution attribute characteristic data of the insulation board raw materials to generate raw material characteristic reaction behavior data; Step S3: Analyze the structural characteristics of the reaction behavior of raw materials in the simulation of insulation board production to generate structural characteristic data of insulation board production simulation. Step S4: Based on the structural feature data of the insulation board production simulation evolution, design the intelligent optimization control relationship for insulation board production and generate an intelligent optimization control engine for insulation board production. The intelligent optimization control engine for insulation board production is used to execute intelligent optimization operations for insulation board production.

[0005] Furthermore, step S1 includes the following steps: Step S11: Use sensor monitoring cluster equipment to monitor and process the environmental and raw material characteristics of the target area of ​​the insulation board production control operation, and generate environmental data and raw material characteristic data of insulation board production respectively. Step S12: Perform anomaly correction and adjustment on the raw material characteristic data for insulation board production to generate standard raw material characteristic data for insulation board production; Step S13: Analyze the physical characteristics of raw material distribution in the standard insulation board production raw material characteristic data to generate physical characteristic data of raw material distribution in the insulation board; Step S14: Based on environmental data and standard insulation board production raw material characteristic data, perform dynamic humidity characteristic analysis of insulation board raw materials to generate dynamic humidity characteristic data of insulation board raw materials. Step S15: Analyze the distribution attribute characteristics of insulation board raw materials based on the physical characteristics data of the distribution of insulation board raw materials and the dynamic characteristics data of the humidity of insulation board raw materials, and generate the distribution attribute characteristic data of insulation board raw materials.

[0006] Furthermore, step S12 includes the following steps: Based on the raw material characteristic data of insulation board production, spatial distribution raw material characteristic analysis is performed to generate spatial distribution characteristic data of insulation board raw materials. By analyzing the spatial distribution characteristics of insulation board raw materials, neighborhood spatial distribution characteristics data is generated, and the collection anomaly detection and processing of insulation board raw material characteristics is performed based on the neighborhood spatial distribution characteristics data, generating insulation board raw material characteristic collection anomaly data. Abnormal data collected from the characteristics of insulation board raw materials are used to correct and adjust the abnormal data of the raw material characteristics of insulation board production, thereby generating standard raw material characteristic data for insulation board production.

[0007] Furthermore, step S14 includes the following steps: Extracting moisture data of raw materials for standard insulation board production; Based on the humidity data of the insulation board raw materials, a time-series characteristic analysis of the humidity of the insulation board raw materials is performed to generate time-series characteristic data of the humidity of the insulation board raw materials. By performing environmental dynamic compensation processing on the humidity time-series characteristic data of insulation board raw materials using environmental data, dynamic characteristic data of humidity of insulation board raw materials is generated.

[0008] Furthermore, step S2 includes the following steps: Step S21: Perform raw material characteristic distribution coupling relationship analysis based on the raw material distribution attribute characteristic data of the insulation board to generate raw material characteristic distribution coupling relationship data; Step S22: Perform graph convolution aggregation relationship analysis on the coupling effect of raw material characteristic distribution based on the raw material characteristic distribution coupling relationship data to generate raw material characteristic distribution coupling relationship data; Step S23: Extract quantitative features of raw material distribution attributes from the raw material distribution attribute feature data of the insulation board to obtain quantitative feature data of raw material distribution attributes; Step S24: Utilize the raw material characteristic distribution coupling relationship data to perform interface coupling characteristic analysis on the quantitative characteristic data of raw material distribution attributes, and generate raw material characteristic interface coupling characteristic data; Step S25: Analyze the distribution characteristics of the porosity effect at the raw material interface based on the characteristic data of the coupling effect at the raw material interface, and generate the distribution characteristic data of the porosity effect at the raw material interface. Step S26: Analyze the reaction behavior of raw materials by using the characteristic data of the coupling effect between raw material properties and the characteristic data of the distribution of porosity at the raw material properties interface, and generate raw material property reaction behavior data.

[0009] Furthermore, the material property interface coupling characteristic data mentioned in step S24 includes material property hydration reaction rate data, material property foaming volume expansion data, and material property interface strength data.

[0010] Furthermore, step S3 includes the following steps: Step S31: Perform reaction kinetic analysis on the reaction behavior data of the raw materials to generate reaction kinetic data of the raw materials. Step S32: Obtain preliminary production data for the insulation board; Step S33: Based on the prior production data of the insulation board, perform multiphase fluid simulation evolution processing on the raw material characteristic reaction kinetic data to generate multiphase fluid simulation evolution data of the insulation board. Step S34: Perform thermo-mechanical finite element simulation reaction field analysis based on the raw material characteristic reaction kinetic data and the insulation board multiphase fluid simulation evolution data to generate thermo-mechanical finite element simulation reaction field data; Step S35: Perform structural field analysis of the curing effect of the insulation board based on the thermal-mechanical finite element simulation reaction field data, and generate structural field data of the curing effect of the insulation board; Step S36: Analyze the structural characteristics of the insulation board production simulation evolution using the structural field data of the insulation board curing effect, and generate structural characteristic data of the insulation board production simulation evolution.

[0011] Furthermore, the structural feature data of the insulation board production simulation evolution mentioned in step S36 includes the pore density distribution data of the insulation board production simulation evolution, the structural performance data of the insulation board production simulation evolution, and the interface homogeneity data of the insulation board production simulation evolution.

[0012] Furthermore, step S4 includes the following steps: Step S41: Analyze the distribution of insulation board production deviation characteristics based on the structural feature data of the insulation board production simulation evolution, and generate insulation board production deviation characteristic distribution data. Step S42: Analyze the distribution of the sensitivity of insulation board production adjustment based on the distribution data of the insulation board production deviation characteristics, and generate the distribution data of the sensitivity of insulation board production adjustment. Step S43: Analyze the insulation board production optimization adjustment using the insulation board production deviation characteristic distribution data and the insulation board production adjustment sensitivity distribution data, and generate insulation board production optimization adjustment data. Step S44: Perform PLC control drive parsing and mapping processing on the insulation board production optimization and adjustment data to generate insulation board production control parsing and mapping data; Step S45: Perform PLC-level control logic analysis on the parsing mapping data of insulation board production control to generate insulation board production level control logic data; Step S46: Analyze the real-time production demand status of insulation boards based on the production level control logic data of insulation boards, and generate real-time production status demand data of insulation boards. Step S47: Perform real-time correction parameter analysis on the production status requirement data of the instant insulation board to generate real-time correction parameters for the hierarchical control of the insulation board. Step S48: Design the intelligent optimization control relationship for insulation board production by using the control logic data of the insulation board production level and the real-time correction parameters of the insulation board level control, and generate the intelligent optimization control engine for insulation board production.

[0013] This specification provides an intelligent optimization system for insulation board production based on raw material characteristics, used to execute the intelligent optimization method for insulation board production based on raw material characteristics as described above. The intelligent optimization system for insulation board production based on raw material characteristics includes: The insulation board raw material distribution attribute analysis module is used to monitor and process data on the environmental and raw material characteristics of the target area of ​​the insulation board production control operation using sensor monitoring cluster equipment, and generate environmental data and insulation board raw material characteristic data respectively; based on the environmental data and insulation board raw material characteristic data, the module performs distribution attribute feature analysis of insulation board raw materials, and generates insulation board raw material distribution attribute feature data. The raw material characteristic reaction behavior analysis module is used to analyze the reaction behavior of raw material characteristics based on the distribution attribute characteristic data of insulation board raw materials, and generate raw material characteristic reaction behavior data. The insulation board simulation evolution structure analysis module is used to analyze the reaction behavior data of raw material characteristics and the structural characteristics of insulation board production simulation evolution, and generate insulation board production simulation evolution structure characteristic data. The intelligent optimization control module for insulation board production is used to design intelligent optimization control relationships for insulation board production based on the structural feature data of insulation board production simulation evolution, and to generate an intelligent optimization control engine for insulation board production. The intelligent optimization control engine for insulation board production is used to execute intelligent optimization operations for insulation board production.

[0014] The beneficial effects of this application are as follows: This invention, through a sensor monitoring cluster device, achieves synchronous and comprehensive monitoring of the environment and raw material characteristics of the target area for insulation board production control, overcoming the limitations of single-dimensional data collection. It can simultaneously generate accurate environmental data and raw material characteristic data for insulation board production, providing comprehensive and fundamental data support. By performing spatial distribution analysis and neighborhood spatial distribution characteristic analysis on the raw material characteristic data, abnormal data during the raw material characteristic data collection process can be accurately detected, and this abnormal data can be used to correct and adjust the original raw material characteristic data, effectively solving the problems of easily occurring abnormal data collection and the lack of an effective abnormality correction mechanism. Further analysis of the physical characteristics of raw material distribution is performed on standard raw material characteristic data, extracting raw material humidity data, analyzing humidity temporal characteristics, and combining environmental data for dynamic compensation of humidity temporal characteristics. This accurately captures the dynamic laws of raw material humidity changes with the environment, comprehensively and accurately reflecting the core attributes of raw material distribution, effectively avoiding the problem of deviations in subsequent analysis due to insufficient data support in existing technologies. Based on accurate raw material distribution attribute characteristic data for insulation boards, in-depth analysis of the reaction behavior of raw material characteristics is conducted, effectively solving the problems of being unable to deeply explore the laws of raw material characteristic reaction behavior and the difficulty in accurately predicting the raw material reaction process. First, the coupling relationship of raw material characteristics is analyzed. Then, graph convolution and aggregation processing is used to accurately capture the coupling patterns between different components of the raw materials. Quantitative feature extraction is performed on the raw material distribution attribute data, providing a clear quantitative basis for subsequent interface coupling analysis. Using the coupling relationship data, interface coupling feature analysis is conducted on the quantified feature data, clearly identifying the core influencing factors of the raw material reaction. A comprehensive analysis of the reaction behavior mechanism of the raw material characteristics is achieved, enabling accurate prediction of key reaction processes such as raw material hydration and foaming, effectively avoiding problems such as incomplete reaction and weak interface bonding. Based on accurate raw material characteristic reaction behavior data, a structural feature analysis of the evolution of the insulation board production process is conducted, addressing the issues of lacking effective simulation evolution analysis, inability to simulate structural changes during the insulation board curing process in advance, and difficulty in avoiding production defects.By performing reaction kinetic analysis on raw material characteristic reaction behavior data, the core kinetic laws such as the rate and extent of raw material reaction are accurately captured, providing a basic kinetic basis for simulation evolution. Prior production data of insulation boards are introduced, and combined with historical experience data to improve the rationality of simulation evolution and its relevance to actual production. Based on prior data, multiphase fluid simulation evolution processing is performed on the kinetic data to clearly simulate the fluid motion laws of raw materials during the production process. Thermal-mechanical finite element simulation reaction field analysis is conducted by combining kinetic data and multiphase fluid simulation data to accurately reproduce the thermal field, force field distribution, and interactions during the production process. Further analysis of the insulation board curing effect structural field captures the structural change characteristics during the curing process, comprehensively and accurately reflecting the structural evolution laws during the insulation board production process. This allows for early prediction and avoidance of production defects such as uneven pore distribution and substandard structural performance, reducing the incidence of defective products. Based on the structural feature data of the simulation evolution of insulation board production, the intelligent optimization control relationship of insulation board production was designed and a control engine was generated. This solved the problems of fixed parameter mode of production control, inability to dynamically correct parameters according to raw material characteristics and reaction state, and difficulty in achieving precise optimization control, thus realizing intelligent and precise regulation of insulation board production. By analyzing the distribution of production deviation characteristics through simulation structural feature data, the potential deviations and their distribution patterns during production can be accurately identified. Based on the deviation characteristics, the distribution of production adjustment sensitivity is analyzed, clarifying the adjustment response efficiency of different production stages and parameters, providing a quantitative basis for optimization. Combining deviation characteristics and adjustment sensitivity data, optimization adjustment analysis is conducted to obtain optimized production adjustment data. Through PLC control drive parsing mapping and hierarchical control logic analysis, the optimized adjustment data is transformed into implementable PLC control logic, ensuring that optimization instructions can accurately connect to production equipment. Combining hierarchical control logic with real-time production demand status, real-time hierarchical control correction parameters are obtained, achieving dynamic adaptation to the production process. This enables efficient execution of intelligent production optimization operations, allowing for real-time correction of control parameters based on raw material characteristics, reaction states, and dynamic changes in production deviations. This significantly improves the automation and intelligence level of insulation board production, further ensuring product quality stability, increasing production efficiency, and reducing energy consumption and raw material losses.

