Existing building parameterization design method based on BIM

Abstract

The invention discloses a BIM-based existing building parameterization design method, and particularly relates to the field of building optimization design, and the method comprises the following steps: firstly, carrying out the data collection of an existing building, building a BIM model, simulating the daily use condition of the BIM model, and obtaining a noise data set of each region; judging whether noise pollution exists or not through the noise data, if yes, dividing the area into pollution areas, and summarizing the data to generate a pollution information set; performing clustering analysis based on the information set, generating a pollution level form, and generating a comprehensive pollution coefficient by using a pre-trained machine learning model; and selecting average or maximum noise as an optimization target according to the coefficient, finding an optimal optimization parameter combination by using a genetic algorithm, and finally forming an optimization design scheme of the whole building. According to the method, differentiated design of different noise level areas is guaranteed, the forced sound insulation requirement of a high-noise area can be met, and an area with low noise can be moderately optimized.

Description

Technical Field

[0001] The present invention relates to the field of building optimization design, and more specifically, to a BIM-based parametric design method for existing buildings. Background Art

[0002] In modern urban construction and development, noise pollution has become a key issue affecting the comfort and safety of buildings. Especially in existing buildings, due to the lack of sufficient consideration of noise control in the initial design stage, many buildings are troubled by noise pollution in daily use. Traditional noise control methods mostly use simple installation of sound insulation materials or partial modification of walls, lacking systematic evaluation and dynamic optimization of the entire building.

[0003] With the popularization of BIM (Building Information Modeling) technology, building design and management are gradually moving towards digitalization and intelligence. BIM models can be used to manage and analyze building structures, material usage and daily usage in a digital way. Especially in the field of noise pollution control, BIM technology provides strong support for parametric optimization design. However, in the field of noise pollution assessment and control, the existing technology still lacks a systematic method for multi-dimensional analysis and optimization using big data and intelligent algorithms. Therefore, a parametric design method for noise control of existing buildings based on BIM is proposed, which realizes dynamic optimization and cost control of building noise through data collection, pollution assessment, machine learning and genetic algorithms. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions: The BIM-based parametric design method for existing buildings includes the following steps: Collect data from existing buildings and establish BIM models, simulate the daily use of existing buildings, and divide the BIM models into regions to obtain multiple building areas and obtain noise data sets for the target areas; Determine whether the target area is noise polluted based on the noise data set of the target area. If there is noise pollution, the area is divided into a polluted area, and the noise data sets of all polluted areas are summarized to obtain a pollution information set. Based on the pollution information set, cluster analysis is performed to obtain a pollution level form for the target area. The pollution level form for the target area is then fed into a pre-trained machine learning model to generate a comprehensive pollution coefficient. Based on the comprehensive pollution coefficient, average noise or maximum noise is used as the optimization target. In the established BIM model, the optimization target of the target area is simulated, and the genetic algorithm is used to find the optimization parameter combination that minimizes the cost of achieving the optimization target. The optimization parameter combinations of all polluted areas are summarized to obtain the optimal design plan for the entire building.

[0005] In a preferred embodiment, the noise data set of the target area is composed of multiple noise data groups, each noise data group corresponds to a time period of data collection, and all time periods have no time overlap and together cover the entire preset sampling window.

[0006] In a preferred embodiment, judging whether the target area is noise polluted according to the noise data set of the target area refers to: The noise data measured in the target area is evaluated with reference to the preset noise standard. If the noise data measured in the target area is higher than the preset noise standard, it indicates that there is noise pollution. If the noise data measured in the target area is not higher than the preset noise standard, it indicates that there is no noise pollution.

