Green intelligent building multi-factor fusion planning design method

Abstract

The invention relates to the technical field of green intelligent building planning and design, and discloses a green intelligent building multi-factor fusion planning and design method. The method comprises the steps of firstly obtaining geographic information data and ecological environment parameters of a building site, collecting peripheral multi-dimensional environment data and performing fusion processing, constructing a three-dimensional space topology model, and generating an initial space planning model; and then climate simulation and resource circulation conditions are loaded, a comprehensive planning analysis model is formed, and dynamic collaborative evaluation indexes are output. A multi-factor coordination model and key coordination parameters are obtained by constructing a multi-objective optimization pre-training framework for iterative learning, and then a system collaborative simulation result is generated. And establishing a configuration model to optimize facility deployment parameters to obtain an optimal configuration scheme. And finally, dynamically adjusting parameters according to the efficiency evaluation framework to realize planning control of the green intelligent building. According to the method, multiple factors are integrated, optimization of building planning and design is achieved, and the sustainability and the intelligent level of the building are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of green intelligent building planning and design, and specifically to a multi-factor integration planning and design method for green intelligent buildings. Background Art

[0002] With the increasing global attention to sustainable development and building intelligence, green intelligent buildings have become an important development direction in the construction industry. Traditional building planning and design methods have many limitations and are no longer able to meet the diverse needs of modern society for buildings.

[0003] In terms of the utilization of geographical information, traditional designs often simply refer to the site location, without deeply exploring the potential value of geographical information data. For example, for sites with complex terrains and landforms, the impact of terrain undulations on building layout, daylighting, and ventilation is not fully considered, resulting in unreasonable use of building space and increased energy consumption. In some mountainous buildings, due to the lack of scientific design in combination with the terrain in the early planning, not only the construction cost is increased, but also the use experience and energy efficiency of the building are affected.

[0004] In terms of the ecological environment, previous designs rarely comprehensively consider ecological environment parameters. There is a lack of effective integration between buildings and the surrounding ecological systems, and insufficient attention is paid to the habitats of animals and plants and water resource protection. For example, in urban development, some building projects directly destroy the original wetland ecological system for construction, resulting in damaged ecological balance and reduced biodiversity. At the same time, the ecological regulation functions of wetlands for the city, such as flood control and air purification, are also weakened.

[0005] Climatic factors have also not been fully emphasized in traditional designs. Building designs fail to accurately adapt to the climatic characteristics of different regions, resulting in high building energy consumption. Taking the northern region as an example, some buildings need to consume a large amount of energy for heating in winter, but due to the unreasonable design of the building's insulation performance, heat loss is serious. In the hot southern regions, some buildings do not have good sunshade and natural ventilation designs, resulting in huge air-conditioning cooling energy consumption in summer.

[0006] Resource recycling is even more a shortcoming of traditional building designs. The recycling rates of building materials and energy are low, and a large amount of recyclable resources are wasted. For example, most of the construction waste generated during building demolition is directly landfilled, which not only occupies a large amount of land resources but also causes environmental pollution. At the same time, during the operation of buildings, the energy recovery and reuse mechanisms are imperfect, and renewable energy sources such as solar energy and wind energy cannot be effectively collected and utilized.

[0007] In addition, in the traditional building planning and design process, various factors are independent of each other, lacking systematic integration analysis and collaborative optimization. Poor communication and collaboration among different professional design teams result in defects in the overall performance of building design schemes. For example, when the structural design team designs the building structure without sufficient communication with the equipment design team, it may lead to insufficient equipment installation space or unreasonable layout, affecting the overall function and usage effect of the building.

[0008] With the continuous improvement of people's requirements for building quality, environmental friendliness, and intelligence, it is urgent to develop a green intelligent building planning and design method that can integrate multiple factors such as geographical information, ecological environment, climate, and resource circulation. This method needs to achieve the collaborative optimization of multiple factors to improve the sustainability, functionality, and intelligence level of buildings, meet the needs of modern society for green intelligent buildings, and promote the development of the building industry towards a more environmentally friendly, efficient, and intelligent direction. Summary of the Invention

[0009] The purpose of the present invention is to provide a multi-factor integration planning and design method for green intelligent buildings to solve the problems raised in the above background technology.

[0010] To achieve the above purpose, the present invention provides the following technical solution: A multi-factor integration planning and design method for green intelligent buildings, the method includes: Obtain the geographical information data and ecological environment parameters of the building site; Collect multi-dimensional environmental data around the site and perform fusion processing, establish a three-dimensional spatial topology model, conduct multi-factor coupling analysis on the three-dimensional spatial topology model and combine with the geographical information data to generate an initial spatial planning model; Load climate simulation conditions and resource circulation conditions on the initial spatial planning model to form a comprehensive planning analysis model, combine with the ecological environment parameters, and output dynamic collaborative evaluation indicators; Construct a multi-objective optimization pre-training framework and perform iterative learning through the dynamic collaborative evaluation indicators to obtain a multi-factor coordination model, and then extract key coordination parameters; Generate a system collaborative simulation result through the key coordination parameters, the comprehensive planning analysis model, and the geographical information data; Based on the system collaborative simulation result and the facility deployment parameters, establish a configuration model and optimize the facility deployment parameters to obtain the optimal configuration plan for facility deployment; Deduce the current stage configuration plan according to the effectiveness evaluation framework to obtain the current stage effectiveness evaluation indicators, and combine the current stage effectiveness evaluation indicators, the current stage optimal configuration plan, and the current stage actual configuration parameters to dynamically adjust the facility deployment parameters to achieve the planning control of green intelligent buildings.

[0011] Preferably, the dynamic collaborative evaluation indicators at least include the resource recycling efficiency, energy distribution gradient, and spatial optimization potential set; the key coordination parameters at least include the energy coordination nodes, environmental adaptation forms, and resource recycling path parameters; the system collaborative simulation results at least include the energy transfer trajectory, maximum load distribution, and environmental response gradient.

[0012] Preferably, the method for collecting multi-dimensional environmental data around the acquisition site, performing fusion processing, establishing a three-dimensional spatial topology model, and performing multi-factor coupling analysis on the three-dimensional spatial topology model and combining with geographic information data to generate an initial spatial planning model includes the following steps: Performing multi-scale environmental monitoring on the construction site to obtain a multi-dimensional environmental data sequence; Performing fusion processing on the multi-dimensional environmental data sequence to obtain a standardized environmental data set, where the fusion processing includes one or more of data cleaning, normalization, feature association, redundancy elimination, data reconstruction, and consistency verification; Based on the standardized environmental data set, constructing a three-dimensional spatial topology model using spatial interpolation technology; Performing multi-factor coupling analysis on the three-dimensional spatial topology model to generate an initial spatial planning model, where the multi-factor coupling analysis at least includes grid meshing and parameter mapping, dividing different functional blocks through grid meshing, and assigning corresponding geographic information parameters to each functional block.

[0013] Preferably, the method for loading climate simulation conditions and resource recycling conditions into the initial spatial planning model to form a comprehensive planning analysis model, combining ecological environment parameters, and outputting dynamic collaborative evaluation indicators includes the following steps: Loading climate simulation conditions into the initial spatial planning model to constrain the environmental boundary to obtain a first planning analysis model; Overlaying resource recycling conditions on the first planning analysis model to form a comprehensive planning analysis model, where the resource recycling conditions include energy recovery conditions and material recycling conditions; Based on the comprehensive planning analysis model and ecological environment parameters, calculating the dynamic collaborative evaluation indicators, and the specific process includes: Constructing a multi-factor collaborative equation, the equation at least includes an energy balance equation, an environmental response equation, and a resource allocation equation, combining with the comprehensive planning analysis model, and solving the collaborative equation by numerical discretization method to obtain the resource recycling efficiency, energy distribution gradient, and spatial optimization potential set.

