Indoor optimization design method and system based on BIM

Abstract

The invention relates to the technical field of building intelligent management, and discloses a BIM-based indoor optimization design method and system, and the method comprises the following steps: a) building a building information model through BIM software, and collecting the space size, material parameters, structure parameters, environment data and user demand data of a building; and b) an indoor space optimization target is set according to design specifications and user requirements, design constraint conditions are formulated, and the design constraint conditions comprise building specifications, fire protection requirements, human flow lines, functional requirements and ergonomic parameters. According to the invention, through multi-source data fusion, high-precision and low-delay data acquisition is realized; through hybrid modeling, the balance between the accuracy of energy consumption prediction and the calculation efficiency is realized; through reinforcement learning and fuzzy control, adaptive optimization of building environment adjustment is realized; through the modular architecture and the block chain, high expansibility and data security of the system are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of building intelligent management, and specifically to an indoor optimization design method and system based on BIM. Background Art

[0002] In recent years, with the development of building intelligence, intelligent control and energy consumption management systems have gradually become an important part of building operation. The existing technologies mainly rely on a variety of sensors for data collection, and combine modeling and optimization control methods to achieve intelligent regulation of the building environment and energy consumption management. Generally, the existing systems adopt a centralized architecture for data processing, and use traditional rule-based control or data-driven methods for building environment regulation. However, with the continuous expansion of building scale and the increasing complexity of operating environments, traditional technical solutions have gradually revealed many deficiencies in data collection, modeling accuracy, control strategies, and system scalability, making it difficult to meet the requirements of efficient and precise intelligent building management.

[0003] In terms of data collection in the existing technologies, the use of a single type of sensor or centralized data transmission method results in lagging data updates and difficulty in reflecting the dynamic changes of the building environment in real time. During the modeling process, solely relying on physical modeling involves large computational amounts and difficult parameter acquisition, while relying only on data-driven modeling is prone to problems such as insufficient generalization ability, affecting the accuracy of building energy consumption prediction. In terms of intelligent control, the existing technologies generally adopt fixed rule-based control or PID control, lacking self-adaptive optimization capabilities and being unable to effectively respond to environmental changes, resulting in inaccurate energy consumption control and inflexible comfort adjustment. In addition, in terms of system architecture and data security, traditional centralized architectures have problems of limited scalability and vulnerability to data attacks, posing challenges to the long-term stable operation of building management systems. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technologies, the present invention provides an indoor optimization design method and system based on BIM, which solves the problems of insufficient real-time data collection, difficulty in balancing the accuracy and computational efficiency of modeling methods, poor self-adaptability of control strategies, and limited scalability and data security of the system architecture in the existing technologies.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: An indoor optimization design method and system based on BIM, including:

[0006] An indoor optimization design method based on BIM, including the following steps:

[0007] a) Use BIM software to establish a building information model, and collect the spatial dimensions, material parameters, structural parameters, environmental data, and user requirement data of the building;

[0008] b) Set the indoor space optimization goals according to the design specifications and user requirements, and formulate design constraints, where the design constraints include building codes, fire protection requirements, human flow routes, functional requirements, and ergonomic parameters;

[0009] c) Generate multiple indoor design schemes through parametric design tools and intelligent optimization algorithms;

[0010] d) Conduct multi-dimensional simulation analysis on the optimized design schemes, where the simulation analysis includes daylighting simulation, ventilation simulation, energy consumption simulation, and human flow simulation, and generate performance evaluation reports for each scheme;

[0011] e) Select and optimize the optimal design scheme according to the simulation analysis results;

[0012] f) Generate the final indoor optimized design scheme and use it for the drawing of construction drawings, the generation of material lists, and the simulation of the construction process;

[0013] g) Conduct real-time monitoring and adjustment during the construction process;

[0014] h) Combine the use of feedback and intelligent monitoring systems to conduct operation and maintenance optimization and continuously improve future design schemes.

[0015] Preferably, the intelligent optimization algorithm uses one of the genetic algorithm, simulated annealing, or deep learning algorithm for the generation and optimization of design schemes.

[0016] Preferably, the design constraints include building codes, fire protection requirements, human flow routes, functional requirements, and ergonomic parameters.

[0017] Preferably, the steps for generating the optimization scheme include intelligent adjustment of the indoor space through a parametric design tool integrated with BIM.

[0018] An indoor optimization design system based on BIM, comprising:

[0019] A modeling module, used to generate a building information model of a building using BIM software and collect spatial dimensions, material parameters, structural parameters, environmental data, and user requirement data;

[0020] An optimization module, used to determine indoor space optimization goals according to the set design specifications and user requirements, and generate multiple optimized design schemes through parametric design tools and intelligent optimization algorithms;

[0021] A simulation analysis module, used to conduct multi-dimensional simulation analysis on the optimized design schemes, where the analysis includes daylighting, ventilation, energy consumption, and human flow simulations, and generate performance evaluation reports for each scheme;

[0022] A decision support module for selecting and further optimizing the optimal design solution based on the simulation analysis results;

[0023] A construction support module for generating construction drawings, material lists, and construction simulations, and for real-time monitoring and adjustment during the construction process;

[0024] An operation and maintenance management module for obtaining usage feedback data in combination with an intelligent monitoring system, and for performing operation and maintenance optimization to form an optimization closed-loop.

[0025] Preferably, the optimization module uses an AI intelligent optimization algorithm for generating and screening design solutions, and the algorithm includes a genetic algorithm, simulated annealing, or a deep learning algorithm.

[0026] Preferably, the simulation analysis module includes daylighting simulation, ventilation simulation, energy consumption simulation, and pedestrian flow simulation modules for performing multi-dimensional simulation analysis on the design solution.

[0027] Preferably, the optimization objectives in the optimization module include but are not limited to optimizing space utilization, minimizing energy consumption, improving comfort, optimizing daylighting, and noise control.

[0028] Preferably, the system further includes environmental monitoring devices related to the building for collecting and feedbacking indoor environmental data in real time, and for adjusting the design solution according to the feedback data.

[0029] Preferably, the construction support module performs real-time simulation of the construction process through a BIM model, optimizes the construction plan, and reduces construction errors.

