Three-dimensional simulation design method and system based on rock wool curtain wall plate structure

Abstract

The invention relates to the technical field of wallboard simulation design, in particular to a three-dimensional simulation design method and system based on a rock wool curtain wallboard structure. The method comprises the following steps: acquiring microstructure source data of the wallboard; performing isotropic microscopic feature enhancement on the wallboard microscopic morphology source data to obtain wallboard microscopic fiber morphology data; digital twinning reconstruction is carried out on the rock wool curtain wall board based on the wallboard microfiber morphology data, and a first wallboard reconstruction structure model is obtained; performing thermodynamic field mapping on the first wallboard reconstruction structure model to obtain a micro-scale heat conduction characteristic pattern; performing cross-scale physical field coupling superposition on the micro-scale heat conduction characteristic pattern to obtain a wallboard multi-field comprehensive response diagram; and performing cross-scale performance dynamic simulation on the rock wool curtain wall plate based on the wallboard multi-field comprehensive response diagram to obtain a wallboard comprehensive performance evaluation result. Customized design of the rock wool curtain wall plate can be achieved, and design flexibility and applicability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wall panel simulation design, and in particular to a three-dimensional simulation design method and system based on a rock wool curtain wall panel structure. Background Art

[0002] The design of rock wool curtain wall panels involves multiple complex factors, such as structural stability, thermal insulation performance, and fire safety. In the existing three-dimensional simulation design methods, how to accurately simulate the performance of rock wool curtain wall panels under different environmental conditions is a major challenge. For example, under extreme climate conditions, such as high temperature, low temperature, or high humidity, the thermal insulation performance and structural stability of rock wool curtain wall panels will be significantly affected. However, existing simulation software often finds it difficult to accurately simulate the long-term impact of these environmental factors on the performance of curtain wall panels, resulting in a large deviation between the design results and the actual performance. This deviation will not only cause the performance of the curtain wall system to deteriorate in actual use, but also increase the cost of subsequent maintenance and replacement. In practical applications, the design of rock wool curtain wall panels also needs to consider various factors in the construction process, such as installation accuracy, material selection, and construction technology. These factors have an important impact on the final performance of the curtain wall system. However, the existing three-dimensional simulation design methods often ignore the details of these construction processes, resulting in a large difference between the design results and the actual construction situation. For example, during the installation process, if the connection between the curtain wall panel and the steel structure is not tight or there is a deviation, it will directly affect the thermal insulation performance and structural stability of the curtain wall system. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a three-dimensional simulation design method and system based on a rock wool curtain wall panel structure to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a three-dimensional simulation design method based on rock wool curtain wall panel structure includes the following steps:

[0005] Step S1: obtaining wall panel micro-morphology source data; performing isotropic micro-feature enhancement on the wall panel micro-morphology source data to obtain wall panel micro-fiber morphology data; performing digital twin reconstruction of the rock wool curtain wall panel based on the wall panel micro-fiber morphology data to obtain a first wall panel reconstructed structural model;

[0006] Step S2: performing thermodynamic field mapping on the reconstructed structural model of the first wall panel to obtain a micro-scale heat conduction characteristic map; performing cross-scale physical field coupling superposition on the micro-scale heat conduction characteristic map to obtain a multi-field comprehensive response map of the wall panel; performing cross-scale performance dynamic simulation on the rock wool curtain wall panel based on the multi-field comprehensive response map of the wall panel to obtain a comprehensive performance evaluation result of the wall panel;

[0007] Step S3: obtaining a wall panel construction process parameter set; performing a construction error evaluation on the wall panel construction process parameter set to obtain a wall panel construction error index set;

[0008] Step S4: reconstructing the performance boundary conditions of the rock wool curtain wall panel according to the comprehensive performance evaluation results of the wall panel to obtain a reconstructed structural model of the second wall panel; performing extreme environment multi-scenario simulation on the reconstructed structural model of the second wall panel based on the wall panel construction error index set to obtain multi-scenario performance response data of the wall panel; performing fatigue failure risk assessment on the rock wool curtain wall panel according to the multi-scenario performance response data of the wall panel to obtain a prediction result of wall panel performance degradation;

[0009] Step S5: extract target optimization factors from the wall panel performance degradation prediction results to obtain key design adjustment factors of the wall panels; optimize the structural parameters of the rock wool curtain wall panels according to the key design adjustment factors of the wall panels to obtain a wall panel performance enhancement design scheme; reconstruct the second wall panel reconstructed structural model according to the wall panel performance enhancement design scheme to obtain an optimized wall panel three-dimensional simulation model.

[0010] The present invention can more accurately simulate the microstructure of the rock wool curtain wall panel by acquiring the microscopic morphology source data of the rock wool curtain wall panel and performing isotropic microscopic feature enhancement, thereby improving the accuracy of the simulation. This helps to reduce the deviation between the design result and the actual performance, and improve the performance and reliability of the curtain wall system. By performing thermodynamic field mapping and cross-scale physical field coupling superposition on the first wall panel reconstruction structure model, the thermal conductivity characteristics and multi-field comprehensive response of the wall panel under different environmental conditions can be comprehensively evaluated, thereby optimizing the structural design and enhancing the structural stability of the rock wool curtain wall panel. By performing cross-scale performance dynamic simulation on the rock wool curtain wall panel, the comprehensive performance evaluation result of the wall panel can be obtained, which helps to fully understand the performance of the material in practical applications and provide a scientific basis for the design. By obtaining the wall panel construction process parameter set and performing construction error evaluation, the error in the construction process can be quantified, data support can be provided for construction quality control, and the impact of construction errors on the performance of the curtain wall system can be reduced. Based on the wall panel construction error index set, the second wall panel reconstruction structure model is simulated in multiple scenarios in extreme environments, and the performance response of the wall panel in extreme environments can be predicted, thereby improving the environmental adaptability and durability of the rock wool curtain wall panel. By performing fatigue failure risk assessment on multi-scenario performance response data of wall panels, the performance degradation of wall panels can be predicted. By extracting target optimization factors from the wall panel performance degradation prediction results, key design adjustment factors can be identified, and the structural parameters of the rock wool curtain wall panels can be optimized, thereby obtaining a performance-enhanced design solution and improving the overall performance of the curtain wall system. The second wall panel reconstruction structural model is reconstructed according to the wall panel performance enhancement design solution. The present invention can realize customized design of rock wool curtain wall panels, meet the needs of specific projects, and improve the flexibility and applicability of the design.

[0011] Preferably, the present invention further provides a three-dimensional simulation design system based on a rock wool curtain wall panel structure, which is used to execute the three-dimensional simulation design method based on a rock wool curtain wall panel structure as described above. The three-dimensional simulation design system based on a rock wool curtain wall panel structure comprises:

[0012] The digital twin module is used to obtain the wall panel micro-morphology source data; perform isotropic micro-feature enhancement on the wall panel micro-morphology source data to obtain the wall panel micro-fiber morphology data; perform digital twin reconstruction of the rock wool curtain wall panel based on the wall panel micro-fiber morphology data to obtain the first wall panel reconstructed structural model;

[0013] The performance simulation module is used to perform thermodynamic field mapping on the reconstructed structural model of the first wall panel to obtain a micro-scale heat conduction characteristic map; perform cross-scale physical field coupling and superposition on the micro-scale heat conduction characteristic map to obtain a multi-field comprehensive response map of the wall panel; perform cross-scale performance dynamic simulation of the rock wool curtain wall panel based on the multi-field comprehensive response map of the wall panel to obtain a comprehensive performance evaluation result of the wall panel;

[0014] The error evaluation module is used to obtain a wall panel construction process parameter set; perform construction error evaluation on the wall panel construction process parameter set to obtain a wall panel construction error index set;

[0015] The risk assessment module is used to reconstruct the performance boundary conditions of the rock wool curtain wall panel according to the comprehensive performance evaluation results of the wall panel to obtain the reconstructed structural model of the second wall panel; perform extreme environment multi-scenario simulation on the reconstructed structural model of the second wall panel based on the wall panel construction error index set to obtain the multi-scenario performance response data of the wall panel; perform fatigue failure risk assessment on the rock wool curtain wall panel according to the multi-scenario performance response data of the wall panel to obtain the wall panel performance degradation prediction results;

[0016] The simulation model reconstruction module is used to extract the target optimization factors of the wall panel performance degradation prediction results to obtain the key design adjustment factors of the wall panels; optimize the structural parameters of the rock wool curtain wall panels according to the key design adjustment factors of the wall panels to obtain the wall panel performance enhancement design scheme; reconstruct the second wall panel reconstruction structural model according to the wall panel performance enhancement design scheme to obtain the optimized wall panel three-dimensional simulation model.

[0017] The present invention improves design efficiency and accuracy through automated module design, reduces human errors and repetitive work, and enhances the accuracy of design results by accurately acquiring and processing micro-morphological data. The system is capable of comprehensive performance simulation, including thermodynamic field mapping and the generation of multi-field comprehensive response diagrams, providing a comprehensive perspective for the performance analysis of rock wool curtain wall panels. The risk assessment module predicts performance degradation in extreme environments, providing a scientific basis for risk management and maintenance strategies. The simulation model reconstruction module extracts key design adjustment factors based on the performance degradation prediction results, optimizes structural parameters, and enhances overall performance. The system can also provide customized design solutions to meet specific engineering needs, reduce maintenance costs, improve reliability and safety, and enhance environmental adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present invention will become more apparent from the detailed description made with reference to the following drawings:

[0019] Figure 1 A schematic flow chart of the steps of a three-dimensional simulation design method based on a rock wool curtain wall panel structure according to an embodiment is shown.

[0020] Figure 2 A detailed flowchart diagram of step S17 of an embodiment is shown.

[0021] Figure 3 A detailed flowchart diagram of step S265 of an embodiment is shown. DETAILED DESCRIPTION

[0022] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve this, please refer to Figures 1 to 3 The present invention provides a three-dimensional simulation design method based on a rock wool curtain wall panel structure, comprising the following steps:

[0026] Step S1: obtaining wall panel micro-morphology source data; performing isotropic micro-feature enhancement on the wall panel micro-morphology source data to obtain wall panel micro-fiber morphology data; performing digital twin reconstruction of the rock wool curtain wall panel based on the wall panel micro-fiber morphology data to obtain a first wall panel reconstructed structural model;

[0027] Step S2: performing thermodynamic field mapping on the reconstructed structural model of the first wall panel to obtain a micro-scale heat conduction characteristic map; performing cross-scale physical field coupling superposition on the micro-scale heat conduction characteristic map to obtain a multi-field comprehensive response map of the wall panel; performing cross-scale performance dynamic simulation on the rock wool curtain wall panel based on the multi-field comprehensive response map of the wall panel to obtain a comprehensive performance evaluation result of the wall panel;

[0028] Step S3: obtaining a wall panel construction process parameter set; performing a construction error evaluation on the wall panel construction process parameter set to obtain a wall panel construction error index set;

[0029] Step S4: reconstructing the performance boundary conditions of the rock wool curtain wall panel according to the comprehensive performance evaluation results of the wall panel to obtain a reconstructed structural model of the second wall panel; performing extreme environment multi-scenario simulation on the reconstructed structural model of the second wall panel based on the wall panel construction error index set to obtain multi-scenario performance response data of the wall panel; performing fatigue failure risk assessment on the rock wool curtain wall panel according to the multi-scenario performance response data of the wall panel to obtain a prediction result of wall panel performance degradation;

[0030] Step S5: extract target optimization factors from the wall panel performance degradation prediction results to obtain key design adjustment factors of the wall panels; optimize the structural parameters of the rock wool curtain wall panels according to the key design adjustment factors of the wall panels to obtain a wall panel performance enhancement design scheme; reconstruct the second wall panel reconstructed structural model according to the wall panel performance enhancement design scheme to obtain an optimized wall panel three-dimensional simulation model.

