AI enhanced green building design optimization system
Through AI-enhanced green building design optimization system, the building life cycle data is integrated, environmental simulation and dynamic optimization are carried out, and the existing system's shortcomings in data integration, dynamic optimization and multi-objective optimization are solved, and the existing system has been achieved. Comprehensive optimization and sustainability of green buildings.
Patent Information
- Application Number
- CN202410867711.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-01
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-07-01
AI Technical Summary
The existing green building design optimization system has shortcomings in data integration, dynamic optimization and multi-objective optimization, and it is impossible to comprehensively evaluate the full life cycle performance of the building, and it is difficult to provide comprehensive optimization support in various stages of design, construction, operation and maintenance.
Adopt AI-enhanced green building design optimization system, integrate data, perform multi-scale environmental simulation and dynamic optimization through building life cycle data integration, environmental simulation and prediction, dynamic optimization and multi-objective decision support modules, combining energy consumption, comfort, and environment Make balanced decisions with impact and cost.
It has achieved intelligence and comprehensive optimization of architectural design, improved the overall performance and sustainability of green buildings, and significantly improved the scientificity and optimization effect of the design.
Smart Images

Figure CN119047018A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of building analysis, and in particular to an AI-enhanced green building design optimization system. Background Art
[0002] Green building design is an important trend in the current construction field. Its core concept is to reduce resource consumption and environmental pollution through energy-saving, environmental protection, health and comfort design methods. However, traditional green building design methods mainly rely on the experience and expertise of designers and lack systematic data analysis and optimization methods. This is not only inefficient, but also easily affected by human factors, making it difficult to ensure the optimality and comprehensiveness of the design.
[0003] With the development of artificial intelligence technology, especially the advancement of deep learning and big data analysis technology, new possibilities have been provided for green building design. By introducing artificial intelligence, intelligent optimization and evaluation of building design schemes can be achieved, improving the efficiency and quality of design. However, most of the existing systems on the market only focus on one aspect of building design, lack the ability to comprehensively optimize the entire life cycle of the building, and find it difficult to provide comprehensive optimization support in various stages such as design, construction, operation and maintenance.
[0004] The existing green building design optimization system has the following main problems:
[0005] Insufficient data integration: Existing systems are usually unable to effectively integrate data from the entire life cycle of buildings, from design and construction to operation and maintenance, resulting in low data utilization and inability to comprehensively evaluate building performance.
[0006] Limited dynamic optimization capabilities: Lack of dynamic optimization capabilities makes it impossible to make timely adjustments and optimizations based on real-time environmental data and building operating conditions, resulting in unsatisfactory optimization results.
[0007] Lack of multi-objective optimization: Existing systems often only focus on a single objective, such as energy consumption or cost, during the optimization process, and fail to balance multiple objectives such as energy consumption, comfort, environmental impact and cost, making it difficult to achieve comprehensive optimization.
[0008] In response to the above problems, the present invention provides an AI-enhanced green building design optimization system, which realizes the intelligent and comprehensive optimization of green building design through modules such as building life cycle data integration, environmental simulation and prediction, dynamic optimization, and multi-objective decision support. Summary of the invention
[0009] Based on the above objectives, the present invention provides an AI enhanced green building design optimization system.
[0010] AI-enhanced green building design optimization system, including:
[0011] The building life cycle data integration module integrates the full life cycle data of the building from design, construction, operation to maintenance. The full life cycle data includes life cycle analysis data of building materials, energy consumption data, environmental impact data, and maintenance records;
[0012] Environmental simulation and prediction module, which performs multi-scale, multi-physics field environmental simulation based on integrated life cycle data, including climate change prediction, air quality simulation, noise propagation simulation, and water resource management simulation;
[0013] A dynamic optimization module, connected to the environmental simulation and prediction module, performs dynamic optimization at different stages of the building life cycle, including design optimization, construction process optimization, operation management optimization and maintenance strategy optimization;
[0014] The multi-objective decision support module is connected to the dynamic optimization module and is used to make optimization decisions in the dimensions of energy consumption, comfort, environmental impact and cost based on the multi-objective decision theory, and to generate a comprehensive optimization plan that balances various objectives.
[0015] Furthermore, the building life cycle data integration module specifically includes:
[0016] Design data integration unit, used to collect and integrate design drawings, material lists, building codes and standards, and design simulation data during the building design phase;
[0017] Construction data collection unit, used to collect and integrate construction plans, actual construction progress, construction quality inspection records, construction site environmental data and material usage records during the construction phase;
[0018] Operational data monitoring unit, used to monitor and integrate energy consumption data (including electricity, water, and gas consumption), indoor and outdoor environmental data (temperature, humidity, and air quality), equipment operating status, and performance data during the building operation phase;
[0019] Maintenance data recording unit, used to record and integrate maintenance plans, maintenance operation records, equipment replacement records and maintenance cost data during the building maintenance phase;
[0020] The data storage and management unit is connected to each unit to store and manage the integrated full life cycle data to ensure the security, consistency and accessibility of the data;
[0021] The data processing and analysis unit is connected to the data storage and management unit, and is used to process and analyze the full life cycle data, generate life cycle analysis data of building materials, energy consumption analysis reports, environmental impact assessments and maintenance demand forecasts.
