Building health performance optimization design method based on space heat autonomy

Abstract

The invention provides a building health performance optimization design method based on space heat autonomy. According to the method, a thermal comfort comprehensive evaluation model is fused in a calculation process, so that the thermal comfort of a user is comprehensively evaluated; meanwhile, a space-time diagram model is applied to train a prediction model of the space thermal autonomy, dynamic characteristics of the indoor environment in time dimension and spatial layout are accurately captured and analyzed in combination with the activity rule of a user, and the problems that current space thermal autonomy prediction errors are large and the computing power requirement is large are solved. According to the implementation of the method, the efficiency and accuracy of building space heat autonomy prediction can be greatly improved, technical support is provided for optimizing space heat autonomy in the building design process, the passive design strategy of the building is improved, the heat adjusting capacity of the building is enhanced, the living experience of residents is improved, meanwhile, energy is saved, carbon is reduced, and the economic benefit is improved. And the building design is promoted to develop in a more healthy, green and efficient direction.

Description

Technical Field

[0001] The present invention relates to the field of building technology, and particularly to an optimized design method for building health performance based on spatial thermal autonomy. Background Art

[0002] With the development of society, the public's requirements for the quality of life are constantly increasing, and creating a healthy and comfortable indoor building environment has become the core pursuit in the field of building design. There is a close relationship between the thermal comfort of the indoor environment, the comfort feeling of the occupants, the overall satisfaction, and the overall energy consumption of the building. Therefore, accurately predicting and optimizing the thermal comfort of the building has become an indispensable part of current building design.

[0003] In the traditional building design workflow, the evaluation method of thermal comfort is usually based on a thermal comfort model containing fixed formulas (such as Predicted Mean Vote PMV), combined with the hourly calculation of the simulated thermal environment data, and finally integrated into general annual indicators, such as the percentage of time outside the PMV range, the proportion of time outside the set operating temperature range, etc. These traditional thermal comfort indicators often limit the thermal comfort conditions to a narrow temperature range. However, this constant environmental mode not only fails to effectively promote the thermal balance adjustment ability of the occupants themselves, but also leads to a dependence on the frequent operation of active regulation systems such as air conditioners, significantly increasing the energy consumption of the building. Research shows that under natural ventilation conditions, users can accept a wider comfortable temperature range and a larger temperature fluctuation amplitude compared to non-naturally ventilated rooms through their body's thermal regulation ability and thermal adaptation behavior; at the same time, natural ventilation conditions are also beneficial to improving the indoor environmental quality and the health level of the occupants.

[0004] In this context, the proposal and application of the concept of Spatial Thermal Autonomy (sTA) are particularly important. Spatial Thermal Autonomy represents the percentage of the floor area of a building that can meet or exceed a given thermal comfort standard only through passive means. In its calculation process, the thermal comfort evaluation method can be selected and adjusted according to the design requirements. A suitable thermal comfort evaluation method can fully consider the thermal regulation and thermal adaptation ability of the occupants, break through the narrow thermal comfort temperature range defined by traditional thermal comfort indicators, and expand the acceptable temperature fluctuation range of the occupants. On the other hand, in its calculation process, the building is no longer divided into a single thermal zone, but the space is divided into grids of appropriate sizes according to the building use requirements, and the thermal comfort conditions of each grid are judged, so as to capture the time-space changes of the indoor environment and solve the limitation of insufficient attention to the uneven distribution of the thermal environment in the indoor space in the current building design process.

[0005] However, in the current prediction process of spatial thermal autonomy, since traditional thermal comfort methods cannot comprehensively evaluate the actual thermal comfort experience, there is a large gap from the actual feelings of users. At the same time, the current calculation process does not consider the differences in personnel activity time, space, and thermal demand, and its error will accumulate continuously during the calculation process, resulting in a large error between the final result of the spatial thermal autonomy calculation and the actual situation. In addition, the calculation of spatial thermal autonomy requires hourly and grid-based spatial thermal environment simulation of the building throughout the year, with a huge amount of calculation. Conducting a single spatial thermal autonomy assessment of a building consumes a large amount of computing power and time, and it is very difficult to apply it to the optimization process of building design schemes.