[0031] In this embodiment, the microstructure of the rock wool curtain wall panel is first imaged using a scanning electron microscope (SEM) to obtain high-resolution image data, and the image analysis software ImageJ is used for image preprocessing and analysis. Subsequently, the SEM image is processed by applying a filter and an edge enhancement algorithm in ImageJ to highlight the microstructural features of the fiber, and an isotropic filter is used to enhance the isotropic features of the fiber, thereby obtaining the microscopic fiber morphology data of the wall panel. Then, in the three-dimensional modeling software Rhinoceros 3D, the digital twin model of the rock wool curtain wall panel is reconstructed according to the microscopic fiber morphology data, and the geometric parameters of the model are adjusted using a parametric modeling technique to obtain a first wall panel reconstruction structure model. In COMSOL Multiphysics, a thermodynamic field simulation is performed on the first wall panel reconstruction structure model, a heat conduction analysis is set, material properties and boundary conditions are defined, and a microscale heat conduction characteristic map is obtained by running the simulation, and coupled and superimposed with mechanical and electrical field data to obtain a multi-field comprehensive response map of the wall panel. Based on the multi-field comprehensive response map, a cross-scale performance dynamic simulation is performed to evaluate the comprehensive performance of the rock wool curtain wall panel under different environmental conditions to obtain an evaluation result. At the same time, the key process parameters in the wall panel construction process were collected, and the statistical software SPSS was used for data analysis. Based on the construction process parameter set, the Monte Carlo simulation method was used to evaluate the construction error, and the wall panel construction error index set was obtained. According to the comprehensive performance evaluation results, the performance boundary conditions of the rock wool curtain wall panel were reconstructed in Rhinoceros3D to obtain the reconstructed structural model of the second wall panel, and the extreme environment multi-scenario simulation of the reconstructed structural model of the second wall panel was carried out in COMSOL based on the construction error index set to obtain the multi-scenario performance response data of the wall panel. The fatigue analysis software FESAFE was used to evaluate the fatigue failure risk of the rock wool curtain wall panel based on the multi-scenario performance response data, and the wall panel performance degradation prediction results were obtained. In MATLAB, the machine learning algorithm was used to analyze the performance degradation prediction results, and the key design adjustment factors of the wall panel were extracted. The structural parameters of the rock wool curtain wall panel were optimized in Rhinoceros 3D according to the key design adjustment factors to obtain the wall panel performance enhancement design scheme. Finally, the reconstructed structural model of the second wall panel was reconstructed in Rhinoceros 3D according to the performance enhancement design scheme to obtain the optimized three-dimensional simulation model of the wall panel.

[0032] Preferably, step S1 comprises the following steps:

[0033] Step S11: collecting the three-dimensional morphology of the microstructure of the rock wool curtain wall panel to obtain the wall panel micromorphology source data;

[0034] Specifically, a laser scanner can be used to scan the surface of the rock wool curtain wall panel. The scanner is capable of emitting a laser beam and calculating the spatial coordinates of each point on the surface of the rock wool board by measuring the time and angle at which the laser beam is reflected back. Place the rock wool curtain wall panel on a stable platform to ensure that its surface is flat and unobstructed so that the laser scanner can cover the entire surface. Start the scanner software and set the scanning parameters, including scanning resolution, scanning speed, and scanning range. For example, set the resolution to 0.01 mm to ensure that the tiny details on the surface of the rock wool board can be captured. Start the scanning process, and the laser scanner will move along the preset path to scan the surface of the rock wool board point by point and collect data. After the scan is completed, the software will generate a point cloud data set containing the three-dimensional coordinate information of the surface of the rock wool board. Finally, the point cloud data is imported into professional three-dimensional modeling software, such as Autodesk Maya or SolidWorks, and the point cloud data is converted into a three-dimensional model through the software algorithm to obtain the microscopic morphology source data of the rock wool curtain wall panel.

[0035] Step S12: extracting fiber micro-geometric features from the wallboard micro-morphology source data to obtain a wallboard fiber geometric feature vector set;

[0036] Specifically, professional software such as CloudCompare can be used to convert the wallboard micro-morphology source data into a two-dimensional image, and the two-dimensional image is processed through the OpenCV library of MATLAB or Python, and filters are applied to remove noise and improve image quality. Then, the edges and contours of the fibers are identified by threshold segmentation or edge detection algorithms such as Sobel or Canny algorithms. In the feature extraction stage, the cross-sectional image of the fiber is analyzed, and the diameter of the fiber is determined using a circle fitting or ellipse fitting algorithm. The endpoints are tracked along the center line of the fiber to determine the length of the fiber. The curvature change of the fiber center line is calculated to evaluate the curvature, and the angle between the fiber center line and the reference coordinate system is analyzed to determine the fiber direction. These geometric features are converted into numerical vectors to form a feature vector for each fiber. Finally, the geometric feature vector sets of all fibers are merged to form a wallboard fiber geometric feature vector set.

[0037] Step S13: adjusting the fiber structure topology network of the rock wool curtain wall panel according to the wall panel fiber geometric feature vector set to obtain a wall panel fiber network connection topology diagram;

[0038] Specifically, the set of geometric feature vectors of the wall panel fibers can be input into professional topological analysis software, such as MATLAB or the igraph package of the R language. In the software, each fiber is represented as a node in the network, and the connection between the nodes represents the spatial relationship between the fibers. The length and direction characteristics of the fibers are used to determine the weight of the connection between the nodes. The shortest path algorithm or the minimum spanning tree algorithm in graph theory is applied to optimize the connection between the fibers to ensure the connectivity and structural stability of the network. For example, fibers with shorter lengths and smaller angles can be connected preferentially to simulate the natural aggregation tendency of fibers in rock wool boards. The connection strength of the nodes is adjusted according to the curvature and diameter characteristics of the fibers to reflect the differences in mechanical properties of different fibers. The software will generate a wall panel fiber network connection topology diagram, showing the connection relationship between the fibers and the overall structure of the network.

[0039] Step S14: reconstructing the spatial configuration of the wall panel fiber network connection topology diagram to obtain a wall panel fiber space model;

[0040] Specifically, the wall panel fiber network connection topology diagram can be imported into a 3D modeling software, such as SolidWorks or 3ds Max. In the software, three-dimensional spatial coordinates are assigned to each fiber node according to the connection relationship in the topology diagram. The length and direction characteristics of the fiber are used to determine the specific position of the node in space. A three-dimensional geometric model of the fiber is constructed based on the spatial coordinates and connection relationship of the node. Curves or cylinders are used to represent the fibers to intuitively display the spatial direction and mutual relationship of the fibers. The fiber model is optimized in detail according to actual needs, such as adjusting the thickness and surface texture of the fibers. The constructed wall panel fiber space model is compared with the physical properties of the actual rock wool board, such as density, strength, etc., and the model is adjusted if necessary to ensure the accuracy and practicality of the model. Finally, the wall panel fiber space model is output.

[0041] Step S15: numerically simulate the fiber interface characteristics of the rock wool curtain wall panel based on the wall panel fiber space model to obtain rock wool fiber interface stress-strain coupling data, and evaluate the interface connection strength of the rock wool fiber interface stress-strain coupling data to obtain fiber interface connection strength evaluation data;

[0042] Specifically, the fiber space model of the wall panel can be imported into finite element analysis (FEA) software, such as ANSYS or ABAQUS, which can simulate complex mechanical behavior. In the FEA software, define the material properties of the rock wool fiber, including elastic modulus, Poisson's ratio and yield strength. These parameters can be obtained from experimental data or literature. The fiber space model is meshed to create a finite element mesh for numerical simulation. Select an appropriate mesh size to ensure the accuracy and computational efficiency of the simulation. Set the boundary conditions of the simulation, such as fixing the fiber at one end to simulate the tension or compression of the fiber. Apply the corresponding load according to the actual working conditions, such as tensile force or pressure. Run the FEA software for numerical simulation to calculate the stress and strain distribution of the fiber under a given load. The software will provide stress-strain coupling data of the fiber interface. After the simulation is completed, analyze the obtained stress-strain data to identify stress concentration areas and potential failure points. Use the post-processing tools in the FEA software to analyze the stress-strain coupling data of the fiber interface and evaluate the interface connection strength. The failure criteria of the interface element, such as the maximum stress criterion or the energy release rate criterion, can be used to evaluate the connection strength of the interface. Finally, the fiber interface connection strength evaluation data is output.

[0043] Step S16: quantifying the fiber network toughness of the fiber interface connection strength evaluation data to obtain a fiber network connection capacity index, and isotropically enhancing the microscopic fiber morphology of the rock wool curtain wall panel according to the fiber network connection capacity index to obtain microscopic fiber morphology data of the wall panel;

[0044] Specifically, the fiber interface connection strength assessment data can be imported using material science software, such as MATLAB or Python's NumPy library. Statistical analysis methods, such as analysis of variance (ANOVA), are used to analyze the interface connection strength data to identify key toughness parameters in the fiber network, such as the average connection strength and standard deviation. A suitable toughness quantification model, such as the Weibull distribution model, is selected to fit the interface connection strength data to obtain the toughness parameters of the fiber network, such as shape parameters and scale parameters. According to the parameters of the Weibull distribution model, the toughness quantification indicators of the fiber network, such as reliability and failure probability, are calculated. The wallboard fiber spatial model is imported using three-dimensional modeling software, such as Rhinoceros 3D. According to the toughness quantification indicators, the spatial distribution and connection mode of the fibers are adjusted. For example, if the toughness analysis shows that the connection strength of certain areas is low, the connection capacity of these areas can be enhanced by increasing the fiber density or changing the fiber direction. The fiber network is spatially reorganized using an isotropic enhancement algorithm, such as the K-means clustering algorithm, to ensure the uniform distribution of fibers in all directions, thereby improving the overall performance of the material. Set specific parameter values, for example, increase the fiber density by 10%, or adjust the distribution range of the fiber direction to ±15°, to achieve isotropic feature enhancement. Output the microscopic fiber morphology data of the wallboard after isotropic feature enhancement.

[0045] Step S17: Perform digital twin reconstruction of the rock wool curtain wall panel based on the micro-fiber morphology data of the wall panel to obtain a reconstructed structural model of the first wall panel.

[0046] Specifically, please refer to the sub-steps of step S17 for the detailed implementation process of this embodiment.

[0047] The present invention can obtain fine design data, enhance design details, and improve the accuracy and reliability of the design through the acquisition of microstructure three-dimensional morphology. By extracting the fiber geometric feature vector set, the specific geometric characteristics of the fiber are optimized, and the material use efficiency and structural stability are improved. By optimizing the fiber structure topological network, the connection mode between fibers is improved, and the overall performance of the material is enhanced, especially when subjected to complex stress. The spatial configuration reconstruction makes the obtained model more in line with the actual application requirements, providing an accurate basis for performance simulation and structural design. By numerically simulating the interface characteristics between fibers, stress-strain coupling data is obtained to deeply understand the micromechanical behavior of the material. By evaluating the interface connection strength, identifying weak links, strengthening the design, and improving the structural durability. By quantifying the toughness of the fiber network, the material's impact resistance and deformation ability are improved. The microscopic fiber morphology is enhanced by isotropic characteristics, so that the material performance is more balanced, and the uniformity and reliability are improved. Finally, based on the digital twin reconstruction of the microscopic fiber morphology data, the obtained structural model can truly reflect the material properties and provide an accurate digital model for performance testing and verification.

