Rainwater garden optimization method and system based on BIM dynamic rainfall flood simulation

Abstract

The invention relates to the technical field of intelligent construction. The invention provides a rainwater garden optimization method and system based on BIM dynamic rainfall flood simulation. The method comprises the following steps: extracting site planning data, rainwater garden geometric parameters and a peripheral pipe network topological relation, and constructing a rainfall flood analysis model; calling a hydrological and hydraulic engine interface, and executing dynamic simulation of the rainwater garden under a continuous rainfall event based on a historical rainfall sequence or a designed rainfall scene; on the basis of the dynamic simulation result, the sensitivity weight of the key design parameters is recognized, and the permeability coefficient, the water storage layer depth and the vegetation coverage rate parameter set are adjusted through iteration till the runoff reduction rate and pollution load control target is met; and generating a plurality of candidate schemes, performing weight scoring based on the full life cycle cost and the ecological benefits, and outputting an optimal parameter combination and a three-dimensional visual design scheme to a BIM platform. The problem that the design optimization efficiency is low and the period is long due to the lack of automatic and intelligent parameter optimization and scheme comparison and selection ability in the existing rainwater garden design is solved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent construction technology, and in particular to a rain garden optimization method and system based on BIM dynamic rain and flood simulation. Background Art

[0002] Urbanization has exacerbated surface hardening, leading to surges in stormwater runoff, increased peak volumes, and increased pollution. This has put immense pressure on traditional drainage systems and has led to widespread waterlogging. Low-impact development (LID) facilities, such as rain gardens, have become a key component of sponge city development due to their advantages in source control, infiltration reduction, and water purification.

[0003] Current rain garden designs often rely on empirical formulas, simplified models, or isolated hydrological and hydraulic software, which have significant shortcomings: First, the design process is disconnected from the overall building / site planning, resulting in fragmented information and poor coordination; Second, simulation analyses are mostly static or simple scenarios, which cannot accurately reflect the dynamic infiltration, storage, overflow and long-term performance of actual rainfall events; Third, there is a lack of automated and intelligent parameter optimization and solution comparison capabilities based on dynamic simulation results, resulting in low design optimization efficiency and long cycles. Summary of the Invention

[0004] The purpose of the present invention is to provide a rain garden optimization method and system based on BIM dynamic rainwater simulation, aiming to solve the problem of low efficiency and long cycle of design optimization caused by the lack of automated intelligent parameter optimization and scheme comparison capabilities in existing rain garden designs.

[0005] The present invention is achieved through the following technical solutions: A rain garden optimization method based on BIM dynamic rainwater simulation includes the following steps: Based on the building information model platform, site planning data, rain garden geometric parameters and surrounding pipe network topology are extracted to build a stormwater analysis model. Based on the output of the stormwater analysis model, the hydrological and hydraulic engine interface is called to perform a dynamic simulation of the rain garden's infiltration-retention-overflow process under continuous rainfall events based on historical rainfall sequences or designed rainfall scenarios, and obtain dynamic simulation results. Based on the dynamic simulation results, the sensitivity weights of key design parameters are identified, and the parameter sets of hydraulic conductivity, aquifer depth, and vegetation coverage are iteratively adjusted until the runoff reduction rate and pollution load control targets are met. Based on the iterative adjustment results, multiple candidate schemes that meet the performance evaluation indicators are generated, and weighted scores are given based on the full life cycle cost and ecological benefits. The optimal parameter combination and three-dimensional visualization design scheme are output to the BIM platform.

[0006] Optionally, the specific process of extracting site planning data, rain garden geometric parameters, and surrounding pipe network topology based on the building information model platform to construct a stormwater analysis model is as follows: Based on the Building Information Modeling platform, site planning data including site elevation, underlying surface type, and area distribution are automatically extracted. The three-dimensional coordinates, outline dimensions, and geometric parameters of the layered structure of the rain garden are also extracted, along with the topological relationship of the surrounding pipe network connected to the rain garden overflow outlet. Based on the site planning data, geometric parameters and surrounding pipe network topology, the heterogeneous data is uniformly converted into a standardized format corresponding to the hydrological and hydraulic engine through the built-in or external data conversion interface of the BIM platform; By using data in a standardized format, a stormwater analysis model including rain garden units, site catchment areas, and associated pipe networks is dynamically constructed in the hydrological and hydraulic engine, and hydraulic connections between the components are established. The stormwater analysis model is output to subsequent simulation steps through a preset interface.

