Structural simulation optimization method and system for smart building

Abstract

The invention discloses a structure simulation optimization method and system for a smart building, and relates to the technical field of smart architecture.The method comprises the steps that a structure monitoring data flow of a target smart building is collected and obtained, and a building structure space simulation model is obtained; according to intelligent building design requirements and user demand information, a building structure optimization target is obtained, through the building structure optimization target, a building structure effect fitness function is obtained, parameter optimization analysis is carried out, a to-be-adjusted structure parameter optimization threshold value is obtained, iterative optimization is carried out, and building structure optimization parameters are determined. And carrying out structure optimization on the target smart building. The technical problems that in the prior art, the building structure design is unreasonable, and the safety and reliability of a building are affected are solved, and the technical effects that reasonable structure optimization is obtained, and the safety and reliability of the building are improved are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent buildings, and in particular to a structural simulation optimization method and system for intelligent buildings. Background Art

[0002] With the continuous advancement of computer technology and numerical simulation methods, building structure simulation technology has made significant progress in accuracy, efficiency and visualization. Building structure simulation involves multiple disciplines, such as structural engineering, computer science and physics. Interdisciplinary cooperation helps promote technological innovation and solve complex engineering problems.

[0003] The existing technology has the technical problem of unreasonable building structure design, which affects the safety and reliability of the building. Summary of the invention

[0004] The present application provides a structural simulation optimization method and system for smart buildings, which are used to solve the technical problems in the prior art of unreasonable building structure design that affect building safety and reliability.

[0005] In view of the above problems, the present application provides a structural simulation optimization method and system for smart buildings.

[0006] In a first aspect of the present application, a structural simulation optimization method for a smart building is provided, the method comprising:

[0007] The structure monitoring data stream of the target smart building is collected and acquired, wherein the structure monitoring data stream includes structure design parameter information, material performance parameters and stress monitoring data stream, and simulation modeling is performed based on the structure monitoring data stream to obtain a building structure space simulation model; the building structure optimization target is acquired according to the smart building design requirements and user demand information, and the building structure effect fitness function is obtained through the building structure optimization target; the building structure space simulation model is parameter evaluated based on the building structure effect fitness function to obtain a building structure fitness evaluation result; the building structure space simulation model is parameter optimized and analyzed based on the building structure fitness evaluation result to obtain an optimization threshold of the structure parameter to be adjusted; the optimization threshold of the structure parameter to be adjusted is iteratively optimized through the building structure space simulation model to determine the building structure optimization parameters, and the target smart building is structurally optimized based on the building structure optimization parameters.

[0008] A second aspect of the present application provides a structural simulation optimization system for smart buildings, the system comprising:

[0009] A module for acquiring a spatial simulation model of a building structure, which is used to collect and acquire a structural monitoring data stream of a target smart building, wherein the structural monitoring data stream includes structural design parameter information, material performance parameters, and stress monitoring data streams, and performs simulation modeling based on the structural monitoring data stream to obtain a spatial simulation model of the building structure; a module for acquiring a fitness function for the effect of a building structure, which is used to acquire a building structure optimization target according to the design requirements of the smart building and user demand information, and to acquire a building structure effect fitness function through the building structure optimization target; a module for acquiring a fitness evaluation result of a building structure, which is used to acquire a fitness function for the effect of a building structure; The result acquisition module is used to perform parameter evaluation on the building structure space simulation model based on the building structure effect fitness function to obtain the building structure fitness evaluation result; the to-be-adjusted structure parameter optimization threshold acquisition module is used to perform parameter optimization analysis on the building structure space simulation model based on the building structure fitness evaluation result to obtain the to-be-adjusted structure parameter optimization threshold; the smart building structure optimization module is used to iteratively optimize the to-be-adjusted structure parameter optimization threshold through the building structure space simulation model, determine the building structure optimization parameters, and perform structural optimization on the target smart building based on the building structure optimization parameters.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] The structure monitoring data stream of the target smart building is collected and acquired, and simulation modeling is performed based on the structure monitoring data stream to obtain a building structure space simulation model; the building structure optimization target is acquired according to the smart building design requirements and user demand information, and the building structure effect fitness function is acquired through the building structure optimization target; the building structure space simulation model is parameter evaluated based on the building structure effect fitness function to obtain the building structure fitness evaluation result, and the building structure space simulation model is parameter optimized and analyzed to obtain the optimization threshold of the structure parameter to be adjusted; the optimization threshold of the structure parameter to be adjusted is iteratively optimized through the building structure space simulation model to determine the building structure optimization parameters, and the target smart building is structurally optimized based on the building structure optimization parameters. The technical effect of obtaining reasonable structural optimization and helping to improve the safety and reliability of the building is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a flow chart of a structural simulation optimization method for smart buildings provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of a flow chart of determining building structure optimization parameters in a structure simulation optimization method for a smart building provided in an embodiment of the present application;

[0015] Figure 3 A schematic diagram of the structure of a structural simulation and optimization system for smart buildings provided in an embodiment of the present application.

[0016] Explanation of the reference numerals: building structure space simulation model acquisition module 10, building structure effect fitness function acquisition module 20, building structure fitness evaluation result acquisition module 30, to-be-adjusted structural parameter optimization threshold acquisition module 40, smart building structure optimization module 50. DETAILED DESCRIPTION

[0017] The present application provides a structural simulation optimization method and system for smart buildings, which is used to solve the technical problems in the prior art that the building structure design is unreasonable and affects the safety and reliability of the building.

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0019] Embodiment 1

[0020] like Figure 1 As shown, the present application provides a structural simulation optimization method for smart buildings, the method comprising:

[0021] Step S100: Acquire the structural monitoring data stream of the target smart building, wherein the structural monitoring data stream includes structural design parameter information, material performance parameters and stress monitoring data stream, and perform simulation modeling based on the structural monitoring data stream to obtain a building structure space simulation model.