[0048] Preferably, step S17 comprises the following steps:

[0049] Step S171: constructing a microstructure discrete unit of the rock wool curtain wall panel based on the microfiber morphology data of the wall panel to obtain a microstructure discrete unit set of the wall panel;

[0050] Specifically, the wallboard microfiber morphology data can be imported into computer-aided design (CAD) software, such as AutoCAD or SolidWorks. These data should contain the geometric features of each fiber, such as diameter, length, and spatial coordinates. In the CAD software, discrete units are constructed according to the geometric features of the microfibers. Each fiber can be regarded as a discrete unit, and a cylinder or an elongated cube is used to represent the fiber. The specific operations include: selecting appropriate cylinder parameters, such as setting the diameter to 0.5 mm and the length to 10 mm to simulate the size of the actual rock wool fiber. Using the copy and array functions of the software, these discrete units are arranged according to the spatial distribution in the microfiber morphology data to ensure that the relative positions between the discrete units are consistent with the actual situation. After completing the construction of the discrete units, the meshing tool in the software is used to mesh the entire microstructure. Select a suitable mesh size, such as a mesh size of 1 mm. Finally, the constructed wallboard microstructure discrete unit set is exported as a standard format file (such as STL or OBJ).

[0051] Step S172: topologically reorganize the discrete unit set of the wall panel microstructure to obtain a reconstructed wall panel microstructure prototype;

[0052] Specifically, the discrete unit set of the wall panel microstructure can be imported into 3D modeling software, such as Rhinoceros3D or Blender. These software are capable of handling complex geometric shapes and topological structures. In the software, the discrete unit set is reorganized using topology optimization tools. The specific operations include: selecting a topology optimization algorithm, such as a density-based topology optimization method, and setting the optimization goal to improve the strength and toughness of the structure. According to the mechanical properties of the material and the actual application requirements, set the optimization parameters, such as the maximum allowable material usage of 50%. Run the topology optimization program, and the software will automatically adjust the connection method and arrangement of the discrete units to generate a new microstructure prototype. After obtaining the reconstructed microstructure prototype, use the visualization function of the software to check the connectivity and stability of the structure. If necessary, the position or connection method of some discrete units can be manually adjusted. Finally, the reconstructed wall panel microstructure prototype is exported as a standard format file (such as STEP or IGES).

[0053] Step S173: performing parameterized digital mapping on the rock wool curtain wall panel based on the reconstructed microstructure prototype of the wall panel to obtain a microstructure parameter mapping diagram of the wall panel;

[0054] Specifically, the prototype of the reconstructed microstructure of the wall panel can be imported into parametric modeling software, such as CATIA or Revit. These software support parameter-based modeling, allowing the geometric parameters of the structure to be defined and adjusted. In the software, define the key parameters that affect the performance of the rock wool curtain wall panel, such as fiber diameter, fiber spacing, fiber direction, and fiber density. Set a parameter list for each parameter, such as setting the fiber diameter to 0.5mm, 1mm, 1.5mm, etc., and setting the fiber spacing to 5mm, 10mm, 15mm, etc. Use the parametric function of the software to create a parametric model of the wall panel microstructure based on the defined parameters. For example, use the "table" or "family" function to define the geometric parameters of the fiber, and adjust the position and size of the fiber in a parameter-driven manner. Set the parameter range and step size of the parametric model, such as the step size of the fiber diameter is 0.5mm and the step size of the fiber spacing is 5mm. Then, run the parameter scanning function of the software to generate a series of parametric wall panel microstructure models, each corresponding to a specific set of parameter values. The software generates a panel microstructure parameter map, which is a database or chart of all parameterized models showing the effect of different parameter values ​​on the panel microstructure.

[0055] Step S174: encoding the microscopic fiber structure characteristics of the rock wool curtain wall panel based on the wall panel microstructure parameter mapping diagram to obtain a wall panel microstructure characteristic code set;

[0056] Specifically, the wallboard microstructure parameter map can be imported into data analysis software, such as Python's Pandas library or MATLAB. These software are capable of processing and analyzing large-scale data sets. In the software, the characteristics of the microscopic fiber structure, such as the volume fraction, orientation distribution, porosity, etc. of the fiber, are extracted for each parameterized model in the parameter map. For example, the orientation distribution of the fiber is extracted from a two-dimensional or three-dimensional image of the parameterized model using image processing technology. The extracted features are converted into numerical codes to form a wallboard microstructure feature code set. For example, the volume fraction of the fiber is encoded as 0.45, the orientation distribution is encoded as [0.2, 0.3, 0.5] (representing the fiber ratio in the three main directions, respectively), and the porosity is encoded as 0.15. A set of encoding rules is defined to map the numerical code of each feature to a specific bit or field. For example, a 16-bit feature code is defined, in which the first 8 bits represent the fiber volume fraction, the next 4 bits represent the orientation distribution, and the last 4 bits represent the porosity. According to the encoding rules, a unique feature code is generated for each parameterized model in the parameter map. These feature codes constitute the wall panel microstructure feature code set.

[0057] Step S175: Use the wall panel microstructure feature code set to perform digital twin mapping conversion on the microstructure of the rock wool curtain wall panel to obtain a first wall panel reconstructed structural model.

[0058] Specifically, the wall panel microstructure feature code sets can be obtained from step S174, which contain numerical codes for parameters such as fiber volume fraction, orientation distribution, and porosity. Ensure that the feature code sets are stored in CSV or JSON format and read using data analysis tools such as Python or MATLAB. Select a suitable digital twin platform, such as Digital Twin Platform (DTP), which is a software platform capable of processing complex data and performing three-dimensional modeling. DTP supports direct mapping from data to model and allows users to dynamically adjust the model based on input parameters. In DTP, parameter mapping rules are set to map each parameter code in the feature code set to the corresponding attribute in the digital model. For example, the fiber volume fraction code is mapped to the "volume fraction" in the model material properties, the orientation distribution code is mapped to the "fiber direction", and the porosity code is mapped to the "porosity". Use the DTP modeling tool to build a three-dimensional digital model of the rock wool curtain wall panel according to the parameter mapping rules. During the model building process, the model parameters are dynamically adjusted to match the numerical values ​​in the feature code set. For example, if the fiber volume fraction in the feature code set is 0.45, the volume fraction of the fiber material is set to 45% in the model. After the model is built, the details of the model are optimized to ensure that it accurately reflects the microstructure of the rock wool curtain wall panel. This includes adjusting the arrangement of the fibers, optimizing the pore structure, and simulating the micromechanical behavior of the material. Run the simulation in DTP to verify the accuracy of the digital twin model. By comparing with experimental data or known performance indicators, ensure that the model can accurately predict the actual behavior of the rock wool curtain wall panel. Finally, the reconstructed structural model of the first wall panel after the digital twin mapping conversion is exported to a standard format file, such as STEP or IGES.

[0059] The present invention is constructed through microstructure discrete units, which can simulate the microstructure of rock wool curtain wall panels in detail, capture the complex interactions within the material, and improve the simulation accuracy. Topological reorganization provides the flexibility to optimize the material structure while maintaining physical properties to meet diverse engineering needs. Quantification and simulation of microstructures are ensured through parameterized digital mapping. Material properties are systematically managed through feature coding to improve data processing efficiency. Digital models corresponding to actual physical structures are created through digital twin mapping conversion technology, which revolutionizes the prediction of material behavior and performance.

[0060] Preferably, step S2 comprises the following steps:

[0061] Step S21: performing thermodynamic boundary mapping on the reconstructed structural model of the first wall panel to obtain initial thermodynamic field data of the wall panel;

[0062] Specifically, the reconstructed structural model of the wall panel can be imported into thermodynamic analysis software, such as ANSYS or COMSOL Multiphysics. These software can handle complex thermodynamic problems and provide boundary mapping functions. In the software, the thermodynamic boundary conditions of the model are defined. For example, one side of the wall panel is set as the heated surface with a temperature set to 60°C, and the other side is set as the ambient surface with a temperature set to 20°C. At the same time, convection boundary conditions are defined, such as the convection heat transfer coefficient is 10W / (m 2 ·K). Enter the thermodynamic properties of the wall panel material, including specific heat capacity, density, and thermal conductivity. For example, set the thermal conductivity of rock wool to 0.04W / (m·K), specific heat capacity to 800J / (kg·K), and density to 150kg / m 3 The software will calculate the initial thermodynamic field data of the wall panel according to the input boundary conditions and material properties, including temperature distribution and heat flux density. The calculated initial thermodynamic field data will be output in the form of graphics and numerical values, including temperature cloud diagrams, heat flow line distribution, etc.

[0063] Step S22: constructing a heat conduction discrete grid for the first wall panel reconstructed structure model according to the initial thermodynamic field data of the wall panel to obtain a wall panel heat conduction grid model;

[0064] Specifically, the initial thermodynamic field data of the wall panel can be imported into finite element analysis software, such as ABAQUS or ANSYS. In the software, the reconstructed structural model of the wall panel is meshed. Select an appropriate mesh type and size, for example, use a tetrahedral mesh and set the mesh size to 2 mm to ensure the accuracy and computational efficiency of the simulation. According to the thermodynamic properties of the wall panel material, assign corresponding thermal conductivity, specific heat capacity and density to each element in the mesh model. For example, the thermal conductivity is set to 0.04W / (m·K) for the rock wool material. Apply the thermodynamic boundary conditions defined in step S21 to the corresponding boundaries of the mesh model. For example, set the temperature of the heated surface to 60°C, the temperature of the ambient surface to 20°C, and apply convection boundary conditions. Check the integrity and accuracy of the mesh model to ensure that there are no mesh quality issues, such as overstretched or distorted elements. If necessary, optimize and adjust the mesh. Finally, output the constructed wall panel thermal conduction mesh model.

[0065] Step S23: numerically simulate the internal heat conduction characteristics of the rock wool curtain wall panel based on the wall panel heat conduction grid model to obtain micro-scale heat conduction flux data;

[0066] Specifically, you can start finite element analysis software, such as ABAQUS, and import the wall panel thermal conduction mesh model. Set up a thermal conduction analysis task in the software and select an appropriate thermal conduction analysis type, such as steady-state thermal conduction or transient thermal conduction analysis. Enter detailed thermal physical properties for the rock wool material in the model, including thermal conductivity (e.g., 0.04W / (m·K)), specific heat capacity (e.g., 800J / (kg·K)), and density (e.g., 150kg / m 3 ). The fiber part of the model is meshed and the mesh size is set to 0.5 mm to improve the accuracy of the simulation. Run the heat conduction analysis, and the software will calculate the heat conduction flux at each mesh node, including the heat flux density and temperature gradient. After the simulation is completed, extract the micro-scale heat conduction flux data, which includes the heat flux density vector and temperature value at each mesh node. Output the micro-scale heat conduction flux data in the form of numerical tables and cloud maps.