[0007] Optionally, the specific process of the dynamic simulation of the entire process of infiltration-storage-overflow is as follows: Take the historical rainfall sequence or designed rainfall scenario as input conditions and start the simulation by calling the hydrological and hydraulic engine interface; The dynamic infiltration rate of each layered medium and the change of aquifer storage capacity in the rain garden unit are iteratively calculated according to the preset step size on the continuous rainfall time axis; Based on the relationship between the real-time water level of the aquifer and the elevation of the overflow outlet, the overflow triggering time is determined and the overflow volume is calculated; Synchronize the hydraulic conductivity status of the surrounding pipe networks and update the flow and direction of the pipe network nodes; The output includes time series of runoff infiltration, detention volume occupancy, overflow event frequency, and dynamic process line data of pollution load migration path.

[0008] Optionally, the specific process of identifying the sensitivity weights of key design parameters based on the dynamic simulation results and iteratively adjusting the parameter set of permeability coefficient, aquifer depth, and vegetation coverage until the runoff reduction rate and pollution load control targets are met is as follows: Based on the dynamic process line data, the runoff reduction rate, peak flow delay time, cumulative frequency of overflow events and average pollutant removal rate of the rain garden during the simulation period are extracted; Conduct orthogonal experiments or Monte Carlo sampling perturbations on parameters such as permeability coefficient, aquifer depth, and vegetation coverage. Calculate the magnitude of changes in performance indicators due to perturbations of each parameter through multiple rounds of dynamic simulations. Quantify the sensitivity weight of each parameter using variance analysis or regression models. According to the sensitivity weight ranking, high-weight parameters are adjusted first; if the runoff reduction rate does not meet the standard, the permeability coefficient or aquifer depth is increased in the order of weight; if the pollution load removal rate does not meet the standard, the vegetation cover rate or aquifer depth is increased first to extend the hydraulic retention time; After each round of parameter adjustment, the dynamic simulation is re-executed until the following conditions are met simultaneously: The total runoff reduction rate is greater than or equal to the design target value; The frequency of overflow events is less than or equal to the allowed threshold; The removal rate of key pollutants is greater than or equal to the control standard.

[0009] Optionally, the specific process of using the regression model to quantify the sensitivity weight of each parameter is: Based on the multiple rounds of dynamic simulation data sets generated by the orthogonal test or Monte Carlo sampling perturbation, a multiple linear regression model is constructed for each performance indicator; the multiple linear regression model is expressed as shown in the following formula (1):

[0010] in, For the performance indicators, They correspond to the total runoff reduction rate, peak flow delay time, cumulative frequency of overflow events and average pollutant removal rate respectively; is the permeability coefficient; is the aquifer depth; is the vegetation coverage rate; is the intercept term; 、 and The parameters are 、 and The regression coefficient of is the random error term; The regression coefficients were fitted using the least squares method using the multi-round dynamic simulation data set, and the standardized regression coefficients were calculated to eliminate the dimension effect, as shown in the following formula (2):

[0011] in, is the standardized regression coefficient, Corresponding parameters 、 and , Corresponding performance indicators; For parameters The standard deviation of That is, parameters 、 、 one; is the standard deviation of the performance index; For parameters Performance indicators the original impact strength; Based on the standardized regression coefficient, the sensitivity score of each parameter to each performance indicator is calculated as shown in the following formula (3):

[0012] in, Representation parameters Performance indicators sensitivity scores; Combining all performance indicators, the overall sensitivity weight of each parameter is calculated as shown in the following formula (4):

[0013] in, For parameters sensitivity weight.

[0014] Optionally, the specific process of generating multiple candidate solutions that meet the performance evaluation indicators based on the iterative adjustment results, weighting and scoring them based on the full life cycle cost and ecological benefits, and outputting the optimal parameter combination and three-dimensional visual design solution to the BIM platform is as follows: Based on the parameter combination set that meets the runoff reduction rate and pollution load control objectives generated after iterative adjustment, multiple candidate design schemes are constructed; Extracting ecological benefit index data corresponding to the performance index data in the dynamic simulation results from each candidate solution, wherein the ecological benefit index data includes pollutant removal rate, runoff reduction contribution, and peak pressure relief value for the associated pipe network; Calculate the full life cycle costs of each option during the construction, maintenance and renewal phases; Based on the ecological benefit index data and the whole life cycle cost, a comprehensive evaluation system including cost indicators and ecological benefit indicators is constructed. The entropy weight method or hierarchical analysis method is used to determine the weight of each indicator, and the total score of each scheme is calculated according to the weight; Based on the total scores of each scheme, the optimal scheme is selected and ranked. The corresponding permeability coefficient, aquifer depth and vegetation coverage parameter combination and geometric structure information of the optimal scheme are generated and output into a three-dimensional visual design scheme model through the API interface of the BIM platform.