[0006] Therefore, aiming at the problems of large prediction error, high computing power demand, and long time consumption of spatial thermal autonomy, it is urgent to develop a prediction model of building spatial thermal autonomy for actual use scenarios that can comprehensively evaluate thermal comfort. It can not only fully consider the thermal comfort needs of residents, broaden the thermal comfort range of residents, and improve their overall health level, but also achieve the accuracy and efficiency of building spatial thermal autonomy prediction. Summary of the Invention

[0007] The present invention aims to propose an optimized design method for building health performance based on spatial thermal autonomy. By integrating a comprehensive thermal comfort evaluation model into the calculation process, a comprehensive and overall evaluation of the thermal comfort of users is realized; at the same time, a spatio-temporal graph model is applied to train the prediction model of spatial thermal autonomy (sTA), combined with the activity rules of users, to accurately capture and analyze the dynamic characteristics of the indoor environment in the time dimension and spatial layout, and solve the problems of large prediction error and high computing power demand of current spatial thermal autonomy. The implementation of the present invention can greatly improve the efficiency and accuracy of building spatial thermal autonomy prediction, provide technical support for optimizing spatial thermal autonomy in the building design process, improve the passive design strategy of buildings, enhance the thermal regulation ability of buildings themselves, improve the living experience of residents, and at the same time save energy and reduce carbon, promoting the development of building design towards a more healthy, green, and efficient direction.

[0008] The present invention is realized through the following technical solutions. The present invention proposes an optimized design method for building health performance based on spatial thermal autonomy, and the method includes the following steps:

[0009] S1. Construction of a thermal comfort model combining multi-modal deep learning and fuzzy neural network;

[0010] The specific content of step S1 is as follows:

[0011] S1.1: Collection of regional personnel physiological indicators based on high-precision physiological sensing technology and construction of a database;

[0012] S1.2: Construction of a database for integrating subjective and objective perceptions of regional personnel's emotions, cognitive states, and thermal sensations;

[0013] S1.3: Construction of a regional climate time series prediction model based on multi-sensor fusion data;

[0014] S1.4: Collection of indoor thermal environment parameters of typical regional buildings;

[0015] S1.5: Construction of a thermal comfort model for comprehensive indicators of regional personnel based on multi-modal data;

[0016] S2: Construction of a building indoor thermal environment - heat demand prediction model based on a spatio-temporal graph convolutional network;

[0017] The specific steps of step S2 are as follows:

[0018] S2.1: Construction of a spatio-temporal thermal environment dataset for typical regional buildings;

[0019] S2.2: Collection and dataset construction of regional personnel behavior - heat demand;

[0020] S2.3: Feature extraction and preprocessing of multi-dimensional data driven by deep learning;

[0021] S2.4: Training of a building indoor spatio-temporal thermal environment - heat demand prediction model based on a spatio-temporal graph convolutional network;

[0022] S3: Construction of a building space thermal autonomy prediction model based on a spatio-temporal Transformer;

[0023] The specific steps of step S3 are as follows:

[0024] S3.1: Construction of a dataset for building space thermal autonomy;

[0025] S3.2: Concatenation of time encoding and space encoding with input features;

[0026] S3.3: Training of a space thermal autonomy prediction model based on a spatio-temporal Transformer;

[0027] S3.4: Performance verification of the space thermal autonomy prediction model.

[0028] Further, in step S1.2, based on the data collected by the recording device and the near-infrared brain functional imaging device, through language feature recognition tools, time series analysis, frequency domain analysis, event-related analysis, and optical path correction algorithms, analyze the language expression and brain activity status of regional personnel under different seasons, usage scenarios, activity states, and thermal environment conditions, and combine the subjective thermal sensations, thermal comfort, relevant cognitive ability tests, and emotional states of the personnel collected through subjective questionnaires to establish a database of the thermal sensations and related emotional cognitive states of regional personnel.