[0022] Specifically, structural design parameter information includes collecting design drawings and planning documents of buildings, extracting detailed information such as the building's geometry, structure type, size, layout, etc.; material performance parameters include obtaining material property data used for construction, such as the strength of steel, the elastic modulus of concrete, the density of bricks, etc., which usually come from material suppliers or relevant standards. The stress monitoring data stream is through sensors installed at key locations of the building, real-time or periodic monitoring and recording of the stress distribution of the building under different use conditions, including temperature, humidity, load and other influencing factors. The above data are sorted, cleaned and integrated into a unified database to ensure the accuracy and integrity of the data. Using the building information modeling (BIM) software, the integrated data is input into the software, and a three-dimensional building structure model is created through the software's modeling tools. The model contains information such as the building's geometry, material properties and stress distribution, and preliminary simulation calculations are performed to simulate the structural behavior of the building under different environments and load conditions to verify the accuracy and reliability of the model. After data integration and simulation modeling, a detailed three-dimensional building structure space simulation model is finally generated. This model can accurately reflect the physical and mechanical properties of the building in the actual environment, and provide reliable basic data and tools for subsequent structural optimization and analysis, ensuring the safety and reliability of the building structure in actual use, and improving the durability and performance of the building.

[0023] Step S200: According to the smart building design requirements and user demand information, the building structure optimization target is obtained, and the building structure effect fitness function is obtained through the building structure optimization target.

[0024] Specifically, the design requirements of smart buildings include design specifications and standards such as the functional requirements, environmental adaptability, energy efficiency, and sustainability of the building. User demand information involves the specific requirements of building users, such as space utilization, comfort, safety, and economy. According to the design requirements and user needs, determine the specific goals that need to be optimized for the building structure. For example, such as minimizing the weight of the structure, maximizing the stiffness of the structure, optimizing the structural layout, etc. In many cases, multiple goals need to be optimized at the same time, and trade-offs and priority ranking are required. Define the fitness function and establish a mathematical function to quantify the degree of realization of the optimization goals of the building structure. The fitness function usually involves multiple parameters and weights to reflect the importance of different optimization goals. For example, for minimizing the weight of the structure, the fitness function is a function of the total weight of the structure. For maximizing the stiffness of the structure, the fitness function involves the deflection or deformation of the structure. The fitness function can be linear or nonlinear, and the specific form depends on the nature and complexity of the optimization goal. The input parameters of the fitness function come from the previous simulation model and monitoring data to ensure that the function can accurately reflect the actual structural performance. The fitness function can comprehensively reflect the importance of multiple optimization goals, support multi-objective optimization design, and make the optimization process more comprehensive and balanced.

[0025] Step S300: performing parameter evaluation on the building structure space simulation model based on the building structure effect fitness function to obtain a building structure fitness evaluation result.

[0026] Specifically, parameter evaluation is performed based on the fitness function of the building structure effect. The parameters are input, and the key structural parameters (such as size, material properties, stress distribution, etc.) extracted from the simulation model are input into the fitness function. The previously defined fitness function is used to evaluate these structural parameters and calculate the fitness value of each design scheme. These values ​​reflect the performance of the design scheme on the optimization target. By comparing the fitness values ​​of different schemes, it is determined which design schemes are closer to the optimization target. For example, under the goal of minimizing weight, the smaller the fitness value, the better; under the goal of maximizing stiffness, the larger the fitness value, the better. All calculated fitness values ​​are summarized to form a comprehensive evaluation table or database. The evaluation results are intuitively displayed using charts, graphs or other visualization tools, and a report containing detailed evaluation results is generated. The report content includes the fitness value of each design scheme, the degree of realization of each optimization target, and improvement suggestions, which helps to improve the quality and performance of building structure design and ensure the superiority of the final design scheme.

[0027] Step S400: performing parameter optimization analysis on the building structure space simulation model based on the building structure fitness evaluation result to obtain an optimization threshold of the structure parameter to be adjusted.

[0028] Specifically, according to the fitness evaluation results, identify the advantages and disadvantages of each design solution and determine the parameters that need to be further optimized, such as the size, material properties, stress distribution, etc. of certain components. Clarify the specific goals that need to be optimized, such as reducing structural weight, improving structural stiffness, reducing material costs, etc. Select a suitable optimization algorithm, such as genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, etc., to effectively search the parameter space, input the parameters to be optimized and the objective function (fitness function) into the optimization algorithm, build the optimization model, run the optimization algorithm, and continuously adjust the parameters through iterative calculation to find the optimal solution. After each iteration, evaluate the new parameter combination according to the fitness function and retain the solution with the best performance. According to the output of the optimization algorithm, determine the optimal value or optimal range of each parameter that needs to be optimized, such as the optimal cross-sectional size of the beam, the optimal material properties of the column, the optimal stress distribution of the node, etc. Set a reasonable optimization threshold for each parameter to ensure that these optimizations can be achieved in practical applications. For example, the minimum and maximum range of the cross-sectional size of the beam, the allowable range of variation of the material properties, etc. Through parameter optimization analysis, the quality and performance of building structure design can be improved and the safety of the structure can be ensured.

[0029] Step S500: Iteratively optimizing the optimization threshold of the structural parameter to be adjusted through the building structure space simulation model, determining the building structure optimization parameters, and performing structural optimization on the target smart building based on the building structure optimization parameters.