[0007] In a preferred embodiment, performing a cluster analysis operation based on the pollution information set refers to: Step 1: Determine the number of cluster centers, i.e., the K value; Step 2: Initialize cluster centers: randomly select K initial cluster centers, each cluster center represents a noise level interval; Step 3: Calculate the distance from each regional data point to the cluster center: Use the Euclidean distance formula to calculate the distance between the noise measurement value of each region and each cluster center; Step 4: Classify data points: Classify the noise data points in each area to the nearest cluster center to form multiple noise level area clusters, each area cluster represents a noise interval; Step 5: Update cluster centers: Calculate the average value of all data points in each noise region cluster and update the cluster center of each cluster; Step 6: Iterate until convergence: Repeat steps 2 to 5 until the cluster center no longer changes or the preset number of iterations is reached.

[0008] In a preferred embodiment, determining the number of cluster centers, i.e., the K value, refers to: There are multiple preset interval levels for representing noise levels, and the total number of interval levels is the number of cluster centers.

[0009] In a preferred embodiment, the pollution level table of the target area includes: The interval level corresponding to each noise level region cluster and the total number of data in each noise level region cluster.

[0010] In a preferred embodiment, the pollution level table of the target area is fed into a pre-trained machine learning model to generate a comprehensive pollution coefficient, which means: The pre-trained machine learning models are: ; n represents the total number of noise level region clusters, i represents the index number of the noise level region cluster, represents the total number of data in the i-th noise level region cluster, represents the interval level corresponding to the i-th noise level region cluster, represents the preset influence coefficient corresponding to the i-th noise level area cluster. All influence coefficients are positive and their sum is one. Represents the comprehensive pollution coefficient.

[0011] In a preferred embodiment, using average noise or maximum noise as an optimization target based on the comprehensive pollution coefficient means: The comprehensive pollution coefficient is compared with the preset pollution threshold. If the comprehensive pollution coefficient is greater than the preset pollution threshold, the maximum noise of the target area is used as the optimization target. If the comprehensive pollution coefficient is less than or equal to the preset pollution threshold, the average noise of the target area is used as the optimization target.

[0012] In a preferred embodiment, using a genetic algorithm to find an optimization parameter combination that minimizes the cost of achieving the optimization target refers to: Encoding and initial population: Encode the optimization parameter combination into chromosome form and randomly generate m chromosomes as the initial population; Fitness evaluation: Taking the realization of optimization goal as the constraint condition in fitness evaluation, the fitness evaluation formula is established: ; Indicates the type of optimized material The amount of money spent, m represents the type of optimized material The total number of species, is the fitness value; Selection operation: Use the roulette wheel selection method to select offspring as new parents; Crossover operation: randomly exchange data in chromosomes of different parents; Mutation operation: randomly select data of different offspring chromosomes for adjustment; Iteration and termination conditions: When the pre-set termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the best combination of optimization parameters.

[0013] Technical effects and advantages of the present invention: The present invention comprehensively collects and analyzes the noise data of existing buildings based on the BIM model. By using cluster analysis and machine learning models, the noise pollution areas and their specific noise levels can be accurately identified, avoiding the defects of inaccurate judgment of noise problems in traditional methods.

[0014] By introducing genetic algorithms, the present invention can automatically generate the optimal noise control solution and find the best balance between cost and noise control effect. Compared with the traditional sound insulation material stacking, the present invention can achieve the optimal noise control effect with the minimum transformation cost, and has a higher level of intelligence and economy.

[0015] The present invention flexibly selects average noise or maximum noise as the optimization target according to the noise data and pollution level of each area, thereby ensuring differentiated design for areas with different noise levels. It can not only meet the mandatory sound insulation needs in high-noise areas, but also appropriately optimize areas with lower noise levels.

[0016] Through the BIM model, the present invention can integrate and manage noise data, pollution information sets and optimization schemes, and generate a global building noise optimization design scheme. This method can not only simplify the design process, but also improve the overall efficiency of noise optimization design.