[0029] Further, in step S1.5, based on the indoor and outdoor thermal environment conditions, physiological indicators, subjective thermal sensations, emotions, and cognitive states collected in the previous steps, construct a multi-modal dataset; apply a fuzzy logic system, and by defining fuzzy rules and membership functions, comprehensively analyze all thermal comfort-related indicators in the multi-modal data to establish a comprehensive index thermal comfort model for regional personnel, so as to achieve a comprehensive evaluation based on objective physiological and mental health data, cognitive abilities, and subjective evaluation data.

[0030] Further, the specific content of step S2.1 is as follows:

[0031] S2.1.1: Obtain the design parameters of typical regional buildings based on lidar;

[0032] S2.1.2: Construct a building form and energy consumption model;

[0033] S2.1.3: Simulate the spatial thermal environment parameters based on a high-performance computing (HPC) cluster.

[0034] Further, the specific content of step S2.2 is as follows:

[0035] S2.2.1: Conduct on-site collection of the behavior and physiological indicators of regional personnel;

[0036] S2.2.2: Conduct a clustering analysis of the behavior-thermal demand of regional personnel; specifically: conduct a clustering analysis on different behavior types of regional personnel, and combine physiological indicators to determine the thermal demand coefficients for different populations, different activity intensities, their physiological states, and clothing thermal resistance conditions;

[0037] S2.2.3: Establish a spatio-temporal mapping relationship between the behavior and thermal demand of regional personnel; specifically: correspond the time and space information of the occurrence of the behavior of regional personnel with the thermal demand coefficients to construct a spatio-temporal matrix of the behavior-thermal demand of regional personnel.

[0038] Further, the step S2.4 is specifically as follows: Based on the dataset, a spatio-temporal graph convolutional network is applied to construct a building indoor spatio-temporal thermal environment-thermal demand prediction model. The building floor plan is transformed into a graph structure, with grids as nodes to describe the topological structure of the space. At the same time, the thermal demand, activities, and number of people at each node at different times are used as features for convolutional processing in the time dimension.

[0039] Further, the step S3.1 is specifically as follows:

[0040] S3.1.1: Obtaining the building indoor spatio-temporal thermal environment-thermal demand dataset;

[0041] S3.1.2: Predicting the building indoor spatio-temporal thermal comfort index;

[0042] S3.1.3: Calculating the thermal autonomy of the building indoor space.

[0043] Further, the step S3.3 is specifically as follows: Based on the time-space distribution data of the building indoor space thermal environment parameters and the thermal demand of people, combined with the spatio-temporal Transformer model, a building indoor space thermal autonomy prediction model is constructed; through the multi-head attention mechanism, spatial attention is used to capture the heat conduction in space, time attention is used to model the impact of daily and seasonal changes on the thermal environment and people's behavior, and for each time step, a space-time attention matrix is used to capture the correlation of each spatio-temporal position.

[0044] The present invention also proposes an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the building health performance optimization design method based on spatial thermal autonomy are implemented.

[0045] The present invention also proposes a computer-readable storage medium for storing computer instructions, and when the computer instructions are executed by a processor, the steps of the building health performance optimization design method based on spatial thermal autonomy are implemented.

[0046] Compared with the prior art, the beneficial effects of the present invention are:

[0047] The present invention provides an optimized design method for building health performance based on spatial thermal autonomy, aiming to improve the prediction efficiency and accuracy of the spatial thermal autonomy of buildings, realize the optimized iteration of the spatial thermal autonomy of buildings during the building design process, thereby expanding the scope of buildings regulated by passive methods, and improving the energy efficiency of buildings while optimizing the thermal comfort performance of buildings. Through the improvement of the thermal comfort evaluation model, the present invention can more comprehensively and accurately reflect the thermal comfort requirements of residents in different regions, different climates, and different age groups, and expand the temperature range of building thermal comfort; by applying the spatio-temporal graph model, it is possible to more efficiently predict the thermal environment, thermal demand distribution of buildings and calculate the spatial thermal autonomy of buildings, so that building schemes can better identify, utilize or improve thermal non-uniformity, thereby effectively reducing local thermal discomfort and overall improving the thermal comfort performance.