[0015] Optionally, in the process of iteratively adjusting the parameter set of permeability coefficient, aquifer depth, and vegetation coverage until the runoff reduction rate and pollution load control targets are met, automatic parameter optimization is performed using a genetic algorithm, specifically comprising the following steps: Initialize an initial population containing multiple randomly generated parameter combinations, each parameter combination corresponds to a value of hydraulic conductivity, aquifer depth, and vegetation coverage; Based on the dynamic simulation results, calculating a fitness function value for each parameter combination, wherein the fitness function is defined as the inverse of the comprehensive deviation between the actual value of the performance indicator and the design target value, the performance indicator including the total runoff reduction rate, the cumulative frequency of overflow events, and the key pollutant removal rate; Perform genetic operations on the current population, including roulette wheel selection based on fitness function values, arithmetic crossover between parameter values, and Gaussian mutation to generate a new generation of population; Repeat dynamic simulation, fitness calculation and genetic operation until the fitness function value of the optimal parameter combination in the population has no significant improvement for consecutive preset generations or reaches the maximum number of iterations, and output the optimal parameter combination that meets the control objective as the iterative adjustment result.

[0016] Based on the same inventive concept, the present invention also provides a rain garden optimization system based on BIM dynamic rain and flood simulation, which is used to implement the rain garden optimization method based on BIM dynamic rain and flood simulation, including: The data extraction and modeling module is used to automatically extract site planning data, rain garden geometry parameters, and surrounding pipe network topology based on the building information model platform, and construct an integrated stormwater analysis model through a data conversion interface; A dynamic simulation module, connected to the data extraction and modeling module, is used to call the hydrological and hydraulic engine interface to perform a dynamic simulation of the entire process of infiltration, storage, and overflow of the rain garden based on historical rainfall sequences or designed rainfall scenarios, and output dynamic process line data of the time series; A parameter optimization module connected to the dynamic simulation module; A scheme generation module, connected to the parameter optimization module, is used to construct candidate schemes based on the optimized parameter combination set, calculate the full life cycle cost and ecological benefit indicators of each scheme, select the optimal scheme through weighted scoring, and output the optimal parameter combination and geometric construction information to the BIM platform to generate a three-dimensional visual design scheme; Among them, the parameter optimization module includes: Sensitivity analysis unit, used to extract performance indicators based on dynamic process line data and quantify the sensitivity weights of hydraulic conductivity, aquifer depth and vegetation cover through orthogonal experiments or Monte Carlo sampling perturbations; Iterative adjustment unit, used to prioritize the adjustment of high-weight parameters according to the sensitivity weight ranking, and iteratively optimize the parameter set through multiple rounds of dynamic simulation until the runoff reduction rate and pollution load control targets are met; The genetic algorithm optimization unit is used to initialize the parameter population, calculate the fitness function value and perform genetic operations to achieve automatic parameter optimization.

[0017] Based on the same inventive concept, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above-mentioned rain garden optimization method based on BIM dynamic rainwater simulation.

[0018] Based on the same inventive concept, the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned rain garden optimization method based on BIM dynamic rainwater simulation is implemented.

[0019] The technical solution of the present invention has at least the following advantages and beneficial effects: Based on the BIM platform, site planning data, rain garden geometric parameters, and the topological relationship of the surrounding pipe network are extracted to construct a stormwater analysis model. This breaks the barrier of disconnection between rain gardens and the overall planning of buildings / sites in traditional designs, realizes the integration and sharing of design information, significantly improves the coordination between various systems, deeply integrates rain garden design into the overall site planning, and optimizes the systematic layout of urban stormwater management.