[0017] The present invention uses the comprehensive pollution coefficient as the judgment basis for the optimal design, thereby ensuring that excessive sound insulation design is not performed in areas with relatively light noise pollution, thereby avoiding unnecessary waste of resources and improving the economic benefits of architectural design. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 It is a schematic diagram of the BIM-based parametric design method for existing buildings in the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Reference Figure 1 The following embodiments are obtained: Embodiment 1: A BIM-based parametric design method for existing buildings, comprising the following steps: Data collection is performed on existing buildings and a BIM model is established. Data simulation is performed on the daily use of existing buildings, and the BIM model is divided into regions to obtain multiple building areas and obtain noise data sets for the target areas. The actual use data of existing buildings is obtained through data collection (such as noise), and these data are integrated into the BIM model to establish a digital model that reflects the real situation of the building. The BIM model can visualize the structure and environment of the building and provide basic data for subsequent optimization design. Simulate the daily use situation and subsequently analyze the impact of the noise generated by these situations and the noise of the environment in which the building is located. This helps to identify problems in the use of the building, namely noise pollution, and ensure that the optimization plan is targeted at actual needs. The building is divided into multiple areas according to function or space for easy management and targeted optimization. For example, office areas and public areas are divided into independent areas. By arranging sensors in different areas, noise data is obtained to form a noise data set for each area. This step is the basis for subsequent judgment of whether there is noise pollution in the area. Data collection can accurately reflect the noise situation in different areas.

[0021] According to the noise data set of the target area, it is judged whether there is noise pollution in the target area. If there is noise pollution, the area is divided into a polluted area, and the noise data sets of all polluted areas are summarized to obtain a pollution information set; by analyzing the noise data, it is judged whether the noise level of each area exceeds the standard threshold. If the noise level in a certain area is high, it can be determined that there is noise pollution in the area. The result of this step determines whether the noise optimization of the area is required in the future. The data of all areas with noise pollution are summarized to form a pollution information set, which contains the noise characteristics of each polluted area. This provides a data basis for the subsequent noise level classification and optimization design.

[0022] Based on the pollution information set, cluster analysis is performed to obtain the pollution level form of the target area, and then the pollution level form of the target area is transmitted to the pre-trained machine learning model to generate a comprehensive pollution coefficient. Based on the comprehensive pollution coefficient, the average noise or maximum noise is used as the optimization target; the pollution area is divided into different noise levels using the cluster analysis method to generate a pollution level form. In this way, areas with different pollution levels can be distinguished, which is convenient for targeted design of optimization measures. For example, low-pollution areas and high-pollution areas may require different treatment methods. By inputting the pollution level form into the pre-trained machine learning model, a comprehensive pollution coefficient for each area is generated. This coefficient can reflect the overall pollution situation of the area, which is convenient for the subsequent use of the comprehensive pollution coefficient to determine the optimization method. According to the size of the comprehensive pollution coefficient, it is determined whether to use the average noise or the maximum noise as the optimization target. For areas with low pollution coefficients, the average noise may be sufficient to deal with it, while for areas with high pollution coefficients, the maximum noise is used as the optimization target to ensure effective sound insulation even in high noise conditions.

[0023] In the established BIM model, the optimization target of the target area is simulated, and the genetic algorithm is used to find the optimization parameter combination that minimizes the cost of achieving the optimization target. The optimization parameter combination of all polluted areas is summarized to obtain the optimization design plan for the entire building. Noise optimization simulation is carried out in the BIM model, and the effects of different optimization measures are estimated through the digital model. This can evaluate the effect of noise control before actual transformation, saving time and cost. The optimal combination of noise and sound insulation measures is found through genetic algorithms to ensure that the transformation cost is minimized while achieving the noise control target. The genetic algorithm can make intelligent choices among multiple solutions to find a design that can achieve noise optimization and is cost-effective. The optimization results of all polluted areas are integrated to generate a noise control design plan for the entire building. This plan combines specific optimization measures in different areas to ensure that the noise environment of the entire building is comprehensively improved, and the final design effect can be displayed through the visualization function of the BIM model.