[0067] Step S24: reconstructing the spatial characteristics of the micro-scale heat conduction flux data to obtain a micro-scale heat conduction characteristic map;

[0068] Specifically, the microscale heat conduction flux data can be imported into data processing and visualization software, such as MATLAB or Python's Matplotlib library. Use mathematical tools in the software, such as Fourier transform or wavelet transform, to extract the spatial characteristics of the heat conduction flux data, including the main heat conduction paths and thermal resistance areas. Reconstruct the microscale heat conduction characteristic map based on the extracted spatial features. This includes creating isotherm maps, heat flow line maps, and heat flux vector field maps. During the visualization process, select appropriate color mapping and scale to clearly show the changes in temperature gradients and heat flux density. Generate microscale heat conduction characteristic maps, including two-dimensional and three-dimensional views, to intuitively display the thermal conduction characteristics inside the rock wool curtain wall panel.

[0069] Step S25: performing cross-scale physical field coupling superposition on the micro-scale heat conduction characteristic diagram to obtain a multi-field comprehensive response diagram of the wall panel;

[0070] Specifically, micro-scale heat conduction characteristic diagrams can be obtained from step S24, including data such as temperature distribution and heat flux density. At the same time, data of other physical fields, such as mechanical stress field, electric field, etc., are collected, which are derived from previous simulations or experimental measurements. Select advanced simulation software, such as COMSOL Multiphysics or ANSYS. These software provide the functions of cross-scale simulation and multi-physics field coupling analysis. In the software, the heat conduction characteristic diagram is integrated with other physical field data. For example, the temperature distribution data is superimposed with the mechanical stress field data to analyze the thermal stress coupling effect. Set the coupling analysis parameters and select the appropriate coupling algorithm and solver. For example, an iterative solver is used to deal with thermal-mechanical coupling problems, and convergence criteria are set. In order to improve the accuracy of the coupling analysis, the mesh of the key area is refined. For example, for areas with expected stress concentration or large temperature gradient, the mesh size is set to 0.1 mm. Run the coupling simulation, and the software will calculate the interaction and comprehensive response of cross-scale physical fields. This includes stress distribution caused by thermal expansion, thermoelectric effects, etc. After the simulation is completed, the multi-field comprehensive response diagram of the wall panel is extracted, including the thermal-mechanical coupling stress diagram, the thermoelectric potential distribution diagram, etc. The accuracy of the simulation results is verified by comparing with the experimental data. The multi-field comprehensive response diagram is visualized and output in the form of color cloud diagrams and vector fields to clearly show the interaction and comprehensive effects between different physical fields.

[0071] Step S26: Based on the reconstructed structural model of the first wall panel and the multi-field comprehensive response diagram of the wall panel, a cross-scale performance dynamic simulation is performed on the rock wool curtain wall panel to obtain a comprehensive performance evaluation result of the wall panel.

[0072] Specifically, please refer to the sub-steps of step S26 for the detailed implementation process of this embodiment.

[0073] The present invention provides accurate initial thermodynamic field data for the reconstructed structural model of the wall panel through thermodynamic boundary mapping. The constructed discrete grid model of heat conduction makes the simulation of heat conduction characteristics more refined, and deeply reveals the heat transfer mechanism inside the material. By numerically simulating the internal heat conduction characteristics of the fiber and obtaining micro-scale heat conduction flux data, the thermal performance of the material can be evaluated. The heat conduction characteristic map formed by spatial feature reconstruction is helpful for visual analysis of the thermal conduction characteristics of the material. The cross-scale physical field coupling and superposition enhances the understanding of the behavior of the material under the action of multiple physical fields, and the cross-scale performance dynamic simulation based on the reconstructed structural model and the multi-field comprehensive response map provides a comprehensive performance evaluation result of the wall panel.

[0074] Preferably, step S26 comprises the following steps:

[0075] Step S261: extracting features from the reconstructed structural model of the first wall panel to obtain a microstructure feature vector set of the wall panel;

[0076] Specifically, the data file of the reconstructed structural model of the first wall panel can be imported into a structural analysis software, such as ABAQUS or ANSYS. In the software, set the feature extraction parameters, including geometric features (such as fiber diameter, spacing) and topological features (such as connection nodes, paths). Select a specific analysis tool, such as the "Feature Vector Extraction" tool, to identify the key microstructural features of the model. Run the feature extraction algorithm, and the software will automatically scan the model and identify key features, such as the distribution density, direction, and connection pattern of the fibers. For example, extract the diameter and spatial coordinates of each fiber in the fiber bundle, and convert these data into feature vectors. Vectorize the extracted features to form a parametric representation. For example, if there are 100 fibers in the model, and the feature vector of each fiber contains three parameters: its diameter, length, and direction, then a vector set containing 300 parameters will be obtained.

[0077] Step S262: performing feature analysis on the multi-field comprehensive response diagram of the wall panel to obtain a frequency spectrum feature space of the wall panel response diagram;

[0078] Specifically, the data file of the multi-field comprehensive response diagram of the wall panel can be imported into data analysis software, such as MATLAB or Python with NumPy and SciPy libraries. The response diagram data is preprocessed, including denoising and normalization. For example, wavelet transform is used to remove high-frequency noise in the signal, and then the data is standardized by Z-score normalization method. Spectral analysis tools such as fast Fourier transform (FFT) are applied to perform spectral decomposition on the response diagram data to extract frequency domain features. The parameters of FFT are set, such as the sampling frequency is 1000Hz, to adapt to the characteristics of the data. Key spectral features such as the main frequency components, frequency distribution range and amplitude characteristics are extracted from the spectral analysis results. For example, the main vibration frequencies and corresponding amplitude values ​​in the response diagram are identified. The extracted spectral features are constructed into the spectral feature space of the wall panel response diagram. This feature space can be represented by a three-dimensional or multi-dimensional graph, where each dimension corresponds to a spectral feature. The data of the spectral feature space of the wall panel response diagram is output as a graphical and numerical report.

[0079] Step S263: performing cross-scale performance correlation mapping modeling based on the wallboard microstructure feature vector set and the wallboard response graph frequency spectrum feature space to obtain the wallboard performance correlation response function;

[0080] Specifically, the wallboard microstructure feature vector set and the wallboard response map spectral feature space can be imported into data analysis and modeling software, such as MATLAB or Python's pandas and scikit-learn libraries. Select key microstructure features such as fiber diameter, spacing and direction from the feature vector set, and select key response features such as main frequency components and amplitude features from the spectral feature space. Use machine learning algorithms, such as random forests or neural networks, to establish an association mapping model between microstructure features and response features. For example, using a neural network model, the input layer contains microstructure features, the hidden layer is used to extract nonlinear relationships, and the output layer predicts response features. Train the model using historical data or simulation data. Set training parameters, such as a learning rate of 0.01, 1000 iterations, and a batch size of 32. Evaluate the performance of the model, using a cross-validation method, such as k-fold cross-validation, setting the k value to 5 to ensure the generalization ability of the model. After training, a wallboard performance association response function is obtained, which is able to predict response features based on microstructure features.

[0081] Step S264: performing a thermal-mechanical-electrical multi-field coupling numerical simulation on the rock wool curtain wall panel based on the wall panel performance correlation response function to obtain a cross-scale dynamic response simulation result;

[0082] Specifically, the wall panel performance correlation response function can be imported into multi-physics simulation software, such as COMSOL Multiphysics. Set up thermal-mechanical-electrical multi-field coupling analysis in the software. Define the heat conduction equation of the thermal field, the mechanical equilibrium equation of the force field, and the electric potential equation of the electric field. Set boundary conditions for the model, such as fixed boundaries, heat sources, force loads, and potential differences. Input the thermal, mechanical, and electrical material properties of the rock wool curtain wall panel, such as thermal conductivity, elastic modulus, and electrical conductivity. Run coupled numerical simulations. Set solver parameters, such as a time step of 0.01 seconds and a total simulation time of 1 second. After the simulation is completed, extract the cross-scale dynamic response simulation results, including temperature distribution, stress distribution, and electric potential distribution. Verify the accuracy of the simulation results by comparing with experimental data. If necessary, adjust the model parameters or boundary conditions and rerun the simulation. Visualize the cross-scale dynamic response simulation results, such as cloud maps and vector field maps, to intuitively display the multi-field coupling effect.

[0083] Step S265: Perform collaborative performance evaluation on the cross-scale dynamic response simulation results to obtain comprehensive performance evaluation results of the wall panels.

[0084] Specifically, please refer to the sub-steps of step S265 for the detailed implementation process of this embodiment.

[0085] The present invention deeply understands the microstructural characteristics of the wall panels through feature extraction, and enhances the understanding of material properties. By analyzing the characteristics of the multi-field comprehensive response diagram of the wall panels, the behavior pattern of the material under the action of multiple physical fields is revealed, and the understanding of the material response is enhanced. The performance of the material at different scales is accurately simulated by the established cross-scale performance correlation mapping model, which improves the accuracy of the simulation results. The dynamic response of the material in a complex environment is comprehensively evaluated through the thermal-mechanical-electrical multi-field coupling numerical simulation, providing a comprehensive evaluation for the application of the material. The comprehensive performance of the wall panels is systematically evaluated through the collaborative performance evaluation, ensuring the reliability and stability of the material in practical applications.

[0086] Preferably, step S265 includes the following steps:

[0087] Step S2651: performing confidence evaluation on the cross-scale dynamic response simulation results to obtain a wall panel performance simulation reliability evaluation set;

[0088] Specifically, the cross-scale dynamic response simulation results can be imported into statistical analysis software, such as SciPy and Statsmodels libraries using R language or Python. Confidence intervals are calculated for key performance parameters obtained from the simulation, such as maximum stress, maximum displacement, etc. A 95% confidence level is selected, and 1000 resamplings are performed using the bootstrap method to estimate the distribution of these parameters. Based on the results of the confidence intervals, the reliability of the simulation results is evaluated. For example, if the 95% confidence interval of the maximum stress is completely below the yield strength of the material, the simulation results are considered reliable. Identify the input parameters that have the greatest impact on the simulation results. For example, the Sobol index is used to quantify the contribution of different parameters to the output uncertainty. The wall panel performance simulation reliability evaluation set is output as a report, including the confidence interval, reliability rating, and sensitivity analysis results for each performance parameter.

[0089] Step S2652: performing random perturbations on the cross-scale dynamic response simulation results to obtain a random perturbation data set of wall panel performance;

[0090] Specifically, the cross-scale dynamic response simulation results can be imported into data processing software, such as using MATLAB or Python's NumPy library. Select a suitable random perturbation model, such as Monte Carlo simulation, to simulate the uncertainty and variability of the wall panel performance parameters. Set the parameters of the random perturbation, such as selecting a normal distribution or a uniform distribution, and determine the mean and standard deviation of the distribution. For example, for the maximum stress parameter, assume that its mean is 300MPa and the standard deviation is 15MPa. Implement random perturbations in the software to generate a large amount of perturbation data. For example, generate 1,000 random perturbation values ​​of the maximum stress to simulate performance variation under different conditions. Combine the generated random perturbation values ​​with the original simulation results to construct a random perturbation dataset for wall panel performance. This dataset contains the performance parameter values ​​after considering random variation. Verify the rationality of the random perturbation dataset by comparing it with experimental data or field monitoring data. If necessary, adjust the perturbation parameters and regenerate the dataset. Output the random perturbation dataset for wall panel performance.

[0091] Step S2653: performing extreme value distribution mapping on the random disturbance data set of wall panel performance to obtain a probability distribution diagram of wall panel performance response;

[0092] Specifically, randomly disturbed data sets of wall panel performance can be obtained from step S2652. These data sets contain performance parameter values ​​simulated under different random conditions. Select statistical analysis software, such as R language or Python's SciPy library, and use the extreme value distribution fitting tool in the software to perform extreme value distribution mapping on the performance parameters in the randomly disturbed data set. For example, select the generalized extreme value (GEV) model to fit the maximum and minimum values ​​of the performance parameters. Estimate the parameters of the GEV model, including location parameters, scale parameters, and shape parameters. Use the maximum likelihood estimation (MLE) method and set the number of iterations of the optimization algorithm to 1000 times and the tolerance to 1e -6 Generate probability distribution plots of the panel performance response based on the estimated parameters. For example, plot the cumulative distribution function (CDF) and probability density function (PDF) of the maximum stress and maximum displacement. Output the probability distribution plots of the panel performance response as graphical and numerical reports.