[0020] With the help of the hydrological and hydraulic engine interface, based on historical rainfall sequences or designed rainfall scenarios, the entire process of infiltration-retention-overflow in rain gardens under continuous rainfall events is dynamically simulated. Compared with traditional static or simple scenario simulations, this can more finely and accurately reflect the dynamic working process of rain gardens in actual rainfall events, effectively present their long-term performance, and provide data support that is more in line with actual working conditions for design decisions.

[0021] By identifying the sensitivity weights of key design parameters, the system automatically and iteratively adjusts parameter sets such as the permeability coefficient, aquifer depth, and vegetation coverage until the runoff reduction rate and pollution load control targets are achieved. This changes the current situation in which traditional designs lack automated and intelligent parameter optimization capabilities. At the same time, multiple candidate solutions are generated based on dynamic simulation results, and weighted scores are given based on the full life cycle costs and ecological benefits. The system quickly outputs the optimal parameter combination and three-dimensional visual design solution, greatly improving design optimization efficiency, shortening the design cycle, and reducing manpower and time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 Schematic diagram of a flow chart of a rain garden optimization method based on BIM dynamic rainwater simulation according to an embodiment of the present invention; Figure 2 This is a structural diagram of a rain garden optimization system based on BIM dynamic rainwater simulation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following is a specific implementation method with reference to the accompanying drawings.

[0024] Reference Figure 1 , a rain garden optimization method based on BIM dynamic rainwater simulation, including the following steps: Step 1: Based on the building information model platform, extract site planning data, rain garden geometric parameters and surrounding pipe network topology to build a stormwater analysis model.

[0025] In some embodiments, the specific process of extracting site planning data, rain garden geometric parameters, and surrounding pipe network topology based on the building information model platform to construct a stormwater analysis model is as follows: Based on the Building Information Modeling platform, site planning data including site elevation, underlying surface type, and area distribution are automatically extracted. The three-dimensional coordinates, outline dimensions, and geometric parameters of the layered structure of the rain garden are also extracted, along with the topological relationship of the surrounding pipe network connected to the rain garden overflow outlet. Based on the site planning data, geometric parameters and surrounding pipe network topology, the heterogeneous data is uniformly converted into a standardized format corresponding to the hydrological and hydraulic engine through the built-in or external data conversion interface of the BIM platform; By using data in a standardized format, a stormwater analysis model including rain garden units, site catchment areas, and associated pipe networks is dynamically constructed in the hydrological and hydraulic engine, and hydraulic connections between the components are established. The stormwater analysis model is output to subsequent simulation steps through a preset interface.

[0026] Step 2: Based on the output of the stormwater analysis model, the hydrological and hydraulic engine interface is called to perform a dynamic simulation of the entire process of infiltration, storage, and overflow of the rain garden under continuous rainfall events based on historical rainfall sequences or designed rainfall scenarios to obtain dynamic simulation results.

[0027] In some embodiments, the specific process of the dynamic simulation of the infiltration-storage-overflow process is as follows: Take the historical rainfall sequence or designed rainfall scenario as input conditions and start the simulation by calling the hydrological and hydraulic engine interface; The dynamic infiltration rate of each layered medium and the change of aquifer storage capacity in the rain garden unit are iteratively calculated according to the preset step size on the continuous rainfall time axis; Based on the relationship between the real-time water level of the aquifer and the elevation of the overflow outlet, the overflow triggering time is determined and the overflow volume is calculated; Synchronize the hydraulic conductivity status of the surrounding pipe networks and update the flow and direction of the pipe network nodes; The output includes time series of runoff infiltration, detention volume occupancy, overflow event frequency, and dynamic process line data of pollution load migration path.

[0028] Step 3: Based on the dynamic simulation results, identify the sensitivity weights of key design parameters and iteratively adjust the permeability coefficient, aquifer depth, and vegetation coverage parameter set until the runoff reduction rate and pollution load control targets are met.