[0015] Therefore, this invention achieves multi-dimensional synchronous monitoring of the production environment and raw material characteristics through a sensor monitoring cluster device. It combines environmental data with the distribution and attribute characteristics of raw materials for comprehensive analysis, and establishes a raw material characteristic data anomaly correction mechanism. This effectively solves the problems of existing technologies, such as single-dimensional monitoring, susceptibility to data anomalies, and lack of correction methods, providing accurate and reliable data support for production parameter setting. By deeply analyzing key characteristics such as the coupling relationship of raw material characteristic distribution and the effect of interfacial porosity, it accurately uncovers the laws governing raw material reaction behavior, effectively predicting reaction processes such as raw material hydration and foaming, avoiding drawbacks such as incomplete reaction and weak interfacial bonding, and improving the efficiency of raw material production. The system improves material reaction efficiency and effectiveness; it introduces a simulation and evolution analysis process for insulation board production, which can simulate structural changes during the curing process of insulation boards in advance, avoid production defects, and reduce the incidence of defective products; it constructs an intelligent optimization control engine based on real-time data, which dynamically corrects control parameters by combining production deviation characteristics and adjustment sensitivity, replacing the traditional fixed parameter control mode. This effectively solves the problems of uneven pore distribution, insufficient structural strength, and substandard insulation performance in insulation boards, significantly improving product quality stability, while increasing production efficiency, reducing energy consumption and raw material loss, and realizing large-scale, high-quality production of insulation boards, perfectly meeting the transformation and upgrading needs of the building energy conservation industry. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the steps in the intelligent optimization method for producing insulation boards based on raw material characteristics according to the present invention. Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S3. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. Functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods. The term "and / or" as used herein includes any and all combinations of one or more of the associated items listed.

[0019] To achieve the above objectives, please refer to Figures 1 to 2 This invention provides an intelligent optimization method and system for the production of insulation boards based on raw material characteristics. In the embodiments of this invention, please refer to... Figure 1 The diagram shown is a flowchart illustrating the steps of an intelligent optimization method for insulation board production based on raw material characteristics according to the present invention. The intelligent optimization method for insulation board production based on raw material characteristics includes the following steps: To achieve the above objectives, a smart optimization method for insulation board production based on raw material characteristics includes the following steps: Step S1: Use sensor monitoring cluster equipment to monitor and process the environmental and raw material characteristics of the target area for insulation board production control, and generate environmental data and raw material characteristic data for insulation board production respectively; based on the environmental data and raw material characteristic data for insulation board production, perform raw material distribution attribute feature analysis to generate raw material distribution attribute feature data for insulation board. In this embodiment of the invention, the target area for the control and regulation of insulation board production is defined as the entire process of raw material pretreatment, mixing, conveying, and fabric distribution in the continuous insulation board production line. The sensor monitoring cluster equipment is divided into two categories: environmental monitoring units and raw material characteristic monitoring units. These two types of units are deployed at fixed points within the target area. All monitoring units adopt a unified time synchronization mechanism and synchronously carry out data acquisition operations at a fixed sampling frequency. The environmental monitoring unit collects comprehensive environmental data, including ambient temperature, relative humidity, wind speed, and air pressure, within the target area. The raw material characteristic monitoring unit collects comprehensive raw material characteristic data, including particle size, bulk density, moisture content, slurry viscosity, and fiber dispersion state, for various raw materials used in insulation board production. The two types of data are aligned and matched according to the collection timestamp, generating continuous time-series environmental data and raw material characteristic data for insulation board production, respectively. Based on the collected raw material characteristic data for insulation board production, spatial distribution neighborhood analysis was used to identify and correct abnormal data, generating standard and reliable raw material characteristic data. Physical characteristics of raw material distribution were extracted based on this standard data, clarifying the spatial distribution patterns of powder particle size distribution, fiber dispersion state, and slurry homogeneity. Simultaneously, environmental data was combined to dynamically compensate for the temporal characteristics of raw material humidity, eliminating interference from environmental fluctuations in humidity detection. This yielded dynamic humidity characteristics that truly reflected the changing patterns of the raw materials themselves. Finally, the physical characteristics of raw material distribution and the dynamic characteristics of raw material humidity were matched and fused according to spatial coordinates and time series, comprehensively analyzing the distribution attribute patterns of raw materials throughout the entire production process. This generated raw material distribution attribute characteristic data for insulation boards, providing accurate and comprehensive basic data support for subsequent raw material reaction behavior analysis.

[0020] Step S2: Analyze the reaction behavior of the raw materials based on the distribution attribute characteristic data of the insulation board raw materials to generate raw material characteristic reaction behavior data; In this embodiment of the invention, the spatial distribution characteristics of the multi-component raw materials of the insulation board are analyzed to determine the coupling relationship of the raw material properties. This analysis elucidates the interactions between the cementitious components, foaming components, and reinforcing components, as well as the coupling relationships of raw material properties in spatial neighborhoods and temporal upstream and downstream areas, clarifying the strong correlations between different components and regions. Based on this, a convergent analysis is conducted on the coupling relationships to capture the transmission effect of coupling in the spatial dimension and the dynamic evolution law in the temporal dimension, obtaining a complete characterization of the coupling effect of raw material property distribution. Simultaneously, quantitative feature extraction of core attributes is performed on the raw material distribution attribute characteristic data. Focusing on the core attributes affecting hydration reaction, foaming process, and matrix hardening, multi-dimensional quantitative features are extracted to form a quantitative characterization system of raw material distribution attributes. The quantitative features are weighted and corrected using coupling relationships, and an analysis of the interface coupling effect of raw material properties is conducted. The coupling law of the cementitious particle hydration interface, the foaming system pore wall interface, and the fiber-matrix bonding interface is analyzed, obtaining the core features of interface hydration, interface expansion, and interface bonding. Based on the characteristics of interfacial coupling, further analysis of the distribution characteristics of interfacial porosity was conducted to elucidate the influence of interfacial properties on pore nucleation, pore stability, and pore spatial distribution, thus revealing the core characteristics of pore structure evolution. Finally, by integrating the characteristics of interfacial coupling and the distribution characteristics of interfacial porosity, and dividing the process into three continuous stages—hydration induction, foaming expansion, and solidification stabilization—the reaction behavior of raw materials from mixing to initial setting was analyzed. The reaction progress, rate changes, and risk points at each stage were clarified, generating complete data on the reaction behavior of raw materials, providing accurate reaction law basis for subsequent simulation evolution analysis.

[0021] Step S3: Analyze the structural characteristics of the reaction behavior of raw materials in the simulation of insulation board production to generate structural characteristic data of insulation board production simulation. In this embodiment of the invention, based on the reaction behavior data of raw materials, a kinetic analysis of the reaction of raw materials is conducted. The kinetic laws of the hydration reaction of the gelling system, the expansion reaction of the foaming system, and the curing and hardening reaction of the matrix are analyzed, clarifying the progress rate, characteristic time nodes, and core influencing parameters of each reaction process, generating kinetic characterization data for the entire reaction cycle. Simultaneously, prior production data of insulation boards that are fully matched with the current production line, product specifications, and formulation system are acquired. This prior production data covers all dimensions of data on raw material characteristics, process parameters, finished product performance, and abnormal operating conditions of historical qualified batches, and is used for benchmark calibration of the simulation model to ensure the matching degree between the simulation process and the actual production process. Using the reaction kinetic data as the core input, combined with the calibrated simulation model, multiphase fluid simulation evolution processing of the insulation board is carried out. For the gas-liquid-solid three-phase multiphase flow process of the foaming slurry, the flow state of the slurry, the nucleation and growth of bubbles, and the entire process of aggregation and breakup are simulated throughout the entire reaction cycle, obtaining multiphase flow field evolution data in the entire computational domain. Combining reaction kinetics data and multiphase fluid simulation evolution data, a thermo-mechanical finite element simulation reaction field analysis was conducted. A bidirectional, fully coupled solution mode for temperature and stress fields was adopted, using hydration exothermics as the internal heat source and foaming expansion internal pressure as the stress load. The distribution and evolution of the temperature and stress fields within the computational domain throughout the entire cycle were simulated, yielding complete characterization data of the thermo-mechanical coupled reaction field. Based on the thermo-mechanical finite element simulation reaction field data, a structural field analysis of the curing effect of the insulation board was performed. For the entire curing cycle from initial setting to final setting of the slurry, the evolution laws of the entire process—hardening of the cementitious matrix, shaping of the pore structure, and bonding of the interface structure—were analyzed. The spatial distribution and temporal evolution characteristics of the matrix mechanical properties, pore structure, and interface properties within the entire computational domain were clarified, obtaining complete data of the curing effect structural field. Finally, based on the solidification effect structural field data, we conducted a simulation evolution structural feature analysis of the insulation board production process. We extracted the pore density distribution characteristics, structural performance distribution characteristics, and interface homogeneity distribution characteristics in the entire computational domain. We then integrated the structural evolution time series data throughout the entire simulation cycle to generate simulation evolution structural feature data covering the entire structure and production cycle of the insulation board. This provides accurate predictive basis for subsequent intelligent optimization control.

[0022] Step S4: Based on the structural feature data of the insulation board production simulation evolution, design the intelligent optimization control relationship for insulation board production and generate an intelligent optimization control engine for insulation board production. The intelligent optimization control engine for insulation board production is used to execute intelligent optimization operations for insulation board production.

[0023] In this embodiment of the invention, based on the structural feature data of the simulated evolution of insulation board production, a deviation feature distribution analysis is conducted. Using the standard structural feature value of a qualified product matching the current product as a benchmark, the deviation between the simulation results and the standard value is calculated. The type, level, and spatial distribution characteristics of the deviation are identified, distinguishing between systematic full-area deviations and local random deviations. The production section corresponding to the deviation is located, generating complete deviation feature distribution data. Based on the deviation feature distribution data, a sensitivity distribution analysis of insulation board production adjustment is conducted. For three types of adjustable parameters—raw material formulation, production process, and production environment—the response relationship between adjustment parameters and structural feature deviations is established. The sensitivity of different adjustment parameters to various types of deviations is calculated, identifying the highly sensitive adjustment parameters corresponding to different regions and types of deviations, generating adjustment sensitivity distribution data that perfectly matches the deviation features. Combining the deviation feature distribution data and the adjustment sensitivity distribution data, an optimization adjustment analysis of insulation board production is conducted. Processing priorities are determined according to deviation levels. For different types and regions of deviations, corresponding highly sensitive adjustment parameters are matched to formulate adjustment schemes, clarifying the correction direction, correction boundary, and execution sequence of the adjustment parameters, generating production optimization adjustment data covering all production sections. For production optimization and adjustment data, PLC control drive parsing and mapping processing for insulation board production is carried out. Based on the type of adjustment parameters and their corresponding production sections, the corresponding control points of the production line PLC control system are matched, establishing a one-to-one mapping relationship between process optimization adjustment parameters and PLC control point setpoints. The adjustment boundaries, response times, and execution conditions of the mapping relationship are clarified, generating production control parsing and mapping data that can be directly parsed and executed. For the production control parsing and mapping data, PLC hierarchical control logic analysis is conducted. According to the production line process flow and control priority, three fixed levels are divided: the overall control layer, the section control layer, and the equipment control layer. The control range, linkage sequence, data transmission rules, and interlocking trigger logic of each level are clarified, generating production hierarchical control logic data with clear priorities, clear timing, and complete interlocking. Based on the production hierarchical control logic data, combined with the real-time operating status of the production line, the real-time characteristics of the current batch of raw materials, and the current production progress node, real-time insulation board production demand status analysis is conducted. The core control objectives and status requirements of each control level in the current production stage are clarified, generating real-time production status requirement data that perfectly matches the current production status. Based on real-time production status demand data, conduct real-time correction parameter analysis for hierarchical control, match highly sensitive adjustment parameters of the corresponding control level according to demand priority, determine the execution sequence and execution conditions of the correction parameters within the safety process boundary, and generate hierarchical control real-time correction parameters that conform to the hierarchical control logic.Finally, by integrating the control logic data of the insulation board production level with the real-time correction parameters of the insulation board level control, a fully closed-loop real-time intelligent optimization control system is constructed. The design of the intelligent optimization control relationship for insulation board production is completed, and an intelligent optimization control engine for insulation board production is generated. The control engine can independently complete real-time data acquisition, deviation analysis, parameter optimization, and control command output for the entire production process, and execute complete intelligent optimization operations for insulation board production.