[0030] Specifically, an iterative optimization model is constructed, and the optimization threshold of the structural parameter to be adjusted is input into the simulation model as the initial parameter. The rationality and feasibility of the initial parameter are verified through the simulation model to ensure that the model can accurately reflect the actual situation. An appropriate iterative algorithm (such as genetic algorithm, particle swarm optimization algorithm or simulated annealing algorithm) is selected for parameter optimization. In each iteration, the fitness function is used to evaluate the pros and cons of the current parameter combination. According to the fitness value, the parameter combination is adjusted to gradually approach the optimal solution. The iteration stop condition is set, such as reaching the maximum number of iterations, the fitness value change is less than the set threshold, or the fitness value reaches the target value. When the iteration process converges, the optimal parameter combination is determined. Confirm the optimal parameter combination obtained in the iterative optimization process to ensure the operability and rationality of these parameters in practical applications. The effectiveness of the optimal parameters is verified again through the simulation model to ensure that the performance of the optimized building structure meets expectations. The structure of the target smart building is optimized based on the optimized parameters, and the optimized parameters are applied to the building structure design drawings. The design plan is updated. According to the new design plan, the construction plan and material selection are adjusted to ensure that the actual construction can be carried out according to the optimized plan. During the actual construction process, the optimization effect is monitored and evaluated to ensure that the building structure performance reaches the expected target. Based on the evaluation results, the design scheme is further adjusted and optimized to continuously improve the building structure performance. The accuracy and reliability of smart building design are ensured through iterative optimization and parameter optimization.

[0031] In a possible implementation, step S100 further includes:

[0032] Step S110: obtaining a data preprocessing program, and preprocessing the structure monitoring data stream based on the data preprocessing program to obtain a structure standard monitoring data stream.

[0033] Step S120: Perform three-dimensional modeling based on the structural design parameter information and material performance parameters in the structural standard monitoring data stream to generate a building structure frame space model.

[0034] Step S130: performing force simulation analysis on the building structure frame space model through the stress monitoring data stream in the structural standard monitoring data stream to obtain a foundation structure space simulation model.

[0035] Step S140: comparing and verifying the infrastructure space simulation model to obtain a model reliability coefficient, and optimizing parameters of the infrastructure space simulation model based on the model reliability coefficient to obtain the building structure space simulation model.

[0036] Specifically, we first need to obtain a special data preprocessing program, which is applied to the structural monitoring data stream of the target smart building. These data streams may contain various complex, diverse, and possibly non-standard or inaccurate data. Through the operation of this preprocessing program, a series of operations are performed. For example, the noise and outliers in the data are cleaned up to make the data purer; the format of the data is unified and standardized to make it easier for subsequent processing and analysis; the missing data is reasonably filled to ensure the integrity of the data. After such a comprehensive and meticulous preprocessing process, the structural standard monitoring data stream is obtained. Compared with the initial structural monitoring data stream, this data stream is more accurate, standardized, and has higher availability, ensuring that the entire process can be promoted based on high-quality data, thereby improving the credibility and effectiveness of the final result.

[0037] Structural design parameter information is extracted from the structural standard monitoring data stream. This information describes various aspects of the building in detail, such as the overall shape, which may include whether the building is a cuboid, cylinder or other peculiar shape; specific dimensions, such as precise values ​​of height, width, length, etc.; as well as the division of internal space and the layout of different areas. Material performance parameters are also fully utilized. These parameters describe the various characteristics of the materials used in the building, such as how strong a certain material is, what is the elastic modulus, or the density. Using professional 3D modeling software or tools, start building a model based on these rich structural design parameter information and material performance parameters. For shape, accurately shape the outline of the building according to the design parameters. For size, strictly determine the size and proportion of each part according to the given values. The material performance parameters will be reflected in the model as the characteristics of different parts, such as areas with high strength will appear more solid in the model, and parts with good elasticity may have corresponding performance. The resulting building structure frame space model is a very detailed and realistic 3D representation that not only shows the appearance of the building, but also contains its internal structure and material properties.

[0038] The stress monitoring data stream contains detailed information about the stresses borne by various parts of the building, such as specific values ​​of pressure, tension, etc. at different locations. Apply these stress data to the already constructed spatial model of the building structure frame. This is like applying actual forces to the model, putting it in a state of stress. Use professional simulation analysis tools or software to simulate and calculate the response of the model under these stresses. Analyze how the various parts of the model deform, how to resist stress, whether cracks or other damage will occur, etc. Through this stress simulation analysis, you can fully understand the performance of the building under different stress conditions. The resulting basic structure space simulation model not only contains the original structural frame of the building, but also incorporates various changes and characteristics under stress conditions. Through this model, you can predict various stress conditions that the building may encounter in actual use, and take corresponding measures in advance to optimize the structural design or strengthen key parts to ensure the safety and reliability of the building.

[0039] Comparison and verification of the infrastructure space simulation model involves a detailed comparison of the infrastructure space simulation model with known historical data of actual buildings or data obtained through other reliable channels. During the comparison process, the consistency, accuracy and rationality of the model in all aspects will be checked. Through this comparison, a model reliability coefficient will be obtained. This coefficient is a quantitative indicator used to indicate the reliability of the infrastructure space simulation model. It is a numerical value. The higher the value, the more reliable the model is. On the contrary, it indicates that there are some deviations or uncertainties. Parameters are tuned based on this model reliability coefficient. If the reliability coefficient is low, it is necessary to carefully analyze which parameters in the model may have problems, such as the setting of certain structural dimensions, the value of material performance parameters, etc. By adjusting these parameters, the model is closer to the actual situation. During the tuning process, it is necessary to repeatedly perform comparison verification and parameter adjustment until a satisfactory result is obtained, that is, the model reliability coefficient reaches an acceptable level. The final building structure space simulation model is an optimized and improved model with higher accuracy and reliability. It can better reflect the actual structure and stress conditions of the building, and provide a more reliable basis for subsequent building design optimization, safety assessment, etc.

[0040] In a possible implementation, step S200 further includes:

[0041] Step S210: Decomposing the building structure optimization target to determine a set of structural optimization sub-targets.

[0042] Step S220: constructing a smart building structure database, and performing associated data aggregation on the smart building structure database based on the structure optimization sub-target set to obtain a sub-target building structure data set.

[0043] Step S230: performing objective function effect fitting on the sub-objective building structure data sets respectively to obtain a set of structural sub-objective fitness functions.

[0044] Step S240: weighted fusion of each fitness function in the structure sub-objective fitness function set to obtain the building structure effect fitness function.