[0030] The present invention provides an indoor optimization design method and system based on BIM. It has the following beneficial effects:

[0031] 1. The present invention adopts a multi-source data fusion and edge computing architecture, achieving high-precision and low-latency data acquisition. Compared with the single-sensor data acquisition scheme in the prior art, it solves the problems of lagging data update and large noise interference, ensures the real-time and reliability of building environmental parameters, and improves the system response speed.

[0032] 2. The present invention combines a hybrid method of physical modeling and data-driven modeling, achieving the effect of accurately predicting building energy consumption and environmental change trends. Compared with the situation in the prior art where a large prediction deviation is caused by relying on a single data model, it solves the problems of complex physical model calculation and insufficient generalization ability of the data-driven method, and improves the adaptability and calculation efficiency of the model.

[0033] 3. The present invention introduces an intelligent control strategy that combines reinforcement learning and fuzzy control, achieving the ability to adaptively optimize building operation parameters. Compared with the limitations of the fixed-rule control method in the prior art, it solves the problems that the control strategy is difficult to adjust in real time and has insufficient adaptability to environmental changes, and improves the flexibility and energy efficiency ratio of building intelligent management.

[0034] 4. The present invention adopts a modular architecture and combines blockchain technology, achieving the goals of strong system scalability and high data security. Compared with the security vulnerabilities of the traditional centralized management architecture in the prior art, it solves the problems of difficult system update and maintenance and high risk of data tampering, and improves the long-term reliability and future expansion ability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 is a flowchart of the method steps of the present invention;

[0036] Figure 2 is a system architecture diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0038] Please refer to the attached Figure 1 - Figure 2 , the embodiments of the present invention provide an indoor optimization design method based on BIM. An indoor optimization design method based on BIM includes the following steps:

[0039] a) Use BIM software to establish a building information model, and collect the spatial dimensions, material parameters, structural parameters, environmental data, and user requirement data of the building;

[0040] In this embodiment, step a mainly involves the establishment of BIM modeling and the collection and input of relevant data. This step includes, but is not limited to, the extraction of building structure information, indoor space division, material parameter setting, environmental data acquisition, and user requirement analysis, etc., to ensure that the subsequent optimization process has complete data support.

[0041] As an option, when performing BIM modeling, a three-dimensional modeling software (such as Revit, ArchiCAD, Bentley, etc.) is used to establish a building space information model. Specifically, the parametric modeling function in the BIM software is utilized to accurately model the main structures such as walls, floors, ceilings, doors, and windows. Generally, parameters such as wall thickness, material, and insulation performance need to be clearly marked in the BIM model for energy efficiency assessment during subsequent optimization processes.

[0042] In a possible implementation, each component in the model is assigned physical and performance attributes. For example, the thermal resistance R of a wall is calculated as follows:

[0043]

[0044] where d is the wall thickness in meters (m); k is the thermal conductivity of the wall material in watts per meter-kelvin (W / (m·K)).

[0045] In some embodiments, for buildings with complex structures, a multi-level information architecture needs to be introduced during BIM modeling. Specifically, multi-level families are used to manage different component types, and the database association function is utilized to store the information of relevant components for subsequent calls by optimization algorithms.

[0046] In addition, in this embodiment, BIM modeling not only includes structural information but also the division of indoor functional spaces. Generally, according to the building's usage function, the space is divided into work areas, rest areas, storage areas, etc., and specific parameters such as area, floor height, and ventilation requirements are set for each space area. As an option, the volume V of each area can be automatically calculated through the space analysis module of the BIM software:

[0047] V = L × W × H;

[0048] where L is the length of the space in meters (m); W is the width of the space in meters (m); H is the floor height in meters (m).

[0049] In a possible implementation, in combination with an environmental data collection module, the indoor environmental data in the BIM model is integrated. Specifically, sensors or external databases are used to collect factors including indoor temperature, humidity, air quality, noise, etc., and these data are associated with the corresponding space areas in the BIM model. For example, the temperature data can be calculated through the temperature field distribution equation:

[0050]

[0051] where T(x,y,z) is the temperature at a certain point in the space in degrees Celsius (°C); T0 is the reference temperature in degrees Celsius (°C); q is the heat source intensity per unit volume in watts per cubic meter (W / m3 ; ρ is the air density, with the unit of kg / m 3 ; c p is the specific heat capacity of air, with the unit of J / (kg·K).

[0052] In some embodiments, the integration of BIM data also includes the analysis and modeling of user requirements. As an option, a database is used to store the personalized requirements of users, including preferences for lighting, ventilation, and spatial layout. In specific implementation, through the user interface, user requirement data is obtained and converted into parameter inputs in the BIM model. For example, if the user wishes to increase the lighting area, the system will automatically adjust the size of the windows and recalculate the illuminance distribution.

[0053] In another possible implementation, to enhance the data compatibility of the BIM model, the IFC (Industry Foundation Classes) standard format can be used for data storage and exchange. Generally, the IFC format can ensure the compatibility of model data between different software, facilitating the subsequent invocation of optimization algorithms and simulation calculations.

[0054] In summary, step a in this embodiment involves multiple aspects such as the establishment of the BIM model, space division, component parameter setting, environmental data acquisition, and user requirement integration. Through the complete BIM modeling process, it is ensured that the subsequent optimization design has accurate data support and also provides the necessary input data for subsequent simulation analysis.

[0055] b) Set the indoor space optimization goal according to the design specifications and user requirements, and formulate design constraint conditions, where the design constraint conditions include building codes, fire requirements, people flow lines, functional requirements, and ergonomic parameters;

[0056] After completing the BIM modeling and data collection in step a, it is necessary to clarify the design goal and set the optimization constraint conditions on this basis. Generally, the setting of the optimization goal should be based on the comprehensive consideration of building functional requirements, energy consumption control requirements, and comfort improvement, while also taking into account construction feasibility and economy.

[0057] In this embodiment, step b mainly involves the setting of the optimization goal and the definition of the constraint conditions. The core of this step is to construct a reasonable optimization function and combine the building design constraints to ensure that all variables are within the feasible range during the optimization process. Specifically, the setting of the optimization goal usually includes but is not limited to multiple dimensions such as space utilization optimization, energy efficiency optimization, and comfort optimization.

[0058] In one possible implementation, the goal of space utilization optimization can be achieved by maximizing the proportion of available space. Generally, the space utilization rate U can be expressed as:

[0059]

[0060] Wherein: A u is the available space area, with the unit of m 2 ; A t is the total building area, with the unit of m 2 .