[0024] Furthermore, step S1 includes the following steps: Step S11: Use sensor monitoring cluster equipment to monitor and process the environmental and raw material characteristics of the target area of ​​the insulation board production control operation, and generate environmental data and raw material characteristic data of insulation board production respectively. In this embodiment of the invention, the target area is defined as the raw material pretreatment section and the raw material mixing and conveying section of the continuous production line for insulation boards. The sensor monitoring cluster equipment is divided into an environmental monitoring unit and a raw material characteristic monitoring unit. The environmental monitoring unit is deployed at the four corners and the center of the target area. Each position is equipped with a temperature and humidity sensor, a wind speed sensor, and an ambient air pressure sensor. The sampling frequency is set to 1Hz. The ambient temperature, relative humidity, wind speed, and air pressure data of the target area are collected synchronously. The data collected by all environmental monitoring units are synchronously summarized through a wired transmission link, aligned according to the collection timestamp, and generated continuous time-series environmental data. The raw material characteristic monitoring unit is deployed at three monitoring points: the raw material metering inlet, the mixer outlet, and the conveying pipeline. Each point is equipped with a laser particle size analyzer, a density sensor, an online moisture content monitor, and a viscosity sensor. The laser particle size analyzer has a measurement range covering 0.1μm-3000μm, and the density sensor has a measurement range covering 0.5g / cm³-3.0g / cm³. The sampling frequency is set to 2Hz and synchronized with the timestamp of the environmental monitoring unit. It collects data on the particle size, bulk density, real-time moisture content, and viscosity of the mixed slurry for the cement, fly ash, foaming agent, foam stabilizer, and polypropylene fiber used in the production of insulation boards. The data is classified and stored according to the type of raw material and the monitoring point, generating raw material characteristic data for insulation board production that is synchronized with the environmental data.

[0025] Step S12: Perform anomaly correction and adjustment on the raw material characteristic data for insulation board production to generate standard raw material characteristic data for insulation board production; In this embodiment of the invention, the raw material characteristic data for insulation board production is divided into grids according to the spatial coordinates of monitoring points. Each monitoring point corresponds to a unique spatial grid unit. Using each grid unit as the center, the raw material characteristic data of the surrounding eight adjacent grid units are extracted to complete the spatial distribution raw material characteristic analysis and generate spatial distribution characteristic data for insulation board raw materials. Using the raw material characteristic data of each grid unit as a baseline value, the absolute value of the difference between the raw material characteristic data of adjacent grid units and the baseline value is calculated to complete the neighborhood spatial distribution characteristic analysis and generate neighborhood spatial distribution characteristic data for raw materials. A neighborhood difference threshold is set to 15% of the baseline value. When the absolute value of the difference between adjacent grid units exceeds the neighborhood difference threshold, the raw material characteristic data of that grid unit is determined to be abnormal data, and abnormal data for insulation board raw material characteristics is generated. The arithmetic mean of the raw material characteristic data of the surrounding eight adjacent grid units corresponding to the abnormal data is used to replace the abnormal data of that grid unit, completing the anomaly correction adjustment and generating standard raw material characteristic data for insulation board production.

[0026] Step S13: Analyze the physical characteristics of raw material distribution in the standard insulation board production raw material characteristic data to generate physical characteristic data of raw material distribution in the insulation board; In this embodiment of the invention, the characteristic data of raw materials for standard insulation board production are extracted according to the type of raw material. Specifically, particle size distribution data and bulk density data for cement and fly ash are extracted, as are length distribution data and aspect ratio data for polypropylene fibers, and viscosity and density data for the mixed slurry are extracted. For powder raw materials, a particle size distribution curve is plotted with particle size range as the abscissa and raw material volume percentage as the ordinate. The D10, D50, and D90 characteristic values ​​of the particle size distribution curve are extracted to calculate the particle size distribution characteristics of the powder raw materials. For fiber raw materials, the fiber quantity percentage in different length ranges is statistically analyzed to calculate the fiber dispersion uniformity characteristics. For the mixed slurry, the coefficients of variation of slurry viscosity and density at different monitoring points are calculated based on their spatial distribution to generate slurry homogeneity characteristics. By integrating the powder particle size distribution characteristics, fiber dispersion uniformity characteristics, and slurry homogeneity characteristics, the physical characteristic analysis of raw material distribution is completed, generating physical characteristic data of insulation board raw material distribution.

[0027] Step S14: Based on environmental data and standard insulation board production raw material characteristic data, perform dynamic humidity characteristic analysis of insulation board raw materials to generate dynamic humidity characteristic data of insulation board raw materials. In this embodiment of the invention, continuous time-series humidity data of insulation board raw materials at each monitoring point are extracted from the characteristic data of standard insulation board production raw materials. These data are then divided into consecutive time windows, each lasting 60 seconds. The average value and slope of the humidity data within each time window are calculated to complete the time-series characteristic analysis of insulation board raw material humidity, generating time-series characteristic data of insulation board raw material humidity. Simultaneously collected environmental data are used to extract environmental temperature, relative humidity, and wind speed data within the corresponding time window. A multiple linear regression model is established between the slope of raw material humidity change and these environmental factors. The influence weights of environmental factors on raw material humidity changes are calculated, and these influence weights are used to correct the time-series characteristic data of raw material humidity, completing the environmental dynamic compensation processing of humidity time-series characteristics and generating dynamic characteristic data of insulation board raw material humidity.

[0028] Step S15: Analyze the distribution attribute characteristics of insulation board raw materials based on the physical characteristics data of the distribution of insulation board raw materials and the dynamic characteristics data of the humidity of insulation board raw materials, and generate the distribution attribute characteristic data of insulation board raw materials.

[0029] In this embodiment of the invention, the particle size distribution characteristics, fiber dispersion uniformity characteristics, and slurry homogeneity characteristics of the raw material distribution physical feature data of the insulation board are extracted. These three types of features are then standardized and assigned values ​​to generate a raw material physical feature quantification matrix. The raw material humidity dynamic feature data of the insulation board raw material humidity dynamic feature data, including the dynamic compensation value and humidity change slope for each monitoring point within the corresponding time window, are extracted to generate a raw material humidity dynamic feature quantification matrix. The raw material physical feature quantification matrix and the raw material humidity dynamic feature quantification matrix are then matched and fused according to the same spatial coordinates and time window of the monitoring points. The coupling correlation degree between the raw material physical features and humidity dynamic features within each spatial grid cell is calculated, completing the analysis of the distribution attribute characteristics of the insulation board raw material and generating insulation board raw material distribution attribute feature data covering the entire monitoring area and the entire time series.

[0030] Furthermore, step S12 includes the following steps: Based on the raw material characteristic data of insulation board production, spatial distribution raw material characteristic analysis is performed to generate spatial distribution characteristic data of insulation board raw materials. By analyzing the spatial distribution characteristics of insulation board raw materials, neighborhood spatial distribution characteristics data is generated, and the collection anomaly detection and processing of insulation board raw material characteristics is performed based on the neighborhood spatial distribution characteristics data, generating insulation board raw material characteristic collection anomaly data. Abnormal data collected from the characteristics of insulation board raw materials are used to correct and adjust the abnormal data of the raw material characteristics of insulation board production, thereby generating standard raw material characteristic data for insulation board production.

[0031] In this embodiment of the invention, the entire process of raw material conveying, mixing, and spreading in the insulation board production is designated as the monitoring target area. The target area is a continuous rectangular working surface with a length of 12m and a width of 3m. The longitudinal direction is along the material conveying direction, and the transverse direction is perpendicular to the material conveying direction. The target area is divided into 36 continuous non-overlapping spatial grid units with a size of 1m×1m. Each grid unit corresponds to a unique two-dimensional spatial coordinate, and the origin of the coordinate is set as the initial position of the raw material metering and feeding port. The raw material characteristic data for insulation board production is time-series data synchronously collected by monitoring equipment deployed corresponding to the spatial grid units. The collection timestamp interval is fixed at 0.5s. The data covers the particle size and bulk density of the cementitious powder raw materials, the viscosity and density of the mixed slurry, and the real-time moisture content of all raw materials. The raw material characteristic data of all grid units are aligned according to the collection timestamp. Each raw material characteristic value under the same timestamp is uniquely bound to the spatial coordinate of the corresponding grid unit. The raw materials are divided into three categories according to the raw material category: cementitious material group, foaming slurry group, and reinforcing fiber group, and processed separately. Along the longitudinal direction of material transport, a continuous spatial distribution sequence of various characteristics of each type of raw material is generated in ascending order of coordinates. Along the transverse direction, the distribution of raw material characteristic values ​​in different transverse grids under the same longitudinal coordinate is statistically analyzed. The longitudinal continuous sequence and transverse cross-sectional distribution data are integrated to complete the spatial distribution analysis of raw material characteristics across the entire region, generating spatial distribution characteristic data of insulation board raw materials with spatial coordinate identifiers, timestamp alignment, and clear classification. For each grid cell with spatial coordinates in the spatial distribution characteristic data of insulation board raw materials, the analysis range is defined using the 8-neighborhood rule. Centered on the target grid cell, the values ​​of the same timestamp, same raw material category, and same characteristic index of eight adjacent grid cells in the vertical, horizontal, and four diagonal directions are extracted to complete neighborhood data matching. For each target grid cell, the absolute difference between its characteristic value and the characteristic values ​​of each adjacent grid cell is calculated. The arithmetic mean of the corresponding characteristic values ​​of the eight neighboring grid cells is calculated, and the distribution interval of the neighboring values ​​is statistically analyzed to complete the neighborhood spatial distribution characteristic analysis, generating the raw material neighborhood spatial distribution characteristic data bound to each grid cell. The neighborhood difference judgment threshold is set to 15% of the arithmetic mean of the neighborhood of the target grid cell. When the absolute difference between the characteristic value of the target grid cell and the arithmetic mean of its neighborhood exceeds the neighborhood difference judgment threshold, and the absolute difference between the target grid cell and six or more adjacent grid cells also exceeds the neighborhood difference judgment threshold, the raw material characteristic data corresponding to the timestamp and category of the target grid cell is judged as abnormal data. A unique label is created based on spatial coordinates, raw material category, characteristic index, and collection timestamp. This completes the detection and processing of abnormal data across the entire area and time period, generating fully labeled abnormal data for the raw material characteristics of insulation boards. Based on the labeling information of the abnormal data, the abnormal values ​​corresponding to the spatial coordinates, collection timestamp, raw material category, and characteristic index in the raw material characteristic data of insulation board production are located, enabling precise location and removal of abnormal values.For the target grid cell where outliers were removed, valid values ​​for the corresponding raw material category and characteristic indicators of the eight neighboring grid cells at the same acquisition time stamp were extracted. These valid values ​​were the neighboring data not marked as acquisition anomalies. Correction weights were assigned based on the spatial distance between the neighboring grid cells and the target grid cell: the four grid cells adjacent to the target grid cell at its edge each received a weight of 0.18, and the four grid cells diagonally adjacent to the target grid cell each received a weight of 0.07, for a total weight of 1. The valid neighboring values ​​were then weighted according to the assigned weights to obtain the corrected value for the target grid cell. The corrected values ​​were then filled back into the positions corresponding to the original outlier values. Raw material characteristic data not marked as acquisition anomalies remained unchanged. This process completed anomaly correction and adjustment across the entire monitoring area, all raw material categories, all characteristic indicators, and all time periods, generating standard insulation board production raw material characteristic data that perfectly matched the original data's spatial coordinates and time series, without any abnormal jumps in values.