[0048] By applying the design method of the present invention, building schemes can foresee and optimize the performance of buildings in different thermal environments during the design stage. By promoting the adoption of passive design strategies (such as improving building envelopes, sunshade design, rationalizing spatial layouts, etc.), the dependence on active temperature control systems such as traditional air conditioners can be reduced, the energy consumption of building thermal environment regulation can be effectively reduced, the energy performance of buildings can be optimized, and the long-term adaptability and climate resilience of buildings can be improved. With the rapid development and popularization of the Internet of Things and smart homes, the present invention can further optimize building design schemes by combining the advantages of local thermal environment regulation of personal comfort systems, and promote the development of buildings towards a more sustainable, intelligent and adaptable direction. Brief Description of the Drawings

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0050] Figure 1 It is a flowchart of an optimized design method for building health performance based on spatial thermal autonomy described in the present invention. Detailed Embodiments

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the 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. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0052] Combined with Figure 1, the present invention proposes an optimized design method for building health performance based on spatial thermal autonomy, and the method includes the following steps:

[0053] S1. Construction of a thermal comfort model combining multi-modal deep learning and fuzzy neural network;

[0054] The specific content of step S1 is as follows:

[0055] S1.1: Collection of regional personnel's physiological indicators based on high-precision physiological sensing technology and construction of a database;

[0056] S1.2: Construction of a database for regional personnel's emotions, cognitive states, and thermal sensations by integrating subjective and objective perceptions; In step S1.2, based on the data collected by recording devices and near-infrared functional brain imaging (fNIRS) devices, through language feature recognition tools, time series analysis, frequency domain analysis, event-related analysis, and optical path correction algorithms, analyze the language expressions and brain activity states of regional personnel under different seasons, usage scenarios, activity states, and thermal environment conditions, and combine the subjective thermal sensations, thermal comfort, relevant cognitive ability tests, and emotional states of the personnel collected through subjective questionnaires to establish a database for regional personnel's thermal sensations and their related emotional and cognitive states;

[0057] S1.3: Construction of a regional climate time series prediction model based on multi-sensor fusion data;

[0058] S1.4: Collection of indoor thermal environment parameters of regional typical buildings;

[0059] S1.5: Construction of a comprehensive index thermal comfort model for regional personnel based on multi-modal data; In step S1.5, based on the indoor and outdoor thermal environment conditions, physiological indicators, subjective thermal sensations, emotions, and cognitive states collected in the previous steps, construct a multi-modal data set; Apply a fuzzy logic system, and by defining fuzzy rules and membership functions, comprehensively analyze all thermal comfort-related indicators in the multi-modal data to establish a comprehensive index thermal comfort model for regional personnel, so as to achieve a comprehensive evaluation based on objective physiological-mental health data, cognitive ability, and subjective evaluation data;

[0060] S2. Construction of a building indoor thermal environment-thermal demand prediction model based on a spatio-temporal graph convolutional network;

[0061] The specific content of step S2 is as follows:

[0062] S2.1: Construction of a spatio-temporal thermal environment data set for regional typical buildings; The specific content of step S2.1 is as follows:

[0063] S2.1.1: Obtaining the design parameters of regional typical buildings based on lidar;

[0064] S2.1.2: Construction of a building form and energy consumption model;

[0065] S2.1.3: Simulation of Spatial Thermal Environment Parameters Based on High-Performance Computing (HPC) Cluster;

[0066] S2.2: Collection of Regional Human Behavior-Thermal Demand and Construction of Dataset; The specific steps of S2.2 are as follows:

[0067] S2.2.1: On-site Collection of Regional Human Behavior and Physiological Indexes;

[0068] S2.2.2: Cluster Analysis of Regional Human Behavior-Thermal Demand; Specifically: Conduct cluster analysis on different behavior types of regional people, and determine the thermal demand coefficient for different populations, different activity intensities, their physiological states, and clothing thermal resistance conditions in combination with physiological indexes;

[0069] S2.2.3: Establishment of Spatiotemporal Mapping Relationship between Regional Human Behavior and Thermal Demand; Specifically: Correlate the time and space information of the occurrence of regional human behavior with the thermal demand coefficient, and construct a spatiotemporal matrix of regional human behavior-thermal demand;