[0093] Step S2654: reconstructing the confidence interval of the wall panel performance response probability distribution diagram according to the wall panel performance simulation reliability evaluation set to obtain wall panel performance confidence region mapping data;

[0094] Specifically, the wall panel performance simulation reliability evaluation set and the wall panel performance response probability distribution diagram can be imported into data analysis software, such as MATLAB or Python's NumPy and SciPy libraries. Based on the confidence assessment results in the reliability evaluation set, the confidence interval is calculated for each performance parameter of the performance response probability distribution diagram. For example, a 95% confidence interval is calculated and 1000 resamplings are performed using the bootstrap method. On the performance response probability distribution diagram, the confidence interval of each performance parameter is marked. For example, on the cumulative distribution function (CDF) graph, confidence bands are drawn for the 95% confidence intervals of the maximum stress and maximum displacement. For each performance parameter, based on the results of the confidence interval, the confidence domain mapping data of the wall panel performance response is reconstructed. This includes determining the boundaries of the confidence domain and the statistical characteristics within the interval. The wall panel performance confidence domain mapping data is output as a graphical and numerical report, including the boundary values ​​of the confidence domain and related statistical information.

[0095] Step S2655: extract sensitivity features from the wall panel performance confidence region mapping data to obtain a curtain wall panel performance key influencing factor set, and perform risk grading on the wall panel performance confidence region mapping data according to the curtain wall panel performance key influencing factor set to obtain wall panel performance risk stratification mapping data;

[0096] Specifically, the wallboard performance confidence region mapping data can be obtained from step S2654, which includes confidence intervals and probability distribution diagrams of different performance parameters. Select a sensitivity analysis tool, such as the Sobol index or the Morris method. In this example, the Sobol index is selected for sensitivity analysis. Use Monte Carlo simulation combined with the Sobol index method to perform sensitivity analysis on the wallboard performance confidence region mapping data. Set the number of simulations to 5000 times to ensure the statistical significance of the results. Through Sobol index analysis, determine the top five parameters that have the greatest impact on wallboard performance, such as fiber diameter, fiber orientation, thermal conductivity, density, and elastic modulus. Select a suitable risk grading method, such as the analytic hierarchy process (AHP) or fuzzy logic, to perform risk assessment on wallboard performance. In this example, the analytic hierarchy process (AHP) is selected. In the AHP, a judgment matrix is ​​constructed, key influencing factors are compared in pairs, and weights are set. For example, a relative importance score is set for each factor based on expert experience and historical data. Run the AHP algorithm, calculate the weight of each factor, and perform risk grading on the wallboard performance confidence region mapping data based on these weights. For example, the risk level is divided into five levels: very low, low, medium, high and very high. Based on the risk grading results, the wall panel performance risk stratification mapping data is generated. These data include the risk level and corresponding confidence interval of each performance parameter.

[0097] Step S2656: Perform a comprehensive performance evaluation on the wall panel performance risk stratification mapping data to obtain a comprehensive performance evaluation result of the wall panel.

[0098] Specifically, the wallboard performance risk stratification mapping data can be obtained from step S2655, which includes the risk level and corresponding confidence interval of different performance parameters. Select a comprehensive performance evaluation tool, such as a weighted scoring method or a multi-criteria decision analysis (MCDM), which can help comprehensively consider the impact of multiple performance parameters. In this example, a weighted scoring method is selected. According to the importance of each performance parameter, a weight is assigned. For example, based on expert experience and historical data, fiber diameter, fiber orientation, thermal conductivity, density and elastic modulus are assigned weights of 0.2, 0.15, 0.25, 0.2 and 0.2 respectively. A scoring standard is established for each performance parameter. For example, the performance parameters are divided into five levels according to the risk level, and each level corresponds to a score from 1 (extremely high risk) to 5 (extremely low risk). Using the weighted scoring method, the score of each performance parameter is calculated. For example, if the risk level of the fiber diameter is "medium" and the corresponding score is 3, then its weighted score is 3×0.2=0.6. The weighted scores of all performance parameters are added together to obtain the comprehensive performance score of the wallboard. For example, if the sum of the weighted scores of all parameters is 2.5, the comprehensive performance of the wall panel is 2.5 on a scale of 1 to 5. Analyze the comprehensive performance score results to determine the overall performance level of the wall panel. For example, if the comprehensive performance score is lower than 3, the wall panel design needs to be optimized. Output the wall panel comprehensive performance evaluation results as a report, including the score, weight and comprehensive performance score of each performance parameter.

[0099] The present invention enhances the credibility of simulation results through confidence assessment, ensuring the reliability of wall panel performance simulation. The robustness of simulation results is enhanced by introducing random perturbation simulation, and the changes in wall panel performance under uncertain conditions are effectively evaluated. Through extreme value distribution mapping and the generation of performance response probability distribution diagrams, intuitive understanding and analysis of the statistical characteristics and potential risks of wall panel performance are achieved. The accuracy of performance prediction is improved through the precise construction of confidence intervals. Sensitivity analysis is deepened through sensitivity feature extraction, key factors affecting wall panel performance are identified, and material optimization and design improvements are guided. Through risk grading and management, risk grading is performed on wall panel performance confidence domain mapping data to effectively manage and control risks in the design and construction process. Comprehensive performance evaluation provides a comprehensive performance overview to help grasp the overall performance level of the wall panel.

[0100] Preferably, step S3 comprises the following steps:

[0101] Step S31: obtaining a wall panel construction process parameter set, and quantifying the characteristics of the wall panel construction process parameter set to obtain a wall panel construction process parameter characteristic set;

[0102] Specifically, the wallboard construction process parameters can be collected through field measurements and historical project data, including but not limited to temperature, humidity, material ratio, curing time, etc. Select a suitable feature quantification method, such as principal component analysis (PCA) or statistical feature extraction (such as mean, standard deviation, maximum and minimum). In this example, the statistical feature extraction method is selected. Use data preprocessing tools, such as Python's Pandas library, to clean the collected construction process parameter data, including removing outliers and filling missing values. Perform feature extraction on the preprocessed data. For example, for the temperature parameter, calculate its mean, standard deviation and extreme value during the construction process; for the material ratio, calculate its mean and standard deviation. Construct the extracted statistical features into a feature set of wallboard construction process parameters. For example, the temperature feature set includes "average temperature: 20℃", "temperature fluctuation: 5℃", "highest / lowest temperature: 30℃ / 10℃"; the material ratio feature set includes "average ratio: 1.5" and "ratio fluctuation: 0.1".

[0103] Step S32: performing entropy coding conversion on the wall panel construction process parameter feature set to obtain an entropy coding set of wall panel process parameters;

[0104] Specifically, the feature set of wallboard construction process parameters can be imported into data analysis software, such as MATLAB or Python's SciPy library. Select a suitable entropy coding method, such as Shannon entropy coding, which is an information entropy-based coding method used to quantify the uncertainty and information content of the data. Calculate the entropy value of each parameter in the feature set. For example, for the temperature fluctuation parameter, use the Shannon entropy formula to calculate its entropy value: Among them, P(x i ) is the parameter value x i The probability of occurrence, n is the total number of temperature fluctuation parameters. According to the calculated entropy value, each parameter is encoded and converted. For example, the entropy value is converted into a binary code, and the encoding length of each parameter is proportional to its entropy value. The converted entropy codes are constructed into an entropy coding set of wallboard process parameters. For example, the entropy coding of the temperature fluctuation parameter is "1010", and the entropy coding of the material ratio fluctuation parameter is "1100". The entropy coding set of wallboard process parameters is output as a structured data format.

[0105] Step S33: performing error probability mapping on the entropy coding set of wallboard process parameters to obtain construction error probability distribution mapping data;

[0106] Specifically, the entropy coding set of the wallboard process parameters can be imported into the data analysis software, such as using Python's Pandas library for data processing. Select a suitable error analysis model, such as a Bayesian network or a hidden Markov model (HMM), to analyze the relationship between the process parameters and the construction error. In this example, the Bayesian network model is selected. Use historical construction data and expert knowledge to establish association rules between process parameters and construction errors. For example, temperature fluctuations are associated with errors of uneven curing. Probability distribution estimates are performed on the entropy coding of each process parameter to determine the probability distribution of the construction error. For example, the maximum likelihood estimation (MLE) method is used to estimate the error probability distribution of the temperature fluctuation parameter. The estimated probability distribution is mapped to each process parameter to obtain the construction error probability distribution mapping data. For example, if the entropy coding of the temperature fluctuation is "1010", the corresponding error probability distribution is a mean of 0.03 and a standard deviation of 0.01.

[0107] Step S34: spatially mapping the construction error probability distribution mapping data to obtain a wallboard construction error spatial distribution map;

[0108] Specifically, the construction error probability distribution mapping data can be imported into a geographic information system (GIS) software, such as ArcGIS or QGIS. In the GIS software, set the spatial mapping parameters, including the coordinate system, scale, and map projection. For example, select the UTM coordinate system and a scale of 1:1000. Combine the construction error probability distribution data with the location information of the wall panels for spatial processing. For example, match the error probability distribution data of each construction section to the corresponding wall position. Use the mapping function of the GIS software to generate a spatial distribution map of the wall panel construction errors. For example, use color gradients to represent the error probabilities of different construction sections, red represents high error probability areas, and green represents low error probability areas. Perform spatial analysis on the generated spatial distribution map to identify high error incidence areas and potential risk points. For example, use hotspot analysis (HotSpotAnalysis) to identify the clustered areas of construction errors. Output the wall panel construction error spatial distribution map as an image file, such as PNG or JPEG format, and an editable GIS project file.

[0109] Step S35: performing error correlation evaluation on the wall panel construction error spatial distribution diagram to obtain a wall panel error correlation evaluation matrix, and performing hierarchical quantization encoding on the wall panel error correlation evaluation matrix to obtain a wall panel construction error index set.

[0110] Specifically, the spatial distribution map of wallboard construction errors can be imported into data analysis software, such as using Python's Geopandas library for geospatial data analysis. Select appropriate statistical analysis tools, such as correlation analysis or cluster analysis, to evaluate the correlation between different construction errors. In this example, the Pearson correlation coefficient is selected to measure the linear relationship between errors. Perform correlation analysis on the construction error data in the spatial distribution map. For example, analyze the correlation between temperature error and material ratio error, calculate the correlation coefficient, and set the significance level to 0.05. Based on the results of the correlation analysis, construct a wallboard error correlation evaluation matrix. For example, if the correlation coefficient between temperature error and material ratio error is 0.8, fill in 0.8 in the corresponding cell in the matrix. Select an appropriate hierarchical quantization encoding method, such as fuzzy C-means clustering (FCM) or k-means clustering, to perform hierarchical quantization encoding on the error correlation evaluation matrix. In this example, the FCM clustering method is selected. In the FCM clustering method, the number of clusters is set to 3, representing the three error correlation levels of low, medium, and high, and the fuzzy coefficient is set to 2 to enhance the fuzziness of clustering. The FCM clustering algorithm is run to perform hierarchical quantitative encoding on the error correlation evaluation matrix to obtain the correlation level of each construction error. The results of the hierarchical quantitative encoding are organized into a set of wall panel construction error indicators, for example, "temperature error-material ratio error: high correlation", and output as a structured data format.