[0022] Furthermore, the life cycle analysis data specifically includes:
[0023] Calculate the environmental impact and resource consumption of materials at each stage of production, transportation, use and recycling. The total life cycle impact formula is: Among them, LCA is the total life cycle impact, EI i is the unit environmental impact of the i-th stage, Q i is the material quantity or usage in the i-th stage, and n is the number of stages;
[0024] The energy consumption analysis report specifically includes:
[0025] The energy consumption data is smoothed using the moving average method, and the formula is: Among them, MA t is the moving average at time t, E t-i is the energy consumption data at the ti-th moment, and n is the time window size;
[0026] Pattern recognition: Using regression analysis to build an energy consumption prediction model: E t =β 0 +β 1 ×t+ t , where E t is the energy consumption at time t, β 0 and β 1 are the regression coefficients, t is the error term;
[0027] The environmental impact assessment and maintenance demand forecast specifically include:
[0028] Using the weighted comprehensive evaluation method, the formula is:
[0029] Among them, EI is the total environmental impact score, W i is the weight of the i-th environmental factor, I i is the impact score of the i-th environmental factor, and m is the number of environmental factors;
[0030] The maintenance demand prediction specifically includes:
[0031] Use exponential smoothing to predict future maintenance needs, the formula is:
[0032] in, is the forecast demand at time t+1, D t is the actual demand at time t, is the forecast demand at time t, and α is the smoothing coefficient.
[0033] Furthermore, the environmental simulation and prediction module specifically includes:
[0034] The climate change prediction unit is used to predict climate change using the regional climate model RCM based on the integrated life cycle data and historical climate data, expressed as:
[0035] T future =T current +ΔT, where T future is the future temperature, T current is the current temperature, ΔT is the temperature change predicted by the climate model;
[0036] Use the combined method of global climate model GCM and regional climate model RCM to predict climate change under different scenarios: future =P current ×(1+R), where P future is the future precipitation, P current is the current precipitation, R is the precipitation change rate;
[0037] The air quality simulation unit is used to simulate the air quality around the building based on life cycle data, emission source data and meteorological data, and simulate the diffusion of pollutants based on the Gaussian diffusion model. The formula is:
[0038] Where C(x,y,z) is the pollutant concentration at point (x,y,z), Q is the emission source intensity, σ x ,σ y ,σ z are diffusion coefficients respectively, combined with CFD (computational fluid dynamics) to simulate air flow and pollutant diffusion, the formula is: +S, where u is the velocity vector, D is the diffusion coefficient, and S is the source term;
[0039] The noise propagation simulation unit is used to simulate the propagation of noise inside and outside the building based on the building layout, material properties and environmental data. The noise propagation is simulated using the sound wave propagation model. The formula is:
[0040] L p =L w -20log 10 (r)-αr, where L p is the sound pressure level at the receiving point, L w is the sound power level of the sound source, r is the distance from the sound source to the receiving point, α is the air absorption coefficient, and considering reflection and absorption in combination with the building acoustic model, the formula is:
[0041] L p =L w -20log 10 (r)-αr-R, where R is the sound absorption coefficient of the building material;
[0042] The water resource management simulation unit is used to simulate the water resource management and water cycle system of the building area based on water use data, precipitation data and geographic information, and simulate precipitation and runoff based on the hydrological model. The formula is:
[0043] R = P-ET-I, where R is runoff, P is precipitation, ET is evapotranspiration, and I is infiltration. The stormwater management model SWMM is used to simulate the urban water cycle system. The simulation is expressed as:
[0044] Where Q is the water flow rate, n is the roughness coefficient, A is the cross-sectional area, R h is the hydraulic radius and S is the water flow slope.
[0045] Furthermore, the dynamic optimization module specifically includes:
[0046] The design optimization unit is used to optimize the building layout and material selection during the building design stage. The optimized building layout uses a genetic algorithm combined with climate change prediction data to maximize natural ventilation and daylighting, which is expressed as:
[0047] Among them, F layout is the layout optimization objective function, A i is the area of the ith space, E i is the lighting effect of the i-th space, W i is the ventilation effect of the i-th space, n is the number of spaces; the optimization material selection is based on life cycle analysis combined with air quality simulation and environmental impact data, and low environmental impact building materials are selected. The optimization is expressed as:
[0048] Among them, EI total is the total environmental impact, EI j is the unit environmental impact of the jth material, Q j is the usage of the jth material, and m is the number of material types;
[0049] The construction process optimization unit is used to optimize the construction plan and material usage during the construction phase to reduce environmental impact and improve construction efficiency. The optimized construction plan uses the critical path method combined with noise propagation simulation and air quality data to optimize the construction progress, reduce construction period and environmental impact, expressed as: min Among them, T total is the total construction period, D k is the duration of the kth construction task, and p is the number of construction tasks; the optimized material use utilizes linear programming to optimize material use and reduce waste and cost, which is expressed as: Among them, Cmaterials is the total material cost, c l is the unit cost of the lth material, x l is the usage of the lth material, q is the number of material types;
[0050] The operation management optimization unit is used to optimize energy management and equipment operation to improve energy efficiency and comfort during the building operation phase based on the environmental monitoring data provided by the environmental simulation and prediction module. The optimized energy management is based on the predictive control method to improve energy efficiency, which is expressed as:
[0051] Among them, E total is the total energy consumption, P t is the power demand at the tth moment, Δt is the time interval, and T is the total time; the optimization equipment operation is based on the equipment performance data and environmental monitoring data to optimize the equipment operation parameters, and the formula is: Among them, E efficiency is the equipment efficiency, O output is the device output power, I input Input power to the device;
[0052] The maintenance strategy optimization unit is used to optimize the maintenance plan and strategy during the building maintenance phase based on the long-term environmental data and equipment status data provided by the environmental simulation and prediction module to extend the equipment life and reduce maintenance costs. The optimized maintenance plan is based on a predictive maintenance algorithm to optimize the maintenance plan and reduce failures and maintenance costs, which is expressed as: in,
[0053] C maintenance is the total maintenance cost, c t is the unit maintenance cost at time t, M t is the maintenance amount at the tth moment; the optimized maintenance strategy adopts the reliability center maintenance method to optimize the maintenance strategy and improve the equipment reliability, which is expressed as:
[0054] Among them, R total is the total reliability, R n is the reliability of the nth device, and N is the number of devices.