[0061] In some embodiments, in order to improve the space utilization rate, it may be necessary to optimize and adjust the furniture layout, room partitions, etc. Specifically, the room size and furniture placement can be dynamically adjusted through the parametric adjustment function of the BIM model to maximize the available space. As an option, the space usage efficiency of different design schemes can be evaluated by establishing a space optimization model based on the simulation of pedestrian flow in combination with user behavior data.

[0062] In another possible implementation, setting the energy efficiency optimization goal usually involves multiple aspects such as building lighting, ventilation, and energy consumption control. Generally, the energy consumption can be reduced by reducing the demand for artificial lighting and optimizing the natural ventilation path. Specifically, the building energy consumption E can be expressed as:

[0063] E = E l + E h + E v ;

[0064] Wherein: E l is the lighting energy consumption, with the unit of kWh; E h is the HVAC (Heating, Ventilation, and Air Conditioning) energy consumption, with the unit of kWh; E v is the ventilation system energy consumption, with the unit of kWh.

[0065] In some embodiments, the lighting energy consumption E i is further affected by the daylight factor D f , and the calculation formula is as follows:

[0066]

[0067] Wherein: E in is the indoor illuminance, with the unit of lux; E out is the outdoor illuminance, with the unit of lux.

[0068] In order to optimize the energy efficiency of the building, the influence of different window design schemes on the daylight factor can be evaluated through the lighting simulation function of the BIM model, and the demand for artificial lighting can be reduced in combination with intelligent lighting control strategies.

[0069] In terms of comfort optimization, the optimization objectives usually involve multiple aspects such as air quality, temperature and humidity control, and noise management. Specifically, the Air Quality Index (AQI) is affected by the concentration of indoor pollutants, and the calculation formula is as follows:

[0070] AQI = Σ i C i ×W i ;

[0071] Where: C i is the concentration of the i-th pollutant, with the unit of ppm; W i is the weight coefficient of this pollutant.

[0072] As an option, during the comfort optimization process, the parameters of the indoor fresh air system can be dynamically adjusted by combining intelligent sensor data to maintain the air quality within a healthy range. In addition, the spatial layout can be optimized by combining noise simulation analysis to reduce noise interference and improve the overall comfort.

[0073] In some embodiments, in order to ensure that the optimization scheme meets the ergonomic requirements, a minimum living space standard needs to be set. Specifically, the minimum room area A min can be calculated according to the human activity requirements as follows:

[0074] A min = ∑ i (S i ×N i );

[0075] Where: S i is the minimum space required for the i-th activity, with the unit of m 2 ; N i is the expected number of people performing this activity simultaneously.

[0076] In terms of construction feasibility constraints, the optimization scheme needs to meet the requirements of structural mechanics to ensure the stability of the building. Generally, the structural stability can be calculated by the safety factor SF as follows:

[0077]

[0078] Where: F y is the yield strength of the material, with the unit of MPa; F a is the actual bearing stress, with the unit of MPa.

[0079] In another possible implementation, in order to ensure construction feasibility, the construction simulation function of BIM can be combined to evaluate the construction difficulty of different optimization schemes and select the optimal scheme for subsequent implementation.

[0080] In summary, step b in this embodiment mainly involves the setting of optimization objectives and the definition of constraint conditions. By setting reasonable optimization objectives and combining building codes, ergonomics, and construction feasibility constraints, the rationality and feasibility of the optimization process are ensured, providing a solid theoretical basis for subsequent optimization calculations and simulation analyses.

[0081] c) Generate multiple interior design solutions through parametric design tools and intelligent optimization algorithms;

[0082] After completing the setting of optimization objectives and the definition of constraint conditions in step b, it is necessary to enter the optimization calculation and solution generation stage. Generally, this step relies on parametric modeling, intelligent optimization algorithms, and data-driven analysis methods to find the optimal design solution under the premise of set constraint conditions.

[0083] In this embodiment, step c mainly involves the execution of optimization calculations and the generation of preliminary design solutions. The key to this step lies in the mathematical modeling of the optimization problem and its solution in combination with algorithms. Specifically, optimization calculations usually include the construction of objective functions, the setting of constraints on variable parameters, and the iterative solution process.

[0084] In a possible implementation, the optimization objective can be expressed as the following multi-objective optimization function:

[0085] minF(x) = αF1(x) + βF2(x) + γF3(x);

[0086] Where: F1(x) represents the optimization objective function for space utilization; F2(x) represents the optimization objective function for energy efficiency; F3(x) represents the optimization objective function for comfort; α, β, γ are weight coefficients, which are dynamically adjusted according to optimization requirements.

[0087] In some embodiments, the space utilization optimization function F1(x) can be calculated based on maximizing the available space, such as:

[0088]

[0089] Where: A u is the area of the available space, in m 2 ; A t is the total building area, in m 2 .

[0090] In another possible implementation, the energy efficiency optimization objective F2(x) mainly involves minimizing the building energy consumption. Generally, this objective can be defined by the following energy consumption calculation model:

[0091]

[0092] Where: E lis the lighting energy consumption, with the unit of kWh; E h is the heating, ventilation, and air conditioning (HVAC) energy consumption, with the unit of kWh; E v is the ventilation system energy consumption, with the unit of kWh.

[0093] As an option, the comfort optimization objective F3(x) can be modeled based on air quality, temperature and humidity, and noise level. Specifically, air quality optimization can adopt pollutant concentration constraints, such as:

[0094] F3(x) = ∑ i C i ×W i ;

[0095] where: C i is the concentration of the i-th pollutant, with the unit of ppm; W i is the weight coefficient of this pollutant.

[0096] In the optimization calculation process, in some embodiments, a genetic algorithm is used for iterative solution. Specifically, the fitness function of the genetic algorithm is defined as:

[0097] Fitness(x) = -F(x);

[0098] where: x represents the optimization variable vector;

[0099] The negative sign is used to convert the minimization problem into maximizing the fitness.

[0100] Generally, the genetic algorithm includes operations such as selection, crossover, and mutation. As an option, in the crossover stage, a single-point crossover method can be adopted to improve the optimization efficiency. Specifically, the single-point crossover method can be expressed as:

[0101]

[0102] where: x1 and x2 are the parent individuals; k is the crossover point index.