[0014] Preferably, the method for obtaining the spatial optimization potential set includes the following steps: Calculating the energy load difference of each functional block based on the energy distribution gradient; Identify the functional blocks in the comprehensive planning analysis model where the energy load difference is not less than the load threshold, and obtain the set of spatial optimization potentials.

[0015] Preferably, the steps of constructing a multi-objective optimization pre-training framework, performing iterative learning through dynamic collaborative evaluation metrics to obtain a multi-factor coordination model, and then extracting key coordination parameters include the following: Construct a multi-objective optimization pre-training framework based on a feature fusion network; Perform multi-stage training and verification on the pre-training framework through dynamic collaborative evaluation metrics to obtain a multi-factor coordination model; Input the dynamic collaborative evaluation metrics to be analyzed into the multi-factor coordination model, and output the predicted set of spatial optimization potentials; Based on the predicted set of spatial optimization potentials, extract key coordination parameters, where the key coordination parameters at least include energy coordination nodes, environmental adaptation forms, and resource recycling path parameters.

[0016] Preferably, the steps of extracting key coordination parameters based on the predicted set of spatial optimization potentials include the following: Determine the geometric center point of the predicted set of spatial optimization potentials as the energy coordination node; Fit the environmental adaptation form according to the distribution characteristics of the predicted set of spatial optimization potentials to obtain environmental adaptation form parameters, where the environmental adaptation form parameters include form curvature and spatial extension dimension; Analyze the energy load gradient direction of the predicted set of spatial optimization potentials, calculate the weighted average of the gradient direction, and convert it into a standard resource recycling path, which is the resource recycling path parameter.

[0017] Preferably, the steps of generating a system collaborative simulation result through key coordination parameters, a comprehensive planning analysis model, and geographical information data include the following: Use the energy coordination node as the reference anchor point, map the environmental adaptation form parameters into the comprehensive planning analysis model, adjust the resource recycling path parameters, and refine the grid of associated blocks to complete the update of the comprehensive planning analysis model. Define the co-evolution rules, co-evolution directions, and co-evolution step lengths to form a co-evolution planning model; Based on the co-evolution planning model, use a dynamic iterative method to solve the multi-factor collaborative equation, and generate a system collaborative simulation result according to the results of each iterative stage during the solution process, specifically including: When the co-evolution rules are satisfied, perform path optimization to obtain the current energy transfer trajectory, co-evolution step length, co-evolution direction, energy load distribution, and environmental response gradient, and update the co-evolution planning model; Resolve the multi-factor collaboration equation again based on the updated co-evolution planning model until the termination condition is reached, and end the co-evolution process; Calculate the maximum load distribution and environmental response gradient according to the energy load distribution and environmental response gradient at each iteration stage; The co-evolution rule is defined as triggering path optimization if the cumulative amount of the current energy difference is not less than the difference threshold; The co-evolution direction is determined based on the historical evolution trend and the current energy distribution direction; The energy transfer trajectory and the co-evolution step size are determined according to the climate parameters and the resource recycling efficiency respectively.

[0018] Preferably, based on the system co-simulation results and the facility deployment parameters, a configuration model is established and the facility deployment parameters are optimized to obtain the optimal configuration plan for facility deployment, including the following steps: Establish a configuration model, where the configuration model at least includes a variable definition module, an objective function module and a constraint condition module. Define the variable module based on the facility deployment parameters. The facility deployment parameters at least include equipment layout density, energy conversion efficiency, monitoring coverage range and data transmission delay. Construct the objective function module based on the second effectiveness evaluation value and the resource consumption value. The second effectiveness evaluation value is calculated according to the system co-simulation results. The resource consumption value at least includes construction cost value, operation and maintenance cost value and energy loss value. The constraint condition module includes a facility deployment constraint module and an effectiveness guarantee constraint module. Define the effectiveness guarantee constraint module based on functional integrity, response timeliness and system stability; Use the genetic algorithm to perform an initial solution to the configuration model to obtain an initial optimized configuration plan; Perform global optimization on the configuration model through the particle swarm algorithm, and obtain the optimal solution set of the particle swarm as the optimal configuration plan for facility deployment.

[0019] Preferably, the present invention further includes a computer device, which includes a memory, a processor and a communication interface, and they are connected through a bus; the memory is used to store a set of computer program instructions and data, and transmit the stored data to the processor. The processor executes the program instructions stored in the memory to execute the green intelligent building multi-factor integration planning and design method as described in any one of the above.

[0020] Compared with the prior art, the beneficial effects of the present invention are: In terms of the scientificity and rationality of planning and design, by obtaining the geographical information data and ecological environment parameters of the building site, collecting multi-dimensional environmental data around the site and integrating and processing it, establishing a three-dimensional spatial topology model and conducting multi-factor coupling analysis, the generated initial spatial planning model fully considers the actual situation of the site. For example, in a complex terrain site, according to geographical information such as the undulation and slope of the terrain, the layout and height of the building can be reasonably planned to perfectly integrate the building with the terrain. This not only reduces the amount of earthwork and construction costs, but also utilizes the terrain advantages to achieve natural ventilation and lighting, improving the energy efficiency of the building. Combining ecological environment parameters such as vegetation distribution and soil type, the original ecological resources can be protected and utilized during planning, avoiding damage to the ecological system and achieving the harmonious coexistence of the building and the ecological environment.

[0021] In terms of resource utilization and energy management, by loading climate simulation conditions and resource recycling conditions to form a comprehensive planning analysis model, the key information such as resource recycling efficiency and energy distribution gradient is included in the output dynamic collaborative evaluation indicators. This enables the building to accurately plan the utilization of energy and resources at the design stage. For example, by analyzing the energy distribution gradient, the energy demand differences in different areas of the building can be determined, and the energy supply facilities can be reasonably configured to reduce the losses during the energy transmission process. At the same time, the energy recovery conditions and material recycling conditions in the resource recycling conditions promote the collection and utilization of renewable energy and the recycling of building materials during the use of the building. For example, installing solar panels on the building roof to collect solar energy for power supply, collecting and treating rainwater for non-drinking uses in the building, effectively reducing the building's dependence on external energy and resources, improving the resource recycling efficiency, and reducing energy consumption and operating costs.

[0022] Construct a multi-objective optimization pre-training framework and iteratively learn to obtain a multi-factor coordination model. The extracted key coordination parameters further optimize the building design. Key coordination parameters such as energy coordination nodes, environment adaptation forms, and resource recycling path parameters provide important basis for the spatial layout and functional design of the building. Taking the environment adaptation form parameters as an example, according to the climate characteristics of the site and the surrounding environment, by fitting the environment adaptation form, a building shape that is more conducive to natural ventilation and shading can be designed, reducing the usage time of air conditioning and lighting systems, thereby reducing energy consumption. The resource recycling path parameters optimize the flow process of resources within the building system, improving the resource utilization efficiency.

[0023] In terms of facility deployment, a configuration model is established based on the results of system co-simulation, and the facility deployment parameters are optimized to obtain the optimal configuration plan, making the layout of building equipment more reasonable. For example, optimizing according to parameters such as equipment layout density, energy conversion efficiency, monitoring coverage, and data transmission delay can improve the operation efficiency of the building intelligent system. A reasonable equipment layout can reduce interference between equipment, improve energy conversion efficiency, and reduce energy loss. At the same time, optimizing the monitoring coverage can ensure that all areas of the building are effectively monitored, promptly discover and handle problems, and guarantee the safe and stable operation of the building. Reducing data transmission delay improves the response speed of the building intelligent system and enhances the user experience.