[0055] Furthermore, the multi-objective decision support module specifically includes:
[0056] An objective function definition unit is used to define objective functions of energy consumption, comfort, environmental impact and cost;
[0057] A weight setting unit, used to set the weight of each objective function according to user needs and priorities;
[0058] A multi-objective optimization algorithm unit, used to solve the optimal solution of each objective function based on a multi-objective optimization algorithm;
[0059] The comprehensive optimization scheme generation unit is used to synthesize the optimal solutions of various objective functions and generate a comprehensive optimization scheme that balances various objectives.
[0060] Furthermore, the objective function definition unit specifically includes:
[0061] Energy consumption objective function: With the goal of minimizing building energy consumption, define the energy consumption objective function E, the formula is: Among them, P t is the power demand at time t, Δt is the time interval, and T is the total time;
[0062] Comfort objective function: To maximize the comfort level in the building, define the comfort objective function C, the formula is: Among them, S i is the comfort score of the i-th space, A i is the area of the i-th space, n is the number of spaces;
[0063] Environmental impact objective function: With the goal of minimizing environmental impact, define the environmental impact objective function I, the formula is: Among them, EI j is the unit environmental impact of the jth material, Q j is the usage of the jth material, and m is the number of material types;
[0064] Cost objective function: With the goal of minimizing construction cost, the cost objective function K is defined, and the formula is: Among them, C k is the unit cost of the kth item, x k is the usage of the kth item, and p is the number of items.
[0065] Furthermore, the weight setting unit sets the weight w of each objective function according to user needs and priorities. i , the formula is: W = {w E ,w C ,w I ,w K}, where w E is the weight of the energy consumption target, w C is the weight of the comfort target, w I is the weight of the environmental impact target, w K is the weight of the cost target, and ∑w i =1.
[0066] Furthermore, the multi-objective optimization algorithm unit uses a weighted sum method to perform multi-objective optimization and solve the comprehensive optimization objective function F, and the formula is:
[0067] F=w E ·E+w C ·C+w I I+w K K, where F is the comprehensive optimization objective function and weight w i The objective functions E, C, I, and K are respectively energy consumption, comfort, environmental impact, and cost objective functions, which are set by the weight setting unit. The particle swarm optimization is used to find the optimal solution and update the optimization parameters.
[0068] According to the optimal solution obtained by particle swarm optimization, a comprehensive optimization plan that balances various objectives is generated. The formula is: Optimal Solution = arg minF, where Optimal Solution is the comprehensive optimization plan and F is the comprehensive optimization objective function.
[0069] Furthermore, the particle swarm optimization specifically includes:
[0070] Initialize the particle swarm, set the position and velocity of the particles, each particle represents a candidate solution, and its position and velocity vectors are x i and v i :
[0071] Among them, i represents the i-th particle, and n is the dimension of the problem;
[0072] Evaluate fitness: Calculate the fitness value of each particle. For multi-objective optimization problems, the fitness function is the weighted sum of multiple objective functions:
[0073] f(x i )=w E ·E(x i )+w C ·C(x i )+w I ·I(x i )+w K ·K(x i ), where E(x i ) is the energy consumption objective function, C(x i ) is the comfort objective function, I(x i ) is the environmental impact objective function, K(x i ) is the cost objective function, w E ,w C ,w I ,w K are the weights of each objective function respectively;
[0074] Update individual optimal and global optimal: For each particle, update the individual optimal position p iand the global optimal position g;
[0075]
[0076] g(t+1)=X i (t)if f(X i (t)) <f(g(t));
[0077] Update particle velocity and position:
[0078]
[0079] x i (t+1)=x i (t)+v i (t+1);
[0080] Among them, ω is the inertia weight, c 1 and c 2 They are individual learning factor and social learning factor, r 1 and r 2 is a random number between 0 and 1;
[0081] Repeatedly evaluate fitness, update individual optimal and global optimal, and update particle speed and position until the termination condition is met.
[0082] Beneficial effects of the present invention:
[0083] The present invention, through the building life cycle data integration module, comprehensively integrates the full life cycle data from design, construction, operation to maintenance, including life cycle analysis data of building materials, energy consumption data, environmental impact data and maintenance records, etc. The environmental simulation and prediction module performs multi-scale and multi-physical field environmental simulation, providing data support for climate change prediction, air quality simulation, noise propagation simulation and water resource management simulation. On this basis, the dynamic optimization module performs design optimization, construction process optimization, operation management optimization and maintenance strategy optimization at different stages, combines real-time environmental data and simulation results, realizes dynamic optimization of the building life cycle, and improves the overall performance and sustainability of green building design.