[0103] In a possible implementation, to improve the optimization efficiency, a simulated annealing algorithm can be combined for local search. Generally, the temperature decay function of simulated annealing can be defined as:

[0104] T k+1 = λT k ;

[0105] where: T k is the temperature at the k-th iteration; λ is the decay coefficient, satisfying 0 < λ < 1.

[0106] In some embodiments, for complex design schemes, it may be necessary to introduce a deep learning model to improve the optimization efficiency. Specifically, a neural network can be used to perform regression modeling on the optimization objective, and its loss function can be expressed as:

[0107]

[0108] where: N is the number of training samples; The predicted value of the neural network.

[0109] After completing the optimization calculation, the system automatically generates multiple design schemes and screens them. Generally, the Pareto front analysis method can be used to select the optimal non-dominated solution set. Specifically, the definition of the Pareto optimal solution is as follows:

[0110] Such that F(y) ≤ F(x) and F(y) ≠ F(x);

[0111] As an option, during the scheme screening process, the analytic hierarchy process (AHP) can be combined to perform subjective weight evaluation to ensure that the final scheme meets the user's requirements.

[0112] In summary, step c in this embodiment mainly involves the execution of the optimization calculation and the process of generating schemes. By constructing a multi-objective optimization function and combining genetic algorithms, simulated annealing algorithms, and deep learning methods, the convergence and accuracy of the optimization calculation are ensured. Finally, based on Pareto front analysis and the analytic hierarchy process, the optimal design scheme is screened, laying a foundation for subsequent simulation analysis and construction implementation.

[0113] d) Perform multi-dimensional simulation analysis on the optimized design scheme. The simulation analysis includes daylighting simulation, ventilation simulation, energy consumption simulation, and pedestrian flow simulation, and generate a performance evaluation report for each scheme;

[0114] After completing the optimization calculation and scheme generation in step c, it is necessary to perform simulation analysis on multiple alternative schemes to verify the feasibility of the optimization scheme and further adjust the parameters to obtain the final optimized design scheme. Generally, the purpose of the simulation analysis is to evaluate key indicators such as space utilization rate, energy consumption, daylighting effect, and air quality to ensure that the final scheme meets the established optimization objectives.

[0115] In this embodiment, step d mainly involves the execution of the simulation analysis and the result evaluation. The key to this step is to perform multi-dimensional simulation on the optimized design scheme and make adjustments in combination with the simulation data. Specifically, the simulation analysis mainly includes the following aspects: daylighting simulation, ventilation simulation, energy consumption simulation, and pedestrian flow simulation.

[0116] In one possible implementation, daylighting simulation is mainly used to evaluate the indoor light environment under natural lighting conditions to determine whether it meets the requirements of comfort and energy efficiency. Generally, daylighting analysis can be carried out by calculating the indoor illuminance distribution E(x, y, z), and its calculation formula is as follows:

[0117]

[0118] Where: I is the light source intensity, with the unit of lm (lumen); θ is the incident angle; d is the distance from the light source to the target point, with the unit of m.

[0119] In some embodiments, in order to optimize the indoor daylighting effect, the orientation, area, and glass material of the windows can be adjusted. As an option, daylighting simulation software (such as Radiance or DIALux) is used to simulate the daylighting effects of different design schemes, and the scheme with uniform illuminance distribution and less excessive glare is selected.

[0120] In another possible implementation, ventilation simulation is used to evaluate the air flow situation to ensure that the indoor air quality meets the expected standards. Generally, ventilation analysis can be based on CFD simulation, and the air velocity v(x, y, z) and pressure distribution p(x, y, z) are calculated by solving the Navier-Stokes equations:

[0121]

[0122] Where: ρ is the air density, with the unit of kg / m 3 ; μ is the air dynamic viscosity, with the unit of Pa·s; F is the external force.

[0123] In some embodiments, in order to optimize the ventilation effect, the window position, vent size, and configuration of mechanical ventilation equipment can be adjusted. As an option, the effects of natural ventilation schemes and mechanical ventilation schemes can be compared, and the optimized scheme with uniform air velocity and lower pollutant concentration can be selected.

[0124] In terms of energy consumption simulation, in this embodiment, through energy consumption simulation software (such as EnergyPlus or IES-VE), the building energy consumption of different design schemes is calculated, and the energy-saving effects of different strategies are compared and analyzed. Generally, the building energy consumption E(x) is calculated as follows:

[0125] E(x) = E l + E h + E v ;

[0126] Where: E l is the lighting energy consumption, with the unit of kWh; E h is the heating, ventilation, and air conditioning (HVAC) energy consumption, with the unit of kWh; Ev For the energy consumption of the ventilation system, the unit is kWh.

[0127] As an option, based on the changes in parameters such as building orientation, exterior wall insulation performance, and window type, the impact on energy consumption can be analyzed, and the optimization plan with the highest energy efficiency can be selected.

[0128] In terms of pedestrian flow simulation, in this embodiment, through the Agent-based simulation method, the pedestrian flow under different design schemes is analyzed to optimize the indoor moving line design. Generally, the pedestrian movement model can calculate the pedestrian speed v based on the social force model i :

[0129]

[0130] Where: is the target moving force of the individual; is the social distance repulsive force between individuals; is the physical collision force with the object.

[0131] In some embodiments, in order to optimize the pedestrian flow organization, the channel width, room layout, and entrance and exit positions can be adjusted. As an option, the pedestrian passage time of different schemes can be compared, and the optimization design with the shortest average passing time can be selected.

[0132] After the simulation analysis is completed, in this embodiment, the simulation data of different schemes will be comprehensively compared, and the design parameters will be adjusted according to the simulation results. Generally, the weighted scoring method can be used to evaluate the advantages and disadvantages of different schemes, and the specific calculation is as follows:

[0133] S = w1S1 + w2S2 + w3S3 + w4S4;

[0134] Where: S is the final score; S1, S2, S3, S4 correspond to the scores of daylighting, ventilation, energy consumption, and pedestrian flow optimization respectively; w1, w2, w3, w4 are the weight coefficients.

[0135] To sum up, step d in this embodiment mainly involves the execution of simulation analysis and the adjustment of optimization plans. Through daylighting, ventilation, energy consumption, and pedestrian flow simulation, the rationality of the optimization plan is ensured, and the optimal plan is selected in combination with the scoring system, providing a scientific basis for the implementation of the subsequent construction plan.