[0029] In some embodiments, the specific process of identifying the sensitivity weights of key design parameters based on dynamic simulation results and iteratively adjusting the permeability coefficient, aquifer depth, and vegetation coverage parameter set until the runoff reduction rate and pollution load control targets are met is as follows: Based on the dynamic process line data, the runoff reduction rate, peak flow delay time, cumulative frequency of overflow events and average pollutant removal rate of the rain garden during the simulation period are extracted; Conduct orthogonal experiments or Monte Carlo sampling perturbations on parameters such as permeability coefficient, aquifer depth, and vegetation coverage. Calculate the magnitude of changes in performance indicators due to perturbations of each parameter through multiple rounds of dynamic simulations. Quantify the sensitivity weight of each parameter using variance analysis or regression models. According to the sensitivity weight ranking, high-weight parameters are adjusted first; if the runoff reduction rate does not meet the standard, the permeability coefficient or aquifer depth is increased in the order of weight; if the pollution load removal rate does not meet the standard, the vegetation cover rate or aquifer depth is increased first to extend the hydraulic retention time; After each round of parameter adjustment, the dynamic simulation is re-executed until the following conditions are met simultaneously: The total runoff reduction rate is greater than or equal to the design target value; The frequency of overflow events is less than or equal to the allowed threshold; The removal rate of key pollutants is greater than or equal to the control standard.

[0030] In some embodiments, the specific process of using the regression model to quantify the sensitivity weight of each parameter is as follows: Based on the multiple rounds of dynamic simulation data sets generated by the orthogonal test or Monte Carlo sampling perturbation, a multiple linear regression model is constructed for each performance indicator; the multiple linear regression model is expressed as shown in the following formula (1):

[0031] in, For the performance indicators, They correspond to the total runoff reduction rate, peak flow delay time, cumulative frequency of overflow events and average pollutant removal rate respectively; is the permeability coefficient; is the aquifer depth; is the vegetation coverage rate; is the intercept term; 、 and The parameters are 、 and The regression coefficient of is the random error term; The regression coefficients were fitted using the least squares method using the multi-round dynamic simulation data set, and the standardized regression coefficients were calculated to eliminate the dimension effect, as shown in the following formula (2):

[0032] in, is the standardized regression coefficient, Corresponding parameters 、 and , Corresponding performance indicators; For parameters The standard deviation of That is, parameters 、 、 one; is the standard deviation of the performance index; For parameters Performance indicators the original impact strength; Based on the standardized regression coefficient, the sensitivity score of each parameter to each performance indicator is calculated as shown in the following formula (3):

[0033] in, Representation parameters Performance indicators sensitivity scores; Combining all performance indicators, the overall sensitivity weight of each parameter is calculated as shown in the following formula (4):

[0034] in, For parameters sensitivity weight.

[0035] In some embodiments, the process of iteratively adjusting the set of parameters of permeability coefficient, aquifer depth, and vegetation coverage until the runoff reduction rate and pollution load control targets are met is performed by automatically optimizing the parameters using a genetic algorithm, specifically comprising the following steps: Initializing an initial population containing multiple randomly generated parameter combinations, each parameter combination corresponds to a value of the permeability coefficient, the aquifer depth, and the vegetation coverage rate; calculating a fitness function value for each parameter combination based on the dynamic simulation results, wherein the fitness function is defined as the inverse of the comprehensive deviation between the actual value of the performance indicator and the design target value, and the performance indicators include the total runoff reduction rate, the cumulative frequency of overflow events, and the removal rate of key pollutants; performing genetic operations on the current population, including roulette wheel selection based on the fitness function value, arithmetic crossover between parameter values, and Gaussian mutation, to generate a new generation of population; repeating dynamic simulation, fitness calculation, and genetic operations until the fitness function value of the optimal parameter combination in the population has no significant improvement for a continuous preset number of generations or reaches a maximum number of iterations, and outputting the optimal parameter combination that meets the control target as an iterative adjustment result.

[0036] Step 4: Based on the iterative adjustment results, generate multiple candidate solutions that meet the performance evaluation indicators, perform weighted scoring based on the full life cycle cost and ecological benefits, and output the optimal parameter combination and 3D visualization design solution to the BIM platform.

[0037] In some embodiments, the specific process of generating multiple candidate solutions that meet the performance evaluation indicators based on the iterative adjustment results, weighting and scoring based on the full life cycle cost and ecological benefits, and outputting the optimal parameter combination and three-dimensional visual design solution to the BIM platform is as follows: Based on the parameter combination set that meets the runoff reduction rate and pollution load control objectives generated after iterative adjustment, multiple candidate design schemes are constructed; Extracting ecological benefit index data corresponding to the performance index data in the dynamic simulation results from each candidate solution, wherein the ecological benefit index data includes pollutant removal rate, runoff reduction contribution, and peak pressure relief value for the associated pipe network; Calculate the full life cycle costs of each option during the construction, maintenance and renewal phases; Based on the ecological benefit index data and the whole life cycle cost, a comprehensive evaluation system including cost indicators and ecological benefit indicators is constructed. The entropy weight method or hierarchical analysis method is used to determine the weight of each indicator, and the total score of each scheme is calculated according to the weight; Based on the total scores of each scheme, the optimal scheme is selected and ranked. The corresponding permeability coefficient, aquifer depth and vegetation coverage parameter combination and geometric structure information of the optimal scheme are generated and output into a three-dimensional visual design scheme model through the API interface of the BIM platform.