[0084] The present invention adopts a multi-objective decision support module, defines the objective functions of energy consumption, comfort, environmental impact and cost, sets weights, and uses the weighted sum method to perform multi-objective optimization. Combined with the particle swarm optimization algorithm, the optimal solution is solved and the optimization parameters are updated to generate a comprehensive optimization plan that balances various objectives. Through the comprehensive optimization plan generation unit, the optimal solution is fed back to the dynamic optimization module to guide the optimization decisions in each stage of building design, construction, operation and maintenance, and achieve a comprehensive balance and optimization of energy consumption, comfort, environmental impact and cost. This multi-objective decision support mechanism significantly improves the scientific nature and optimization effect of green building design, and fully reflects the innovation and practical value of this system. BRIEF DESCRIPTION OF THE DRAWINGS
[0085] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0086] Figure 1 A schematic diagram of the functional modules of the optimization system according to an embodiment of the present invention;
[0087] Figure 2 Schematic diagram of a multi-objective decision support module according to an embodiment of the present invention. DETAILED DESCRIPTION
[0088] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.
[0089] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0090] like Figure 1-Figure 2 As shown, the AI-enhanced green building design optimization system includes:
[0091] The building life cycle data integration module integrates the full life cycle data of the building from design, construction, operation to maintenance. The full life cycle data includes the life cycle analysis data of building materials, energy consumption data, environmental impact data, and maintenance records;
[0092] Environmental simulation and prediction module, which conducts multi-scale and multi-physics environmental simulation based on integrated life cycle data. Environmental simulation includes climate change prediction, air quality simulation, noise propagation simulation, and water resource management simulation.
[0093] Dynamic optimization module, connected with environmental simulation and prediction module, performs dynamic optimization at different stages of building life cycle, including design optimization, construction process optimization, operation management optimization and maintenance strategy optimization;
[0094] The multi-objective decision support module is connected to the dynamic optimization module and is used to make optimization decisions in terms of energy consumption, comfort, environmental impact and cost based on the multi-objective decision theory, and generate a comprehensive optimization plan that balances various objectives;
[0095] Based on virtual reality interaction, it is connected with the multi-objective decision support module to display the implementation effect of the optimization plan through virtual reality technology. Users can intuitively evaluate and adjust the plan through immersive experience.
[0096] The building life cycle data integration module specifically includes:
[0097] Design data integration unit, used to collect and integrate design drawings, material lists, building codes and standards, and design simulation data during the building design phase;
[0098] Construction data collection unit, used to collect and integrate construction plans, actual construction progress, construction quality inspection records, construction site environmental data and material usage records during the construction phase;
[0099] Operational data monitoring unit, used to monitor and integrate energy consumption data (including electricity, water, and gas consumption), indoor and outdoor environmental data (temperature, humidity, and air quality), equipment operating status, and performance data during the building operation phase;
[0100] Maintenance data recording unit, used to record and integrate maintenance plans, maintenance operation records, equipment replacement records and maintenance cost data during the building maintenance phase;
[0101] The data storage and management unit is connected to each unit to store and manage the integrated full life cycle data to ensure the security, consistency and accessibility of the data;
[0102] The data processing and analysis unit is connected to the data storage and management unit, and is used to process and analyze the full life cycle data, generate life cycle analysis data of building materials, energy consumption analysis reports, environmental impact assessments and maintenance demand forecasts.
[0103] The life cycle analysis data specifically includes:
[0104] Calculate the environmental impact and resource consumption of materials at each stage of production, transportation, use and recycling. The total life cycle impact formula is: Among them, LCA is the total life cycle impact, EI i is the unit environmental impact of the i-th stage, Q i is the material quantity or usage in the i-th stage, and n is the number of stages;
[0105] The energy consumption analysis report specifically includes:
[0106] The energy consumption data is smoothed using the moving average method, and the formula is: in, is the moving average at time t, E t-i is the energy consumption data at the ti-th moment, and n is the time window size;
[0107] Pattern recognition: Using regression analysis to build an energy consumption prediction model: E t =β 0 +β 1 ×t+ t , where E t is the energy consumption at time t, β 0 and β 1 are the regression coefficients, t is the error term;
[0108] Environmental impact assessment and maintenance needs forecasting specifically include:
[0109] Using the weighted comprehensive evaluation method, the formula is:
[0110] Among them, EI is the total environmental impact score, W i is the weight of the i-th environmental factor, I i is the impact score of the i-th environmental factor, and m is the number of environmental factors;
[0111] Maintenance demand forecasting specifically includes:
[0112] Use exponential smoothing to predict future maintenance needs, the formula is:
[0113] in, is the forecast demand at time t+1, D tis the actual demand at time t, is the forecast demand at time t, and α is the smoothing coefficient.