[0024] By deducing the configuration plan based on the effectiveness evaluation framework and dynamically adjusting the facility deployment parameters, the dynamic optimization of the green intelligent building planning and control is realized. During the entire life cycle of the building, as the external environment and internal needs change, the facility deployment parameters can be adjusted in a timely manner to ensure that the building is always in the best operating state. For example, in different seasons, adjusting the operating parameters of the building's ventilation and air conditioning systems according to climate changes can not only meet the requirements of indoor comfort but also achieve efficient energy utilization. This dynamic optimization mechanism improves the adaptability and sustainability of the building and extends its service life. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is the working principle diagram of the multi-factor fusion planning and design method for the green intelligent building described in the present invention; Figure 2 It is the flowchart for generating the initial space planning model; Figure 3 It is the flowchart for forming the comprehensive planning analysis model and outputting indicators; Figure 4 It is the flowchart for constructing the framework to obtain the key coordination parameters; Figure 5 It is the flowchart for extracting the key coordination parameters based on the potential set. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] Please refer to Figures 1-5 , the present invention provides a multi-factor fusion planning and design method for a green intelligent building, and the specific implementation steps are as follows: Obtain the geographical information data and ecological environment parameters of the construction site. The geographical information data covers the geographical location, topography, geological conditions, etc. of the site, which can be obtained through geographical information systems (GIS), satellite remote sensing, on-site surveys, etc. The ecological environment parameters include the climate type, sunshine duration, annual average temperature, humidity, wind speed and direction of the site, as well as soil type, vegetation coverage, distribution of surrounding water systems, etc. These parameters can be obtained from local meteorological departments, environmental protection departments, geological exploration reports and other channels.

[0028] Collect multi-dimensional environmental data around the site and perform fusion processing. Use a variety of sensors, such as temperature sensors, humidity sensors, light sensors, noise sensors, etc., to conduct multi-scale environmental monitoring of the construction site and obtain multi-dimensional environmental data sequences. There may be problems such as missing data, errors or inconsistent formats in these data sequences, so fusion processing is required. The processing process includes data cleaning to remove incorrect and duplicate data; normalization to unify data with different dimensions into the same numerical range; feature association to find the connections between different data features; redundancy elimination to remove redundant information; data reconstruction to reorganize data according to specific rules; and consistency verification to ensure the accuracy and consistency of the data. After fusion processing, a standardized environmental data set is obtained. Based on the standardized environmental data set, spatial interpolation technology is used to construct a three-dimensional spatial topology model. Through multi-factor coupling analysis of the model and combining geographical information data, an initial spatial planning model is generated. Multi-factor coupling analysis includes grid meshing to divide different functional blocks and assign corresponding geographical information parameters to each functional block.

[0029] Load climate simulation conditions and resource recycling conditions into the initial spatial planning model. Loading climate simulation conditions to constrain the environmental boundary to obtain the first planning analysis model. Then superimpose resource recycling conditions, such as energy recovery conditions and material recycling conditions, to form a comprehensive planning analysis model. Combining ecological environment parameters, construct a multi-factor collaborative equation and solve the equation through numerical discretization methods to output dynamic collaborative evaluation indicators, which at least include resource recycling efficiency, energy distribution gradient and spatial optimization potential set.

[0030] Construct a multi-objective optimization pre-training framework and perform iterative learning through dynamic collaborative evaluation indicators. Based on the feature fusion network, construct a multi-objective optimization pre-training framework, and perform multi-stage training and verification on the pre-training framework through dynamic collaborative evaluation indicators to obtain a multi-factor coordination model. Input the dynamic collaborative evaluation indicators to be analyzed into the multi-factor coordination model, and output the predicted spatial optimization potential set. Based on this, extract key coordination parameters, which at least include energy coordination nodes, environmental adaptation forms and resource recycling path parameters.

[0031] Generate the system collaborative simulation results through key coordination parameters, comprehensive planning analysis models, and geographic information data. Take the energy coordination node as the benchmark anchor point, map the environmental adaptation form parameters into the comprehensive planning analysis model, adjust the resource circulation path parameters, and refine the grid of associated blocks to complete the update of the comprehensive planning analysis model. Define the co-evolution rules, co-evolution directions, and co-evolution step sizes to form a co-evolution planning model. Based on the co-evolution planning model, use the dynamic iteration method to solve the multi-factor collaborative equation, and generate the system collaborative simulation results according to the results of each iteration stage, including the energy transfer trajectory, maximum load distribution, and environmental response gradient.

[0032] Based on the system collaborative simulation results and facility deployment parameters, establish a configuration model and optimize the facility deployment parameters. The established configuration model includes at least a variable definition module, an objective function module, and a constraint condition module. Define the variable module based on the facility deployment parameters, and the facility deployment parameters include at least equipment layout density, energy conversion efficiency, monitoring coverage, and data transmission delay. Construct the objective function module based on the second efficiency evaluation value and the resource consumption value. The second efficiency evaluation value is calculated based on the system collaborative simulation results, and the resource consumption value includes at least construction cost value, operation and maintenance cost value, and energy loss value. The constraint condition module includes a facility deployment constraint module and an efficiency guarantee constraint module, and defines the efficiency guarantee constraint module based on functional integrity, response timeliness, and system stability. Use the genetic algorithm to perform an initial solution of the configuration model to obtain an initial optimized configuration plan, and then perform a global optimization of the configuration model through the particle swarm algorithm to obtain the particle swarm optimal solution set as the optimal configuration plan for facility deployment.

[0033] Deduce the current stage configuration plan according to the efficiency evaluation framework to obtain the current stage efficiency evaluation index. Combine the current stage efficiency evaluation index, the current stage optimal configuration plan, and the current stage actual configuration parameters to dynamically adjust the facility deployment parameters to achieve the planning control of the green intelligent building.

[0034] The present invention will be further described below in conjunction with Embodiments 1 to 5: Embodiment 1: When carrying out the planning and design of a green intelligent building, collect multi-dimensional environmental data around the site and perform fusion processing to establish a three-dimensional space topology model and generate an initial space planning model. Conduct multi-scale environmental monitoring on the building site, use various sensors to set monitoring points at different heights and different positions, and continuously obtain multi-dimensional environmental data sequences such as temperature, humidity, light intensity, and air quality for a long time. These data may have outliers, such as incorrect data due to sensor failures or inconsistent data formats.

[0035] Next, perform fusion processing on the multi-dimensional environmental data sequence. First, conduct data cleaning, carefully check the data, and remove those data points with obvious errors, such as data points where the temperature value significantly exceeds the normal range of the local climate. Then, perform normalization to unify data with different dimensions into the range of 0-1, which is convenient for subsequent analysis and processing. After that, conduct feature correlation to study the mutual relationships among temperature, humidity, and light intensity. For example, it is found that when the light intensity is high, the temperature tends to rise and the humidity may decrease. At the same time, perform redundancy elimination to remove duplicate-recorded data or redundant information that has little impact on the overall analysis. Then, perform data reconstruction to reorganize the data in the order of space and time to better reflect the environmental change law. Finally, perform consistency verification to ensure that the data collected by each sensor is logically consistent. After these fusion processing steps, a standardized environmental data set is obtained.