[0032] Furthermore, step S14 includes the following steps: Extracting moisture data of raw materials for standard insulation board production; Based on the humidity data of the insulation board raw materials, a time-series characteristic analysis of the humidity of the insulation board raw materials is performed to generate time-series characteristic data of the humidity of the insulation board raw materials. By performing environmental dynamic compensation processing on the humidity time-series characteristic data of insulation board raw materials using environmental data, dynamic characteristic data of humidity of insulation board raw materials is generated.

[0033] In this embodiment of the invention, the characteristic data of raw materials for standard insulation board production are divided into spatial grid units according to the three core processes of raw material pretreatment, mixing, and conveying in the insulation board production line. Each grid unit is bound to a unique two-dimensional spatial coordinate. All data are synchronized and aligned according to timestamps at fixed 0.5s intervals. The data is divided into three categories according to raw material type: cementitious powder raw material group, mixed slurry group, and modified admixture group. Humidity data extraction rules are defined according to raw material type and production process. The cementitious powder raw material group corresponds to the grid unit at the raw material metering and feeding port to extract real-time moisture content data of cement, fly ash, and heavy calcium carbonate powder; the mixed slurry group corresponds to the grid unit at the mixer outlet and the middle section of the conveying pipeline to extract the overall moisture content data of foamed mixed slurry; the modified admixture group corresponds to the grid unit at the metering station of foam stabilizer and foaming agent to extract the moisture content data of liquid phase admixture. All extracted humidity data retains spatial coordinate identifiers, collection timestamps, and raw material category identifiers completely consistent with the original standard data. Following the chronological order of material flow on the production line, and along the increasing direction of the vertical spatial coordinates, a continuous humidity data sequence corresponding to each raw material category is generated. Humidity data from all grid cells under the same timestamp are integrated into horizontal cross-sectional data based on spatial coordinates, ensuring that the extracted insulation board raw material humidity data completely matches the spatial and temporal dimensions of the original standard data, with no data misalignment or temporal deviation. This provides a unified data source for subsequent temporal feature analysis. For the extracted insulation board raw material humidity data, each spatial grid cell is used as an independent analysis unit. A fixed-length sliding time window is divided according to the chronological order of collection timestamps. The duration of the sliding time window is set to 60 seconds, and the sliding step size is set to 10 seconds. Each time window contains 120 sets of continuously collected humidity data. For each independent sliding time window, the arithmetic mean of the humidity data within the window is first calculated as the baseline humidity value for that window. Then, the difference in humidity values ​​between the first and last data collection points within the window is calculated, and combined with the window duration, the humidity change slope is calculated to characterize the rate of humidity change per unit time. Simultaneously, the fluctuation amplitude of the humidity data within the window, i.e., the difference between the maximum and minimum humidity values ​​within the window, is calculated to characterize the stability of humidity during that period. By continuously sliding time windows along the time axis, the humidity time-series characteristics of all time periods and all spatial grid cells are calculated. The calculation results for each sliding window are bound to the spatial coordinates of the corresponding grid cell and the start and end timestamps of the window. These results are integrated according to the raw material category to generate humidity time-series characteristic data of the insulation board raw materials, containing three core indicators: baseline humidity value, humidity change slope, and humidity fluctuation amplitude, with complete spatial and temporal matching. The environmental data is continuous time-series data that is completely synchronized with the humidity data of the insulation board raw materials and covers the entire monitoring area. It includes four core indicators for the target area at each time point: ambient temperature, ambient relative humidity, ambient wind speed, and ambient air pressure. All environmental indicator data are taken as the arithmetic mean of 5 fixed monitoring points in the entire monitoring area, generating environmental time-series data that is completely aligned with the time window of the humidity time-series characteristic data.For the humidity time-series characteristic data corresponding to each sliding time window, the correlation between the humidity change slope within that window and the corresponding ambient temperature, relative humidity, and wind speed is first established. The influence weights of the three environmental indicators on the humidity change slope are calculated respectively. Ambient temperature is positively correlated with the humidity change slope, relative humidity is negatively correlated, and wind speed is positively correlated. Based on the calculated influence weights of the three environmental indicators, the humidity change offset caused by environmental factors within that time window is calculated. This offset is used to correct the humidity change slope in the original humidity time-series characteristic data, eliminating the interference of environmental fluctuations on the humidity change characteristics of raw materials. At the same time, the ambient air pressure is used to correct the air pressure influence of the benchmark humidity value, eliminating the systematic bias of ambient air pressure changes on the moisture content detection value. All correction calculations are completed according to the time window, spatial grid unit, and raw material category. The corrected characteristic data retains the original spatial coordinates and timestamps, completing the dynamic environmental compensation processing of humidity time-series characteristics across all time periods and regions, generating dynamic humidity characteristic data of insulation board raw materials that eliminates environmental interference and truly reflects the humidity change law of the raw materials themselves.

[0034] Furthermore, step S2 includes the following steps: Step S21: Perform raw material characteristic distribution coupling relationship analysis based on the raw material distribution attribute characteristic data of the insulation board to generate raw material characteristic distribution coupling relationship data; In this embodiment of the invention, the raw material distribution attribute feature data of the insulation board is full-dimensional feature data with 1m×1m spatial grid coordinates and a fixed 0.5s timestamp alignment. It includes a raw material physical feature quantification matrix and a humidity dynamic feature quantification matrix, covering the core attribute indicators of four major categories of raw materials: cementitious powder, mixed slurry, reinforcing fiber, and functional admixtures. The analysis process uses a single spatial grid cell as the smallest analysis unit and a fixed analysis time window of 60s. For a single target grid cell under the same timestamp, the core attribute indicators of the four major categories of raw materials within the cell are extracted first. For cementitious powder, particle size distribution feature value, bulk density, and real-time moisture content are extracted; for mixed slurry, homogeneity features, kinematic viscosity, and overall moisture content are extracted; for reinforcing fiber, dispersion uniformity features and aspect ratio are extracted; and for functional admixtures, the dosage ratio features of foaming agent and foam stabilizer are extracted. This completes the dimensional alignment of multi-component attribute indicators within a single grid. Based on this, coupling relationship calculations are carried out. First, the coupling relationship analysis between components within a single grid is completed, calculating the correlation between cement particle size distribution and fly ash filling effect, the correlation between slurry moisture content and kinematic viscosity, the correlation between fiber dispersion and slurry homogeneity, and the correlation between foaming agent dosage and slurry viscosity. Then, the spatial neighborhood coupling relationship analysis is completed, calculating the spatial coupling correlation between the target grid and the same component attribute indices of the 8 neighboring grids. Finally, the temporal upstream and downstream coupling relationship analysis is completed, calculating the temporal coupling correlation between the raw material attributes of the upstream grid and the corresponding attributes of the downstream grid along the material conveying direction. A correlation degree with an absolute value greater than 0.6 is considered a strong coupling relationship, 0.3-0.6 is considered a medium coupling relationship, and less than 0.3 is considered a weak coupling relationship. All coupling correlation results are uniquely bound to the corresponding spatial coordinates, timestamps, and raw material categories, and integrated according to coupling type to generate raw material characteristic distribution coupling relationship data.

[0035] Step S22: Perform graph convolution aggregation relationship analysis on the coupling effect of raw material characteristic distribution based on the raw material characteristic distribution coupling relationship data to generate raw material characteristic distribution coupling relationship data; In this embodiment of the invention, based on 36 1m×1m spatial grid units defined in the insulation board production line, each grid unit is defined as an independent node in the graph structure. The basic attributes of the nodes are the core attribute indicators of the four major categories of raw materials within the grid. The connection edges between nodes are determined by the coupling correlation degree in the raw material characteristic distribution coupling relationship data, thus constructing an undirected weighted graph structure. In the graph structure, when there is a strong or moderate coupling relationship between two nodes, a corresponding connection edge is generated. The weight of the edge corresponds one-to-one with the absolute value of the coupling correlation degree. The weight of the edge for a strong coupling relationship is set to 1, the weight of the edge for a moderate coupling relationship is set to 0.5, and no connection edge is generated for a weak coupling relationship, ensuring that the graph structure only retains the connection relationships with effective coupling effects. Based on this, hierarchical graph convolutional aggregation processing is carried out. The first layer of aggregation processing targets the first-order neighborhood of the target node, that is, the 8 neighboring grid nodes directly connected to the target node. The attribute indicators of the neighboring nodes are weighted and summed according to the edge weights, and then fused with the attribute indicators of the target node itself to obtain the first-order aggregated feature of the target node. The second layer of aggregation processing targets the second-order neighborhood of the target node, that is, the neighboring nodes of the first-order neighboring nodes. The second-order aggregation fusion is carried out according to the same weight rules to obtain the second-order aggregated feature of the target node, capturing the spatial transmission effect of coupling. At the same time, temporal aggregation processing is carried out along the time axis. The node aggregation features of the current timestamp graph structure are fused with the node aggregation features of the graph structure of the previous fixed time step to capture the dynamic change law of coupling. The final aggregation features of all nodes are bound to corresponding spatial coordinates and collected timestamps, and are classified and integrated according to production section and raw material category to generate raw material characteristic distribution coupling relationship data.

[0036] Step S23: Extract quantitative features of raw material distribution attributes from the raw material distribution attribute feature data of the insulation board to obtain quantitative feature data of raw material distribution attributes; In this embodiment of the invention, the distribution attribute characteristic data of the insulation board raw materials covers three core production stages: raw material pretreatment, mixing, and transportation. All data are uniquely bound to spatial grid coordinates and collection timestamps. Quantitative feature extraction focuses on the core attributes affecting the entire reaction process of hydration, foaming, and curing of the insulation board, and is carried out in four fixed dimensions. The first dimension is the quantitative characteristics related to the hydration activity of the cementitious system. For each spatial grid cell, four core indicators are extracted: cement particle size distribution D50 value, fly ash activity corresponding quantitative value, real-time moisture content of cementitious materials, and bulk density of cementitious materials. Fixed weights are assigned according to the proportion of cement and fly ash in the cementitious system, and the weighted calculation yields the quantitative value of the hydration activity of the cementitious system for each grid cell, characterizing the potential and rate potential of the hydration reaction of the cementitious materials. The second dimension focuses on the quantitative characteristics related to the pore-forming properties of the foaming system. For each spatial grid cell, four core indicators are extracted: the proportion of foaming agent, the proportion of foam stabilizer, the kinematic viscosity of the mixed slurry, and the overall moisture content of the slurry. Fixed weights are assigned according to the proportions of the foaming and gelling systems, and a weighted calculation is performed to obtain the quantitative value of the pore-forming properties of the foaming system for each grid cell, characterizing the pore-forming stability and pore size controllability during the foaming process. The third dimension focuses on the quantitative characteristics related to the structural stability of the reinforcement system. For each spatial grid cell, three core indicators are extracted: the uniformity of polypropylene fiber dispersion, the fiber aspect ratio, and the fiber content. A weighted calculation is performed to obtain the quantitative value of the structural stability of the reinforcement system for each grid cell, characterizing the reinforcing effect of the fiber on the gelling matrix and its interfacial bonding potential. The fourth dimension focuses on the quantitative characteristics related to the spatial distribution homogeneity. Along the longitudinal direction of material transport, the coefficients of variation of the first three types of quantitative values ​​for all transverse grid cells under the same longitudinal coordinate are calculated to obtain the spatial homogeneity quantitative value for each longitudinal section, characterizing the uniformity of the raw material properties distributed across the transverse section of the production line. All extracted quantitative features are bound to corresponding spatial grid coordinates and collection timestamps, and stored according to four dimensions to generate quantitative feature data of raw material distribution attributes.