[0114] The environmental simulation and prediction module specifically includes:
[0115] The climate change prediction unit is used to predict climate change using the regional climate model RCM based on the integrated life cycle data and historical climate data, expressed as:
[0116] T future =T current +ΔT, where T future is the future temperature, T current is the current temperature, ΔT is the temperature change predicted by the climate model;
[0117] Use the combined method of global climate model GCM and regional climate model RCM to predict climate change under different scenarios: future =P current ×(1+R), where P future is the future precipitation, P current is the current precipitation, R is the precipitation change rate;
[0118] The air quality simulation unit is used to simulate the air quality around the building based on life cycle data, emission source data and meteorological data, and simulate the diffusion of pollutants based on the Gaussian diffusion model. The formula is:
[0119] Where C(x,y,z) is the pollutant concentration at point (x,y,z), Q is the emission source intensity, σ x ,σ y ,σ z are diffusion coefficients respectively, combined with CFD (computational fluid dynamics) to simulate air flow and pollutant diffusion, the formula is: Among them, u is the velocity vector, D is the diffusion coefficient, and S is the source term;
[0120] The noise propagation simulation unit is used to simulate the propagation of noise inside and outside the building based on the building layout, material properties and environmental data. The noise propagation is simulated using the sound wave propagation model. The formula is:
[0121] L p =L w -20log 10 (r)-αr, where L p is the sound pressure level at the receiving point, L w is the sound power level of the sound source, r is the distance from the sound source to the receiving point, α is the air absorption coefficient, and considering reflection and absorption in combination with the building acoustic model, the formula is:
[0122] L p =L w -20log 10 (r)-αr-R, where R is the sound absorption coefficient of the building material;
[0123] The water resource management simulation unit is used to simulate the water resource management and water cycle system of the building area based on water use data, precipitation data and geographic information, and simulate precipitation and runoff based on the hydrological model. The formula is:
[0124] R = P-ET-I, where R is runoff, P is precipitation, ET is evapotranspiration, and I is infiltration. The stormwater management model SWMM is used to simulate the urban water cycle system. The simulation is expressed as:
[0125] Where Q is the water flow rate, n is the roughness coefficient, A is the cross-sectional area, R h is the hydraulic radius and S is the water flow slope.
[0126] The dynamic optimization module specifically includes:
[0127] The design optimization unit is used to optimize the building layout and material selection during the building design stage. The building layout is optimized by combining genetic algorithms with climate change prediction data to maximize natural ventilation and lighting, which is expressed as:
[0128] Among them, F layout is the layout optimization objective function, A i is the area of the ith space, E i is the lighting effect of the i-th space, W i is the ventilation effect of the i-th space, n is the number of spaces; the optimization of material selection is based on life cycle analysis combined with air quality simulation and environmental impact data to select building materials with low environmental impact, and the optimization is expressed as:
[0129] Among them, EI total is the total environmental impact, EI j is the unit environmental impact of the jth material, Q j is the usage of the jth material, and m is the number of material types;
[0130] The construction process optimization unit is used to optimize the construction plan and material usage during the construction phase to reduce environmental impact and improve construction efficiency. The construction plan is optimized using the critical path method combined with noise propagation simulation and air quality data to optimize the construction progress and reduce construction period and environmental impact. It is expressed as: Among them, T total is the total construction period, D kis the duration of the kth construction task, and p is the number of construction tasks; Optimizing material use Linear programming is used to optimize material use and reduce waste and cost, which is expressed as: Among them, C materials is the total material cost, c l is the unit cost of the lth material, x l is the usage of the lth material, q is the number of material types;
[0131] The operation management optimization unit is used to optimize energy management and equipment operation during the building operation phase based on the environmental monitoring data provided by the environmental simulation and prediction module to improve energy efficiency and comfort. It optimizes energy management based on the predictive control method to improve energy efficiency, which is expressed as:
[0132] Among them, E total is the total energy consumption, P t is the power demand at the tth moment, Δt is the time interval, and T is the total time; the equipment operation is optimized based on the equipment performance data and environmental monitoring data, and the equipment operation parameters are optimized. The formula is: Among them, E efficiency is the equipment efficiency, O output is the device output power, I input Input power to the device;
[0133] The maintenance strategy optimization unit is used to optimize the maintenance plan and strategy during the building maintenance phase based on the long-term environmental data and equipment status data provided by the environmental simulation and prediction module to extend the equipment life and reduce maintenance costs. The maintenance plan is optimized based on the predictive maintenance algorithm to optimize the maintenance plan and reduce failures and maintenance costs, which is expressed as: Among them, C maintenance is the total maintenance cost, c t is the unit maintenance cost at time t, M t is the maintenance amount at the tth moment; the optimized maintenance strategy adopts the reliability center maintenance method to optimize the maintenance strategy and improve the equipment reliability, which is expressed as:
[0134] Among them, R total is the total reliability, R n is the reliability of the nth device, and N is the number of devices.
[0135] The objective function of the multi-objective decision support module is used to generate a comprehensive optimization solution, while the previous dynamic optimization parts (design optimization, construction process optimization, operation management optimization and maintenance strategy optimization) perform specific optimization work in their respective stages. The comprehensive optimization solution of the multi-objective decision support module can guide and adjust these specific optimization processes so that the optimization results in each stage can better balance multiple goals such as energy consumption, comfort, environmental impact and cost. Therefore, the multi-objective decision support module specifically includes:
[0136] An objective function definition unit is used to define objective functions of energy consumption, comfort, environmental impact and cost;
[0137] A weight setting unit, used to set the weight of each objective function according to user needs and priorities;
[0138] A multi-objective optimization algorithm unit, used to solve the optimal solution of each objective function based on a multi-objective optimization algorithm;
[0139] The comprehensive optimization scheme generation unit is used to synthesize the optimal solutions of various objective functions and generate a comprehensive optimization scheme that balances various objectives.