[0136] e) According to the simulation analysis results, select and optimize the optimal design scheme;

[0137] After the simulation analysis and optimization plan adjustment in step d are completed, it is necessary to enter the stage of determining the final design plan and implementing the construction. Generally, this step aims to select the optimal plan based on the simulation data and optimization calculation results and convert it into an executable construction plan.

[0138] In this embodiment, step e mainly involves the determination of the final plan, the setting of construction technical parameters, and the monitoring and adjustment during the implementation process. Specifically, this step includes the generation of construction drawings, the optimized selection of materials and processes, and the dynamic monitoring of the construction process.

[0139] In a possible implementation, the determination of the construction plan is based on the final scoring results of the aforementioned optimized plan. Generally, the multi-objective weighted evaluation method can be used to comprehensively score multiple candidate plans.

[0140] In some embodiments, to improve construction feasibility, a three-dimensional construction model can be generated based on BIM (Building Information Modeling) technology to accurately simulate the construction process. As an option, the structural layout can be visually adjusted through BIM software (such as Revit or Navisworks), and construction conflicts can be detected in advance to reduce the risk of on-site modifications.

[0141] Regarding the setting of construction technical parameters, in this embodiment, the key construction parameters are determined based on the structural characteristics of the optimized plan. Specifically, for the selection of building materials, the wall insulation materials can be optimized according to the energy efficiency simulation results, and its thermal conductivity λ should meet the following conditions:

[0142]

[0143] Where: U max is the maximum allowable heat transfer coefficient; d is the wall thickness, in m; k is the thermal resistance of the material, in m 2 ·K / W.

[0144] As an option, high-efficiency insulation materials such as vacuum insulation panels (VIP) or aerogels can be used to reduce heat transfer losses and improve energy efficiency.

[0145] Regarding the optimization of construction technology, in some embodiments, modular prefabrication technology is adopted for structure erection to improve construction efficiency and reduce costs. Specifically, the size D of the prefabricated component can be set as follows according to the structural optimization parameters:

[0146]

[0147] Where: L total is the total building length, in m; N is the number of modules.

[0148] In a possible implementation, to ensure construction quality, an intelligent monitoring system can be introduced during the construction process. Generally, Internet of Things (IoT) sensors can be used to monitor key construction parameters in real time and combined with big data analysis techniques for deviation detection. As an option, a laser scanner can be used to monitor the structural offset, and its calculation formula is as follows:

[0149]

[0150] Where: x meas , y meas , z meas are the measured coordinates; x ref , y ref , z ref are the design reference coordinates.

[0151] In some embodiments, to improve construction accuracy, robotic construction technology can be introduced to reduce human error and improve construction efficiency. As an option, an automated bricklaying robot can be used, and its laying accuracy meets the following constraints:

[0152] ε ≤ δ max ;

[0153] Where: ε is the actual laying error, in mm; δ max is the allowable maximum error range.

[0154] After the construction is completed, in this embodiment, acceptance inspection and performance testing are carried out to ensure that the finally built structure meets the optimized design requirements. Generally, a on-site environmental monitoring system can be used to test building energy consumption, air quality and structural stability, and the construction quality can be evaluated through data analysis.

[0155] In summary, step e in this embodiment mainly involves the determination of the final plan, the setting of construction technical parameters and the dynamic monitoring of the construction process. Through technical means such as BIM modeling, intelligent monitoring and automated construction, the accuracy of the construction process is ensured, and finally an efficient and energy-saving optimized design scheme is realized, providing a reliable guarantee for the long-term operation of the building.

[0156] f) Generate the final indoor optimized design scheme and use it for the drawing of construction drawings, the generation of material lists and the simulation of the construction process;

[0157] In this embodiment, step f mainly involves the performance monitoring, data collection and operation optimization of the building in the later stage. Specifically, this step includes environmental parameter monitoring, energy consumption management, structural health assessment and the optimization of the intelligent control system.

[0158] In a possible implementation, environmental parameter monitoring is mainly used to evaluate the indoor air quality, temperature and humidity distribution, and lighting level of a building. Generally, an Internet of Things (IoT) sensor network can be adopted for real-time monitoring, and key environmental parameters P are recorded through a data acquisition system. i :

[0159] P i = {T, H, CO2, PM 2.5 , L};

[0160] Where: T is the indoor temperature, with the unit of °C; H is the relative humidity, with the unit of %; CO2 is the carbon dioxide concentration, with the unit of ppm; PM 2.5 is the concentration of fine particulate matter, with the unit of μg / m 3 ; L is the illuminance, with the unit of lux.

[0161] In some embodiments, to optimize the indoor environmental quality, the ventilation mode can be automatically adjusted by combining the HVAC (heating, ventilation, and air conditioning) system and the intelligent window control system. As an option, an environment regulation method based on fuzzy control can be adopted, and its regulation rules satisfy the following relationship:

[0162] F(T, H, CO2) = max{f1(T), f2(H), f3(CO2)};

[0163] Where: f1(T) is the temperature control function; f2(H) is the humidity control function; f3(CO2) is the air quality control function.

[0164] In terms of energy consumption management, in this embodiment, the energy consumption situation of each energy-consuming unit in the building is analyzed in real time through an energy consumption monitoring system. Generally, the total building energy consumption E can be decomposed as follows:

[0165] E = E l + E h + E v + E d ;

[0166] Where: E l is the lighting energy consumption, with the unit of kWh; E h is the HVAC (heating, ventilation, and air conditioning) energy consumption, with the unit of kWh; E v is the ventilation system energy consumption, with the unit of kWh; E d is the equipment operation energy consumption, with the unit of kWh.

[0167] In some embodiments, to optimize the building energy efficiency, a load prediction method based on machine learning can be adopted to dynamically adjust the energy scheduling strategy. As an option, a long short-term memory (LSTM) neural network can be used to predict the future energy consumption change trend, and its prediction model is as follows:

[0168] E t+1 = f(E t , E t-1 ,..., E t-n );

[0169] Where: E t is the energy consumption at the current moment; f(·) is the prediction function of the LSTM network.

[0170] In terms of structural health assessment, in this embodiment, a structural health monitoring (SHM) system is adopted to monitor the key structural components of the building for a long time. Generally, the structural stress σ and strain ε can be measured by strain gauges and accelerometers, and their relationship is as follows:

[0171] σ = E·ε;

[0172] Where: E is the elastic modulus of the material, with the unit of GPa; ε is the measured strain, dimensionless.