[0045] Specifically, it is a comprehensive requirement to clarify the goal of building structure optimization, such as reducing the dead weight of the structure, improving space utilization, and enhancing wind resistance under the premise of ensuring safety. Then, this overall goal is carefully decomposed, involving disassembly from different dimensions and levels. From the perspective of structural safety, sub-goals such as improving the strength of certain key parts and improving the stability of the overall structure are disassembled. From the perspective of material use, it includes goals such as selecting more suitable building materials to reduce costs or improve performance. From the perspective of space utilization, it can be decomposed into sub-goals such as optimizing internal layout and increasing effective use of space. From the perspective of environmental adaptability, various sub-goals such as enhancing wind resistance, earthquake resistance, and water resistance can be disassembled. Through such disassembly, a set of structural optimization sub-goals is determined. Each sub-goal in this set has a clear direction and operability.

[0046] Construct a smart building structure database, which is a repository containing rich information related to building structures. It can include design parameters, actual performance data, material properties, construction processes and other information of various buildings. For each sub-goal in the set of structural optimization sub-goals, the smart building structure database is aggregated with associated data, which means that data closely related to specific sub-goals must be screened out from the huge database. For example, for the sub-goal of improving the strength of key parts, it is necessary to find the structural design data, previous strength test data, and material performance data of the key parts from the database, and aggregate these related data together to form a building structure data set specifically for this sub-goal. Similarly, for other sub-goals, similar associated data screening and aggregation operations will be performed to obtain a series of sub-goal building structure data sets. These data sets provide the basis and basis for the subsequent specific analysis and optimization of each sub-goal. By in-depth study of these data sets, we can better understand the current status and potential improvement direction of each sub-goal. The smart building structure database provides strong data support for building structure optimization, making the optimization process more scientific, accurate and efficient.

[0047] After obtaining the data sets of each sub-target building structure, the next step is to fit the objective function effect on them respectively. The objective function here is a mathematical expression used to measure the degree of achievement or effect of each sub-target. By using various data analysis and fitting techniques, try to find the best matching relationship between the data set and the objective function. After such processing, the fitness function corresponding to each sub-target can be obtained. This fitness function quantitatively describes the realization of the sub-target, and the degree of achievement of the sub-target under different conditions or parameter settings. The formed set of structural sub-target fitness functions is like a set of evaluation tools, which provides a measurement standard for each sub-target. These fitness functions can be used for subsequent optimization decisions, program evaluation and other work.

[0048] The importance and influence of each sub-goal may not be exactly the same. By weighting and fusing the fitness functions in the set of structural sub-goal fitness functions, the relative weights of different sub-goals are comprehensively considered. The weighting process is to assign a suitable weight coefficient to each fitness function according to actual needs and emphasis. These weight coefficients reflect the importance of each sub-goal in the overall building structure effect. For example, if safety is the most critical factor, the sub-goal fitness function related to safety may be given a higher weight; if aesthetics is relatively less important, its corresponding weight may be lower. Then, multiply each fitness function by its corresponding weight and sum all the results to obtain the building structure effect fitness function. This function integrates the information of all sub-goals and reflects the differences in their respective importance, reflecting the comprehensive effect of the entire building structure more comprehensively and accurately. In practical applications, this building structure effect fitness function can be used to conveniently evaluate and compare different building structure design schemes, construction strategies, etc. By comparing the values ​​of this function in different situations, it can be determined which scheme or strategy can better achieve the overall building structure optimization goal.

[0049] In a possible implementation, step S400 further includes:

[0050] Step S410: extracting the performance of the structure to be optimized based on the building structure fitness evaluation result to obtain performance variable information of the building structure to be optimized.

[0051] Step S420: performing associated parameter analysis on the building structure space simulation model according to the building structure performance variable information to be optimized, and determining associated structural parameter type information to be optimized.

[0052] Step S430: performing structure-performance correlation fitting on the smart building structure database to obtain a mapping relationship between structure parameters and building structure performance.

[0053] Step S440: Calculate the variable information of the building structure performance to be optimized according to the type information of the associated structural parameter to be optimized and based on the structural parameter-building structure performance mapping relationship to obtain the optimization threshold of the structural parameter to be adjusted.

[0054] Specifically, once the results of the building structure fitness assessment are available, we can use them to deeply analyze and extract those aspects of the structural performance that need to be optimized and improved. For example, if the assessment results show that the stability of the structure is not ideal under certain conditions, then the structural performance of "stability" is extracted and becomes an item to be optimized. These extracted specific structural performances are presented in the form of variables, and the variable information of the building structure performance to be optimized is obtained.

[0055] First of all, it is necessary to clarify what the information on the performance variables of the building structure to be optimized specifically includes, such as variables related to insufficient structural strength, or variables related to poor stability and the need to improve seismic performance. Once the information on the performance variables of the building structure to be optimized is available, it is necessary to combine it with the spatial simulation model of the building structure for analysis. In this process, carefully examine each element and parameter in the model. For example, for the case of insufficient strength, it is necessary to analyze the parameters such as the size and material properties of each component in the model; for stability issues, it is necessary to pay attention to the overall layout of the structure, the setting of supports and other parameters. Through such in-depth and meticulous analysis, the type information of structural parameters closely related to these performance variables to be optimized is gradually determined. These types of information can be the size parameters of a specific component, such as the width of a beam and the height of a column; they can also be parameters of a certain connection method, such as the welding strength of a node; they can also be certain characteristic parameters of the material, such as the elastic modulus.