[0036] Based on the standardized environmental data set, use spatial interpolation technology to construct a three-dimensional spatial topology model. Spatial interpolation technology can infer the data at unknown positions based on the data of known monitoring points, thereby constructing a continuous three-dimensional spatial model. Conduct multi-factor coupling analysis on the three-dimensional spatial topology model. Divide the model into different functional blocks through grid meshing, such as residential areas, office areas, public activity areas, etc. Assign corresponding geographical information parameters to each functional block. For example, for residential areas, consider lighting and ventilation conditions and assign appropriate orientation and spacing parameters; for office areas, pay attention to traffic convenience and assign relevant parameters close to roads and public transportation stations. Through these steps, an initial spatial planning model is generated.

[0037] Suppose it is necessary to build a green intelligent building complex integrating office, commerce, and residence on a 50,000-square-meter site in the suburbs of the city. The terrain of this site is relatively flat, there is a river passing by, it is close to the urban main road, and there is also a park nearby.

[0038] Before starting the construction, it is necessary to monitor the surrounding environment of the site. Workers installed various sensors at different positions and heights in the site and its surrounding areas. At the boundary of the construction site, a temperature and humidity sensor is set every 100 meters to monitor the air temperature and humidity in real time; a water quality monitoring sensor is installed on the side close to the river to monitor indicators such as the pH value and dissolved oxygen of the river water; light sensors are set in different areas of the site to measure the light intensity; a noise sensor is installed near the main road to collect traffic noise data. These sensors operate continuously and collect data every 15 minutes, thereby obtaining a multi-dimensional environmental data sequence.

[0039] During the data collection process, some sensors may malfunction, resulting in the collection of incorrect data. For example, an abnormal value of 40°C appeared in the temperature displayed by a certain temperature and humidity sensor in winter. Such data needs to be removed during the data cleaning stage. The data collected by different sensors have different dimensions. For example, the unit of light intensity is lux, and the temperature and humidity are degrees Celsius and percentage respectively. For the convenience of unified analysis, normalization processing is required to unify these data into the interval of [0, 1]. At the same time, research has found that there is a certain correlation between light intensity and temperature and humidity. Generally, when the light intensity increases, the temperature will rise and the humidity will drop. These relationships are mined through feature correlation. During the data collection process, there may be some duplicate records or redundant data that have little effect on the overall analysis. For example, multiple sensors collect highly similar data in a short period of time. This part of the data can be removed through redundancy elimination. In order to better reflect the environmental change law, the data is reorganized in time and space order to complete data reconstruction. Finally, through consistency verification, it is checked whether the data collected by different sensors is logically consistent. For example, whether the relationship between temperature and humidity and light intensity conforms to normal physical laws. If not, the data is further investigated and corrected to obtain a standardized environmental data set.

[0040] Based on the standardized environmental data set, a three-dimensional spatial topology model is constructed using spatial interpolation technology. Spatial interpolation technology can infer the data at unknown positions based on the data of known monitoring points, thereby constructing a continuous three-dimensional space model. For example, given the temperature and humidity data of some monitoring points within the site, the temperature and humidity conditions in the areas where no sensors are installed can be estimated through spatial interpolation technology, and then a three-dimensional temperature and humidity model of the entire site can be constructed. The same method is applied to other environmental data such as light intensity and noise, and finally a three-dimensional spatial topology model containing multiple environmental factors is integrated.

[0041] Perform multi-factor coupling analysis on the constructed three-dimensional spatial topology model to generate an initial spatial planning model. The model is divided into different functional blocks through grid meshing. According to the functional requirements of the building, the site is divided into office areas, commercial areas, residential areas, and public greening areas, etc. Corresponding geographical information parameters are assigned to different functional blocks. For the office area, considering the daily commuting of employees, it is assigned geographical parameters close to the urban main road to ensure traffic convenience; for the commercial area, to attract more customers, it is assigned parameters close to the park and the center of the site to enhance commercial exposure; for the residential area, attention is paid to the living comfort, and it is assigned parameters close to the river and far from the noise interference of the main road. At the same time, considering good lighting and ventilation conditions, the building orientation and building spacing are reasonably planned; the public greening area is set in the center of the site to optimize the overall ecological environment and improve the living and working experience of residents and office workers. After the above series of operations, an initial spatial planning model that meets multiple factor considerations is generated, providing a basic framework for subsequent building design.

[0042] Example 2: The initial spatial planning model is loaded with climate simulation conditions and resource recycling conditions to form a comprehensive planning analysis model, which outputs dynamic collaborative evaluation indicators. Using professional climate simulation software, the initial spatial planning model is loaded with climate simulation conditions. Local climate data, such as annual average temperature, humidity, wind speed and direction, and sunshine duration, is input, and environmental boundaries are constrained to produce the first planning analysis model. This model considers the impact of local climate on buildings. For example, in hot regions, buildings should be oriented to avoid direct sunlight to reduce energy consumption for air conditioning and cooling.

[0043] Resource recycling conditions are added to the first planning analysis model to form a comprehensive planning analysis model. Resource recycling conditions include energy recovery and material recycling. For energy recovery, consider installing solar panels on building roofs to collect solar energy and convert it into electricity, or installing wind turbines around the building to generate wind energy. Material recycling conditions examine the recycling and reuse of building materials, such as whether discarded bricks and steel can be reprocessed for building repairs or expansion.

[0044] Based on the comprehensive planning analysis model and ecological and environmental parameters, dynamic synergy evaluation indicators are calculated. Multi-factor synergy equations are constructed, which involve aspects such as energy balance, environmental response, and resource allocation. Although no formulas are used, it can be understood as constructing equations from the perspectives of energy generation, consumption, and recovery, the impact of the environment on buildings, and the rational allocation of resources. The synergy equations are solved using numerical discretization methods to obtain resource cycle efficiency, energy distribution gradients, and spatial optimization potential sets. When calculating the spatial optimization potential set, the energy load difference of each functional block is calculated based on the energy distribution gradient. Carefully analyze the energy consumption of each functional block, find the functional blocks whose energy load difference is not less than the load threshold, and form these functional blocks into a spatial optimization potential set. This will clearly identify which areas still have room for improvement in energy utilization, providing a basis for subsequent optimization design.

[0045] Consider a scenario where a green smart hotel is planned for a coastal city. This area experiences high summer temperatures, high humidity, and frequent sea breezes, and there are also strong requirements for resource recycling.

[0046] When loading climate simulation conditions into the initial space planning model, professional climate simulation software is used. First, meteorological data for many years in this region are input, including details such as the average summer temperature of about 30°C, the average humidity of 75%, the dominant sea breeze direction of southeast wind, the wind speed of about 3 - 5 m / s, and the annual sunshine duration of about 2,500 hours. Based on these data, the simulation software constrains the environmental boundaries to generate the first planning analysis model. For example, according to the sea breeze direction and speed, the windward and leeward sides of the building are determined in the model. It is considered to set ventilation openings on the windward side to utilize the natural sea breeze to achieve indoor ventilation and cooling, reduce the use of air conditioning systems, and thus reduce energy consumption. At the same time, according to the sunshine duration and angle, the orientation of the building is planned so that most rooms can obtain sufficient sunshine in winter and avoid excessive exposure in summer.

[0047] The resource recycling conditions are superimposed on the first planning analysis model to form a comprehensive planning analysis model. In terms of energy recovery conditions, solar photovoltaic panels are installed on the roof of the hotel and some west-facing walls. Due to the sufficient sunshine in the local area, the solar photovoltaic panels can convert solar energy into electric energy for the daily use of the hotel, such as lighting, equipment operation, etc. After calculation, it is estimated that these solar photovoltaic panels can generate about 500,000 kWh of electricity per year, which can meet about 30% of the hotel's electricity demand. In addition, small wind turbines are set at appropriate positions around the hotel to generate electricity using sea breeze. According to the wind speed and frequency of the sea breeze, these wind turbines are expected to generate 100,000 kWh of electricity per year, further supplementing the hotel's energy supply.