[0173] In some embodiments, to improve the accuracy of structural health assessment, a modal analysis method can be adopted to monitor the natural frequency f n of the building and determine whether there is a structural abnormality. As an option, finite element analysis (FEA) can be combined with sensor data for dynamic update, and its modal parameter calculation is as follows:

[0174]

[0175] Where: k n is the structural stiffness, with the unit of N / m; m n is the equivalent mass of the vibration mode, with the unit of kg.

[0176] In terms of the optimization of the intelligent regulation system, in this embodiment, based on the big data analysis method, the energy efficiency and comfort during the building's use process are optimized and adjusted. Generally, the reinforcement learning (RL) method can be adopted to train the intelligent control strategy, and its objective function is as follows:

[0177]

[0178] Where: R is the long-term return value; r t is the immediate return at the current time step; γ is the discount factor, 0 ≤ γ ≤ 1.

[0179] In some embodiments, to improve the system regulation effect, edge computing technology can be combined to decentralize the control decision calculation to local devices to reduce the cloud computing burden. As an option, an edge server can be adopted to perform local analysis on various sensor data and execute optimization control at the device level.

[0180] After the performance monitoring and optimization adjustment are completed, in this embodiment, an optimization plan suggestion can be generated based on the long-term data analysis results, and an automated optimization plan can be provided in combination with an artificial intelligence-assisted decision-making system. Generally, a data-driven method can be used to iteratively update the optimization strategy to ensure that the building operation state always remains at the best level.

[0181] In summary, step f in this embodiment mainly involves the performance monitoring, energy consumption management, structural health assessment, and intelligent regulation and optimization in the later stage of the building. Through technical means such as IoT monitoring, machine learning prediction, and reinforcement learning optimization, the intelligent management of the entire life cycle of the building is realized, and its operation state is ensured to meet the design optimization goals, providing technical support for the long-term efficient operation of the building.

[0182] g) Conduct real-time monitoring and adjustment during the construction process;

[0183] After the building performance monitoring and intelligent optimization in step f are completed, it is necessary to enter the long-term operation and maintenance and dynamic adjustment stage. Generally, the core of this stage lies in continuously tracking the actual operation situation of the building and adjusting the maintenance strategy based on the long-term data analysis results.

[0184] In this embodiment, step g mainly involves the long-term operation management of the building system, equipment maintenance optimization, and dynamic adjustment of operation parameters. Specifically, this step includes operation state evaluation, maintenance strategy optimization, equipment update, and implementation of an intelligent adjustment plan.

[0185] In a possible implementation manner, the operation state evaluation is analyzed based on long-term monitoring data. Generally, a time series analysis method can be used to predict the trend of key parameters of the building system. For a certain system state X t , its change trend can be expressed as follows:

[0186] X t =αX t-1 +βX t-2 +γ+ε t ;

[0187] Where: α, β are regression coefficients; γ is the system constant term; ε t is the random error.

[0188] In some embodiments, to improve the evaluation accuracy, statistical regression analysis and machine learning methods can be combined to perform anomaly detection on long-term data. As an option, the principal component analysis (PCA) method can be used to perform dimensionality reduction on multi-dimensional data to identify abnormal states, and its calculation method is as follows:

[0189] Z = XW;

[0190] Where: X is the original data matrix; W is the principal component weight matrix.

[0191] In terms of optimizing the maintenance strategy, in this embodiment, predictive maintenance technology is adopted to evaluate the health status of various types of equipment in the building. Generally, the remaining useful life (RUL) of the equipment can be calculated through a degradation model, and its basic form is:

[0192]

[0193] Where: D max is the maximum allowable degradation value of the equipment; D t is the current degradation state; r is the degradation rate.

[0194] In some embodiments, to reduce the maintenance cost, the equipment operation data and environmental impact factors can be combined to establish an adaptive maintenance cycle adjustment model. As an option, the Markov decision process (MDP) can be used to optimize the maintenance plan, and its state transition equation is as follows:

[0195] P(s′|s,a)=∑ t P(s′|s,a,t)P(t|s,a);

[0196] Where: P(s′|s,a) is the state transition probability; s is the current system state; a is the maintenance decision; t is the time variable.

[0197] In terms of equipment update management, in this embodiment, the life cycle assessment (LCA) method is adopted to quantitatively analyze the long-term use value of the equipment. Generally, the life cycle cost C total can be expressed as:

[0198]

[0199] Where: C init is the initial purchase cost; C op is the operation cost; C maint is the maintenance cost; r is the discount rate.

[0200] In some embodiments, to optimize the equipment update strategy, the environmental impact factors and energy efficiency indicators can be combined for multi-objective optimization. As an option, the genetic algorithm (GA) can be used to optimize the update plan, and its fitness function is as follows:

[0201] F(x)=w1f1(x)+w2f2(x)+w3f3(x);

[0202] Where: f1(x) is the energy efficiency optimization objective; f2(x) is the daily standard of maintenance cost; f3(x) is the environmental impact objective; w1, w2, and w3 are weight coefficients.

[0203] In terms of the implementation of the intelligent adjustment plan, in this embodiment, the reinforcement learning method is used to dynamically optimize the operation control strategy of the building. Generally, an adaptive adjustment system can be constructed based on deep reinforcement learning (DeepRL), and its learning objective function is as follows:

[0204]

[0205] Where: Q(s,a) is the state-action value function; r is the immediate reward; γ is the discount factor; s′ is the next state; a′ is the possible future action.

[0206] In some embodiments, to improve the adaptability of the adjustment strategy, edge computing technology can be combined to deploy the control algorithm on the local server to reduce data transmission latency. As an option, the federated learning method can be used to share optimization experiences among multiple buildings, and its update rule is as follows:

[0207]

[0208] Where: θ t is the current model parameter; η is the learning rate: L i is the data loss function of the i-th building.

[0209] After the long-term operation management and dynamic optimization are completed, in this embodiment, a long-term operation optimization strategy can be formulated based on the analysis of the whole life cycle data, and the building operation efficiency can be continuously improved in combination with the automated operation and maintenance system. Generally, a multi-objective decision-making method can be used to iteratively update the optimization strategy to ensure that the building always maintains the best operation state throughout its life cycle.