[0140] The objective function definition unit specifically includes:
[0141] Energy consumption objective function: With the goal of minimizing building energy consumption, define the energy consumption objective function E, the formula is: Among them, P t is the power demand at time t, Δt is the time interval, and T is the total time;
[0142] Comfort objective function: To maximize the comfort level in the building, define the comfort objective function C, the formula is: Among them, S i is the comfort score of the i-th space, A i is the area of the i-th space, n is the number of spaces;
[0143] Environmental impact objective function: With the goal of minimizing environmental impact, define the environmental impact objective function I, the formula is: Among them, EI j is the unit environmental impact of the jth material, Q j is the usage of the jth material, and m is the number of material types;
[0144] Cost objective function: With the goal of minimizing construction cost, the cost objective function K is defined, and the formula is: Among them, C k is the unit cost of the kth item, x k is the usage of the kth item, and p is the number of items.
[0145] The weight setting unit sets the weight w of each objective function according to user needs and priorities. i , the formula is: W = {w E ,w C ,w I ,w K}, where w E is the weight of the energy consumption target, w C is the weight of the comfort target, w I is the weight of the environmental impact target, w K is the weight of the cost target, and ∑w i =1.
[0146] The multi-objective optimization algorithm unit uses the weighted sum method to perform multi-objective optimization and solve the comprehensive optimization objective function F. The formula is:
[0147] F=w E ·E+w C ·C+w I I+w K K, where F is the comprehensive optimization objective function and weight w i The objective functions E, C, I, and K are respectively energy consumption, comfort, environmental impact, and cost objective functions, which are set by the weight setting unit. The particle swarm optimization is used to find the optimal solution and update the optimization parameters.
[0148] According to the optimal solution obtained by particle swarm optimization, a comprehensive optimization plan that balances various objectives is generated. The formula is: Optimal Solution = arg minF, where Optimal Solution is the comprehensive optimization plan and F is the comprehensive optimization objective function.
[0149] Particle swarm optimization specifically includes:
[0150] Initialize the particle swarm, set the position and velocity of the particles, each particle represents a candidate solution, and its position and velocity vectors are x i and v i :
[0151] Among them, i represents the i-th particle, and n is the dimension of the problem;
[0152] Evaluate fitness: Calculate the fitness value of each particle. For multi-objective optimization problems, the fitness function is the weighted sum of multiple objective functions:
[0153] f(x i )=w E ·E(x i )+w C ·C(x i )+w I ·I(xi )+w K ·K(x i ), where E(x i ) is the energy consumption objective function, C(x i ) is the comfort objective function, I(x i ) is the environmental impact objective function, K(x i ) is the cost objective function, w E ,w C ,w I ,w K are the weights of each objective function respectively;
[0154] Update individual optimal and global optimal: For each particle, update the individual optimal position p i and the global optimal position g;
[0155]
[0156] g(t+1)=X i (t)if f(X i (t)) <f(g(t));
[0157] Update particle velocity and position:
[0158] v i (t+1)=ωv i (t)+c 1 r 1 (p i (t)-x i (t))+c 2 r 2 (g(t)-x i (t));
[0159] x i (t+1)=x i (t)+v i (t+1);
[0160] Among them, ω is the inertia weight, c 1 and c 2 They are individual learning factor and social learning factor, r 1 and r 2 is a random number between 0 and 1;
[0161] Repeatedly evaluate fitness, update individual optimal and global optimal, and update particle speed and position until the termination condition is met (reaching the maximum number of iterations or fitness value convergence).
[0162] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.
Claims
1. AI enhanced green building design optimization system, characterized by: include: The building life cycle data integration module integrates the full life cycle data of the building from design, construction, operation to maintenance. The full life cycle data includes life cycle analysis data of building materials, energy consumption data, environmental impact data, and maintenance records; Environmental simulation and prediction module, which performs multi-scale, multi-physics field environmental simulation based on integrated life cycle data, including climate change prediction, air quality simulation, noise propagation simulation, and water resource management simulation; A dynamic optimization module, connected to the environmental simulation and prediction module, performs dynamic optimization at different stages of the building life cycle, including design optimization, construction process optimization, operation management optimization and maintenance strategy optimization; The multi-objective decision support module is connected to the dynamic optimization module and is used to make optimization decisions in the dimensions of energy consumption, comfort, environmental impact and cost based on the multi-objective decision theory, and to generate a comprehensive optimization plan that balances various objectives.
2. The AI enhanced green building design optimization system according to claim 1, characterized in that: The building life cycle data integration module specifically includes: Design data integration unit, used to collect and integrate design drawings, material lists, building codes and standards, and design simulation data during the building design phase; Construction data collection unit, used to collect and integrate construction plans, actual construction progress, construction quality inspection records, construction site environmental data and material usage records during the construction phase; Operational data monitoring unit, used to monitor and integrate energy consumption data, indoor and outdoor environmental data, equipment operating status and performance data during the building operation phase; Maintenance data recording unit, used to record and integrate maintenance plans, maintenance operation records, equipment replacement records and maintenance cost data during the building maintenance phase; The data storage and management unit is connected to each unit to store and manage the integrated full life cycle data to ensure the security, consistency and accessibility of the data; The data processing and analysis unit is connected to the data storage and management unit, and is used to process and analyze the full life cycle data, generate life cycle analysis data of building materials, energy consumption analysis reports, environmental impact assessments and maintenance demand forecasts.