[0037] Step S24: Utilize the raw material characteristic distribution coupling relationship data to perform interface coupling characteristic analysis on the quantitative characteristic data of raw material distribution attributes, and generate raw material characteristic interface coupling characteristic data; In this embodiment of the invention, the data on the coupling relationship of raw material property distribution and the quantitative characteristic data of raw material distribution attributes are fully aligned in terms of spatial grid coordinates and acquisition timestamp dimensions. The analysis process is conducted with a single spatial grid cell as an independent analysis unit, focusing on three types of interface coupling effects at the core of insulation board production: the hydration interface of cementitious particles, the pore wall interface of the foaming system, and the fiber-matrix bonding interface. For the hydration interface of cementitious particles, the coupling effect aggregation characteristic value between cementitious components is extracted from the raw material property distribution coupling relationship data of the target grid cell. The quantitative value of hydration activity of the cementitious system in this cell is then weighted and corrected. The correction weight corresponds to the coupling effect aggregation characteristic value, thus obtaining the hydration coupling characteristic value of the cementitious particle interface. This characteristic value corresponds to the raw material property hydration reaction rate data, accurately characterizing the initiation rate and progress rate of the hydration reaction at the cementitious particle interface. For the pore wall interface of the foaming system, the polymerization characteristic value of the cross-component coupling effect between the foaming system and the cementing system is extracted from the coupling relationship data of the raw material property distribution of the target grid unit. The quantified value of the pore-forming characteristics of the foaming system of this unit is weighted and corrected to obtain the interface expansion coupling characteristic value of the foaming system. This characteristic value corresponds to the volume expansion data of the raw material properties during foaming, accurately characterizing the volume expansion law and expansion limit at the pore wall interface during the foaming process. For the fiber-matrix bonding interface, the polymerization characteristic value of the coupling effect between the fiber and the cementing matrix is ​​extracted from the coupling relationship data of the raw material property distribution of the target grid unit. The quantified value of the structural stability of the reinforcement system of this unit is weighted and corrected to obtain the interface bonding coupling characteristic value of the fiber-matrix. This characteristic value corresponds to the interface strength data of the raw material properties, accurately characterizing the bonding strength and deformation resistance at the interface between the fiber and the cementing matrix. Based on this, along the longitudinal direction of material conveying, the temporal variation law of the three types of interface coupling characteristic values ​​of the upstream and downstream grid units is calculated to capture the dynamic evolution trend of the interface coupling effect with the material conveying process. All characteristic values ​​are bound to corresponding spatial coordinates and collection timestamps, and are integrated by production section to generate the characteristic data of the interface coupling effect of the raw material properties.

[0038] Step S25: Analyze the distribution characteristics of the porosity effect at the raw material interface based on the characteristic data of the coupling effect at the raw material interface, and generate the distribution characteristic data of the porosity effect at the raw material interface. In this embodiment of the invention, the characteristic data of the interface coupling effect of raw material properties includes three core indicators: hydration reaction rate, foaming volume expansion, and interface strength. All indicators are uniquely bound to spatial grid coordinates and acquisition timestamps. The analysis process takes a single spatial grid cell as an independent analysis unit, focusing on the effect of interface properties on pore nucleation, pore stability, and pore distribution. For the analysis of pore nucleation, the hydration reaction rate data and foaming volume expansion data of the target grid cell are extracted. First, the initial setting time of the gelling system is calculated using the hydration reaction rate data, and the peak expansion time of the foaming process is calculated using the foaming volume expansion data. Then, the time difference between the initial setting time and the peak foaming time is calculated to obtain the pore nucleation time matching characteristic value. This characteristic value accurately represents the time matching degree between the hydration process and the foaming process. The closer the time difference is to 0, the higher the time matching degree between foaming and hydration, and the more stable the pore nucleation process. For the analysis of pore stabilization effects, interface strength data and foaming volume expansion data of target grid cells are extracted. A fixed ratio of interface strength data to foaming volume expansion data is calculated to obtain pore stability characteristic values. These characteristic values ​​accurately characterize the deformation resistance of pore walls during foaming expansion. The higher the ratio, the stronger the pores' resistance to coalescence and collapse during expansion, and the better the pore structure stability. For the analysis of pore spatial distribution effects, along the transverse section of the production line, the distribution range of pore nucleation time matching characteristic values ​​and pore stability characteristic values ​​of all grid cells under the same longitudinal coordinate is calculated to obtain pore distribution homogeneity characteristic values, characterizing the uniformity of pore structure distribution within the same cross section. Along the longitudinal direction of material conveying, the changing trends of the two types of characteristic values ​​of upstream and downstream grid cells are calculated to obtain pore effect temporal evolution characteristic values, characterizing the evolution law of pore structure with the material conveying process. All pore effect characteristic values ​​are bound to corresponding spatial coordinates and collection timestamps, and are integrated by production section to generate raw material characteristic interface pore effect distribution characteristic data.

[0039] Step S26: Analyze the reaction behavior of raw materials by using the characteristic data of the coupling effect between raw material properties and the characteristic data of the distribution of porosity at the raw material properties interface, and generate raw material property reaction behavior data.

[0040] In this embodiment of the invention, the characteristic data of the interface coupling effect of raw material properties and the characteristic data of the distribution of porosity effect of the interface of raw material properties are fully aligned in terms of spatial grid coordinates and acquisition timestamp dimensions. The analysis process divides the entire reaction cycle of the insulation board raw material from mixing to initial setting into three continuous stages: hydration induction, foaming expansion, and solidification stabilization. The reaction behavior laws are accurately analyzed in each stage. For the hydration induction stage, the hydration reaction rate data in the interface coupling effect characteristic data is extracted and combined with the pore nucleation time matching characteristics in the interface porosity effect distribution characteristic data to analyze the start-up time, induction period duration, and hydration heat release rate variation of the cementitious system hydration reaction. The reaction behavior characteristics of the hydration induction stage are determined, the influence boundary of the hydration reaction on the subsequent foaming process is clarified, and the abnormal risks of delayed or premature hydration reaction start are accurately predicted. For the foaming and expansion stage, foaming volume expansion data and interfacial strength data are extracted from the interfacial coupling effect characteristic data. Combined with pore stability characteristics and pore distribution homogeneity characteristics from the interfacial porosity distribution characteristic data, the onset time, peak expansion time, volume expansion rate, and pore nucleation and growth patterns of the foaming process are analyzed to determine the reaction behavior characteristics of the foaming and expansion stage, identify the risk points of pore merging and collapse during the foaming process, and accurately predict the abnormal risks of foaming runaway and uneven pore size distribution. For the curing and stabilization stage, interfacial strength data is extracted from the interfacial coupling effect characteristic data. Combined with the pore time evolution characteristics from the interfacial porosity distribution characteristic data, the strength growth law of the cementitious matrix, the pore wall structure stabilization process, and the final shaping law of the pore structure are analyzed to determine the reaction behavior characteristics of the curing and stabilization stage and identify the final formation nodes of the insulation board structure performance. The reaction behavior characteristics of the three stages are continuously integrated in time series and combined with spatial grid coordinates to generate a complete characterization of raw material reaction behavior covering the entire production process and the entire reaction cycle. It includes four core indicators: hydration reaction process, foaming and expansion process, strength growth process, and pore structure evolution process. All indicators are bound to corresponding spatial coordinates and timestamps to generate raw material characteristic reaction behavior data.

[0041] Furthermore, the material property interface coupling characteristic data mentioned in step S24 includes material property hydration reaction rate data, material property foaming volume expansion data, and material property interface strength data.

[0042] Furthermore, as an embodiment of the present invention, reference is made to... Figure 2 As shown, Figure 1 A detailed flowchart illustrating the implementation steps of step S3 is provided in this embodiment. Step S3 includes: Step S31: Perform reaction kinetic analysis on the reaction behavior data of the raw materials to generate reaction kinetic data of the raw materials. In this embodiment of the invention, the raw material characteristic reaction behavior data is continuous time-series data covering the entire reaction cycle of hydration induction, foaming expansion, and curing stabilization of the insulation board raw material. It is bound to a 1m×1m spatial grid coordinate system of the production line and time stamps collected at 0.5s intervals. It includes four core indicators: hydration reaction process, foaming expansion process, strength growth process, and pore structure evolution process. The analysis process uses a single spatial grid cell as the smallest analysis unit, with a full analysis cycle of 1200s from the completion of slurry mixing to initial setting and solidification. A fixed time step of 10s is used, and precise analysis is conducted on three types of core reaction kinetic processes. The first type is the hydration reaction kinetic analysis of the cementitious system. The hydration reaction rate and hydration heat release process data are extracted within the corresponding grid cell throughout the entire cycle. The continuous change curve of hydration degree over time is calculated, and the activation energy, reaction order, peak time and peak intensity of hydration heat release are fitted to accurately characterize the process law and rate change characteristics of the cementitious particle hydration reaction. The second category is the expansion kinetic analysis of the foaming system. This involves extracting foam volume expansion data, pore nucleation and growth data for the entire cycle of the corresponding grid unit, calculating the changes in foaming rate, volume expansion ratio, bubble nucleation rate, and bubble growth rate over time, and fitting the foaming reaction initiation time, peak expansion time, and expansion stabilization time to accurately characterize the kinetic characteristics of the entire process of gas production and expansion in the foaming system. The third category is the matrix curing and hardening kinetic analysis. This involves extracting interface strength data and strength growth process data for the entire cycle of the corresponding grid unit, calculating the growth curves of matrix compressive strength and elastic modulus over time, and fitting the strength growth rate and initial and final setting time nodes to accurately characterize the kinetic characteristics of the cementitious matrix hardening process. All kinetic analysis results are uniquely bound to the corresponding spatial grid coordinates and analysis time step, and are categorized and integrated according to production stage and reaction type to generate complete, spatiotemporally matched raw material characteristic reaction kinetic data.

[0043] Step S32: Obtain preliminary production data for the insulation board; In this embodiment of the invention, the preliminary production data for the insulation board is historical continuous production data that perfectly matches the current production line model, product specifications, and raw material formula system. The data covers complete production batches over the past 12 months, and each batch of data is uniquely bound to the production time, product specifications, and raw material batch information. The data is divided into four fixed dimensions based on data attributes. The first category is historical raw material characteristic data, including core attribute data such as particle size distribution, bulk density, moisture content, activity index, and viscosity of the corresponding batch of cement, fly ash, foaming agent, foam stabilizer, and polypropylene fiber, which is completely aligned with the raw material characteristic monitoring data dimensions. The second category is historical production process parameter data, including the full-process process control data such as raw material metering accuracy, mixer speed, mixing time, slurry spreading speed, mold specifications, and curing environment temperature and humidity of the corresponding batch of production line, covering the entire production process from raw material pretreatment to initial setting and shaping. The third category is historical finished product performance testing data, including core performance indicators such as dry bulk density, thermal conductivity, compressive strength, flexural strength, porosity, and closed-cell rate of the corresponding batch of insulation board finished products, covering all testing contents required by national standards. The fourth category is historical production anomaly data, including corresponding operating condition data, raw material characteristic data, and finished product performance data for anomalies such as foam collapse, uneven pore distribution, insufficient matrix strength, and board cracking that occurred during the production process of the corresponding batch. This clearly defines the correlation between anomalies and production parameters and raw material characteristics. All prior production data are categorized and stored according to product specifications and formulation systems. The data time series and spatial dimensions are aligned with the monitoring data and kinetic analysis data of the current production process, providing a benchmark calibration basis for subsequent simulation evolution processing.