[0056] Work is carried out on the smart building structure database, which stores a large amount of building structure related information, including parameters of various structures and corresponding performance performance. By using data analysis and fitting techniques, these massive data are processed and analyzed. This correlation fitting involves mathematical models and algorithms. For example, regression analysis, neural network and other methods can be used to establish a mapping relationship between structural parameters and building structure performance. For example, for the support vector machine algorithm, it will find the optimal partitioning hyperplane in the database data to determine the boundary and relationship between structural parameters and performance. It can be clearly stated that within which structural parameter value range, the building structure performance will be in a certain state, and crossing this boundary will lead to a significant change in performance. In this way, the support vector machine algorithm provides a mapping relationship between structural parameters and building structure performance. The obtained structural parameter-building structure performance mapping relationship can clearly show how specific structural parameter changes will affect the building structure performance. For example, it may be found that increasing the strength of a certain material will increase the overall stability of the structure by a certain proportion; or changing the cross-sectional size of a certain component will have a specific effect on the bearing capacity of the structure.

[0057] According to the previously determined information on the type of associated structural parameters to be optimized, the specific mapping rules corresponding to these parameter types are found from the structural parameter-building structure performance mapping relationship. Using these mapping rules, the performance variable information of the building structure to be optimized is substituted into it for calculation. For example, if the performance variable to be optimized is to improve a certain structural strength, and the associated structural parameter is the size of a certain component, then the specific numerical range to which the component size needs to be adjusted in order to achieve the strength improvement goal is calculated according to the mapping relationship, and the boundary value of this range is the optimization threshold of the structural parameter to be adjusted. For example, assuming that the mapping relationship established by the neural network algorithm shows that in order to improve the seismic performance of the building to a certain level, the cross-sectional size of a certain key support needs to be increased by at least 5 cm, then this 5 cm is the optimization threshold of the structural parameter. Or through regression analysis, it is concluded that in order to improve the overall stability of the structure by 10%, the tightness of a certain connection method needs to reach a specific value, and this value is the corresponding optimization threshold. Through such precise calculations, it is clear to what extent each related structural parameter needs to be adjusted in order to achieve the performance optimization goal, thereby providing accurate and clear guidance for subsequent actual optimization operations.

[0058] In one possible implementation, Figure 2 As shown, step S500 further includes:

[0059] Step S510: randomly obtaining a plurality of building structure parameters based on the optimization threshold of the structural parameter to be adjusted, and performing simulation fitting on the plurality of building structure parameters through the building structure space simulation model to obtain a plurality of building structure performance simulation results.

[0060] Step S520: Utilizing the building structure effect fitness function to perform parameter evaluation on the plurality of building structure performance simulation results, and obtaining a plurality of building structure fitness evaluation information.

[0061] Step S530: Optimizing the plurality of building structure parameters based on the plurality of building structure fitness evaluation information to determine the building structure optimization parameters.

[0062] Specifically, optimizing the threshold based on the structural parameters to be adjusted means operating within a specific parameter range or limited conditions. This threshold sets the boundary and possibility of parameter values. Randomly obtaining multiple building structure parameters emphasizes the randomness of parameter acquisition. Through random generation, a wider range of possible parameter combinations can be covered, avoiding being limited to specific preset modes, which helps to explore different design possibilities. The model is processed through the building structure space simulation model, which is a tool specifically used to simulate the behavior and performance of building structures under different parameter conditions. It can perform complex calculations and analyses based on the input building structure parameters. These randomly generated parameters are input into the model one by one, allowing the model to simulate various performance characteristics of the corresponding building structure according to the parameters, such as mechanical properties, deformation, stability, etc. Finally, multiple building structure performance simulation results are obtained. These results reflect the actual performance of the building structure under different parameter combinations. These simulation results will serve as an important basis for subsequent evaluation and optimization decisions, helping to determine the building structure parameters that best meet the needs and goals.

[0063] The building structure effect fitness function contains a series of standards and rules for measuring the performance of building structures. It will take into account multiple factors, such as structural stability, strength, durability, economy, etc. When multiple building structure performance simulation results are input into this function, the function will quantitatively evaluate and score each simulation result according to the criteria and weights set internally. In this way, multiple building structure fitness evaluation information corresponding to different building structure performance simulation results can be obtained. These evaluation information are presented in the form of specific values ​​or indicators, reflecting the degree to which each simulation result meets the building structure effect.

[0064] First, there are multiple building structure fitness evaluation information, which reflects the performance of each building structure parameter combination. These evaluation information are analyzed and compared, and the parameter combinations with higher fitness are preliminarily screened out according to the fitness value. In the parameter optimization process, not only a single fitness value should be considered, but also other factors, such as the balance of different performance aspects, practical feasibility, cost-effectiveness, etc. Through further in-depth analysis and weighing, the group or groups of parameters that best meet the overall requirements are selected from multiple parameter combinations with better performance. The parameters that are finally determined are identified as building structure optimization parameters. They represent the best or better building structure parameter settings under the current conditions and goals, which can achieve better building structure effects and meet the needs of safety, functionality, economy and other aspects.

[0065] In a possible implementation, step S500 further includes:

[0066] Step S540: screening the plurality of building structure parameters based on the plurality of building structure fitness evaluation information to obtain the building structure parameter cluster center and the building structure parameters in the remaining clusters.

[0067] Step S550: setting a parameter learning step length, optimizing and learning the building structure parameters in the remaining clusters toward the center of the building structure parameter cluster according to the parameter learning step length, and obtaining a building structure optimization parameter cluster.

[0068] Step S560: comparing and optimizing the building structure optimization parameter clusters, determining the parameter update cluster center, and using the parameter update cluster center as the building structure optimization parameter.

[0069] Specifically, the fitness evaluation information of multiple building structures obtained previously is used to perform specific screening operations, and the numerous building structure parameters are classified and identified according to certain standards and algorithms. In terms of standards, a specific fitness value threshold is set, and only parameter combinations that exceed the threshold can be regarded as cluster centers. In terms of algorithms, intelligent optimization algorithms, such as genetic algorithms and particle swarm algorithms, determine the optimal cluster centers and cluster parameter divisions through iterative searches. In this process, those parameter combinations whose fitness evaluation information shows high consistency and outstanding advantages, that is, the building structure parameters with the best fitness, will be selected and determined as the building structure parameter cluster center. Although other parameter combinations may also have certain characteristics, there are certain gaps in some aspects compared to the cluster center, and these parameter combinations are classified as the remaining cluster building structure parameters.