[0038] Based on the same inventive concept, corresponding to any of the above embodiments, refer to Figure 2 The present invention provides a rain garden optimization system based on BIM dynamic rainwater simulation, which is used to implement the aforementioned rain garden optimization method based on BIM dynamic rainwater simulation, including: The data extraction and modeling module is used to automatically extract site planning data, rain garden geometry parameters, and surrounding pipe network topology based on the building information model platform, and construct an integrated stormwater analysis model through a data conversion interface; A dynamic simulation module, connected to the data extraction and modeling module, is used to call the hydrological and hydraulic engine interface to perform a dynamic simulation of the entire process of infiltration, storage, and overflow of the rain garden based on historical rainfall sequences or designed rainfall scenarios, and output dynamic process line data of the time series; A parameter optimization module connected to the dynamic simulation module; A scheme generation module, connected to the parameter optimization module, is used to construct candidate schemes based on the optimized parameter combination set, calculate the full life cycle cost and ecological benefit indicators of each scheme, select the optimal scheme through weighted scoring, and output the optimal parameter combination and geometric construction information to the BIM platform to generate a three-dimensional visual design scheme; Among them, the parameter optimization module includes: Sensitivity analysis unit, used to extract performance indicators based on dynamic process line data and quantify the sensitivity weights of hydraulic conductivity, aquifer depth and vegetation cover through orthogonal experiments or Monte Carlo sampling perturbations; Iterative adjustment unit, used to prioritize the adjustment of high-weight parameters according to the sensitivity weight ranking, and iteratively optimize the parameter set through multiple rounds of dynamic simulation until the runoff reduction rate and pollution load control targets are met; The genetic algorithm optimization unit is used to initialize the parameter population, calculate the fitness function value and perform genetic operations to achieve automatic parameter optimization.

[0039] Based on the same inventive concept, corresponding to any of the above embodiments, the present invention provides an electronic device, including a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the rain garden optimization method based on BIM dynamic rainwater simulation of the embodiment.

[0040] Optionally, the above-mentioned electronic device may be a server.

[0041] In addition, this embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the rain garden optimization method based on BIM dynamic rainwater flood simulation of the embodiment is implemented.

[0042] It is understood that the processor in the embodiments of the present invention may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0043] The method steps in the embodiments of the present invention can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC.

[0044] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a storage medium or transmitted via a storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

Claims

1. A rain garden optimization method based on BIM dynamic rainwater simulation, characterized in that: The following steps are involved: Based on the building information model platform, site planning data, rain garden geometric parameters and surrounding pipe network topology are extracted to build a stormwater analysis model. Based on the output of the stormwater analysis model, the hydrological and hydraulic engine interface is called to perform a dynamic simulation of the rain garden's infiltration-retention-overflow process under continuous rainfall events based on historical rainfall sequences or designed rainfall scenarios, and obtain dynamic simulation results. Based on the dynamic simulation results, the sensitivity weights of key design parameters are identified, and the parameter sets of hydraulic conductivity, aquifer depth, and vegetation coverage are iteratively adjusted until the runoff reduction rate and pollution load control targets are met. Based on the iterative adjustment results, multiple candidate schemes that meet the performance evaluation indicators are generated, and weighted scores are given based on the full life cycle cost and ecological benefits. The optimal parameter combination and three-dimensional visualization design scheme are output to the BIM platform.

2. The rain garden optimization method based on BIM dynamic rainwater simulation according to claim 1 is characterized in that: The specific process of extracting site planning data, rain garden geometric parameters, and surrounding pipe network topology based on the building information model platform to construct a stormwater analysis model is as follows: Based on the Building Information Modeling platform, site planning data including site elevation, underlying surface type, and area distribution are automatically extracted. The three-dimensional coordinates, outline dimensions, and geometric parameters of the layered structure of the rain garden are also extracted, along with the topological relationship of the surrounding pipe network connected to the rain garden overflow outlet. Based on the site planning data, geometric parameters and surrounding pipe network topology, the heterogeneous data is uniformly converted into a standardized format corresponding to the hydrological and hydraulic engine through the built-in or external data conversion interface of the BIM platform; By using data in a standardized format, a stormwater analysis model including rain garden units, site catchment areas, and associated pipe networks is dynamically constructed in the hydrological and hydraulic engine, and hydraulic connections between the components are established. The stormwater analysis model is output to subsequent simulation steps through a preset interface.