[0048] In terms of material recycling conditions, the waste building materials generated during the hotel construction process are classified and recycled. For example, the waste bricks can be crushed and used for the road base filling; the waste steel can be remelted and processed and used for some small decorative structures or maintenance parts inside the hotel. At the same time, during the hotel operation process, various types of waste are strictly classified, and recyclable papers, plastic bottles, metal products, etc. are recycled to achieve the recycling of resources.

[0049] Based on the comprehensive planning analysis model and the local ecological environment parameters, dynamic collaborative evaluation indicators are calculated. A multi-factor collaborative equation involving aspects such as energy balance, environmental response, and resource allocation is constructed (formulas are not involved here, only explained from a conceptual level). The equation is constructed from perspectives such as the generation of energy (such as solar energy and wind energy power generation), consumption (electricity consumption of various hotel equipment, energy consumption of air conditioning systems, etc.), recovery (potential energy value generated from waste material recycling), the impact of the environment on the building (the impact of sea breeze and sunshine on the indoor environment and energy consumption), and the reasonable allocation of resources (the allocation of various resources in different functional areas). The collaborative equation is solved by numerical discretization methods to obtain the resource recycling efficiency, energy distribution gradient, and space optimization potential set.

[0050] When calculating the set of spatial optimization potential, based on the energy distribution gradient, the energy load difference of each functional block is calculated in detail. Different functional areas of the hotel, such as the guest room area, the dining area, the fitness area, etc., have different energy consumption situations. In the guest room area, it is mainly the electricity consumption of lighting, air conditioning and small appliances; in the dining area, in addition to lighting and air conditioning, there is also a large amount of electricity consumption for kitchen equipment; in the fitness area, it is mainly the electricity consumption of various fitness equipment. After carefully analyzing the energy consumption situation of each functional block, a load threshold is set, for example, the energy consumption difference per square meter per month reaches 5 kWh as the standard. Identify the functional blocks whose energy load difference is not less than this load threshold. For example, in the dining area, due to the large power consumption of kitchen equipment during peak hours, its energy load difference is significantly higher than other areas. These functional blocks are grouped into the set of spatial optimization potential. It is clear that the dining area has great room for improvement in energy utilization. Subsequently, more in-depth energy optimization designs can be carried out for the dining area, such as replacing more energy-efficient kitchen equipment and optimizing the equipment usage time, providing strong support for the goal of achieving a green and intelligent building.

[0051] Example 3: Construct a multi-objective optimization pre-training framework and perform iterative learning through dynamic collaborative evaluation indicators to obtain a multi-factor coordination model and extract key coordination parameters. A multi-objective optimization pre-training framework is constructed based on a feature fusion network. The feature fusion network can integrate different types of data features, such as integrating the geographical information features, environmental data features, energy utilization features, etc. of the building. The pre-training framework is trained and verified in multiple stages through dynamic collaborative evaluation indicators. During the training process, the parameters of the framework are continuously adjusted to make it better adapt to different situations.

[0052] Input the dynamic collaborative evaluation indicators to be analyzed into the multi-factor coordination model, and output the predicted set of spatial optimization potential. The multi-factor coordination model will analyze the relationships between various factors according to the input dynamic collaborative evaluation indicators and predict which areas have greater spatial optimization potential. Based on the predicted set of spatial optimization potential, key coordination parameters are extracted. Determine the geometric center point of the predicted set of spatial optimization potential and use this center point as the energy coordination node. This point plays an important role in energy distribution and coordination, and based on it, the transmission and use of energy can be better planned.

[0053] Fit the environmental adaptation form according to the distribution characteristics of the predicted set of spatial optimization potentials to obtain the environmental adaptation form parameters. The environmental adaptation form parameters include the form curvature and the spatial extension dimension. Observe the distribution of the set of spatial optimization potentials. If the distribution is relatively concentrated, the form curvature may be small; if the distribution is relatively dispersed, the form curvature may be large. Through the analysis of the distribution characteristics, a suitable environmental adaptation form is fitted, so as to obtain parameters such as the form curvature and the spatial extension dimension. Analyze the energy load gradient direction of the predicted set of spatial optimization potentials, calculate the weighted average of the gradient direction, and convert it into a standard resource circulation path, which is the resource circulation path parameter. In this way, the optimal circulation path of resources in the building is determined, and the utilization efficiency of resources is improved.

[0054] Suppose it is necessary to build a green intelligent R & D building in a new technology park. This area has unique climate and geographical environmental characteristics, and at the same time has high requirements for the efficient energy utilization and flexible space layout required for scientific and technological R & D.

[0055] When constructing the multi-objective optimization pre-training framework, it is built based on the feature fusion network. The buildings in this park involve various feature data. For example, in terms of geographical information, it includes the terrain undulation in the park (although the overall is relatively flat, there are still slight slope differences), and the distances from surrounding public facilities (such as bus stops, restaurants, etc.); the environmental data covers the seasonal variation of the light intensity in this area, the annual average temperature, humidity, and the dominant wind direction; the energy utilization characteristics include the energy consumption data of past similar buildings, such as the electricity and water resource consumption in different floors and different functional areas. The feature fusion network integrates these seemingly independent but interrelated data features, providing a comprehensive data basis for subsequent optimization training.

[0056] Perform multi-stage training and verification on the pre-training framework through dynamic collaborative evaluation indicators. During the training process, data such as the resource circulation efficiency, energy distribution gradient, and the set of spatial optimization potentials in the dynamic collaborative evaluation indicators are continuously input into the framework. For example, if it is found in the current stage that the energy consumption in a certain area of the building (such as the experimental area) is too high, the resource circulation efficiency is low (the waste generated in the experiment cannot be fully recycled), and the set of spatial optimization potentials shows that there may be room for improvement in the layout adjustment of this area. According to the feedback of these indicators, the parameters of the framework are adjusted, and the weight distribution of different feature data is adjusted to make the framework pay more attention to the areas with high energy consumption and low resource circulation efficiency. After multiple rounds of training and verification, let the framework continuously learn and adapt to the actual situation, gradually optimize its performance, and thus obtain a multi-factor coordination model.

[0057] Input the dynamic collaborative evaluation indicators to be analyzed into the multi-factor coordination model, and output the predicted set of spatial optimization potential. Assume that the current dynamic collaborative evaluation indicators to be analyzed show that during the high-temperature period in summer, the energy load in the server room area of the R & D building is too large, resulting in an abnormal energy distribution gradient on the entire floor, and the resource recycling efficiency is also low in this area (the waste heat generated by the computer room cooling is not effectively utilized). After receiving these indicators, the multi-factor coordination model analyzes the relationships between various factors through its internal algorithms and logic, and predicts that the server room area and some adjacent office areas have great potential for spatial optimization.

[0058] Based on the predicted set of spatial optimization potential, extract the key coordination parameters. First, determine the geometric center point of the predicted set of spatial optimization potential (server room area and adjacent office areas), and use this center point as the energy coordination node. Based on this point, it is possible to better plan the transmission and distribution of energy. For example, consider setting up energy storage devices near this point to temporarily store the excess electrical energy generated by the computer room for use by other areas during peak electricity consumption.