[0111] The present invention can accurately capture the key variables in the construction process by quantifying construction process parameters through features. The processability of the parameter set is improved through entropy coding conversion, making the data more compact. The error probability mapping clarifies the types and probabilities of errors that are prone to occur in construction, which helps to identify and prevent problems in advance. Through the visualization of the spatial distribution map of construction errors, it helps to locate high-risk areas and achieve targeted quality control. The error correlation assessment reveals the mutual influence between construction errors and promotes a comprehensive understanding of the complex relationships in the construction process. The construction error indicator set is structured through hierarchical quantitative coding, which improves management efficiency.

[0112] Preferably, step S4 comprises the following steps:

[0113] Step S41: Based on the first wall panel reconstruction structure model and according to the comprehensive performance evaluation result of the wall panel, semantic mapping of performance boundary conditions is performed on the curtain wall panel structure to obtain wall panel performance boundary condition mapping data;

[0114] Specifically, the reconstructed structural model of the first wall panel and the comprehensive performance evaluation results of the wall panel can be imported into a structural analysis software, such as ABAQUS or ANSYS. Define the key parameters that affect the performance of the curtain wall panel in the software, such as maximum stress, maximum displacement, durability, etc., and set performance standards or thresholds for each parameter. Set semantic mapping rules for performance boundary conditions. For example, if the maximum stress exceeds 300MPa, it is defined as a "high stress area" and requires enhanced processing. Use the software's scripts or built-in tools to automatically perform semantic mapping based on the comprehensive performance evaluation results. For example, all areas exceeding the stress threshold are automatically marked in ABAQUS by writing a Python script. Output the performance boundary condition mapping results as a data file, such as CSV or XML format, recording the performance parameters and corresponding semantic labels of each area. Verify the accuracy of the performance boundary condition mapping by comparing with the experimental data. If necessary, adjust the mapping rules and re-execute the mapping. Through the above steps, the wall panel performance boundary condition mapping data can be obtained.

[0115] Step S42: performing multi-scale decoupling on the wall panel performance boundary condition mapping data to obtain a wall panel performance boundary condition decoupling factor;

[0116] Specifically, the wall panel performance boundary condition mapping data can be imported into data analysis software, such as MATLAB or Python's NumPy and SciPy libraries. Select an appropriate multiscale analysis method, such as wavelet transform or multiscale entropy analysis, to process performance data at different scales. Set decoupling parameters, such as selecting the basis function and number of decomposition layers for wavelet transform. In this example, the Daubechies wavelet basis function is selected and a 3-layer wavelet decomposition is performed. Run the multiscale analysis algorithm to decouple the performance boundary condition mapping data. For example, use MATLAB's wavelet decomposition toolbox to perform multiscale decomposition on stress and displacement data. Extract decoupling factors from the multiscale analysis results, which represent performance characteristics at different scales. For example, extract the coefficients of each wavelet decomposition layer as decoupling factors.

[0117] Step S43: performing parameterized reconstruction of the curtain wall panel structure based on the first wall panel reconstruction structural model and the wall panel performance boundary condition decoupling factor to obtain a preliminary wall panel structural parameter model;

[0118] Specifically, the first wall panel reconstructed structural model and the wall panel performance boundary condition decoupling factor can be imported into parametric modeling software, such as CATIA or Revit. In the software, set up a parametric modeling environment, define the parameters of the model, such as plate thickness, connector strength, etc., and associate them with the decoupling factor. For example, set the plate thickness as the variable "t" and adjust its value according to the decoupling factor. Adjust the model parameters according to the decoupling factor. For example, if the decoupling factor indicates that a certain area needs to be strengthened, increase the thickness of the plate in that area or change the design of the connector. Reconstruct the curtain wall panel structure using the parametric function of the software. For example, use the "parametric design table" function in CATIA to dynamically adjust the model parameters according to the decoupling factor. Output the preliminary structural parameter model of the wall panel as a standard format file.

[0119] Step S44: performing structural stability evaluation on the preliminary structural parameter model of the wall panel to obtain a wall panel structural stability index;

[0120] Specifically, the preliminary structural parameter model of the wall panel can be imported into a structural analysis software, such as SAP2000 or ETABS. In the software, select the type of structural stability analysis, such as linear stability analysis or nonlinear stability analysis. For example, select nonlinear stability analysis to consider material and geometric nonlinearity. Set the boundary conditions and applied loads of the model. For example, set fixed supports and live loads, such as wind loads and self-weight. Run the structural stability analysis. For example, use the "Performance-Based Design" tool in SAP2000 and set the performance goals to "no buckling" and "minimum displacement". Extract structural stability indicators from the analysis results, such as buckling factor, maximum displacement, and stress ratio. For example, a buckling factor greater than 1 indicates that the structure is stable. Output the wall panel structural stability indicators as a report, including key data such as buckling factor and maximum displacement.

[0121] Step S45: reconstructing the boundary conditions of the rock wool curtain wall panel structure according to the wall panel structure stability index to obtain a reconstructed structural model of the second wall panel;

[0122] Specifically, based on the stability index of the wall panel structure, areas that do not meet the design requirements can be identified, for example, the buckling factor of some areas is below the safety threshold. Select structural design software, such as Autodesk Revit or Rhinoceros3D, and adjust the boundary conditions of the rock wool curtain wall panel in the software according to the stability index. For example, if the buckling factor is too low, add support points or adjust the layout of the connectors to enhance the structural stability. Use the parametric function of the software to modify the structural model. For example, adjust the size of beams and columns in Revit, or modify the thickness of the wall in Rhinoceros 3D. Apply the modified parameters and rebuild the structural model. For example, use the "Regenerate" function of Revit to update the entire structural model. Perform a structural stability analysis again to verify whether the reconstructed model meets all design requirements. If necessary, further adjust the parameters until all stability criteria are met. Export the reconstructed structural model of the second wall panel that meets the stability requirements to a standard format file.

[0123] Step S46: Designing an extreme environment multi-scenario simulation scheme for the rock wool curtain wall panel to obtain an extreme environment multi-scenario simulation scheme;

[0124] Specifically, you can collaborate with the engineering team to identify the extreme environmental conditions that rock wool curtain wall panels are likely to encounter in actual applications, including extreme temperatures, strong winds, earthquakes, etc. COMSOL Multiphysics is selected as the multi-physics simulation software because it can handle multi-physics problems such as structure, heat transfer and fluid dynamics. Create a new model project in COMSOL and name it "Extreme Environment Simulation of Rock Wool Curtain Wall Panels". Prepare an accurate three-dimensional geometric model of the rock wool curtain wall panel, including the size of the panel, the location of the connectors, and the material properties. For example, define the first scenario in which one side of the rock wool curtain wall panel will be exposed to high temperature, set the temperature to 50°C, and simulate continuous exposure. Define the second scenario to simulate the impact of earthquakes on curtain wall panels, set the ground acceleration to 0.4g, select "sine wave" as the earthquake waveform, set the frequency to 1Hz, and set the duration to 60 seconds. Define the third scenario to simulate the impact of strong winds on curtain wall panels. According to the wind tunnel test data, set the wind pressure values ​​in different areas, and simulate the wind direction from 0 degrees to 90 degrees, with the duration of each direction set to 3600 seconds. Define detailed boundary conditions and load types for each scenario. For example, for high temperature scenarios, set the back of the curtain wall panel to adiabatic conditions; for earthquake scenarios, set the bottom of the curtain wall panel to fixed support; for strong wind scenarios, set wind pressure distribution and wind direction changes. Mesh each scenario and select the appropriate mesh size and type. For example, for high temperature scenarios, the mesh size is set to 2mm to capture temperature gradient changes. Set solver parameters for each scenario, such as time step and number of iterations, to ensure the stability and accuracy of the simulation. Record the setting parameters, boundary conditions, load types, and solver parameters for each scenario in detail in the simulation solution document, including the specific values ​​of the simulation parameters, screenshots of the simulation process, and charts of expected results. Review the simulation solution with the design team to ensure that the solution covers all key extreme environmental conditions. Output the final simulation solution as a report in PDF format.

[0125] Step S47: Based on the wall panel construction error index set and the extreme environment multi-scenario simulation scheme, the second wall panel reconstruction structure model is subjected to an extreme environment multi-scenario simulation to obtain the wall panel multi-scenario performance response data;

[0126] Specifically, the second wall panel reconstruction structural model and the extreme environment multi-scenario simulation scheme can be imported into a multi-physics simulation software, such as COMSOL Multiphysics. The wall panel construction error indicator set is integrated into the simulation model. For example, if the error indicator set includes "temperature error ±3°C" and "material strength fluctuation ±5%", the corresponding parameter variation range is set in the model. Simulation parameters for multiple scenarios are set in the software, including extreme temperature, wind pressure, earthquake, etc. For example, a scenario is set to "high temperature + strong wind", the temperature is set to 50°C, and the wind pressure is set to 1.2kPa. Run the simulation software to simulate each scenario. For example, the "thermal-structural interaction" module of COMSOL is used to simulate the effects of high temperature and wind pressure on the wall panel. Performance response data, such as maximum stress, displacement, and vibration frequency, are extracted from the simulation results of each scenario. For example, the maximum stress value of the wall panel recorded in the "high temperature + strong wind" scenario is 150MPa. The performance response data of all scenarios are sorted into a multi-scenario performance response data set for the wall panel.

[0127] Step S48: Perform limit value mapping and boundary identification on the multi-scenario performance response data of the wall panel to obtain the wall panel performance limit response data; perform risk quantification on the preset fatigue failure assessment index based on the wall panel performance limit response data to obtain the wall panel performance degradation prediction result.

[0128] Specifically, the multi-scenario performance response data of the wallboard can be imported into data analysis software, such as Python's Pandas library. The performance response data is statistically analyzed to identify the limit values ​​of each response parameter. For example, the 99% quantiles of the maximum stress and maximum displacement are found as the limit values ​​using descriptive statistics. The performance state of the wallboard is identified based on the limit values ​​and the preset performance boundaries. For example, if the limit value of the maximum stress exceeds the yield strength of the material, the wallboard is considered to be out of bounds in this scenario. The limit value and boundary identification results are organized into a wallboard performance limit response data set, including the limit stress, displacement, etc. in each scenario. Fatigue failure assessment is performed on the wallboard performance limit response data using fatigue analysis tools, such as MATLAB's fatigue analysis toolbox. For example, the fatigue life of the wallboard is calculated based on the SN curve and the rain flow counting method. Based on the fatigue failure assessment results, the preset fatigue failure assessment indicators are risk quantified. For example, the fatigue failure probability of the wallboard in different scenarios is calculated and compared with the acceptable risk level. Based on the risk quantification results, the performance degradation trend of the wallboard is predicted. For example, the time and degree of performance degradation of the wallboard under extreme environments are predicted. Output panel performance limit response data and performance degradation prediction results as reports and data files.