[0210] In summary, step g in this embodiment mainly involves long-term operation and maintenance, equipment management, and dynamic optimization. Through technical means such as predictive maintenance, life cycle assessment, reinforcement learning optimization, and federated learning, the intelligent operation and maintenance of the whole life cycle of the building are realized, and its long-term operation state is ensured to meet the optimization design goal, providing technical support for future building intelligent management.

[0211] h) Combine the use of feedback and intelligent monitoring systems to optimize operation and maintenance and continuously improve future design solutions;

[0212] After the long-term operation and maintenance and dynamic optimization in step g are completed, it is necessary to enter the system expansion and upgrade optimization phase. Generally, the core of this step lies in continuously optimizing the system architecture based on the data feedback during the building operation process and improving the overall performance through modular upgrade methods.

[0213] In this embodiment, step h mainly involves the expansion and upgrade of the building intelligent system, the optimization of software and hardware compatibility, and the collaborative operation across systems. Specifically, this step includes the extensible design of system modules, the optimization and upgrade of data processing capabilities, the iterative update of intelligent control algorithms, and the adaptation adjustment of multi-system collaborative work.

[0214] In a possible implementation, the extensible design of system modules is developed based on an object-oriented architecture. Generally, a modular architecture can be adopted to enable each functional module to have independent expansion capabilities. For a certain module M i , its expandability can be measured by the following formula:

[0215]

[0216] Where: E(M i ) is the module expansion ability; C new is the complexity of the new functional module; C base is the complexity of the basic module.

[0217] In some embodiments, to improve the compatibility of the system, an open API architecture can be adopted to enable external systems to quickly access the existing platform. As an option, RESTful API can be used for data interaction, and its request structure is as follows:

[0218] Request = {Header, Method, Payload};

[0219] Where: Header is the request header information; Method is the request method, such as GET, POST; Payload is the data payload.

[0220] In terms of the optimization and upgrade of data processing capabilities, a distributed computing architecture is adopted in this embodiment to improve data processing efficiency. Generally, based on edge computing, the computing tasks can be distributed to different nodes to reduce the load on the central server. The data distribution strategy can be expressed as follows:

[0221]

[0222] Where: T total is the overall data processing time; T i is the execution time of the i-th computing task; S iComputing resources allocated for this task.

[0223] In some embodiments, to improve computing efficiency, optimization can be carried out in combination with an artificial intelligence acceleration chip. As an option, a tensor processing unit (TPU) can be used to accelerate the deep learning inference process, and its computing model is as follows:

[0224] O = W·X + B;

[0225] Where: O is the computing output activity; W is the weight matrix; X is the input matrix; B is the bias term.

[0226] In terms of the iterative update of the intelligent control algorithm, in this embodiment, the reinforcement learning method is adopted to continuously optimize the control strategy of the building management system. Generally, a control strategy can be constructed based on the Q-learning method, and its update equation is as follows:

[0227]

[0228] Where: Q(s,a) is the state-action value; α is the learning rate; r is the immediate reward; γ is the discount factor.

[0229] In some embodiments, to improve the convergence speed of the control strategy, pre-training can be carried out in combination with the self-supervised learning method. As an option, an autoencoder can be used to extract features of the system state, and its optimization objective is as follows:

[0230]

[0231] Where: X is the input data; is the reconstructed data.

[0232] In terms of the adaptation and adjustment of multi-system collaborative work, in this embodiment, the multi-agent system (MAS) method is adopted to enable different subsystems to collaborate efficiently. Generally, each subsystem of the building can be modeled as an intelligent agent, and optimal cooperation can be achieved through game theory methods. Its optimization function is as follows:

[0233] U i = ∑ j≠i P ij ·S j ;

[0234] Where: U i is the utility of the i-th system; P ij is the influence weight of the i-th system on the j-th system; S jis the state value of the j-th system.

[0235] In some embodiments, to improve the collaboration efficiency, blockchain technology can be used to encrypt and verify the data exchange between systems. As an option, smart contracts can be utilized for data consistency management, and its execution logic is as follows:

[0236] IfH(D new )=H(D stored )thenapprove;

[0237] Where: H(·) is the hash function; D new is the newly submitted data; D stored is the data stored on the chain.

[0238] After the system expansion and upgrade optimization are completed, in this embodiment, an intelligent prediction model can be constructed based on long-term monitoring data to guide future expansion decisions. Generally, the Bayesian Optimization method can be used to optimize the expansion plan, and its objective function is as follows:

[0239]

[0240] Where: U(x) is the utility of the expansion plan; D is the historical data.

[0241] In summary, step h in this embodiment mainly involves the expansion and upgrade of the building intelligent system, data processing optimization, control strategy update, and cross-system collaboration adaptation. Through the modular architecture, reinforcement learning optimization, blockchain data management, and game theory collaboration method, the long-term evolution of the building intelligent system is realized, and its adaptation to future functional requirements and technological upgrades is ensured, providing a continuously optimized solution for intelligent building management.

[0242] An indoor optimization design system based on BIM:

[0243] After the design and optimization of the overall system architecture are completed, a complete module system needs to be constructed to achieve the efficient operation of the building intelligent system. Generally, the system consists of multiple functional modules, including data acquisition, modeling, intelligent control, optimization decision-making, and system expansion, etc. The modules interact through data streams and control signals to ensure the stability and efficiency of the system. As an option, a distributed computing architecture can be combined to improve the computing efficiency and adapt to the dynamic changes of complex building environments.

[0244] In this embodiment, the system mainly includes the following core modules: a data acquisition module, a modeling module, an intelligent control module, an optimization decision-making module, and a system expansion module. Specifically, each module cooperates with each other to form a complete building intelligent management system.

[0245] In terms of the data acquisition module, in this embodiment, a multi-source data fusion technology is adopted to improve data accuracy. Generally, a distributed sensing network can be used to collect information such as temperature, humidity, and energy consumption, and real-time transmission is carried out through a wireless communication protocol. As an option, an edge computing architecture can be combined to perform preprocessing at the data source end to reduce the central computing burden. The data acquisition process can be expressed as:

[0246]

[0247] where: D(t) is the total data volume at time t; S i (t) is the acquisition data of the i-th sensor; ε is the acquisition error.

[0248] In terms of the modeling module, in this embodiment, a hybrid modeling method is adopted, combining physical modeling and data-driven modeling to improve the system's prediction ability. Generally, a thermodynamic model of the building environment can be established based on the energy balance equation, and the computational fluid dynamics (CFD) method can be combined to simulate the air flow characteristics. As an option, a neural network model can be used to fit the non-linear dynamic characteristics of the building system to improve the adaptability to complex environmental changes.