[0059] Fit the environmental adaptation form according to the distribution characteristics of the predicted set of spatial optimization potential to obtain the environmental adaptation form parameters. Observe the spatial distribution of this area and find that the server room is distributed in a long strip shape, and the adjacent office areas are arranged around some of its edges. By analyzing this distribution characteristic, fit the environmental adaptation form. For example, in order to better utilize natural ventilation and lighting, in the building design, the building shape of this area can be designed to have a certain curvature to increase the lighting area and ventilation effect. Thus, the environmental adaptation form parameters are obtained. The form curvature reflects the degree of curvature of the building shape, and the spatial extension dimension clarifies the spatial expansion possibility of this area in different directions. For example, it is determined that the floor height can be appropriately increased in a certain direction to optimize space utilization.

[0060] Analyze the energy load gradient direction of the predicted spatial optimization potential set, calculate the weighted average of the gradient directions, and convert it into a standard resource recycling path, which is the resource recycling path parameter. Taking a server room as an example, its energy load is mainly concentrated on the heat generated by equipment operation and power consumption. The energy load gradient direction points to the outside of the room for heat dissipation and power output. Calculate the weighted average of these gradient directions, and assign different weights to each gradient direction considering the energy demands and importance of different areas. For example, the office area has a relatively stable power demand and a relatively high weight; while auxiliary areas such as corridors have a lower weight. After obtaining the weighted average through calculation, convert it into a standard resource recycling path. For instance, determine to collect waste heat from the server room and transfer it through a specific pipeline system to the fresh air system in the adjacent office area to preheat the fresh air in winter and achieve the recycling of waste heat. This waste heat transfer path is the resource recycling path parameter, thereby improving the resource utilization efficiency of the entire area.

[0061] Embodiment 4: Generate system collaborative simulation results through key coordination parameters, a comprehensive planning analysis model, and geographical information data. Use the energy coordination node as a reference anchor point and map the environmental adaptation form parameters into the comprehensive planning analysis model. The energy coordination node is like a core hub around which the building layout and energy distribution are adjusted. The environmental adaptation form parameters are used to optimize the building's shape and spatial layout to better adapt to the surrounding environment. Adjust the resource recycling path parameter and refine the grid of the associated blocks to complete the update of the comprehensive planning analysis model. According to the requirements and efficiency of resource recycling, adjust the resource recycling path parameter, and at the same time perform a more detailed grid division on the associated functional blocks for more accurate analysis and simulation.

[0062] Define the co-evolution rules, co-evolution direction, and co-evolution step size to form a co-evolution planning model. The co-evolution rule is defined as triggering path optimization if the current cumulative energy difference is not less than the difference threshold. Monitor the energy usage situation in real time. When the energy difference accumulates to a certain extent, optimize the energy transmission path. The co-evolution direction is determined based on the historical evolution trend and the current energy distribution direction. Refer to the previous energy usage situation and the current energy distribution to determine the evolution direction of energy. The energy transfer trajectory and co-evolution step size are determined according to climate parameters and resource recycling efficiency respectively. Climate conditions affect the energy transmission, and the resource recycling efficiency determines the step size of each evolution.

[0063] Based on the co-evolution planning model, a dynamic iterative method is used to solve the multi-factor cooperation equation. During the solution process, when the co-evolution rules are met, path optimization is carried out to obtain the current energy transfer trajectory, co-evolution step size, co-evolution direction, energy load distribution, and environmental response gradient, and then the co-evolution planning model is updated. Then, based on the updated co-evolution planning model, the multi-factor cooperation equation is solved again until the termination condition is reached, and the co-evolution process ends. According to the energy load distribution and environmental response gradient in each iteration stage, the maximum load distribution and environmental response gradient are calculated, so as to generate the system co-simulation results.

[0064] Suppose a green intelligent resort hotel is to be built in an eco-tourism resort area, which has rich natural landscapes such as mountains and lakes, and has strict requirements for efficient energy utilization.

[0065] Taking the energy coordination node as the reference anchor point, in the planning and design of this resort hotel, the core area of the hotel's energy consumption is determined through preliminary analysis. For example, the large kitchen and hot spring bath areas of the hotel are places with relatively large energy consumption, and the geometric center point between these two areas is determined as the energy coordination node. Map the environmental adaptation form parameters into the comprehensive planning analysis model. According to the terrain and landscape distribution of the resort area, the building form of the hotel is designed as a curve shape that echoes the trend of the surrounding mountains, so as to determine the environmental adaptation form parameters, such as form curvature and spatial extension dimension, etc. Then, adjust the resource recycling path parameters. Considering the utilization of the hot spring water resources in the hotel, optimize the path of the hot spring water from the collection point to the bath and then to the recycling and treatment point, and reduce the energy loss during transportation. At the same time, refine the grid of the associated blocks, accurate to parameters such as the area of each region and the density of personnel activities, and complete the update of the comprehensive planning analysis model.

[0066] Define the co-evolution rules, co-evolution direction, and co-evolution step size to form the co-evolution planning model. The co-evolution rule is defined as if the cumulative amount of the current energy difference is not less than the difference threshold, then path optimization is triggered. Suppose the difference threshold is set to 500 kW·h (kW·h is kilowatt-hour, a unit of energy, indicating the electrical energy consumed by an electrical device with a power of 1 kilowatt in 1 hour), and the cumulative amount of the energy difference is calculated by the formula Calculate, where represents the cumulative amount of the energy difference, represents the number of statistical time periods, represents the total energy supply in the th time period, The total energy consumption within a time period. The co-evolution direction is determined based on the historical evolution trend and the current energy distribution direction. By analyzing the energy consumption data of the hotel at different time periods in the past week and combining the current energy usage in each area, the direction in which energy mainly flows from the energy supply area to the high-energy-consuming areas is determined as the co-evolution direction. The energy transfer trajectory and the co-evolution step size are determined based on climate parameters and resource recycling efficiency respectively. For example, in summer, due to the high temperature, the energy transfer trajectory is more inclined to guide the excess heat to the refrigeration system for reuse. When the resource recycling efficiency is high, the co-evolution step size is appropriately increased to accelerate the optimization process.

[0067] Based on the co-evolution planning model, a dynamic iterative method is used to solve the multi-factor co-evolution equation. During the solution process, path optimization is carried out when the co-evolution rules are met. For example, after a period of operation monitoring, it is found that the cumulative energy difference reaches 550 kW·h, exceeding the difference threshold of 500 kW·h. At this time, path optimization is triggered. By adjusting the layout of the energy transmission pipeline and valve control, the current energy transfer trajectory, co-evolution step size, co-evolution direction, energy load distribution, and environmental response gradient are obtained, and the co-evolution planning model is updated. Then, based on the updated co-evolution planning model, the multi-factor co-evolution equation is solved again, and so on until the termination condition is reached. Assuming the termination condition is set that the cumulative energy difference calculated continuously for 5 times is less than 100 kW·h, the co-evolution process ends. According to the energy load distribution and environmental response gradient in each iteration stage, the maximum load distribution and environmental response gradient are calculated, thereby generating the system co-evolution simulation results. Through these results, the energy utilization situation and environmental impact of the hotel at different operation stages can be clearly understood, providing a favorable basis for subsequent optimization and adjustment.

[0068] Example 5: Based on the system co-evolution simulation results and the facility deployment parameters, a configuration model is established and the facility deployment parameters are optimized to obtain the optimal configuration plan for facility deployment. A configuration model is established, and the configuration model at least includes a variable definition module, an objective function module, and a constraint condition module. In the variable definition module, definitions are made based on the facility deployment parameters, and the facility deployment parameters at least include equipment layout density, energy conversion efficiency, monitoring coverage, and data transmission delay. Reasonably plan the layout density of the equipment, neither too dense to cause interference between equipment nor too sparse to affect the usage efficiency; improve the energy conversion efficiency and reduce the loss of energy during the conversion process; expand the monitoring coverage to ensure comprehensive monitoring of the building environment; reduce the data transmission delay to ensure timely transmission of information.