[0044] Step S33: Based on the prior production data of the insulation board, perform multiphase fluid simulation evolution processing on the raw material characteristic reaction kinetic data to generate multiphase fluid simulation evolution data of the insulation board. In this embodiment of the invention, the computational domain of the simulation evolution is completely consistent with the internal space of the standard insulation board production mold, with a geometric dimension of a cuboid space of 2440mm in length, 1220mm in width, and 120mm in thickness. The computational domain is divided into hexahedral structured meshes with a fixed mesh size of 2mm. The mesh nodes are completely matched with the nodes of the subsequent finite element simulation to ensure consistency of spatial dimensions. The simulation process takes the gas-liquid-solid three-phase multiphase flow of the insulation board foaming slurry as the analysis object. First, the baseline calibration of the simulation model is completed using prior production data of the insulation board. The non-Newtonian fluid viscosity model and the gas-liquid interface surface tension model of the simulation model are calibrated using the kinematic viscosity and surface tension data of the slurry from historical production batches. The core parameters of the bubble coalescence and breakup model are calibrated using the porosity and pore size distribution data of historical finished products. The parameters of the gas production rate model are calibrated using historical foaming expansion process data to ensure the matching degree between the simulation model and the actual production process. The core input source for the simulation process is the reaction kinetic data of the raw material characteristics. Hydration reaction kinetic data provides the energy source and control basis for the slurry viscosity evolution, while foaming expansion kinetic data provides the gas phase mass source and control basis for bubble growth. The simulation calculation time range is perfectly aligned with the cycle of the raw material characteristic reaction kinetic analysis, which is 1200 seconds from the completion of slurry application to initial setting and shaping. The calculation time step is fixed at 0.1 seconds, and the multiphase flow control equations of the entire computational domain are iteratively solved at each time step. The simulation calculation outputs the evolution data of slurry flow velocity field, pressure field, gas-liquid-solid three-phase volume fraction distribution, bubble number density distribution, average bubble particle size distribution, and bubble rise and coalescence processes for each grid node within the computational domain throughout the entire time series. All calculation results are bound to corresponding spatial coordinates and simulation time steps, and are continuously integrated according to the time series to generate multiphase fluid simulation evolution data of insulation boards with complete spatiotemporal dimensions and a high degree of matching with the actual production process.

[0045] Step S34: Perform thermo-mechanical finite element simulation reaction field analysis based on the raw material characteristic reaction kinetic data and the insulation board multiphase fluid simulation evolution data to generate thermo-mechanical finite element simulation reaction field data; In this embodiment of the invention, the geometric computational domain of the thermo-mechanical finite element simulation is completely consistent with that of the multiphase fluid simulation. Hexahedral elements of the same size are used for mesh generation, and the mesh nodes correspond to the multiphase flow simulation mesh nodes, ensuring complete spatial dimension matching. The simulation process employs a bidirectional, fully coupled solution mode for the temperature and stress fields, completing iterative calculations and data transfer for both at each time step. The core input data for the temperature field solution is the hydration reaction kinetics data from the raw material characteristic reaction kinetics data. The hydration heat release rate and hydration degree evolution data are extracted throughout the entire cycle and used as the internal heat source term for the temperature field solution. Simultaneously, the slurry thermophysical parameters and three-phase volume fraction distribution data are extracted from the multiphase fluid simulation evolution data and used as the basis for the material thermal property parameters for the temperature field solution. The boundary conditions adopt a convective heat transfer boundary consistent with the actual production environment. The temperature distribution, temperature gradient distribution, cumulative hydration heat release distribution, and temperature rise rate distribution data within the computational domain are calculated throughout the entire time series, capturing the local temperature rise peak and the temperature field homogeneity variation law throughout the entire cycle. The core input data for stress field solution are the slurry pressure field and bubble expansion internal pressure distribution data from the multiphase fluid simulation evolution data, and the matrix elastic modulus evolution data from the raw material property reaction kinetics data. The boundary conditions use displacement constraints on the inner wall of the mold. The system calculates stress, strain, volumetric deformation, and elastic modulus distributions within the computational domain over the entire time series, capturing localized stress concentrations and uneven deformation regions during the foaming and expansion process. During the bidirectional coupling process, the temperature field calculation results are used to correct the hydration reaction rate and matrix material mechanical properties in real time, while the stress field calculation results are used to correct the bubble expansion boundary and slurry flow state in real time, achieving accurate solutions through thermo-mechanical bidirectional coupling. All solution results are bound to corresponding spatial coordinates and simulation time steps, and are continuously integrated over time to generate thermo-mechanical finite element simulation reaction field data covering the entire computational domain and the entire reaction cycle.

[0046] Step S35: Perform structural field analysis of the curing effect of the insulation board based on the thermal-mechanical finite element simulation reaction field data, and generate structural field data of the curing effect of the insulation board; In this embodiment of the invention, the time range of the solidification effect structural field analysis is the entire 3600s cycle from the initial setting time node of the slurry to the final setting and solidification. The analysis time step is fixed at 30s. The geometric calculation domain of the analysis is completely consistent with the calculation domain of the thermo-mechanical finite element simulation, and the mesh nodes correspond one-to-one to ensure complete matching of spatial and temporal dimensions. The analysis process uses the temperature field, stress field, and elastic modulus distribution data of the initial setting node in the thermo-mechanical finite element simulation reaction field data as initial conditions. At the same time, it combines the matrix strength growth and interface strength evolution data in the raw material characteristic reaction kinetic data to carry out the full-cycle analysis of the solidification effect in three core dimensions. The first dimension is the analysis of the solidification and hardening effect of the cementitious matrix. For each mesh element in the calculation domain, the continuous evolution law of compressive strength, flexural strength, and elastic modulus over time is calculated throughout the entire cycle. The spatial distribution characteristics of the matrix hardening rate are determined, and the distribution range and fluctuation amplitude of mechanical properties in the entire calculation domain are statistically analyzed. Weak areas of the matrix with lagging local strength growth and low performance are captured, and the homogeneity and stability of the matrix hardening process are clarified. The second dimension is the analysis of the solidification and shaping effect of the pore structure. Combining stress distribution and volume deformation distribution data from the thermo-mechanical finite element simulation reaction field, it calculates the deformation, stabilization, and shaping process of bubble pores throughout the entire cycle. It determines the evolution characteristics of pore closure rate, pore size distribution, and porosity over time within each grid cell, statistically analyzes the spatial homogeneity of the pore structure distribution across the entire computational domain, captures abnormal regions of pore collapse, merging, and interconnection, and clarifies the time nodes and stability of the pore structure shaping. The third dimension is the analysis of the solidification and bonding effect of the interface structure. For each grid cell within the computational domain, it calculates the evolution of the interfacial bonding strength between the fiber and the cementitious matrix, and the interfacial strength of the pore wall over time throughout the entire cycle. It determines the rate of increase and final stable value of interfacial strength, statistically analyzes the distribution characteristics of interfacial properties across the entire computational domain, captures areas of weak interfacial bonding, and clarifies the overall stability of the interfacial structure. The analysis results of all three dimensions are bound to corresponding spatial coordinates and analysis time steps, and are continuously integrated according to the time series to generate structural field data of the insulation board solidification effect covering the entire computational domain and the entire solidification cycle.

[0047] Step S36: Analyze the structural characteristics of the insulation board production simulation evolution using the structural field data of the insulation board curing effect, and generate structural characteristic data of the insulation board production simulation evolution.

[0048] In this embodiment of the invention, the final solidification result of the insulation board curing effect structural field data is used as the core basis. Simultaneously, the structural evolution time-series data throughout the entire simulation cycle is combined. The geometric computational domain analyzed is completely consistent with the computational domain of the curing effect structural field analysis, with corresponding grid nodes to ensure complete spatial dimension matching. The analysis process involves precise extraction and integration of three types of core structural features. The first type is the pore density distribution data from the insulation board production simulation evolution. After curing and solidification, the porosity, pore size distribution, and closed-cell rate data of each grid unit in the entire computational domain are extracted. Continuous pore density distribution curves are plotted along the length, width, and thickness directions of the board. The pore volume ratio of different pore size intervals is statistically analyzed. The average porosity and coefficient of variation of the entire board are calculated to determine the overall homogeneity of pore density. Abnormal areas with excessively high or low pore density are marked, generating pore density distribution data covering the entire board space. The second category is structural performance data from the simulation evolution of insulation board production. This involves extracting the dry bulk density, compressive strength, flexural strength, and modulus of elasticity data for each grid cell within the entire computational domain after curing and shaping. The average value of each structural performance index for the entire board is calculated, the distribution range and fluctuation range of each index are statistically analyzed, and the coefficient of variation of the performance index is calculated. This determines the overall stability and compliance of the structural performance, marks weak areas where local structural performance fails to meet standards, and generates structural performance data covering the entire board space. The third category is interface homogeneity data from the simulation evolution of insulation board production. This involves extracting the fiber-matrix interface bonding strength and pore wall interface strength data for each grid cell within the entire computational domain after curing and shaping. The average value of the interface performance index for the entire board is calculated, the fluctuation range and distribution range of interface performance are statistically analyzed, and the coefficient of variation of interface performance is calculated. This determines the overall homogeneity of the interface structure, marks abnormal areas with weak interface bonding, and generates interface homogeneity data covering the entire board space. All three types of core structural feature data are bound to corresponding spatial coordinates. At the same time, combined with the structural evolution time series data within the entire simulation cycle, the time series dimension of the feature data is supplemented, and finally, structural feature data of insulation board production simulation evolution that is complete in spatiotemporal dimensions and covers all structural features of the insulation board is generated.

[0049] Furthermore, the structural feature data of the insulation board production simulation evolution mentioned in step S36 includes the pore density distribution data of the insulation board production simulation evolution, the structural performance data of the insulation board production simulation evolution, and the interface homogeneity data of the insulation board production simulation evolution.

[0050] Furthermore, step S4 includes the following steps: Step S41: Analyze the distribution of insulation board production deviation characteristics based on the structural feature data of the insulation board production simulation evolution, and generate insulation board production deviation characteristic distribution data. In this embodiment of the invention, the structural feature data of the insulation board production simulation evolution includes three core data categories: pore density distribution data, structural performance data, and interface homogeneity data. All data are bound to the hexahedral grid spatial coordinates within the computational domain of a standard 2440mm×1220mm×120mm board, achieving complete alignment with the spatial and index dimensions of the standard structural feature values ​​of qualified insulation board products. The standard structural feature values ​​of qualified insulation board products are derived from the average values ​​of finished product tests of a priori qualified batch that perfectly matches the current production line, product specifications, and formula system. These values ​​also meet the performance index requirements of the national standards for building insulation boards. The standard values ​​are mapped dimensionally using the same grid spatial coordinates as the simulation data, with each grid cell corresponding to a unique standard structural feature value. The analysis process uses a single grid cell as the smallest analysis unit. For each grid cell, the absolute and relative deviations between the simulation calculated values ​​and the corresponding standard values ​​are calculated for the three core structural feature data categories. The absolute deviation is the difference between the simulation calculated value and the standard value, and the relative deviation is the ratio of the absolute deviation to the standard value. A relative deviation with an absolute value within 5% is considered a qualified deviation; a relative deviation with an absolute value between 5% and 10% is considered a minor deviation; and a relative deviation with an absolute value exceeding 10% is considered a severe deviation. All deviation calculation results are bound to the corresponding grid spatial coordinates, structural feature index type, and deviation level. Based on this, continuous distribution curves of deviations for the three core indicators are plotted along the length, width, and thickness directions of the board. The percentage of grids with different deviation levels, the concentrated distribution areas of deviations, and the deviation propagation paths are statistically analyzed across the entire calculation domain. This distinguishes between systematic deviations across the entire board and random deviations in local areas, clarifying the production section origin corresponding to different types of deviations. All deviation analysis results are categorized and integrated according to structural feature index type, deviation level, and spatial distribution area, generating insulation board production deviation characteristic distribution data with complete spatial dimensions, comprehensive index coverage, and clearly defined deviation types.