3. The rain garden optimization method based on BIM dynamic rainwater simulation as claimed in claim 2 is characterized in that: The specific process of the dynamic simulation of the infiltration-storage-overflow process is as follows: Take the historical rainfall sequence or designed rainfall scenario as input conditions and start the simulation by calling the hydrological and hydraulic engine interface; The dynamic infiltration rate of each layered medium and the change of aquifer storage capacity in the rain garden unit are iteratively calculated according to the preset step size on the continuous rainfall time axis; Based on the relationship between the real-time water level of the aquifer and the elevation of the overflow outlet, the overflow triggering time is determined and the overflow volume is calculated; Synchronize the hydraulic conductivity status of the surrounding pipe networks and update the flow and direction of the pipe network nodes; The output includes time series of runoff infiltration, detention volume occupancy, overflow event frequency, and dynamic process line data of pollution load migration path.

4. The rain garden optimization method based on BIM dynamic rainwater simulation as claimed in claim 3 is characterized in that: The specific process of identifying the sensitivity weights of key design parameters based on dynamic simulation results and iteratively adjusting the permeability coefficient, aquifer depth, and vegetation coverage parameter set until the runoff reduction rate and pollution load control targets are met is as follows: Based on the dynamic process line data, the runoff reduction rate, peak flow delay time, cumulative frequency of overflow events and average pollutant removal rate of the rain garden during the simulation period are extracted; Conduct orthogonal experiments or Monte Carlo sampling perturbations on parameters such as permeability coefficient, aquifer depth, and vegetation coverage. Calculate the magnitude of changes in performance indicators due to perturbations of each parameter through multiple rounds of dynamic simulations. Quantify the sensitivity weight of each parameter using variance analysis or regression models. According to the sensitivity weight ranking, high-weight parameters are adjusted first; if the runoff reduction rate does not meet the standard, the permeability coefficient or aquifer depth is increased in the order of weight; if the pollution load removal rate does not meet the standard, the vegetation cover rate or aquifer depth is increased first to extend the hydraulic retention time; After each round of parameter adjustment, the dynamic simulation is re-executed until the following conditions are met simultaneously: The total runoff reduction rate is greater than or equal to the design target value; The frequency of overflow events is less than or equal to the allowed threshold; The removal rate of key pollutants is greater than or equal to the control standard.

5. The rain garden optimization method based on BIM dynamic rainwater simulation according to claim 4 is characterized in that: The specific process of using the regression model to quantify the sensitivity weight of each parameter is as follows: Based on the multiple rounds of dynamic simulation data sets generated by the orthogonal test or Monte Carlo sampling perturbation, a multiple linear regression model is constructed for each performance indicator; the multiple linear regression model is expressed as shown in the following formula (1): in, For the performance indicators, They correspond to the total runoff reduction rate, peak flow delay time, cumulative frequency of overflow events and average pollutant removal rate respectively; is the permeability coefficient; is the aquifer depth; is the vegetation coverage rate; is the intercept term; 、 and The parameters are 、 and The regression coefficient of is the random error term; The regression coefficients were fitted using the least squares method using the multi-round dynamic simulation data set, and the standardized regression coefficients were calculated to eliminate the dimension effect, as shown in the following formula (2): in, is the standardized regression coefficient, Corresponding parameters 、 and , Corresponding performance indicators; For parameters The standard deviation of That is, parameters 、 、 one; is the standard deviation of the performance index; For parameters Performance indicators the original impact strength; Based on the standardized regression coefficient, the sensitivity score of each parameter to each performance indicator is calculated as shown in the following formula (3): in, Representation parameters Performance indicators sensitivity scores; Combining all performance indicators, the overall sensitivity weight of each parameter is calculated as shown in the following formula (4): in, For parameters sensitivity weight.