[0069] Construct an objective function module based on the second performance evaluation value and the resource consumption value. The second performance evaluation value is calculated based on the results of system co-simulation, taking into account factors such as the energy utilization efficiency, environmental adaptability, and space utilization efficiency of the building. The resource consumption value includes at least the construction cost value, operation and maintenance cost value, and energy loss value. On the premise of meeting the building's functional requirements, these costs and losses are minimized as much as possible. The constraint condition module includes a facility deployment constraint module and a performance guarantee constraint module. The performance guarantee constraint module is defined based on functional integrity, response timeliness, and system stability. Ensure that all functions of the building can operate normally, respond promptly to environmental changes and user needs, and the entire system is stable and reliable.

[0070] Use the genetic algorithm to perform an initial solution of the configuration model to obtain an initial optimized configuration plan. The genetic algorithm simulates the biological evolution process and searches for better solutions among numerous possible configuration plans through operations such as selection, crossover, and mutation. Then, use the particle swarm optimization algorithm to perform global optimization on the configuration model. The particle swarm optimization algorithm uses information sharing and mutual cooperation among particles to search in the solution space and obtains the optimal solution set of the particle swarm as the optimal configuration plan for facility deployment. In this way, find the most suitable facility deployment plan for the green intelligent building to achieve the efficient operation and sustainable development of the building.

[0071] Suppose a green intelligent community is to be built in a newly developed area of the city. The community planning includes multiple residential buildings, supporting commercial facilities, and public activity areas, aiming to achieve efficient energy utilization, a comfortable living environment, and intelligent management.

[0072] A configuration model is established, which includes a variable definition module, an objective function module, and a constraint condition module. In the variable definition module, definitions are made based on facility deployment parameters. In terms of equipment layout density, for example, in the parking lot planning of a community, considering the vehicle ownership of residents and the demand for convenient parking, the layout density of charging piles is reasonably set. Through preliminary research and data analysis, it is determined that 1 fast-charging pile and 3 slow-charging piles are set for every 20 parking spaces. This can not only meet the daily charging needs of residents but also avoid resource waste and space congestion caused by overly dense charging piles. In terms of energy conversion efficiency, new types of solar panels and ground-source heat pump systems are selected. The photoelectric conversion efficiency of the solar panels reaches 22%, and the heating / cooling performance coefficients (COP) of the ground-source heat pump system are 4.5 and 5.0 respectively, which greatly improves the energy conversion efficiency compared with traditional equipment. In terms of monitoring coverage, various sensors are installed in the community, such as environmental monitoring sensors and security monitoring cameras. The environmental monitoring sensors are evenly distributed in various areas of the community and can real-time monitor environmental parameters such as air quality (including indicators such as PM2.5, PM10, sulfur dioxide, etc.) and noise level, ensuring that the monitoring coverage reaches more than 98% of the entire community area. In terms of data transmission delay, 5G networks and high-performance Internet of Things devices are used to control the delay of transmitting data from sensors to the community management center within 50 milliseconds, ensuring that information can be transmitted in a timely and accurate manner.

[0073] An objective function module is constructed based on the second efficiency evaluation value and the resource consumption value. The second efficiency evaluation value is calculated based on the results of system co-simulation, comprehensively considering factors such as the energy utilization efficiency, environmental comfort, and space utilization efficiency of the community. For example, by simulating the energy consumption and environmental changes in the community in different seasons and different time periods, it is obtained that during the peak period of air conditioner use in summer, the energy self-sufficiency rate of the community reaches 30% (the proportion of solar and geothermal energy supply in the total energy consumption), the indoor temperature is maintained in the comfortable range of 24-26°C, and the outdoor noise level is lower than 50 decibels. These data together constitute a part of the second efficiency evaluation value. The resource consumption value at least includes the construction cost value, the operation and maintenance cost value, and the energy loss value. In terms of construction cost, it includes land acquisition costs, building material costs, equipment procurement and installation costs, etc. After estimation, the construction cost of the entire community is about 200 million yuan. The operation and maintenance cost covers equipment maintenance, personnel salaries, water and electricity bills, etc., and the estimated annual operation and maintenance cost is 5 million yuan. The energy loss value is obtained by calculating the energy loss of various energy equipment in the community during operation, such as line losses during power transmission and efficiency losses of energy conversion equipment. The annual energy loss converted into costs is about 800,000 yuan.

[0074] The constraint condition module includes a facility deployment constraint module and an effectiveness guarantee constraint module. The effectiveness guarantee constraint module is defined based on functional integrity, response timeliness, and system stability. In terms of functional integrity, it is ensured that various facilities in the community can meet the daily living needs of residents. For example, commercial facilities provide basic shopping and dining services, and public activity areas are equipped with fitness equipment, leisure seats, and other facilities. Response timeliness requires that the community management system can respond promptly to the needs of residents and equipment failures. For example, when a resident reports an equipment failure through the mobile phone APP, the management system needs to respond within 1 hour and arrange maintenance personnel to handle it. In terms of system stability, it is ensured that systems such as electricity, water supply, and network in the community can operate stably, with the annual power outage time not exceeding 24 hours and the network interruption time not exceeding 2 hours per month.

[0075] The genetic algorithm is used to perform an initial solution of the configuration model to obtain an initial optimized configuration plan. The genetic algorithm simulates the biological evolution process, regards various possible plans for community facility deployment as biological individuals, and searches for better solutions among numerous possible configuration plans through operations such as selection, crossover, and mutation. For example, 100 initial plans are randomly generated, and each plan contains specific parameters such as the layout of charging piles, equipment selection, and sensor positions. These plans are evaluated according to the objective function, and plans with higher fitness (i.e., low resource consumption and high effectiveness evaluation value) are selected for crossover and mutation operations. After multiple rounds of iteration, a relatively optimized initial optimized configuration plan is obtained. For example, the best installation position and quantity of solar panels in the community and the reasonable distribution of the ground source heat pump system are determined.

[0076] Then, the particle swarm algorithm is used to perform global optimization on the configuration model. The particle swarm algorithm uses information sharing and mutual cooperation among particles to search in the solution space. The initial optimized configuration plan is used as the initial position of the particle swarm, and each particle represents a facility deployment plan. During the search process, the particle continuously adjusts its flight direction and speed according to its own flight experience and the position of the optimal particle in the group. For example, during the iteration process, the particle continuously tries to adjust the layout density of charging piles, the parameters of energy conversion equipment, etc. By comparing the objective function values of different plans, the optimal solution set of the particle swarm is found as the optimal configuration plan for facility deployment. Finally, the optimal configuration of various facilities in the community is determined, achieving the balance and optimization of the green intelligent community in terms of resource utilization, residents' quality of life, and system stability.

[0077] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0078] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand 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. A multi-factor fusion planning and design method for green intelligent buildings, characterized in that, It includes the following steps: Obtain the geographical information data and ecological environment parameters of the construction site; Collect multi-dimensional environmental data around the site and perform fusion processing, establish a three-dimensional spatial topology model, conduct multi-factor coupling analysis on the three-dimensional spatial topology model and combine with the geographical information data to generate an initial spatial planning model; Load climate simulation conditions and resource recycling conditions into the initial spatial planning model to form a comprehensive planning analysis model, and combine with ecological environment parameters to output dynamic collaborative evaluation indicators; Construct a multi-objective optimization pre-training framework and perform iterative learning through dynamic collaborative evaluation indicators to obtain a multi-factor coordination model, and then extract key coordination parameters; Generate a system collaborative simulation result through the key coordination parameters, the comprehensive planning analysis model and the geographical information data; Based on the system collaborative simulation result and the facility deployment parameters, establish a configuration model and optimize the facility deployment parameters to obtain the optimal configuration plan for facility deployment; Deduce the configuration plan of the current stage according to the effectiveness evaluation framework to obtain the effectiveness evaluation indicators of the current stage, and combine the effectiveness evaluation indicators of the current stage, the optimal configuration plan of the current stage and the actual configuration parameters of the current stage to dynamically adjust the facility deployment parameters to achieve the planning control of the green intelligent building.