[0051] Step S42: Analyze the distribution of the sensitivity of insulation board production adjustment based on the distribution data of the insulation board production deviation characteristics, and generate the distribution data of the sensitivity of insulation board production adjustment. In this embodiment of the invention, the set of adjustment parameters for insulation board production is divided into three fixed dimensions: raw material formulation parameters, production process parameters, and production environment parameters. The raw material formulation parameters include five indicators: cement content, fly ash content, foaming agent content, foam stabilizer content, and polypropylene fiber content. The production process parameters include four indicators: mixer speed, mixer duration, slurry spreading speed, and number of mold spreading layers. The production environment parameters include two indicators: ambient temperature and relative humidity of the production area. All adjustment parameters correspond to control points that can be executed on the production line, and the parameter adjustment range is derived from the safety process boundaries defined by prior production data. The analysis process focuses on severe and mild deviations in the distribution data of insulation board production deviation characteristics. A response relationship model between adjustment parameters and structural characteristic indicators is established based on prior production data. The response relationship model clarifies the change in structural characteristic indicators corresponding to a unit change in a single adjustment parameter. For each type of deviation index, a sensitivity coefficient is calculated for each adjustment parameter. The sensitivity coefficient is the ratio of the rate of change of the structural characteristic index to the rate of change of the adjustment parameter. A sensitivity coefficient greater than 1 is considered a high-sensitivity parameter, a sensitivity coefficient between 0.5 and 1 is considered a medium-sensitivity parameter, and a sensitivity coefficient less than 0.5 is considered a low-sensitivity parameter. Based on this, and considering the spatial distribution characteristics of the deviation, the sensitivity coefficient of each adjustment parameter to deviation indices in different spatial regions is calculated, clarifying the distribution of high-sensitivity adjustment parameters corresponding to deviations in different regions. All sensitivity calculation results are bound to the corresponding deviation index type, spatial grid coordinates, adjustment parameter type, and sensitivity level. All sensitivity analysis results are categorized and integrated according to deviation level, spatial distribution region, and adjustment parameter sensitivity level, generating insulation board production adjustment sensitivity distribution data that fully matches the deviation characteristic distribution data and covers all adjustment parameters and all spatial regions.

[0052] Step S43: Analyze the insulation board production optimization adjustment using the insulation board production deviation characteristic distribution data and the insulation board production adjustment sensitivity distribution data, and generate insulation board production optimization adjustment data. In this embodiment of the invention, processing priorities are determined according to deviation levels, with severe deviations having the highest priority, minor deviations having the second highest priority, and acceptable deviations not requiring adjustment. For each priority deviation index, a highly sensitive adjustment parameter within the corresponding spatial region is selected as the core adjustment object, a moderately sensitive parameter as an auxiliary adjustment object, and a low-sensitivity parameter is not included in the adjustment range. For systemic, full-area deviations, a unified adjustment parameter correction scheme for the entire production line is adopted. For localized, random deviations, a directional adjustment parameter correction scheme for the corresponding production section is adopted. The correction direction of the adjustment parameter corresponds exactly to the deviation direction. When the deviation index is lower than the standard value, the adjustment parameter is corrected in the direction of increasing the index; when the deviation index is higher than the standard value, the adjustment parameter is corrected in the direction of decreasing the index. The correction range of the adjustment parameter is strictly limited within the safety process boundary defined by prior production data, and the single correction range does not exceed 10% of the parameter adjustment range. At the same time, the effect of the corrected structural characteristic index deviation control is verified by combining a response relationship model to ensure that the corrected deviation falls within the acceptable deviation range. Based on this, according to three dimensions—raw material formula parameters, production process parameters, and production environment parameters—the correction direction, correction magnitude, corresponding control section, and corresponding deviation type of all adjustment parameters are integrated. The execution sequence and execution conditions of each adjustment parameter are clarified, and all optimized adjustment results are bound to corresponding deviation indicators, spatial regions, production sections, and execution sequences. All optimized adjustment results are categorized and integrated according to parameter dimensions and execution priorities, generating insulation board production optimized adjustment data that covers all production sections, all adjustment parameters, and perfectly matches deviation characteristics.

[0053] Step S44: Perform PLC control drive parsing and mapping processing on the insulation board production optimization and adjustment data to generate insulation board production control parsing and mapping data; In this embodiment of the invention, the control points of the PLC control system of the insulation board production line are bound to the corresponding execution mechanisms of the production line. The control points are divided into four categories: metering execution points, mixing execution points, material distribution execution points, and environmental control points. The metering execution points correspond to the frequency converters of the cement screw feeder, fly ash screw feeder, foaming agent metering pump, foam stabilizer metering pump, and fiber feeder controller. The mixing execution points correspond to the frequency converters of the main motor and auxiliary motor of the mixer. The material distribution execution points correspond to the frequency converters of the walking motor of the material distribution machine and the material distribution machine discharge port controller. The environmental control points correspond to the air conditioning controller and humidifier controller of the production area. All control points have a unique physical address, control type, adjustment range, and response time calibration value. The parsing and mapping process uses insulation board production optimization adjustment data as input. Based on the type of adjustment parameter and its corresponding production section, it matches the corresponding PLC control point, establishing a mapping relationship between the process optimization adjustment parameters and the PLC control point setpoints. The linear coefficient of the mapping relationship comes from the on-site calibration results of prior production data, which clearly defines the linear correspondence between process parameter values ​​and control point setpoints. For raw material formula parameters, the dosage adjustment value is mapped to the inverter frequency setpoint and feeding time setpoint of the corresponding metering execution point; for production process parameters, the adjustment value is mapped to the inverter frequency setpoint and running time setpoint of the corresponding mixing execution point and material distribution execution point; for production environment parameters, the adjustment value is mapped to the temperature setpoint and humidity setpoint of the corresponding environmental control point. Based on this, the adjustment boundary, response time, and execution conditions of each mapping relationship are defined. All mapping relationships are bound to the corresponding optimized adjustment parameters, PLC control point addresses, control types, linear mapping coefficients, and adjustment boundaries. All mapping relationships are categorized and integrated according to control point type and production section, generating insulation board production control parsing mapping data that fully matches process parameters and PLC control instructions and can be directly parsed and executed.

[0054] Step S45: Perform PLC-level control logic analysis on the parsing mapping data of insulation board production control to generate insulation board production level control logic data; In this embodiment of the invention, the PLC hierarchical control logic is divided into three fixed levels according to the production line process flow and control priority: the full-line control layer, the section control layer, and the equipment control layer. The full-line control layer has the highest priority, the section control layer has the second highest priority, and the equipment control layer has the lowest priority. The three levels complete the bidirectional transmission and interlocking control of up and down data. The full-line control layer covers the linkage control, safety interlocking control, and production cycle control of the entire insulation board production process. The control scope includes the timing linkage, abnormal condition interlocking shutdown, and production line operation cycle adjustment of the entire process of raw material pretreatment, mixing, spreading, and curing. The section control layer is divided into four independent control units according to the production section: raw material pretreatment section, mixing section, spreading section, and curing section. Each control unit covers the linkage control, process timing control, and abnormal interlocking control of all equipment in the corresponding section. The equipment control layer covers the independent control of a single actuator, including start / stop control, parameter adjustment, status feedback, and single-point abnormal protection of the corresponding control point. The analysis process categorizes all control points in the insulation board production control parsing and mapping data, assigning them to corresponding production sections and control functions according to their respective levels. It clarifies the linkage timing, execution sequence, and data feedback path of control points within each level, and outlines the rules for upward and downward data transmission between levels. The entire line control layer issues control commands to the section control layer, the section control layer issues execution commands to the equipment control layer, the equipment control layer reports its operating status to the section control layer, and the section control layer reports its section operating status to the entire line control layer. Based on this, the interlocking trigger conditions and interlocking execution logic for each level are defined. An anomaly in a single piece of equipment triggers an interlock at the equipment control layer; an anomaly in multiple pieces of equipment within a section triggers an interlock at the section control layer; and an anomaly in the entire line's process sequence triggers an interlock at the entire line control layer. All control logic is bound to its corresponding level, control point, execution sequence, and interlocking conditions. All hierarchical control logic is categorized and integrated according to control level and production section, generating insulation board production hierarchical control logic data with clear priorities, well-defined timing, and comprehensive interlocking.

[0055] Step S46: Analyze the real-time production demand status of insulation boards based on the production level control logic data of insulation boards, and generate real-time production status demand data of insulation boards. In this embodiment of the invention, the input data includes real-time operating status data of the production line, real-time characteristic data of the raw materials of the current production batch, current production progress node data, and hierarchical control logic data of the insulation board production. The real-time operating status data of the production line comes from the real-time status feedback of each actuator of the production line, including equipment operating parameters, real-time set values ​​of control points, and equipment operating status. The real-time characteristic data of the raw materials of the current production batch comes from the synchronously collected data of the sensor monitoring cluster equipment, including raw material particle size, bulk density, moisture content, slurry viscosity, and homogeneity index. The current production progress node data is divided into four fixed stages according to the production line process flow: raw material metering stage, raw material mixing stage, slurry distribution stage, and initial setting and curing stage. Each stage corresponds to a clear hierarchical control logic and control objective. The analysis process first identifies the current production stage. Combining this with the insulation board production hierarchy control logic data, the core control objectives for the three control levels corresponding to the current stage are clarified. The core control objective for the entire production line control level is time sequence matching across all work sections and stable production cycle time. The core control objective for the work section control level is achieving the corresponding work section's process parameters and ensuring normal equipment linkage within the work section. The core control objective for the equipment control level is achieving the corresponding actuator's control accuracy and ensuring normal operation. Based on this, the gap between the real-time production line operation data and the corresponding level control objectives is compared. Combined with the deviation between the current batch of raw material real-time characteristic data and the standard raw material characteristics, the data is prioritized according to control level, clarifying the production status objectives that each level needs to achieve in the current stage. Each production status objective corresponds to a specific indicator threshold, completion deadline, and priority. All production status requirements are bound to the corresponding control level, production stage, indicator type, and priority. All production status requirements are categorized and integrated according to control level and priority, generating real-time insulation board production status requirement data that perfectly matches the current production status, is highly real-time, and has clearly defined objectives.

[0056] Step S47: Perform real-time correction parameter analysis on the production status requirement data of the instant insulation board to generate real-time correction parameters for the hierarchical control of the insulation board. In this embodiment of the invention, the production status requirements data of the insulation board are sorted by priority. The highest priority requirements are analyzed for correction parameters first, and the next highest priority requirements are analyzed for correction parameters later. The analysis process matches the control points of the corresponding control level and the highly sensitive adjustment parameters in the distribution data of the adjustment sensitivity of the insulation board production, and is carried out in combination with the safety process boundary of the current production stage. To meet the production status requirements of the entire control layer, control points and corresponding highly sensitive adjustment parameters are matched. The corrected parameters cover the production line's operating cycle time, the timing matching parameters of all work sections, and the temperature and humidity parameters of the curing environment. The correction range is strictly limited within the overall control safety boundary defined by prior production data. For the production status requirements of the work section control layer, control points and corresponding highly sensitive adjustment parameters are matched for the corresponding work section. The corrected parameters cover the mixing speed, mixing duration, material feeding speed, and equipment linkage timing parameters within the corresponding work section. The correction range is strictly limited within the process safety boundary of the corresponding work section. For the production status requirements of the equipment control layer, control points and corresponding highly sensitive adjustment parameters are matched for the corresponding actuators. The corrected parameters cover the inverter frequency, feeding duration, and operating speed parameters of the corresponding metering equipment. The correction range is strictly limited within the rated operating range of the corresponding equipment. Based on this, the interlock compatibility of all correction parameters with the hierarchical control logic is verified to ensure that the execution of correction parameters does not trigger safety interlocks. The execution sequence, execution duration, and feedback cycle of each correction parameter are clearly defined, and all correction parameters are bound to the corresponding control level, control point, corresponding production requirement, and execution sequence. All correction parameters are categorized and integrated according to control level and execution priority to generate real-time correction parameters for insulation board hierarchical control that fully match the immediate production requirements, conform to the hierarchical control logic, and can be directly executed.