6. The rain garden optimization method based on BIM dynamic rainwater simulation according to claim 5 is characterized in that: The specific process of generating multiple candidate solutions that meet the performance evaluation indicators based on the iterative adjustment results, weighting them based on the full life cycle cost and ecological benefits, and outputting the optimal parameter combination and 3D visualization design solution to the BIM platform is as follows: Based on the parameter combination set that meets the runoff reduction rate and pollution load control objectives generated after iterative adjustment, multiple candidate design schemes are constructed; Extracting ecological benefit index data corresponding to the performance index data in the dynamic simulation results from each candidate solution, wherein the ecological benefit index data includes pollutant removal rate, runoff reduction contribution, and peak pressure relief value for the associated pipe network; Calculate the full life cycle costs of each option during the construction, maintenance and renewal phases; Based on the ecological benefit index data and the whole life cycle cost, a comprehensive evaluation system including cost indicators and ecological benefit indicators is constructed. The entropy weight method or hierarchical analysis method is used to determine the weight of each indicator, and the total score of each scheme is calculated according to the weight; Based on the total scores of each scheme, the optimal scheme is selected and ranked. The corresponding permeability coefficient, aquifer depth and vegetation coverage parameter combination and geometric structure information of the optimal scheme are generated and output into a three-dimensional visual design scheme model through the API interface of the BIM platform.

7. The rain garden optimization method based on BIM dynamic rainwater simulation according to claim 4 is characterized in that: The process of iteratively adjusting the permeability coefficient, aquifer depth, and vegetation coverage parameter set until the runoff reduction rate and pollution load control targets are met is performed by using a genetic algorithm to automatically optimize the parameters, specifically including the following steps: Initialize an initial population containing multiple randomly generated parameter combinations, each parameter combination corresponds to a value of hydraulic conductivity, aquifer depth, and vegetation coverage; Based on the dynamic simulation results, calculating a fitness function value for each parameter combination, wherein the fitness function is defined as the inverse of the comprehensive deviation between the actual value of the performance indicator and the design target value, the performance indicator including the total runoff reduction rate, the cumulative frequency of overflow events, and the key pollutant removal rate; Perform genetic operations on the current population, including roulette wheel selection based on fitness function values, arithmetic crossover between parameter values, and Gaussian mutation to generate a new generation of population; Repeat dynamic simulation, fitness calculation and genetic operation until the fitness function value of the optimal parameter combination in the population has no significant improvement for consecutive preset generations or reaches the maximum number of iterations, and output the optimal parameter combination that meets the control objective as the iterative adjustment result.

8. A rain garden optimization system based on BIM dynamic rainwater simulation, used to implement the rain garden optimization method based on BIM dynamic rainwater simulation according to any one of claims 1 to 7, characterized in that: include: The data extraction and modeling module is used to automatically extract site planning data, rain garden geometry parameters, and surrounding pipe network topology based on the building information model platform, and construct an integrated stormwater analysis model through a data conversion interface; A dynamic simulation module, connected to the data extraction and modeling module, is used to call the hydrological and hydraulic engine interface to perform a dynamic simulation of the entire process of infiltration, storage, and overflow of the rain garden based on historical rainfall sequences or designed rainfall scenarios, and output dynamic process line data of the time series; A parameter optimization module connected to the dynamic simulation module; A scheme generation module, connected to the parameter optimization module, is used to construct candidate schemes based on the optimized parameter combination set, calculate the full life cycle cost and ecological benefit indicators of each scheme, select the optimal scheme through weighted scoring, and output the optimal parameter combination and geometric construction information to the BIM platform to generate a three-dimensional visual design scheme; Among them, the parameter optimization module includes: Sensitivity analysis unit, used to extract performance indicators based on dynamic process line data and quantify the sensitivity weights of hydraulic conductivity, aquifer depth and vegetation cover through orthogonal experiments or Monte Carlo sampling perturbations; Iterative adjustment unit, used to prioritize the adjustment of high-weight parameters according to the sensitivity weight ranking, and iteratively optimize the parameter set through multiple rounds of dynamic simulation until the runoff reduction rate and pollution load control targets are met; The genetic algorithm optimization unit is used to initialize the parameter population, calculate the fitness function value and perform genetic operations to achieve automatic parameter optimization.

9. An electronic device, characterized in that: It includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the rain garden optimization method based on BIM dynamic rainwater simulation according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the rain garden optimization method based on BIM dynamic rainwater simulation described in any one of claims 1 to 7 is implemented.

Images