[0024] The noise data set of the target area consists of multiple noise data groups, each of which corresponds to a time period for data collection. All time periods have no time overlap and cover the entire preset sampling window together. Each noise data group corresponds to an independent time period, ensuring that data collection in different time periods does not overlap. This method can ensure that the noise data covers the entire preset sampling window and provides specific noise information for each time period, so as to conduct a comprehensive assessment of the noise situation in the area. The non-overlap of all time periods means that duplicate data recording or omissions can be avoided, ensuring the integrity and reliability of the time series. The segmented collection of noise data sets makes the data more orderly and provides a fine data foundation for subsequent noise analysis, pollution identification and optimization decisions. By collecting noise data in multiple independent time periods, the noise changes in the area in different time periods can be captured, because noise usually shows different levels at different times of the day, and the standards for judging the existence of noise pollution in different areas and time periods are different. For details, see the following description: Judging whether there is noise pollution in the target area based on the noise data set of the target area means: evaluating with reference to the preset noise standard, comparing the noise data measured in the target area with the preset noise standard, if the noise data measured in the target area is higher than the preset noise standard, it indicates that there is noise pollution, if the noise data measured in the target area is not higher than the preset noise standard, it indicates that there is no noise pollution.

[0025] This step can clearly determine whether there is noise pollution in the area by comparing the noise data of the target area with the preset noise standard. This standard-based comparison can provide an objective and quantitative basis for judgment, avoid subjectivity or ambiguity, and ensure an accurate assessment of the regional noise situation.

[0026] By judging whether there is noise pollution, we can determine which areas need further noise control or sound insulation design, so as to propose targeted optimization plans. For polluted areas, we can continue to analyze their noise levels and ultimately design reasonable noise reduction measures; for non-polluted areas, we can avoid unnecessary renovation investment.

[0027] It should be noted that after the target area is divided into a polluted area, since the noise data set of the target area is composed of multiple noise data groups, during the subsequent aggregation, the noise data groups without noise pollution will be eliminated, and only the noise data groups with noise pollution will be retained to reduce the burden of subsequent analysis tasks.

[0028] Noise standards are usually set based on regulations, environmental requirements, and building usage. Standards set noise limits based on the needs of different environments, functions, or areas. Here are some common noise standard classifications: Outdoor noise standards: Generally, noise limits are set for daytime and nighttime according to different environmental functional zones. For example, the noise limit for residential areas during the daytime is ≤55dB, and at night it is ≤45dB. The noise limit for industrial areas during the daytime is ≤65dB, and at night it is ≤55dB.

[0029] Indoor noise standards: Indoor noise standards for residential, office, hospital, school and other buildings: Office area: ≤45dB (daytime). Classroom or conference room: ≤40dB (daytime). Medical area: ≤35dB (daytime).

[0030] Therefore, at the beginning of data collection, time division will be performed. Each noise data group corresponds to a time period for data collection. All time periods have no time overlap and together cover the entire preset sampling window.

[0031] Cluster analysis based on contaminated information sets refers to: Step 1: Determine the number of cluster centers, i.e., the K value; Determine the number of cluster centers, i.e., the K value, means: there are multiple interval levels for representing the noise level, and the total number of interval levels is the number of cluster centers; Determining the K value is the first step of cluster analysis, which indicates how many intervals the noise level is divided into. By presetting multiple interval levels representing the noise level, the noise pollution situation in the region can be refined. The larger the K value, the more detailed the division of the noise interval, thus being able to more accurately reflect the differences in regional noise pollution.

[0032] Step 2: Initialize cluster centers: Randomly select K initial cluster centers, each cluster center represents a noise level interval; initialize K cluster centers to represent the noise level interval in the initial state. By randomly selecting cluster centers, ensure that each cluster center represents a preliminary estimate of different noise levels. This randomness provides diverse initial conditions for the subsequent clustering process and helps the algorithm find a more reasonable clustering structure.