[0070] Determine a suitable parameter learning step size, which determines the speed and magnitude of the building structure parameters in the remaining clusters approaching the cluster center. For those building structure parameters classified as the remaining clusters, they will gradually move or adjust toward the center of the building structure parameter cluster with the set step size. In this process, with each step size advancement, these parameters will gradually approach the better state represented by the cluster center. In this way, a cluster of building structure parameters after optimized learning is finally obtained.

[0071] When comparing and optimizing the cluster of building structure optimization parameters, it is necessary to determine a parameter update cluster center as the final building structure optimization parameter. This parameter update cluster center is obtained by replacing the original parameter cluster center with the optimal fitness parameter after learning optimization. Clarify the goal of building structure optimization, such as minimizing weight, maximizing strength, etc., and define a fitness function to evaluate the performance of each parameter combination according to the optimization goal. Use a suitable optimization algorithm, such as a genetic algorithm, to iteratively optimize the building structure optimization parameter cluster. Each parameter combination in the building structure optimization parameter cluster is regarded as an individual, that is, a chromosome in the genetic algorithm. In the initialization stage, a batch of initial individuals are randomly generated to form the initial population, and then the iteration process is entered. In each round of iteration, the fitness evaluation is performed, and the performance of the parameter combination represented by each individual in terms of building structure is calculated according to a specific fitness function, such as the comprehensive score in terms of strength, stability, etc. The selection operation selects individuals with higher fitness according to the fitness value. These individuals have a greater chance of being selected to participate in subsequent genetic operations. The crossover operation randomly selects some selected individual pairs, generates new offspring individuals through the crossover operation, and combines the characteristics of different individuals. The mutation operation randomly mutates some individuals to increase the diversity of the population and prevent the algorithm from converging to the local optimal solution too early. After rounds of iterations, the individuals in the population continue to evolve and their fitness gradually improves. As the iterations proceed, the parameter cluster gradually develops in a better direction, and those parameter combinations with better fitness are retained and further optimized. Finally, after enough iterations, an optimized building structure parameter cluster is obtained, which contains the optimal or near-optimal parameter combination found after iterative optimization by the genetic algorithm, realizing the effective iterative optimization of the building structure optimization parameter cluster, and replacing the original parameter cluster center with the optimal fitness parameter after learning optimization.

[0072] In a possible implementation, step S550 further includes:

[0073] Step S551: optimizing and learning the building structure parameters in the remaining clusters toward the center of the building structure parameter cluster according to the parameter learning step length to obtain a building structure learning parameter cluster.

[0074] Step S552: performing fitness gradient calculation on the building structure learning parameter cluster, determining the parameter variation direction, and setting the parameter variation increment according to the parameter variation direction.

[0075] Step S553: ​​Based on the parameter variation direction and the parameter variation increment, the variation distribution of the building structure learning parameter cluster is optimized to obtain the building structure optimization parameter cluster.

[0076] Specifically, the building structure parameters in the remaining clusters are identified, which are the parameters other than the center of the building structure parameter cluster. The moving direction and amplitude of these parameters are guided according to the set parameter learning step size. With this step size as a unit, adjustments and optimizations are made towards the center of the building structure parameter cluster. Through such gradual and directional adjustments, a new parameter set is finally formed, namely the building structure learning parameter cluster.

[0077] When calculating the fitness gradient of the architectural structure learning parameter cluster, we are analyzing the impact of each parameter change in different directions on the overall fitness, and finding the direction that can make the parameter fitness rise the fastest and most significantly, which is the maximum gradient direction. Determining this maximum gradient direction as the parameter variation direction means that changing the parameters along this direction will bring the maximum possible improvement in fitness. And setting the parameter variation increment according to this parameter variation direction is to decide how much the parameter value should be changed in this direction. If the variation increment is set to a large value, the parameter changes will be very drastic, and it may quickly approach or reach a better fitness state, but it may also miss some better subtle adjustments because of taking too big a step; if the variation increment is set to a small value, although the speed of progress may be slower, it can be explored and adjusted more finely to avoid instability caused by overly radical changes.

[0078] Based on the parameter mutation direction and mutation increment, the process of performing mutation distribution optimization on the building structure learning parameter cluster is divided into the following steps: 1. Determine the mutation direction. According to the result of fitness gradient calculation, the maximum gradient direction of parameter fitness increase is taken as the parameter mutation direction. In this direction, the parameter fitness increase changes the most. 2. Set the mutation increment. According to the mutation direction, set the appropriate parameter mutation increment. The size of the mutation increment determines the variation amplitude of the parameter in this direction. 3. Perform mutation operation. According to the determined mutation direction and mutation increment, mutate each parameter in the building structure learning parameter cluster. The mutation operation can be achieved by adding or subtracting the mutation increment from the original parameter value. 4. Evaluate the mutation results, evaluate the fitness of the mutated parameter cluster, and calculate the fitness value of each parameter combination. 5. Select optimization parameters. According to the fitness evaluation results, select the parameter cluster with higher fitness as the building structure optimization parameter cluster. Through the above steps, the mutation distribution optimization can be performed on the basis of the building structure learning parameter cluster to obtain a better building structure optimization parameter cluster. These optimized parameter clusters can be used for further building structure design and analysis to improve the performance and quality of the building.

[0079] Embodiment 2

[0080] Based on the same inventive concept as the structural simulation optimization method for smart buildings in the aforementioned embodiment, Figure 3 As shown, the present application provides a structural simulation optimization system for smart buildings. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0081] The building structure space simulation model acquisition module 10 is used to collect and acquire the structure monitoring data stream of the target smart building, wherein the structure monitoring data stream includes structure design parameter information, material performance parameters and stress monitoring data stream, and perform simulation modeling based on the structure monitoring data stream to obtain the building structure space simulation model.