3. The AI enhanced green building design optimization system according to claim 2, characterized in that: The life cycle analysis data specifically includes: Calculate the environmental impact and resource consumption of materials at each stage of production, transportation, use and recycling. The total life cycle impact formula is: Among them, LCA is the total life cycle impact, EI i is the unit environmental impact of the i-th stage, Q i is the material quantity or usage in the i-th stage, and n is the number of stages; The energy consumption analysis report specifically includes: The energy consumption data is smoothed using the moving average method, the formula is: Among them, MA t is the moving average at time t, E t-i is the energy consumption data at the ti-th moment, and n is the time window size; Pattern recognition: Using regression analysis to build an energy consumption prediction model: E t =β0+β1×t+ t , where E t is the energy consumption at the tth moment, β0 and β1 are regression coefficients, t is the error term; The environmental impact assessment and maintenance demand forecast specifically include: Using the weighted comprehensive evaluation method, the formula is: Among them, EI is the total environmental impact score, W i is the weight of the i-th environmental factor, I i is the impact score of the i-th environmental factor, and m is the number of environmental factors; The maintenance demand prediction specifically includes: Use exponential smoothing to predict future maintenance needs, the formula is: in, is the forecast demand at time t+1, D t is the actual demand at time t, is the forecast demand at time t, and α is the smoothing coefficient.
4. The AI enhanced green building design optimization system according to claim 1, characterized in that: The environmental simulation and prediction module specifically includes: The climate change prediction unit is used to predict climate change using the regional climate model RCM based on the integrated life cycle data and historical climate data, expressed as: T future =T current +ΔT, where T future is the future temperature, T current is the current temperature, ΔT is the temperature change predicted by the climate model; Use the combined method of global climate model GCM and regional climate model RCM to predict climate change under different scenarios: future =P current ×(1+R), where P future is the future precipitation, P current is the current precipitation, R is the precipitation change rate; The air quality simulation unit is used to simulate the air quality around the building based on life cycle data, emission source data and meteorological data, and simulate the diffusion of pollutants based on the Gaussian diffusion model. The formula is: in, for The pollutant concentration at the point, Q is the emission source intensity, σ x ,σ y ,σ z are diffusion coefficients respectively. Combined with CFD simulation of air flow and pollutant diffusion, the formula is: Among them, u is the velocity vector, D is the diffusion coefficient, and S is the source term; The noise propagation simulation unit is used to simulate the propagation of noise inside and outside the building based on the building layout, material properties and environmental data. The noise propagation is simulated using the sound wave propagation model. The formula is: L p =L w -20log 10 (r)-αr, where L p is the sound pressure level at the receiving point, L w is the sound power level of the sound source, r is the distance from the sound source to the receiving point, α is the air absorption coefficient, and considering reflection and absorption in combination with the building acoustic model, the formula is: L p =L w -20log 10 (r)-αr-R, where R is the sound absorption coefficient of the building material; The water resource management simulation unit is used to simulate the water resource management and water cycle system of the building area based on water use data, precipitation data and geographic information, and simulate precipitation and runoff based on the hydrological model. The formula is: R = P-ET-I, where R is runoff, P is precipitation, ET is evapotranspiration, and I is infiltration. The stormwater management model SWMM is used to simulate the urban water cycle system. The simulation is expressed as: Where Q is the water flow rate, n is the roughness coefficient, A is the cross-sectional area, R h is the hydraulic radius and S is the water flow slope.
5. The AI enhanced green building design optimization system according to claim 4, characterized in that: The dynamic optimization module specifically includes: The design optimization unit is used to optimize the building layout and material selection during the building design stage. The optimized building layout uses a genetic algorithm combined with climate change prediction data to maximize natural ventilation and daylighting, which is expressed as: Among them, F layout is the layout optimization objective function, A i is the area of the i-th space, E i is the lighting effect of the i-th space, W i is the ventilation effect of the i-th space, n is the number of spaces; the optimization material selection is based on life cycle analysis combined with air quality simulation and environmental impact data, and low environmental impact building materials are selected. The optimization is expressed as: Among them, EI total is the total environmental impact, EI j is the unit environmental impact of the jth material, Q j is the usage of the jth material, and m is the number of material types; The construction process optimization unit is used to optimize the construction plan and material usage during the construction phase to reduce environmental impact and improve construction efficiency. The optimized construction plan uses the critical path method combined with noise propagation simulation and air quality data to optimize the construction progress, reduce construction period and environmental impact, expressed as: min Among them, T total is the total construction period, D k is the duration of the kth construction task, and p is the number of construction tasks; the optimized material use utilizes linear programming to optimize material use and reduce waste and cost, which is expressed as: Among them, C materials is the total material cost, c l is the unit cost of the lth material, x l is the usage of the lth material, q is the number of material types; The operation management optimization unit is used to optimize energy management and equipment operation to improve energy efficiency and comfort during the building operation phase based on the environmental monitoring data provided by the environmental simulation and prediction module. The optimized energy management is based on the predictive control method to improve energy efficiency, which is expressed as: Among them, E total is the total energy consumption, P t is the power demand at the tth moment, Δt is the time interval, and T is the total time; the optimization equipment operation is based on the equipment performance data and environmental monitoring data to optimize the equipment operation parameters, and the formula is: Among them, E efficiency is the equipment efficiency, O output is the device output power, I input Input power to the device; The maintenance strategy optimization unit is used to optimize the maintenance plan and strategy during the building maintenance phase based on the long-term environmental data and equipment status data provided by the environmental simulation and prediction module to extend the equipment life and reduce maintenance costs. The optimized maintenance plan is based on a predictive maintenance algorithm to optimize the maintenance plan and reduce failures and maintenance costs, which is expressed as: Among them, C maintenance is the total maintenance cost, c t is the unit maintenance cost at time t, M t is the maintenance amount at the tth moment; the optimized maintenance strategy adopts the reliability center maintenance method to optimize the maintenance strategy and improve the equipment reliability, which is expressed as: Among them, R total is the total reliability, R n is the reliability of the nth device, and N is the number of devices.