[0033] Step 3: Calculate the distance from each regional data point to the cluster center: Use the Euclidean distance formula to calculate the distance between the noise measurement value of each region and each cluster center; by calculating the distance between the noise measurement value of each region and each cluster center, it can be determined which interval the noise level of each region is closer to. Euclidean distance is a commonly used measurement method that can accurately reflect the similarities or differences between different noise data points in geometric space.

[0034] Step 4: Classify data points: Classify the noise data points in each area to the nearest cluster center to form multiple noise level area clusters, each of which represents a noise interval; classify the noise data points in each area into the category where the nearest cluster center is located to form multiple noise level area clusters. Each cluster represents an area with different noise levels. This step can classify areas with similar noise characteristics into one category, which helps understand the distribution of pollution.

[0035] Step 5: Update cluster centers: Calculate the average value of all data points in each noise region cluster and update the cluster center of each cluster; by calculating the average value of data points in each noise region cluster, the center value of the class can be updated to more accurately reflect the noise characteristics of the class area. The purpose of updating the cluster center is to adjust the representativeness of each noise cluster so that the cluster center gradually approaches the actual distribution of the data.

[0036] Step 6. Iterate until convergence: Repeat steps 2 to 5 until the cluster center no longer changes or the preset number of iterations is reached. Repeat the initialization, distance calculation, classification, and update steps until the cluster center no longer changes significantly, which means that the algorithm has found a relatively stable noise distribution pattern. This step ensures that the clustering results are reliable and consistent, and the final noise level division can accurately reflect the noise pollution in the target area.

[0037] The pollution level table of the target area includes: the interval level corresponding to each noise level area cluster and the total number of data in each noise level area cluster.

[0038] The pollution level form of the target area is fed into the pre-trained machine learning model to generate a comprehensive pollution coefficient: the pre-trained machine learning model is: ; n represents the total number of noise level region clusters, i represents the index number of the noise level region cluster, represents the total number of data in the i-th noise level region cluster, represents the interval level corresponding to the i-th noise level region cluster, represents the preset influence coefficient corresponding to the i-th noise level area cluster. All influence coefficients are positive and their sum is one. Represents the comprehensive pollution coefficient. It is used to amplify the impact of the number of noise data on the comprehensive pollution coefficient, reflecting that the area with more data contributes more to the pollution coefficient. Logarithmic transformation of noise levels is used to smooth out extreme noise data while still maintaining a large range of differences. Further enhance the impact of high noise areas to ensure that high noise areas have a significant impact on pollution. The larger the comprehensive pollution coefficient, the more serious the noise pollution.

[0039] Using average noise or maximum noise as the optimization target based on the comprehensive pollution coefficient means: The comprehensive pollution coefficient is compared with the preset pollution threshold. If the comprehensive pollution coefficient is greater than the preset pollution threshold, the maximum noise of the target area is used as the optimization target. If the comprehensive pollution coefficient is less than or equal to the preset pollution threshold, the average noise of the target area is used as the optimization target.

[0040] It should be noted that the average noise and maximum noise are obtained by eliminating the noise data group without noise pollution and retaining only the noise data group with noise pollution. In the noise optimization process, whether to use the average noise or the maximum noise as the optimization target depends on the overall evaluation of the noise environment and the comprehensive consideration of the building usage.

[0041] Average noise represents the overall noise level of an area over a longer period of time and can better reflect the general noise exposure of the area. If an area has relatively low noise levels most of the time and only has noise peaks for a short period of time, using average noise can avoid over-designing sound insulation measures due to a small number of outliers.

[0042] Occasional noise is a noise peak that occurs in a short period of time, but it does not represent the long-term noise pollution in the area. By calculating the average noise, the impact of these occasional noises can be better smoothed without having to do too much structural optimization for short-term high noise.

[0043] The maximum noise is often the peak noise in a short period of time, while the goal of building optimization is to deal with long-term, continuous noise conditions. If the maximum noise is used as the optimization target, it may lead to over-design and increase unnecessary sound insulation costs. Especially when the noise peak is only an occasional short-term event, using the maximum noise is not necessarily the most economical solution.