[0129] The present invention accurately defines the performance limit of the wall panel structure through semantic mapping of performance boundary conditions, providing clear guidance for structural design. Multi-scale decoupling enhances the ability to analyze factors affecting wall panel performance and improves the understanding of complex structural performance. Parametric reconstruction of the wall panel structure improves design flexibility, allowing rapid adjustment to meet different performance requirements. The safety and reliability of the structure are ensured by quantitative evaluation of structural stability. The structural design is optimized by boundary condition reconstruction based on structural stability indicators, improving the performance and durability of the wall panels. The adaptability and toughness of the wall panels are enhanced by the design of multi-scenario simulation schemes for extreme environments. Multi-scenario simulation combined with a set of construction error indicators comprehensively evaluates the problems that are prone to occur in actual construction. The ultimate performance of the wall panels is accurately predicted by limit value mapping and boundary identification, providing key safety guarantees for the design. Risk quantification and performance degradation prediction based on performance limit response data help to take measures in advance to avoid potential structural failures.

[0130] Preferably, step S5 comprises the following steps:

[0131] Step S51: extracting features from the wall panel performance degradation prediction results to obtain a wall panel performance degradation feature vector set;

[0132] Specifically, the wall panel performance degradation prediction results can be imported into data analysis software, such as using Python's Pandas library for data processing. Select a suitable feature extraction technique, such as principal component analysis (PCA) or independent component analysis (ICA), to reduce the data dimension and extract key features. In this example, the PCA method is selected, and PCA is used to extract features from the wall panel performance degradation prediction results. For example, the PCA function of the Scikit-learn library is used in Python to retain the energy of 95% of the variance and obtain the main eigenvectors. The extracted eigenvectors are constructed into a wall panel performance degradation feature vector set. For example, if PCA extracts 3 main eigenvectors, these vectors represent the main trends of wall panel performance degradation.

[0133] Step S52: performing a Bayesian probability significance test on the wallboard performance degradation feature vector set to obtain a significance ranking table of key degradation influencing factors;

[0134] Specifically, the wall panel performance degradation feature vector set can be imported into statistical analysis software, such as using R language or Python's PyMC3 library for Bayesian analysis. A Bayesian model is constructed to evaluate the significance of the feature vector. For example, a prior distribution, such as a normal distribution, is defined in PyMC3 for model parameters. A significance test is performed on each feature vector using a Bayesian model. For example, the posterior probability of each feature is calculated and compared with the prior probability to evaluate the significance of its impact on performance degradation. Based on the Bayesian test results, a significance ranking table of key degradation influencing factors is constructed. For example, the features are sorted according to the posterior probability of their significance in affecting performance degradation.

[0135] Step S53: performing entropy weight fuzzy comprehensive evaluation on the significance ranking table of key degradation influencing factors to obtain a wallboard degradation influencing weight matrix;

[0136] Specifically, the significance ranking table of key degradation influencing factors can be imported into data analysis software, such as using Python's Pandas library for data management. The entropy value of each factor is calculated to evaluate its information entropy, reflecting the uncertainty of its information. For example, the entropy calculation function in Python's SciPy library is used to calculate the entropy value of each factor based on the significance probability distribution of each factor. The weight of each factor is calculated according to the entropy value, and the weight is inversely proportional to the information entropy of the factor. The lower the information entropy, the greater the weight. For example, if a factor has the lowest entropy value, it indicates that it provides the most effective information, so the highest weight is assigned. A fuzzy comprehensive evaluation method is used to comprehensively evaluate each factor by combining entropy weights and expert scores or other objective data. For example, a fuzzy evaluation matrix is ​​constructed in which rows represent factors and columns represent different evaluation levels (such as "high", "medium", and "low" impacts), and the comprehensive values ​​based on entropy weights and expert scores are filled. Based on the fuzzy comprehensive evaluation results, a wallboard degradation impact weight matrix is ​​constructed. For example, each element in the matrix represents the weighted score of a factor at different evaluation levels.

[0137] Step S54: performing multi-criteria decision mapping on the significance ranking table of key degradation influencing factors according to the wallboard degradation influence weight matrix to obtain the key design adjustment factors of the wallboard;

[0138] Specifically, the wall panel degradation impact weight matrix can be imported into a multi-criteria decision analysis software, such as the PyMCDM library using MATLAB or Python. Define the criteria for multi-criteria decision making, such as performance improvement potential, cost-effectiveness, and implementation difficulty. For example, three criteria are determined: "performance improvement potential" (weight is 0.5), "cost-effectiveness" (weight is 0.3), and "implementation difficulty" (weight is 0.2). Use a multi-criteria decision analysis method, such as the weighted sum method or the analytic hierarchy process (AHP), to combine the weights in the weight matrix with the decision criteria for decision mapping. For example, use the "weighted summation" method in the PyMCDM library to calculate the comprehensive score of each factor based on its score and weight under different criteria. Based on the comprehensive score, extract the design adjustment factors that are most critical to the improvement of wall panel performance. For example, select the top 5 factors with the highest comprehensive scores as key design adjustment factors.

[0139] Step S55: adjusting the structural parameters of the rock wool curtain wall panel based on the key design adjustment factors of the wall panel to obtain a design scheme for enhancing the performance of the wall panel;

[0140] Specifically, the key design adjustment factors can be imported into the structural design software, such as using Autodesk Revit or Rhinoceros 3D. According to the key design adjustment factors, the structural parameter adjustment decision is made. For example, if "fiber diameter" and "fiber orientation" are the key factors, it is decided to increase the fiber diameter to improve the strength and adjust the fiber orientation to optimize the load distribution. In the software, the structural parameters of the rock wool curtain wall panel are adjusted. For example, modify the wall material properties in Revit, or adjust the geometric parameters of the fiber in Rhinoceros 3D. Use finite element analysis (FEA) software, such as ANSYS or ABAQUS, to simulate the performance of the adjusted rock wool curtain wall panel to verify the effect of the structural parameter adjustment. For example, simulate the stress distribution and deformation under the new fiber configuration. Based on the simulation results, further optimize the design scheme. For example, if the simulation shows that the strength is improved but the weight increases after increasing the fiber diameter, the fiber density needs to be readjusted to balance the performance and cost, and the final wall panel performance enhancement design scheme is output as a detailed report.

[0141] Step S56: reconstructing the second wall panel reconstructed structural model through the wall panel performance enhancement design scheme to obtain an optimized wall panel three-dimensional simulation model.

[0142] Specifically, the wall panel performance enhancement design scheme can be imported into 3D modeling software, such as SolidWorks or CATIA. According to the design scheme, the reconstructed structural model of the second wall panel is adjusted in detail. For example, the distribution of fibers and the geometry of the wall are modified in SolidWorks. Use the built-in analysis tools of the 3D modeling software, such as stress analysis or thermal analysis, to verify the performance of the reconstructed model. For example, check whether the maximum stress point under the new design meets the safety requirements. If necessary, perform multidisciplinary optimization, such as thermal-structural coupling analysis, to ensure that the new design performs well in many aspects. For example, simulate the heat conduction and structural stability of the new design in COMSOL Multiphysics. Refine the optimized 3D simulation model of the wall panel and add details to improve the authenticity of the model. For example, add material textures and actual construction details in CATIA. Output the optimized 3D simulation model of the wall panel as a 3D format file.

[0143] The present invention deeply understands the process and key features of wall panel performance degradation through feature extraction, and the Bayesian probability significance test provides scientific probability support to enhance the reliability of the analysis results. The objectivity of the evaluation is increased by the entropy weight fuzzy comprehensive evaluation method. The wall panel degradation impact weight matrix provides a clear basis for multi-criteria decision-making, making the design adjustment more scientific and accurate. The key design adjustment factors of the wall panels obtained by multi-criteria decision mapping guide targeted structural parameter adjustments to improve design efficiency and effectiveness. A systematic wall panel performance enhancement solution is provided by adjusting the structural parameters based on the key design adjustment factors to ensure the comprehensiveness of the performance improvement. The optimized three-dimensional simulation model of the wall panels is closer to practical applications, improving the practicality of the model and the simulation accuracy.

[0144] Preferably, the present invention further provides a three-dimensional simulation design system based on a rock wool curtain wall panel structure, which is used to execute the three-dimensional simulation design method based on a rock wool curtain wall panel structure as described above. The three-dimensional simulation design system based on a rock wool curtain wall panel structure comprises:

[0145] The digital twin module is used to obtain the wall panel micro-morphology source data; perform isotropic micro-feature enhancement on the wall panel micro-morphology source data to obtain the wall panel micro-fiber morphology data; perform digital twin reconstruction of the rock wool curtain wall panel based on the wall panel micro-fiber morphology data to obtain the first wall panel reconstructed structural model;

[0146] The performance simulation module is used to perform thermodynamic field mapping on the reconstructed structural model of the first wall panel to obtain a micro-scale heat conduction characteristic map; perform cross-scale physical field coupling and superposition on the micro-scale heat conduction characteristic map to obtain a multi-field comprehensive response map of the wall panel; perform cross-scale performance dynamic simulation of the rock wool curtain wall panel based on the multi-field comprehensive response map of the wall panel to obtain a comprehensive performance evaluation result of the wall panel;

[0147] The error evaluation module is used to obtain a wall panel construction process parameter set; perform construction error evaluation on the wall panel construction process parameter set to obtain a wall panel construction error index set;

[0148] The risk assessment module is used to reconstruct the performance boundary conditions of the rock wool curtain wall panel according to the comprehensive performance evaluation results of the wall panel to obtain the reconstructed structural model of the second wall panel; perform extreme environment multi-scenario simulation on the reconstructed structural model of the second wall panel based on the wall panel construction error index set to obtain the multi-scenario performance response data of the wall panel; perform fatigue failure risk assessment on the rock wool curtain wall panel according to the multi-scenario performance response data of the wall panel to obtain the wall panel performance degradation prediction results;

[0149] The simulation model reconstruction module is used to extract the target optimization factors of the wall panel performance degradation prediction results to obtain the key design adjustment factors of the wall panels; optimize the structural parameters of the rock wool curtain wall panels according to the key design adjustment factors of the wall panels to obtain the wall panel performance enhancement design scheme; reconstruct the second wall panel reconstruction structural model according to the wall panel performance enhancement design scheme to obtain the optimized wall panel three-dimensional simulation model.

[0150] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0151] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A three-dimensional simulation design method based on rock wool curtain wall panel structure, characterized in that: The following steps are involved: Step S1: Obtain wallboard micro-morphology source data; The isotropic microscopic feature enhancement is performed on the wallboard microscopic morphology source data to obtain the wallboard microscopic fiber morphology data; The rock wool curtain wall panel is digitally twinned and reconstructed based on the micro-fiber morphology data of the wall panel to obtain the reconstructed structural model of the first wall panel; Step S2: performing thermodynamic field mapping on the reconstructed structural model of the first wall panel to obtain a micro-scale heat conduction characteristic map; The micro-scale heat conduction characteristic diagram is coupled and superimposed on the cross-scale physical field to obtain the multi-field comprehensive response diagram of the wall panel; based on the multi-field comprehensive response diagram of the wall panel, the rock wool curtain wall panel is dynamically simulated across scales to obtain the comprehensive performance evaluation results of the wall panel; Step S3: Obtain a wall panel construction process parameter set; Conduct construction error evaluation on the wall panel construction process parameter set to obtain the wall panel construction error index set; Step S4: reconstructing the performance boundary conditions of the rock wool curtain wall panel according to the comprehensive performance evaluation results of the wall panel to obtain a reconstructed structural model of the second wall panel; performing extreme environment multi-scenario simulation on the reconstructed structural model of the second wall panel based on the wall panel construction error index set to obtain multi-scenario performance response data of the wall panel; The fatigue failure risk of rock wool curtain wall panels was evaluated based on the multi-scenario performance response data of the wall panels, and the performance degradation prediction results of the wall panels were obtained; Step S5: extracting target optimization factors from the wall panel performance degradation prediction results to obtain key design adjustment factors of the wall panel; The structural parameters of the rock wool curtain wall panels were optimized according to the key design adjustment factors of the wall panels, and the design scheme for enhancing the performance of the wall panels was obtained; The reconstructed structural model of the second wall panel is reconstructed according to the wall panel performance enhancement design scheme to obtain an optimized wall panel three-dimensional simulation model.