[0082] The building structure effect fitness function acquisition module 20 is used to obtain the building structure optimization target according to the smart building design requirements and user demand information, and obtain the building structure effect fitness function through the building structure optimization target.

[0083] The building structure fitness evaluation result acquisition module 30 is used to perform parameter evaluation on the building structure space simulation model based on the building structure effect fitness function to obtain the building structure fitness evaluation result.

[0084] The module 40 for obtaining the optimized threshold value of the structural parameter to be adjusted is used to perform parameter optimization analysis on the building structure space simulation model based on the building structure fitness evaluation result to obtain the optimized threshold value of the structural parameter to be adjusted.

[0085] The smart building structure optimization module 50 is used to iteratively optimize the optimization threshold of the structural parameter to be adjusted through the building structure space simulation model, determine the building structure optimization parameters, and optimize the structure of the target smart building based on the building structure optimization parameters.

[0086] Furthermore, the building structure space simulation model acquisition module 10 also includes:

[0087] A structural standard monitoring data stream acquisition unit is used to acquire a data preprocessing program, preprocess the structural monitoring data stream based on the data preprocessing program, and acquire the structural standard monitoring data stream.

[0088] A building structure frame space model generation unit is used to perform three-dimensional modeling based on the structural design parameter information and material performance parameters in the structural standard monitoring data stream to generate a building structure frame space model.

[0089] The basic structure space simulation model acquisition unit is used to perform force simulation analysis on the building structure frame space model through the stress monitoring data stream in the structural standard monitoring data stream to obtain the basic structure space simulation model.

[0090] The building structure space simulation model acquisition unit is used to compare and verify the basic structure space simulation model to obtain a model reliability coefficient, and to optimize the parameters of the basic structure space simulation model based on the model reliability coefficient to obtain the building structure space simulation model.

[0091] Furthermore, the building structure effect fitness function acquisition module 20 also includes:

[0092] A structural optimization sub-target set determination unit is used to decompose the building structure optimization target and determine a structural optimization sub-target set.

[0093] The sub-target building structure data set acquisition unit is used to construct a smart building structure database, and based on the structure optimization sub-target set, the smart building structure database is respectively aggregated with associated data to obtain the sub-target building structure data set.

[0094] The structure sub-objective fitness function set acquisition unit is used to perform objective function effect fitting on the sub-objective building structure data sets respectively to obtain the structure sub-objective fitness function set.

[0095] The building structure effect fitness function acquisition unit is used to perform weighted fusion on each fitness function in the structure sub-objective fitness function set to obtain the building structure effect fitness function.

[0096] Furthermore, the to-be-adjusted structural parameter optimization threshold acquisition module 40 further includes:

[0097] Based on the building structure fitness evaluation result, the performance of the structure to be optimized is extracted to obtain the performance variable information of the building structure to be optimized.

[0098] The unit for determining the type information of the associated structural parameters to be optimized is used to perform associated parameter analysis on the building structure space simulation model according to the building structure performance variable information to be optimized, and determine the type information of the associated structural parameters to be optimized.

[0099] A structural parameter-building structure performance mapping relationship acquisition unit is used to perform structural performance correlation fitting on the smart building structure database to obtain a structural parameter-building structure performance mapping relationship.

[0100] The optimization threshold value acquisition unit of the structural parameter to be adjusted is used to calculate the performance variable information of the building structure to be optimized based on the structural parameter-building structure performance mapping relationship according to the type information of the associated structural parameter to be optimized, so as to obtain the optimization threshold value of the structural parameter to be adjusted.

[0101] Furthermore, the smart building structure optimization module 50 also includes:

[0102] The building structure performance simulation result acquisition unit is used to randomly obtain multiple building structure parameters based on the optimization threshold of the structural parameter to be adjusted, simulate and fit the multiple building structure parameters through the building structure space simulation model, and obtain multiple building structure performance simulation results.

[0103] The building structure fitness evaluation information acquisition unit is used to use the building structure effect fitness function to perform parameter evaluation on the multiple building structure performance simulation results to obtain multiple building structure fitness evaluation information.

[0104] A building structure optimization parameter determination unit is used to perform parameter optimization on the multiple building structure parameters based on the multiple building structure fitness evaluation information to determine the building structure optimization parameters.

[0105] Furthermore, the smart building structure optimization module 50 also includes:

[0106] The building structure parameter screening unit is used to screen the multiple building structure parameters based on the multiple building structure fitness evaluation information to obtain the building structure parameter cluster center and the building structure parameters in the remaining clusters.

[0107] The building structure optimization parameter cluster acquisition unit is used to set a parameter learning step length, optimize and learn the building structure parameters in the remaining clusters according to the parameter learning step length toward the center of the building structure parameter cluster, and obtain the building structure optimization parameter cluster.

[0108] The building structure optimization parameter cluster optimization unit is used to compare and optimize the building structure optimization parameter cluster, determine the parameter update cluster center, and use the parameter update cluster center as the building structure optimization parameter.

[0109] Furthermore, the building structure optimization parameter cluster acquisition unit further includes:

[0110] The building structure learning parameter cluster acquisition unit is used to optimize the building structure parameters in the remaining clusters according to the parameter learning step length toward the center of the building structure parameter cluster to obtain the building structure learning parameter cluster.

[0111] A parameter variation increment setting unit is used to perform fitness gradient calculation on the building structure learning parameter cluster, determine the parameter variation direction, and set the parameter variation increment according to the parameter variation direction.

[0112] The building structure learning parameter cluster variation distribution optimization unit is used to perform variation distribution optimization on the building structure learning parameter cluster based on the parameter variation direction and the parameter variation increment to obtain the building structure optimized parameter cluster.