[0044] When the comprehensive pollution coefficient is below a certain threshold, it means that the pollution in the area is relatively controllable. In this case, the noise pollution may not be serious, and using the average noise as the optimization target is sufficient to meet the noise needs of the area. The maximum noise optimization of building structures is often used to deal with high pollution or severe noise areas, but if the comprehensive pollution coefficient is below the judgment threshold, this degree of sound insulation optimization is usually not required.

[0045] The total number of data and the interval level in each noise level area cluster have a direct impact on the comprehensive pollution coefficient. In some areas, the distribution of noise data is relatively uniform, without too many extreme high noise intervals. If the amount of data in these clusters is large and the noise level is relatively concentrated, the average noise can better reflect the actual noise distribution in the area. Such an optimization design can control noise pollution and avoid over-design caused by a few extreme values.

[0046] In highly polluted areas, noise problems are severe and persistent. It is recommended to use maximum noise as the optimization target to ensure that the building structure can provide adequate noise isolation even under the worst conditions. In areas with low comprehensive pollution coefficients, noise problems are not serious and are mostly sporadic. At this time, using average noise optimization can ensure the effect while avoiding unnecessary cost investment.

[0047] Using genetic algorithms to find the optimal parameter combination that minimizes the cost of achieving the optimization goal refers to: Coding and initial population: Encode the optimization parameter combination into chromosome form and randomly generate m chromosomes as the initial population; each chromosome represents a possible solution. Through encoding, different optimization parameter combinations can be expressed in mathematical form, so that the genetic algorithm can operate and optimize these combinations.

[0048] Fitness evaluation: Taking the realization of optimization goal as the constraint condition in fitness evaluation, the fitness evaluation formula is established: ; Indicates the type of optimized material The amount of money spent, m represents the type of optimized material The total number of species, is the fitness value; the formula calculates the total cost of the optimization plan. The lower the fitness value, the more the optimization combination meets the cost-saving requirements.

[0049] Selection operation: Use the roulette wheel selection method to select offspring as new parents; chromosomes with high fitness have a greater chance of being selected, which ensures that better parameter combinations can be inherited to the next generation, gradually optimizing the overall population.

[0050] Crossover operation: randomly exchange the data in chromosomes of different parents; generate new offspring by crossing the chromosome data of two different parents. This simulates genetic recombination in biology, aiming to find a better combination by recombining existing solutions.

[0051] Mutation operation: Randomly select data from different offspring chromosomes for adjustment; randomly select certain genes in the chromosome for fine-tuning to increase the diversity of the population. The mutation operation prevents the algorithm from falling into the local optimum and ensures that more solution space is explored to find the global optimal solution. The mutation probability is usually set to 1% to 5% to maintain the diversity of the population.

[0052] Iteration and termination conditions: When the pre-set termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the best optimization parameter combination. Ensure that the algorithm ends within a reasonable time and output the best parameter combination solution.

[0053] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0054] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0055] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0056] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0057] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The BIM-based parametric design method for existing buildings is characterized by: The following steps are involved: Collect data from existing buildings and establish BIM models, simulate the daily use of existing buildings, and divide the BIM models into regions to obtain multiple building areas and obtain noise data sets for the target areas; Determine whether the target area is noise polluted based on the noise data set of the target area. If there is noise pollution, the area is divided into a polluted area, and the noise data sets of all polluted areas are summarized to obtain a pollution information set. Based on the pollution information set, cluster analysis is performed to obtain a pollution level form for the target area. The pollution level form for the target area is then fed into a pre-trained machine learning model to generate a comprehensive pollution coefficient. Based on the comprehensive pollution coefficient, average noise or maximum noise is used as the optimization target. In the established BIM model, the optimization target of the target area is simulated, and the genetic algorithm is used to find the optimization parameter combination that minimizes the cost of achieving the optimization target. The optimization parameter combinations of all polluted areas are summarized to obtain the optimal design plan for the entire building.