6. The AI enhanced green building design optimization system according to claim 5, characterized in that: The multi-objective decision support module specifically includes: An objective function definition unit is used to define objective functions of energy consumption, comfort, environmental impact and cost; A weight setting unit, used to set the weight of each objective function according to user needs and priorities; A multi-objective optimization algorithm unit, used to solve the optimal solution of each objective function based on a multi-objective optimization algorithm; The comprehensive optimization scheme generation unit is used to synthesize the optimal solutions of various objective functions and generate a comprehensive optimization scheme that balances various objectives.
7. The AI enhanced green building design optimization system according to claim 6, characterized in that: The objective function definition unit specifically includes: Energy consumption objective function: With the goal of minimizing building energy consumption, define the energy consumption objective function E, the formula is: Among them, P t is the power demand at time t, Δt is the time interval, and T is the total time; Comfort objective function: To maximize the comfort level in the building, define the comfort objective function C, the formula is: Among them, S i is the comfort score of the i-th space, A i is the area of the i-th space, n is the number of spaces; Environmental impact objective function: With the goal of minimizing environmental impact, define the environmental impact objective function I, the formula is: Among them, EI j is the unit environmental impact of the jth material, Q j is the usage of the jth material, and m is the number of material types; Cost objective function: With the goal of minimizing construction cost, the cost objective function K is defined, and the formula is: Among them, C k is the unit cost of the kth item, x k is the usage of the kth item, and p is the number of items.
8. The AI enhanced green building design optimization system according to claim 7, characterized in that: The weight setting unit sets the weight w of each objective function according to user needs and priorities. i , the formula is: W = {w E ,w C ,w I ,w K }, where w E is the weight of the energy consumption target, w C is the weight of the comfort target, w I is the weight of the environmental impact target, w K is the weight of the cost target, and ∑w i =1.
9. The AI enhanced green building design optimization system according to claim 8, characterized in that: The multi-objective optimization algorithm unit uses the weighted sum method to perform multi-objective optimization and solve the comprehensive optimization objective function F, the formula is: F=w E ·E+w C ·C+w I I+w K K, where F is the comprehensive optimization objective function and weight w i The objective functions E, C, I, and K are respectively energy consumption, comfort, environmental impact, and cost objective functions, which are set by the weight setting unit. The particle swarm optimization is used to find the optimal solution and update the optimization parameters. According to the optimal solution obtained by particle swarm optimization, a comprehensive optimization plan that balances various objectives is generated. The formula is: OptimalSolution = arg minF, where OptimalSolution is the comprehensive optimization plan and F is the comprehensive optimization objective function.
10. The AI enhanced green building design optimization system according to claim 9, characterized in that: The particle swarm optimization specifically includes: Initialize the particle swarm, set the position and velocity of the particles, each particle represents a candidate solution, and its position and velocity vectors are x i and v i : Among them, i represents the i-th particle, and n is the dimension of the problem; Evaluate fitness: Calculate the fitness value of each particle. For multi-objective optimization problems, the fitness function is the weighted sum of multiple objective functions: f(x i )=w E ·E(x i )+w C ·C(x i )+w I ·I(x i )+w K ·K(x i ), where E(x i ) is the energy consumption objective function, C(x i ) is the comfort objective function, I(x i ) is the environmental impact objective function, K(x i ) is the cost objective function, w E ,w C ,w I ,w K are the weights of each objective function respectively; Update individual optimal and global optimal: For each particle, update the individual optimal position p i and the global optimal position g; g(t+1)=X i (t)if f(X i (t))<f(g(t)); Update particle velocity and position: v i (t+1)=ωv i (t)+c1r1(p i (t)-x i (t))+c2r2(g(t)-x i (t)); x i (t+1)=x i (t)+v i (t+1); Among them, ω is the inertia weight, c1 and c2 are individual learning factors and social learning factors, r1 and r2 are random numbers between 0 and 1; Repeatedly evaluate fitness, update individual optimal and global optimal, and update particle speed and position until the termination condition is met.
Citation Information
Patent Citations
Building sustainable environmental protection management control method and system
CN117852126A
Building design method based on artificial intelligence
CN118171369A
Cited By
Building engineering design method based on BIM
CN119783221A
Bridge deck slab intelligent green construction system and method based on UHPC material
CN119962885A
An intelligent green construction system and method for bridge decks based on UHPC materials
CN119962885B
Green product full life cycle analysis system based on big data
CN120688749A
Green product life cycle analysis system based on big data
CN120688749B