2. The multi-factor integration planning and design method for green intelligent buildings according to claim 1, wherein The dynamic collaborative evaluation indicators at least include the resource recycling efficiency, the energy distribution gradient and the spatial optimization potential set; the key coordination parameters at least include the energy coordination node, the environmental adaptation form and the resource recycling path parameters; the system collaborative simulation result at least includes the energy transfer trajectory, the maximum load distribution and the environmental response gradient.

3. The multi-factor integration planning and design method for green intelligent buildings according to claim 1, characterized in that, The step of collecting multi-dimensional environmental data around the site and performing fusion processing, establishing a three-dimensional spatial topology model, conducting multi-factor coupling analysis on the three-dimensional spatial topology model and combining with the geographical information data to generate an initial spatial planning model includes the following steps: Conduct multi-scale environmental monitoring on the construction site to obtain a multi-dimensional environmental data sequence; Perform fusion processing on the multi-dimensional environmental data sequence to obtain a standardized environmental data set, where the fusion processing includes one or more of data cleaning, normalization, feature association, redundancy elimination, data reconstruction and consistency verification; Based on the standardized environmental data set, use spatial interpolation technology to construct a three-dimensional spatial topology model; Conduct multi-factor coupling analysis on the three-dimensional spatial topology model to generate an initial spatial planning model, where the multi-factor coupling analysis at least includes grid meshing and parameter mapping, divides different functional blocks through grid meshing, and assigns corresponding geographical information parameters to each functional block.

4. The multi-factor integration planning and design method for green intelligent buildings according to claim 1, wherein, The step of loading climate simulation conditions and resource recycling conditions into the initial spatial planning model to form a comprehensive planning analysis model, and combining with ecological environment parameters to output dynamic collaborative evaluation indicators includes the following steps: Load climate simulation conditions into the initial spatial planning model to constrain the environmental boundary to obtain a first planning analysis model; Overlay resource recycling conditions on the first planning analysis model to form a comprehensive planning analysis model, where the resource recycling conditions include energy recovery conditions and material recycling conditions; Based on the comprehensive planning analysis model and ecological environment parameters, calculate the dynamic collaborative evaluation indicators, and the specific process includes: Construct a multi-factor collaborative equation, which at least includes an energy balance equation, an environmental response equation, and a resource allocation equation. Combine with the comprehensive planning analysis model and solve the collaborative equation by numerical discretization method to obtain the resource recycling efficiency, energy distribution gradient, and spatial optimization potential set.

5. The green intelligent building multi-factor integration planning and design method according to claim 4, characterized in that Obtain the spatial optimization potential set, including the following steps: Based on the energy distribution gradient, calculate the energy load difference of each functional block. Identify the functional blocks in the comprehensive planning analysis model where the energy load difference is not less than the load threshold to obtain the spatial optimization potential set.

6. The multi-factor integration planning and design method for green intelligent buildings according to claim 1, characterized in that, The steps of constructing a multi-objective optimization pre-training framework and performing iterative learning through dynamic collaborative evaluation indicators to obtain a multi-factor coordination model, and then extracting key coordination parameters include: Construct a multi-objective optimization pre-training framework based on the feature fusion network. Perform multi-stage training and verification on the pre-training framework through dynamic collaborative evaluation indicators to obtain a multi-factor coordination model. Input the dynamic collaborative evaluation indicators to be analyzed into the multi-factor coordination model and output the predicted spatial optimization potential set. Based on the predicted spatial optimization potential set, extract key coordination parameters, where the key coordination parameters at least include energy coordination nodes, environmental adaptation forms, and resource recycling path parameters.

7. The green intelligent building multi-factor integration planning and design method according to claim 6, wherein, The steps of extracting key coordination parameters based on the predicted spatial optimization potential set include: Determine the geometric center point of the predicted spatial optimization potential set as the energy coordination node. Fit the environmental adaptation form according to the distribution characteristics of the predicted spatial optimization potential set to obtain environmental adaptation form parameters, where the environmental adaptation form parameters include form curvature and spatial extension dimension. Analyze the energy load gradient direction of the predicted spatial optimization potential set, calculate the weighted average value of the gradient direction, and convert it into a standard resource recycling path, which is the resource recycling path parameter.

8. The multi-factor integration planning and design method for green intelligent buildings according to claim 1, wherein, The steps of generating a system collaborative simulation result through key coordination parameters, the comprehensive planning analysis model, and geographic information data include: Take the energy coordination node as the reference anchor point, map the environmental adaptation form parameters into the comprehensive planning analysis model, adjust the resource recycling path parameters and refine the grid of the associated blocks to complete the update of the comprehensive planning analysis model, and define the co-evolution rules, co-evolution direction, and co-evolution step size to form a co-evolution planning model. Based on the co-evolution planning model, use the dynamic iteration method to solve the multi-factor collaborative equation, and generate a system collaborative simulation result according to the results of each iteration stage in the solution process, specifically including: When the co-evolution rule is satisfied, perform path optimization to obtain the current energy transfer trajectory, co-evolution step size, co-evolution direction, energy load distribution, and environmental response gradient, and update the co-evolution planning model. Re-solve the multi-factor collaborative equation based on the updated co-evolution planning model until the termination condition is reached, and end the co-evolution process. Calculate the maximum load distribution and environmental response gradient according to the energy load distribution and environmental response gradient of each iteration stage. The co-evolution rule is defined as triggering path optimization if the cumulative amount of the current energy difference is not less than the difference threshold. The co-evolution direction is determined based on the historical evolution trend and the current energy distribution direction; The energy transfer trajectory and the co-evolution step size are determined according to climate parameters and resource recycling efficiency respectively.

9. The multi-factor fusion planning and design method for green intelligent buildings according to claim 1, wherein, Based on the system co-simulation results and the facility deployment parameters, a configuration model is established and the facility deployment parameters are optimized to obtain the optimal configuration plan for facility deployment, including the following steps: Establish a configuration model, where the configuration model at least includes a variable definition module, an objective function module, and a constraint condition module. Define the variable module based on the facility deployment parameters. The facility deployment parameters at least include equipment layout density, energy conversion efficiency, monitoring coverage, and data transmission delay. Construct the objective function module based on the second efficiency evaluation value and the resource consumption value. The second efficiency evaluation value is calculated according to the system co-simulation results. The resource consumption value at least includes construction cost value, operation and maintenance cost value, and energy loss value. The constraint condition module includes a facility deployment constraint module and an efficiency guarantee constraint module. Define the efficiency guarantee constraint module based on functional integrity, response timeliness, and system stability; Use the genetic algorithm to perform an initial solution to the configuration model to obtain an initial optimized configuration plan; Perform global optimization on the configuration model through the particle swarm algorithm, and obtain the optimal solution set of the particle swarm as the optimal configuration plan for facility deployment.

10. A computer device, characterized in that: The computer device includes a memory, a processor, and a communication interface, which are connected through a bus; the memory is used to store a set of computer program instructions and data, and transmit the stored data to the processor. The processor executes the program instructions stored in the memory to execute the green intelligent building multi-factor fusion planning and design method according to any one of claims 1 to 8.

Images