2. The three-dimensional simulation design method based on rock wool curtain wall panel structure according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: collecting the three-dimensional morphology of the microstructure of the rock wool curtain wall panel to obtain the wall panel micromorphology source data; Step S12: extracting fiber micro-geometric features from the wallboard micro-morphology source data to obtain a wallboard fiber geometric feature vector set; Step S13: adjusting the fiber structure topology network of the rock wool curtain wall panel according to the wall panel fiber geometric feature vector set to obtain a wall panel fiber network connection topology diagram; Step S14: reconstructing the spatial configuration of the wall panel fiber network connection topology diagram to obtain a wall panel fiber space model; Step S15: numerically simulate the fiber interface characteristics of the rock wool curtain wall panel based on the wall panel fiber space model to obtain rock wool fiber interface stress-strain coupling data, and evaluate the interface connection strength of the rock wool fiber interface stress-strain coupling data to obtain fiber interface connection strength evaluation data; Step S16: quantifying the fiber network toughness of the fiber interface connection strength evaluation data to obtain a fiber network connection capacity index, and isotropically enhancing the microscopic fiber morphology of the rock wool curtain wall panel according to the fiber network connection capacity index to obtain microscopic fiber morphology data of the wall panel; Step S17: Perform digital twin reconstruction of the rock wool curtain wall panel based on the micro-fiber morphology data of the wall panel to obtain a reconstructed structural model of the first wall panel.

3. The three-dimensional simulation design method based on rock wool curtain wall panel structure according to claim 2 is characterized in that: Step S17 includes the following steps: Step S171: constructing a microstructure discrete unit of the rock wool curtain wall panel based on the microfiber morphology data of the wall panel to obtain a microstructure discrete unit set of the wall panel; Step S172: topologically reorganize the discrete unit set of the wall panel microstructure to obtain a reconstructed wall panel microstructure prototype; Step S173: performing parameterized digital mapping on the rock wool curtain wall panel based on the reconstructed microstructure prototype of the wall panel to obtain a microstructure parameter mapping diagram of the wall panel; Step S174: encoding the microscopic fiber structure characteristics of the rock wool curtain wall panel based on the wall panel microstructure parameter mapping diagram to obtain a wall panel microstructure characteristic code set; Step S175: Use the wall panel microstructure feature code set to perform digital twin mapping conversion on the microstructure of the rock wool curtain wall panel to obtain a first wall panel reconstructed structural model.

4. The three-dimensional simulation design method based on rock wool curtain wall panel structure according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing thermodynamic boundary mapping on the reconstructed structural model of the first wall panel to obtain initial thermodynamic field data of the wall panel; Step S22: constructing a heat conduction discrete grid for the first wall panel reconstructed structural model according to the initial thermodynamic field data of the wall panel to obtain a wall panel heat conduction grid model; Step S23: numerically simulate the internal heat conduction characteristics of the rock wool curtain wall panel based on the wall panel heat conduction grid model to obtain micro-scale heat conduction flux data; Step S24: reconstructing the spatial characteristics of the micro-scale heat conduction flux data to obtain a micro-scale heat conduction characteristic map; Step S25: performing cross-scale physical field coupling superposition on the micro-scale heat conduction characteristic diagram to obtain a multi-field comprehensive response diagram of the wall panel; Step S26: Based on the reconstructed structural model of the first wall panel and the multi-field comprehensive response diagram of the wall panel, a cross-scale performance dynamic simulation is performed on the rock wool curtain wall panel to obtain a comprehensive performance evaluation result of the wall panel.

5. The three-dimensional simulation design method based on rock wool curtain wall structure according to claim 4 is characterized in that: Step S26 includes the following steps: Step S261: extracting features from the reconstructed structural model of the first wall panel to obtain a microstructure feature vector set of the wall panel; Step S262: performing feature analysis on the multi-field comprehensive response diagram of the wall panel to obtain a frequency spectrum feature space of the wall panel response diagram; Step S263: performing cross-scale performance correlation mapping modeling based on the wallboard microstructure feature vector set and the wallboard response graph frequency spectrum feature space to obtain the wallboard performance correlation response function; Step S264: performing a thermal-mechanical-electrical multi-field coupling numerical simulation on the rock wool curtain wall panel based on the wall panel performance correlation response function to obtain a cross-scale dynamic response simulation result; Step S265: Perform collaborative performance evaluation on the cross-scale dynamic response simulation results to obtain comprehensive performance evaluation results of the wall panels.

6. The three-dimensional simulation design method based on rock wool curtain wall panel structure according to claim 5 is characterized in that: Step S265 includes the following steps: Step S2651: performing confidence evaluation on the cross-scale dynamic response simulation results to obtain a wall panel performance simulation reliability evaluation set; Step S2652: performing random perturbations on the cross-scale dynamic response simulation results to obtain a random perturbation data set of wall panel performance; Step S2653: performing extreme value distribution mapping on the random disturbance data set of wall panel performance to obtain a probability distribution diagram of wall panel performance response; Step S2654: reconstructing the confidence interval of the wall panel performance response probability distribution diagram according to the wall panel performance simulation reliability evaluation set to obtain wall panel performance confidence region mapping data; Step S2655: extract sensitivity features from the wall panel performance confidence region mapping data to obtain a curtain wall panel performance key influencing factor set, and perform risk grading on the wall panel performance confidence region mapping data according to the curtain wall panel performance key influencing factor set to obtain wall panel performance risk stratification mapping data; Step S2656: Perform a comprehensive performance evaluation on the wall panel performance risk stratification mapping data to obtain a comprehensive performance evaluation result of the wall panel.

7. The three-dimensional simulation design method based on rock wool curtain wall structure according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: obtaining a wall panel construction process parameter set, and quantifying the characteristics of the wall panel construction process parameter set to obtain a wall panel construction process parameter characteristic set; Step S32: performing entropy coding conversion on the wall panel construction process parameter feature set to obtain an entropy coding set of wall panel process parameters; Step S33: performing error probability mapping on the entropy coding set of wallboard process parameters to obtain construction error probability distribution mapping data; Step S34: spatially mapping the construction error probability distribution mapping data to obtain a wallboard construction error spatial distribution map; Step S35: performing error correlation evaluation on the wall panel construction error spatial distribution diagram to obtain a wall panel error correlation evaluation matrix, and performing hierarchical quantization encoding on the wall panel error correlation evaluation matrix to obtain a wall panel construction error index set.

8. The three-dimensional simulation design method based on rock wool curtain wall structure according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: Based on the first wall panel reconstruction structure model and according to the comprehensive performance evaluation result of the wall panel, semantic mapping of performance boundary conditions is performed on the curtain wall panel structure to obtain wall panel performance boundary condition mapping data; Step S42: performing multi-scale decoupling on the wall panel performance boundary condition mapping data to obtain a wall panel performance boundary condition decoupling factor; Step S43: performing parameterized reconstruction of the curtain wall panel structure based on the first wall panel reconstruction structural model and the wall panel performance boundary condition decoupling factor to obtain a preliminary wall panel structural parameter model; Step S44: performing structural stability evaluation on the preliminary structural parameter model of the wall panel to obtain a wall panel structural stability index; Step S45: reconstructing the boundary conditions of the rock wool curtain wall panel structure according to the wall panel structure stability index to obtain a reconstructed structural model of the second wall panel; Step S46: Designing an extreme environment multi-scenario simulation scheme for the rock wool curtain wall panel to obtain an extreme environment multi-scenario simulation scheme; Step S47: Based on the wall panel construction error index set and the extreme environment multi-scenario simulation scheme, the second wall panel reconstruction structure model is subjected to an extreme environment multi-scenario simulation to obtain the wall panel multi-scenario performance response data; Step S48: Perform limit value mapping and boundary identification on the multi-scenario performance response data of the wall panel to obtain the wall panel performance limit response data; perform risk quantification on the preset fatigue failure assessment index based on the wall panel performance limit response data to obtain the wall panel performance degradation prediction result.

9. The three-dimensional simulation design method based on rock wool curtain wall structure according to claim 1 is characterized in that: Step S5 includes the following steps: Step S51: extracting features from the wall panel performance degradation prediction results to obtain a wall panel performance degradation feature vector set; Step S52: performing a Bayesian probability significance test on the wallboard performance degradation feature vector set to obtain a significance ranking table of key degradation influencing factors; Step S53: performing entropy weight fuzzy comprehensive evaluation on the significance ranking table of key degradation influencing factors to obtain a wallboard degradation influencing weight matrix; Step S54: performing multi-criteria decision mapping on the significance ranking table of key degradation influencing factors according to the wallboard degradation influence weight matrix to obtain the key design adjustment factors of the wallboard; Step S55: adjusting the structural parameters of the rock wool curtain wall panel based on the key design adjustment factors of the wall panel to obtain a design scheme for enhancing the performance of the wall panel; Step S56: reconstructing the second wall panel reconstructed structural model through the wall panel performance enhancement design scheme to obtain an optimized wall panel three-dimensional simulation model.

10. A three-dimensional simulation design system based on rock wool curtain wall panel structure, characterized in that: Used to execute the three-dimensional simulation design method based on the rock wool curtain wall panel structure according to claim 1, the three-dimensional simulation design system based on the rock wool curtain wall panel structure comprises: The digital twin module is used to obtain the wall panel micro-morphology source data; perform isotropic micro-feature enhancement on the wall panel micro-morphology source data to obtain the wall panel micro-fiber morphology data; perform digital twin reconstruction of the rock wool curtain wall panel based on the wall panel micro-fiber morphology data to obtain the first wall panel reconstructed structural model; The performance simulation module is used to perform thermodynamic field mapping on the reconstructed structural model of the first wall panel to obtain a micro-scale heat conduction characteristic map; perform cross-scale physical field coupling and superposition on the micro-scale heat conduction characteristic map to obtain a multi-field comprehensive response map of the wall panel; perform cross-scale performance dynamic simulation of the rock wool curtain wall panel based on the multi-field comprehensive response map of the wall panel to obtain a comprehensive performance evaluation result of the wall panel; The error evaluation module is used to obtain a wall panel construction process parameter set; perform construction error evaluation on the wall panel construction process parameter set to obtain a wall panel construction error index set; The risk assessment module is used to reconstruct the performance boundary conditions of the rock wool curtain wall panel according to the comprehensive performance evaluation results of the wall panel to obtain the reconstructed structural model of the second wall panel; perform extreme environment multi-scenario simulation on the reconstructed structural model of the second wall panel based on the wall panel construction error index set to obtain the multi-scenario performance response data of the wall panel; perform fatigue failure risk assessment on the rock wool curtain wall panel according to the multi-scenario performance response data of the wall panel to obtain the wall panel performance degradation prediction results; The simulation model reconstruction module is used to extract the target optimization factors of the wall panel performance degradation prediction results to obtain the key design adjustment factors of the wall panels; optimize the structural parameters of the rock wool curtain wall panels according to the key design adjustment factors of the wall panels to obtain the wall panel performance enhancement design scheme; reconstruct the second wall panel reconstruction structural model according to the wall panel performance enhancement design scheme to obtain the optimized wall panel three-dimensional simulation model.

Images