2. The BIM-based parametric design method for existing buildings according to claim 1, characterized in that: The noise data set of the target area is composed of multiple noise data groups, each noise data group corresponds to a time period of data collection, and all time periods have no time overlap and jointly cover the entire preset sampling window.

3. The BIM-based parametric design method for existing buildings according to claim 2 is characterized in that: Judging whether the target area has noise pollution based on the noise data set of the target area refers to: The noise data measured in the target area is evaluated with reference to the preset noise standard. If the noise data measured in the target area is higher than the preset noise standard, it indicates that there is noise pollution. If the noise data measured in the target area is not higher than the preset noise standard, it indicates that there is no noise pollution.

4. The BIM-based parametric design method for existing buildings according to claim 3 is characterized in that: Cluster analysis based on contaminated information sets refers to: Step 1: Determine the number of cluster centers, i.e., the K value; Step 2: Initialize cluster centers: randomly select K initial cluster centers, each cluster center represents a noise level interval; Step 3: Calculate the distance from each regional data point to the cluster center: Use the Euclidean distance formula to calculate the distance between the noise measurement value of each region and each cluster center; Step 4: Classify data points: Classify the noise data points in each area to the nearest cluster center to form multiple noise level area clusters, each area cluster represents a noise interval; Step 5: Update cluster centers: Calculate the average value of all data points in each noise region cluster and update the cluster center of each cluster; Step 6: Iterate until convergence: Repeat steps 2 to 5 until the cluster center no longer changes or the preset number of iterations is reached.

5. The BIM-based parametric design method for existing buildings according to claim 4 is characterized in that: Determining the number of cluster centers, i.e., the K value, refers to: There are multiple preset interval levels for representing noise levels, and the total number of interval levels is the number of cluster centers.

6. The BIM-based parametric design method for existing buildings according to claim 5 is characterized in that: The pollution level table for the target area includes: The interval level corresponding to each noise level region cluster and the total number of data in each noise level region cluster.

7. The BIM-based parametric design method for existing buildings according to claim 6 is characterized in that: Feeding the pollution level form of the target area into the pre-trained machine learning model to generate a comprehensive pollution coefficient means: The pre-trained machine learning models are: ; n represents the total number of noise level region clusters, i represents the index number of the noise level region cluster, represents the total number of data in the i-th noise level region cluster, represents the interval level corresponding to the i-th noise level region cluster, represents the preset influence coefficient corresponding to the i-th noise level area cluster. All influence coefficients are positive and their sum is one. Represents the comprehensive pollution coefficient.

8. The BIM-based parametric design method for existing buildings according to claim 7, characterized in that: Using average noise or maximum noise as the optimization target based on the comprehensive pollution coefficient means: The comprehensive pollution coefficient is compared with the preset pollution threshold. If the comprehensive pollution coefficient is greater than the preset pollution threshold, the maximum noise of the target area is used as the optimization target. If the comprehensive pollution coefficient is less than or equal to the preset pollution threshold, the average noise of the target area is used as the optimization target.

9. The BIM-based parametric design method for existing buildings according to claim 8, characterized in that: Using genetic algorithms to find the optimal parameter combination that minimizes the cost of achieving the optimization goal refers to: Encoding and initial population: Encode the optimization parameter combination into chromosome form and randomly generate m chromosomes as the initial population; Fitness evaluation: Taking the realization of optimization goal as the constraint condition in fitness evaluation, the fitness evaluation formula is established: ; Indicates the type of optimized material The amount of money spent, m represents the type of optimized material The total number of species, is the fitness value; Selection operation: Use the roulette wheel selection method to select offspring as new parents; Crossover operation: randomly exchange data in chromosomes of different parents; Mutation operation: randomly select data of different offspring chromosomes for adjustment; Iteration and termination conditions: When the pre-set termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the best combination of optimization parameters.

Images