[0113] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0114] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0115] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A structural simulation optimization method for smart buildings, characterized in that: The method comprises: Collecting and acquiring a structural monitoring data stream of a target smart building, wherein the structural monitoring data stream includes structural design parameter information, material performance parameters, and stress monitoring data stream, and performing simulation modeling based on the structural monitoring data stream to obtain a building structure space simulation model; According to the smart building design requirements and user demand information, the building structure optimization target is obtained, and the building structure effect fitness function is obtained through the building structure optimization target; Based on the building structure effect fitness function, parameter evaluation is performed on the building structure space simulation model to obtain a building structure fitness evaluation result; Based on the building structure fitness evaluation result, parameter optimization analysis is performed on the building structure space simulation model to obtain an optimization threshold value of the structure parameter to be adjusted; The optimization threshold of the structural parameter to be adjusted is iteratively optimized through the building structure space simulation model to determine the building structure optimization parameters, and the structure of the target smart building is optimized based on the building structure optimization parameters.

2. A structural simulation optimization method for smart buildings according to claim 1, characterized in that: The obtaining of the building structure space simulation model comprises: Acquire a data preprocessing program, and preprocess the structure monitoring data stream based on the data preprocessing program to acquire a structure standard monitoring data stream; Perform three-dimensional modeling based on the structural design parameter information and material performance parameters in the structural standard monitoring data stream to generate a building structural frame space model; Through the stress monitoring data stream in the structural standard monitoring data stream, a stress simulation analysis is performed on the building structure frame space model to obtain a foundation structure space simulation model; The basic structure space simulation model is compared and verified to obtain a model reliability coefficient, and parameters of the basic structure space simulation model are optimized based on the model reliability coefficient to obtain the building structure space simulation model.

3. A structural simulation optimization method for smart buildings according to claim 1, characterized in that: The obtaining of the building structure effect fitness function comprises: Decomposing the building structure optimization target to determine a set of structural optimization sub-targets; Constructing a smart building structure database, and aggregating associated data of the smart building structure database based on the structure optimization sub-target set to obtain a sub-target building structure data set; Performing objective function effect fitting on the sub-objective building structure data sets respectively to obtain a set of structural sub-objective fitness functions; The fitness functions in the structure sub-objective fitness function set are weightedly fused to obtain the building structure effect fitness function.

4. A structural simulation optimization method for smart buildings as claimed in claim 3, characterized in that: The step of obtaining the optimization threshold of the structural parameter to be adjusted includes: Extracting the performance of the structure to be optimized based on the building structure fitness evaluation result to obtain the performance variable information of the building structure to be optimized; Performing associated parameter analysis on the building structure space simulation model according to the building structure performance variable information to be optimized, and determining associated structural parameter type information to be optimized; Performing structural performance correlation fitting on the smart building structure database to obtain a mapping relationship between structural parameters and building structure performance; According to the type information of the associated structural parameters to be optimized and based on the structural parameter-building structure performance mapping relationship, the building structure performance variable information to be optimized is calculated to obtain the optimization threshold of the structural parameter to be adjusted.

5. The structural simulation optimization method for smart buildings according to claim 1, characterized in that: The step of determining the building structure optimization parameters comprises: Based on the optimization threshold of the structural parameter to be adjusted, a plurality of building structure parameters are randomly obtained, and simulation fitting is performed on the plurality of building structure parameters through the building structure space simulation model to obtain a plurality of building structure performance simulation results; Using the building structure effect fitness function to perform parameter evaluation on the multiple building structure performance simulation results to obtain multiple building structure fitness evaluation information; The plurality of building structure parameters are optimized based on the plurality of building structure fitness evaluation information to determine the building structure optimization parameters.

6. A structural simulation optimization method for smart buildings as claimed in claim 5, characterized in that: The step of determining the building structure optimization parameters comprises: Screening the plurality of building structure parameters based on the plurality of building structure fitness evaluation information to obtain a building structure parameter cluster center and building structure parameters in other clusters; Setting a parameter learning step length, optimizing and learning the building structure parameters in the remaining clusters toward the center of the building structure parameter cluster according to the parameter learning step length, and obtaining a building structure optimization parameter cluster; The building structure optimization parameter clusters are compared and optimized to determine the parameter update cluster center, and the parameter update cluster center is used as the building structure optimization parameter.

7. A structural simulation optimization method for smart buildings as claimed in claim 6, characterized in that: The step of obtaining the building structure optimization parameter cluster comprises: Optimizing and learning the building structure parameters in the remaining clusters toward the center of the building structure parameter cluster according to the parameter learning step length to obtain a building structure learning parameter cluster; Performing fitness gradient calculation on the building structure learning parameter cluster, determining a parameter variation direction, and setting a parameter variation increment according to the parameter variation direction; Based on the parameter variation direction and the parameter variation increment, the variation distribution of the building structure learning parameter cluster is optimized to obtain the building structure optimization parameter cluster.

8. A structural simulation and optimization system for smart buildings, characterized in that: The system comprises: A building structure space simulation model acquisition module, which is used to collect and acquire the structure monitoring data stream of the target smart building, wherein the structure monitoring data stream includes structure design parameter information, material performance parameters and stress monitoring data stream, and perform simulation modeling based on the structure monitoring data stream to obtain the building structure space simulation model; A building structure effect fitness function acquisition module, the building structure effect fitness function acquisition module is used to obtain a building structure optimization target according to the smart building design requirements and user demand information, and obtain a building structure effect fitness function through the building structure optimization target; A building structure fitness evaluation result acquisition module, wherein the building structure fitness evaluation result acquisition module is used to perform parameter evaluation on the building structure space simulation model based on the building structure effect fitness function to obtain a building structure fitness evaluation result; A module for obtaining an optimization threshold value of a parameter of a structure to be adjusted, wherein the module is used to perform parameter optimization analysis on the spatial simulation model of the building structure based on the fitness evaluation result of the building structure, and obtain an optimization threshold value of the parameter of the structure to be adjusted; A smart building structure optimization module, the smart building structure optimization module is used to iteratively optimize the optimization threshold of the structural parameter to be adjusted through the building structure space simulation model, determine the building structure optimization parameters, and optimize the structure of the target smart building based on the building structure optimization parameters.

Images