[0057] Step S48: Design the intelligent optimization control relationship for insulation board production by using the control logic data of the insulation board production level and the real-time correction parameters of the insulation board level control, and generate the intelligent optimization control engine for insulation board production.

[0058] In this embodiment of the invention, the intelligent optimization control relationship design uses the control logic data of the insulation board production level as the basis for a fixed control framework, and the real-time correction parameters of the insulation board level control as the dynamic adjustment input to construct a fully closed-loop real-time intelligent optimization control system. The fixed control cycle of the control system is 100ms, and each control cycle completes one full-process control execution and status update. The control system is functionally divided into four fixed execution modules: a real-time data acquisition module, a dynamic deviation analysis module, a parameter optimization and correction module, and a control command output module. The four modules are executed sequentially according to a fixed timing within the control cycle, and bidirectional data transmission is completed between the modules. The real-time data acquisition module interfaces with the sensor monitoring cluster equipment and the production line PLC control system, synchronously acquiring raw material characteristic data, environmental data, and real-time production line operating status data, with complete synchronization between data acquisition and control cycles. The dynamic deviation analysis module interfaces with the real-time acquired data and product standard structural feature values, calculating the deviation characteristic distribution of the current production status in real time, and clarifying the deviation type, deviation level, and spatial distribution. The parameter optimization and correction module interfaces with real-time deviation data, adjustment sensitivity distribution data, and hierarchical control logic data, generating real-time hierarchical control correction parameters, clarifying the correction direction and magnitude of adjustment parameters at each level. The control command output module interfaces with hierarchical control logic data and real-time correction parameters, issuing the corrected control commands to the corresponding PLC control points according to the control level, driving the actuators to complete the corresponding adjustment actions. Based on this, the safety interlock trigger mechanism, emergency handling logic for abnormal working conditions, and control boundary locking rules of the control system are clearly defined to ensure the operational stability and safety of the control engine. The execution sequence, data transmission path, and control logic of all modules are fixedly encapsulated. The resulting intelligent optimization control engine for insulation board production can independently complete real-time data acquisition, deviation analysis, parameter optimization, and control command output throughout the entire insulation board production process, and execute complete intelligent optimization operations for insulation board production.

[0059] This specification provides an intelligent optimization system for insulation board production based on raw material characteristics, used to execute the intelligent optimization method for insulation board production based on raw material characteristics as described above. The intelligent optimization system for insulation board production based on raw material characteristics includes: The insulation board raw material distribution attribute analysis module is used to monitor and process data on the environmental and raw material characteristics of the target area of ​​the insulation board production control operation using sensor monitoring cluster equipment, and generate environmental data and insulation board raw material characteristic data respectively; based on the environmental data and insulation board raw material characteristic data, the module performs distribution attribute feature analysis of insulation board raw materials, and generates insulation board raw material distribution attribute feature data. The raw material characteristic reaction behavior analysis module is used to analyze the reaction behavior of raw material characteristics based on the distribution attribute characteristic data of insulation board raw materials, and generate raw material characteristic reaction behavior data. The insulation board simulation evolution structure analysis module is used to analyze the reaction behavior data of raw material characteristics and the structural characteristics of insulation board production simulation evolution, and generate insulation board production simulation evolution structure characteristic data. The intelligent optimization control module for insulation board production is used to design intelligent optimization control relationships for insulation board production based on the structural feature data of insulation board production simulation evolution, and to generate an intelligent optimization control engine for insulation board production. The intelligent optimization control engine for insulation board production is used to execute intelligent optimization operations for insulation board production.

[0060] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0061] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A smart optimization method for the production of insulation boards based on raw material characteristics, characterized in that, Includes the following steps: Step S1: Use sensor monitoring cluster equipment to monitor and process the environmental and raw material characteristics of the target area for insulation board production control, and generate environmental data and raw material characteristic data for insulation board production respectively; based on the environmental data and raw material characteristic data for insulation board production, perform raw material distribution attribute feature analysis to generate raw material distribution attribute feature data for insulation board. Step S2: Analyze the reaction behavior of the raw materials based on the distribution attribute characteristic data of the insulation board raw materials to generate raw material characteristic reaction behavior data; Step S3: Analyze the structural characteristics of the reaction behavior of raw materials in the simulation of insulation board production to generate structural characteristic data of insulation board production simulation. Step S4: Based on the structural feature data of the insulation board production simulation evolution, design the intelligent optimization control relationship for insulation board production and generate an intelligent optimization control engine for insulation board production. The intelligent optimization control engine for insulation board production is used to execute intelligent optimization operations for insulation board production.

2. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Use sensor monitoring cluster equipment to monitor and process the environmental and raw material characteristics of the target area of ​​the insulation board production control operation, and generate environmental data and raw material characteristic data of insulation board production respectively. Step S12: Perform anomaly correction and adjustment on the raw material characteristic data for insulation board production to generate standard raw material characteristic data for insulation board production; Step S13: Analyze the physical characteristics of raw material distribution in the standard insulation board production raw material characteristic data to generate physical characteristic data of raw material distribution in the insulation board; Step S14: Based on environmental data and standard insulation board production raw material characteristic data, perform dynamic humidity characteristic analysis of insulation board raw materials to generate dynamic humidity characteristic data of insulation board raw materials. Step S15: Analyze the distribution attribute characteristics of insulation board raw materials based on the physical characteristics data of the distribution of insulation board raw materials and the dynamic characteristics data of the humidity of insulation board raw materials, and generate the distribution attribute characteristic data of insulation board raw materials.

3. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 2, characterized in that, Step S12 includes the following steps: Based on the raw material characteristic data of insulation board production, spatial distribution raw material characteristic analysis is performed to generate spatial distribution characteristic data of insulation board raw materials. By analyzing the spatial distribution characteristics of insulation board raw materials, neighborhood spatial distribution characteristics data is generated, and the collection anomaly detection and processing of insulation board raw material characteristics is performed based on the neighborhood spatial distribution characteristics data, generating insulation board raw material characteristic collection anomaly data. Abnormal data collected from the characteristics of insulation board raw materials are used to correct and adjust the abnormal data of the raw material characteristics of insulation board production, thereby generating standard raw material characteristic data for insulation board production.

4. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 3, characterized in that, Step S14 includes the following steps: Extracting moisture data of raw materials for standard insulation board production; Based on the humidity data of the insulation board raw materials, a time-series characteristic analysis of the humidity of the insulation board raw materials is performed to generate time-series characteristic data of the humidity of the insulation board raw materials. By performing environmental dynamic compensation processing on the humidity time-series characteristic data of insulation board raw materials using environmental data, dynamic characteristic data of humidity of insulation board raw materials is generated.

5. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Perform raw material characteristic distribution coupling relationship analysis based on the raw material distribution attribute characteristic data of the insulation board to generate raw material characteristic distribution coupling relationship data; Step S22: Perform graph convolution aggregation relationship analysis on the coupling effect of raw material characteristic distribution based on the raw material characteristic distribution coupling relationship data to generate raw material characteristic distribution coupling relationship data; Step S23: Extract quantitative features of raw material distribution attributes from the raw material distribution attribute feature data of the insulation board to obtain quantitative feature data of raw material distribution attributes; Step S24: Utilize the raw material characteristic distribution coupling relationship data to perform interface coupling characteristic analysis on the quantitative characteristic data of raw material distribution attributes, and generate raw material characteristic interface coupling characteristic data; Step S25: Analyze the distribution characteristics of the porosity effect at the raw material interface based on the characteristic data of the coupling effect at the raw material interface, and generate the distribution characteristic data of the porosity effect at the raw material interface. Step S26: Analyze the reaction behavior of raw materials by using the characteristic data of the coupling effect between raw material properties and the characteristic data of the distribution of porosity at the raw material properties interface, and generate raw material property reaction behavior data.

6. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 5, characterized in that, The characteristic data of the interface coupling effect of raw material properties mentioned in step S24 include raw material property hydration reaction rate data, raw material property foaming volume expansion data, and raw material property interface strength data.

7. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Perform reaction kinetic analysis on the reaction behavior data of the raw materials to generate reaction kinetic data of the raw materials. Step S32: Obtain preliminary production data for the insulation board; Step S33: Based on the prior production data of the insulation board, perform multiphase fluid simulation evolution processing on the raw material characteristic reaction kinetic data to generate multiphase fluid simulation evolution data of the insulation board. Step S34: Perform thermo-mechanical finite element simulation reaction field analysis based on the raw material characteristic reaction kinetic data and the insulation board multiphase fluid simulation evolution data to generate thermo-mechanical finite element simulation reaction field data; Step S35: Perform structural field analysis of the curing effect of the insulation board based on the thermal-mechanical finite element simulation reaction field data, and generate structural field data of the curing effect of the insulation board; Step S36: Analyze the structural characteristics of the insulation board production simulation evolution using the structural field data of the insulation board curing effect, and generate structural characteristic data of the insulation board production simulation evolution.

8. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 7, characterized in that, The structural feature data of the insulation board production simulation evolution mentioned in step S36 includes the pore density distribution data of the insulation board production simulation evolution, the structural performance data of the insulation board production simulation evolution, and the interface homogeneity data of the insulation board production simulation evolution.

9. The intelligent optimization method for insulation board production based on raw material characteristics according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Analyze the distribution of insulation board production deviation characteristics based on the structural feature data of the insulation board production simulation evolution, and generate insulation board production deviation characteristic distribution data. Step S42: Analyze the distribution of the sensitivity of insulation board production adjustment based on the distribution data of the insulation board production deviation characteristics, and generate the distribution data of the sensitivity of insulation board production adjustment. Step S43: Analyze the insulation board production optimization adjustment using the insulation board production deviation characteristic distribution data and the insulation board production adjustment sensitivity distribution data, and generate insulation board production optimization adjustment data. Step S44: Perform PLC control drive parsing and mapping processing on the insulation board production optimization and adjustment data to generate insulation board production control parsing and mapping data; Step S45: Perform PLC-level control logic analysis on the parsing mapping data of insulation board production control to generate insulation board production level control logic data; Step S46: Analyze the real-time production demand status of insulation boards based on the production level control logic data of insulation boards, and generate real-time production status demand data of insulation boards. Step S47: Perform real-time correction parameter analysis on the production status requirement data of the instant insulation board to generate real-time correction parameters for the hierarchical control of the insulation board. Step S48: Design the intelligent optimization control relationship for insulation board production by using the control logic data of the insulation board production level and the real-time correction parameters of the insulation board level control, and generate the intelligent optimization control engine for insulation board production.

10. A smart optimization system for insulation board production based on raw material characteristics, characterized in that, For executing the intelligent optimization method for insulation board production based on raw material characteristics as described in claim 1, the intelligent optimization system for insulation board production based on raw material characteristics includes: The insulation board raw material distribution attribute analysis module is used to monitor and process data on the environmental and raw material characteristics of the target area of ​​the insulation board production control operation using sensor monitoring cluster equipment, and generate environmental data and insulation board raw material characteristic data respectively; based on the environmental data and insulation board raw material characteristic data, the module performs distribution attribute feature analysis of insulation board raw materials, and generates insulation board raw material distribution attribute feature data. The raw material characteristic reaction behavior analysis module is used to analyze the reaction behavior of raw material characteristics based on the distribution attribute characteristic data of insulation board raw materials, and generate raw material characteristic reaction behavior data. The insulation board simulation evolution structure analysis module is used to analyze the reaction behavior data of raw material characteristics and the structural characteristics of insulation board production simulation evolution, and generate insulation board production simulation evolution structure characteristic data. The intelligent optimization control module for insulation board production is used to design intelligent optimization control relationships for insulation board production based on the structural feature data of insulation board production simulation evolution, and to generate an intelligent optimization control engine for insulation board production. The intelligent optimization control engine for insulation board production is used to execute intelligent optimization operations for insulation board production.

Images