[0249] The heat transfer model can be described as follows:

[0250] Q = UA(T in -T out );

[0251] where: Q is the heat transfer amount; U is the heat transfer coefficient; A is the heat transfer surface area; T in is the indoor temperature; T out is the outdoor temperature.

[0252] In terms of the intelligent control module, in this embodiment, a reinforcement learning method is adopted to optimize the autonomous adjustment ability of the building system. Generally, based on the Q-learning algorithm, real-time adjustment of the environmental feedback can be carried out. As an option, a fuzzy control method can be combined to improve the robustness of the control system and avoid over-reliance on a specific data distribution. The optimization strategy of reinforcement learning can be expressed as follows:

[0253]

[0254] where: Q(s,a) is the state-action value; α is the learning rate; r is the immediate reward; γ is the discount factor.

[0255] In terms of the optimization decision-making module, an adaptive optimization algorithm is adopted in this embodiment to improve the energy efficiency ratio of the building system. Generally, the control parameters can be dynamically adjusted based on the Bayesian optimization method. As an option, the genetic algorithm (GA) can be used for multi-objective optimization to meet the requirements of different operating scenarios. The optimization objective function can be defined as:

[0256]

[0257] where: f(x) is the optimization objective function; w i is the weight coefficient; g i (x) are the sub-objective functions.

[0258] In terms of the system expansion module, a modular architecture is adopted in this embodiment to improve the scalability of the system. Generally, based on the microservice architecture, different functional modules can be independently updated and expanded. As an option, blockchain technology can be combined to encrypt and store system data to improve data security. The blockchain data storage mechanism can be described as follows:

[0259] H(D new ) = H(D stored );

[0260] where: H(·) is the hash function; D new is the newly submitted data; D stored is the data stored on the chain.

[0261] After the modules work together, in this embodiment, based on long-term data accumulation, self-supervised learning methods can be used to iteratively optimize the system. Generally, time series modeling techniques can be combined to enable the building intelligent management system to have the ability of adaptive evolution, improving the stability and energy efficiency ratio during long-term operation.

[0262] In summary, all the modules in this embodiment cooperate with each other, including data acquisition, modeling, intelligent control, optimization decision-making, and system expansion. By combining multi-source data fusion, hybrid modeling, reinforcement learning optimization, adaptive decision-making, and modular architecture, the efficient operation of building intelligent management is achieved, providing technical support for future expansion and optimization.

[0263] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An indoor optimization design method based on BIM, characterized in that, It includes the following steps: a) Use BIM software to establish a building information model, and collect the spatial dimensions, material parameters, structural parameters, environmental data, and user requirement data of the building; b) Set the indoor space optimization goals according to the design specifications and user requirements, and formulate design constraints, where the design constraints include building codes, fire protection requirements, people flow lines, functional requirements, and ergonomic parameters; c) Generate multiple indoor design schemes through parametric design tools and intelligent optimization algorithms; d) Conduct multi-dimensional simulation analysis on the optimized design schemes, where the simulation analysis includes daylighting simulation, ventilation simulation, energy consumption simulation, and people flow simulation, and generate performance evaluation reports for each scheme; e) Select and optimize the optimal design scheme according to the simulation analysis results; f) Generate the final indoor optimized design scheme, and use it for the drawing of construction drawings, the generation of material lists, and the simulation of the construction process; g) Conduct real-time monitoring and adjustment during the construction process; h) Combine the use of feedback and intelligent monitoring systems to conduct operation and maintenance optimization and continuously improve future design schemes.

2. The indoor optimization design method based on BIM according to claim 1, characterized in that, The intelligent optimization algorithm is designed for the generation and optimization of design schemes by using one of genetic algorithms, simulated annealing, or deep learning algorithms.

3. The indoor optimization design method based on BIM according to claim 1, characterized in that The design constraints include building codes, fire protection requirements, people flow lines, functional requirements, and ergonomic parameters.

4. The indoor optimization design method based on BIM according to claim 1, wherein, The step of generating the optimization scheme includes the intelligent adjustment of the indoor space through the parametric design tool integrated with BIM.

5. An indoor optimization design system based on BIM, which is used for an indoor optimization design method according to any one of claims 1-4, characterized in that It includes: A modeling module, which is used to generate a building information model of the building by using BIM software, and collect spatial dimensions, material parameters, structural parameters, environmental data, and user requirement data; An optimization module, which is used to determine the indoor space optimization goals according to the set design specifications and user requirements, and generate multiple optimized design schemes through parametric design tools and intelligent optimization algorithms; A simulation analysis module, which is used to conduct multi-dimensional simulation analysis on the optimized design schemes, where the analysis includes daylighting, ventilation, energy consumption, and people flow simulations, and generate performance evaluation reports for each scheme; A decision support module, which is used to select and further optimize the optimal design scheme according to the simulation analysis results; A construction support module, which is used to generate construction drawings, material lists, and construction simulations, and conduct real-time monitoring and adjustment during the construction process; An operation and maintenance management module, which is used to obtain usage feedback data by combining with an intelligent monitoring system, and conduct operation and maintenance optimization to form an optimization closed-loop.

6. The indoor optimization design system based on BIM according to claim 5, wherein The optimization module uses an AI intelligent optimization algorithm for the generation and screening of design schemes, and the algorithm includes genetic algorithms, simulated annealing, or deep learning algorithms.

7. An indoor optimization design system based on BIM according to claim 5, characterized in that, The simulation analysis module includes daylighting simulation, ventilation simulation, energy consumption simulation, and people flow simulation modules, which are used to conduct multi-dimensional simulation analysis on the design schemes.

8. An indoor optimization design system based on BIM according to claim 5, characterized in that, The optimization goals in the optimization module include but are not limited to optimizing space utilization, minimizing energy consumption, improving comfort, optimizing daylighting, and noise control.

9. The indoor optimization design system based on BIM according to claim 5, characterized in that, The system further includes environmental monitoring equipment related to the building, which is used to collect and feedback indoor environmental data in real time, and adjust the design scheme according to the feedback data.

10. The indoor optimization design system based on BIM according to claim 5, characterized in that, The construction support module conducts real-time simulation of the construction process through the BIM model, optimizes the construction plan, and reduces construction errors.

Images