[0070] S2.3: Feature Extraction and Preprocessing of Multidimensional Data Driven by Deep Learning;

[0071] S2.4: Training of Building Indoor Spatiotemporal Thermal Environment-Thermal Demand Prediction Model Based on Spatiotemporal Graph Convolutional Network; The specific steps of S2.4 are as follows: On the basis of the dataset, apply the Spatiotemporal Graph Convolutional Networks (ST-GCN) to construct a building indoor spatiotemporal thermal environment-thermal demand prediction model, convert the building floor plan into a graph structure, with grids as nodes to describe the topological structure of the space, and at the same time take the thermal demand, activities, and number of people at each node at different times as features for convolutional processing in the time dimension;

[0072] S3. Construction of Building Space Thermal Autonomy Prediction Model Based on Spatiotemporal Transformer (ST-Transformer);

[0073] The specific steps of S3 are as follows:

[0074] S3.1: Construction of Building Space Thermal Autonomy Dataset; The specific steps of S3.1 are as follows:

[0075] S3.1.1: Acquisition of Building Indoor Spatiotemporal Thermal Environment-Thermal Demand Dataset;

[0076] S3.1.2: Prediction of Building Indoor Spatiotemporal Thermal Comfort Index;

[0077] S3.1.3: Calculation of Building Indoor Space Thermal Autonomy;

[0078] S3.2: Concatenate the time encoding and spatial encoding with the input features;

[0079] S3.3: Train a spatial thermal autonomy prediction model based on the Spatio-Temporal Transformer (ST-Transformer); The specific steps of S3.3 are as follows: Based on the time-space distribution data of the indoor spatial thermal environment parameters and the thermal demands of the occupants in the building, combined with the Spatio-Temporal Transformer model, construct a prediction model for the indoor spatial thermal autonomy of the building; Through the multi-head attention mechanism, use spatial attention to capture the heat conduction in space, use temporal attention to model the impact of daily and seasonal variations on the thermal environment and the occupants' behavior, and for each time step, use the spatio-temporal attention matrix to capture the correlations at each spatio-temporal position;

[0080] S3.4: Verify the performance of the spatial thermal autonomy prediction model.

[0081] Embodiment

[0082] The present invention is described in detail below in conjunction with specific embodiments:

[0083] According to Figure 1 As shown, the present invention provides an optimization design method for the building health performance based on spatial thermal autonomy, including the following steps:

[0084] Step 1: Construct a thermal comfort model combining multi-modal deep learning and fuzzy neural network;

[0085] The specific steps of Step 1 are as follows:

[0086] Step 1.1: Collect the physiological indicators of the local population based on high-precision physiological sensing technology and construct a database;

[0087] Step 1.2: Integrate the subjective and objective perceptions to construct a database of the local population's emotions, cognitive states, and thermal sensations;

[0088] Step 1.3: Construct a time series prediction model for the local climate based on multi-sensor fusion data;

[0089] Step 1.4: Collect the indoor thermal environment parameters of typical local buildings;

[0090] Step 1.5: Construct a thermal comfort model for the comprehensive indicators of the local population based on multi-modal data;

[0091] The specific steps of Step 1.1 are as follows:

[0092] First, determine the climate zone where the building is located. The division of climate zones is based on the climate characteristics of the region where the building is located to ensure effective optimization of building design for different climate conditions. After determining the climate zone, next, according to the age structure distribution of local residents, representative subjects of each age group are selected for physiological data collection. To ensure the representativeness and scientific nature of the sampling, the present invention adopts a random sampling method, randomly selecting eligible subjects from each age group and inviting them to participate in data collection. This step ensures that the subject group is widely representative in terms of age structure and can accurately reflect the physiological response differences of people of different age groups to the indoor thermal environment.

[0093] During the physiological data collection process, a portable physiological collection device is used for real-time monitoring. This device can continuously record multiple physiological parameters of the subjects, including but not limited to: skin temperature, heart rate, skin conductivity, and respiratory rate, etc. The collection of these physiological data covers the seasonal changes throughout the year to comprehensively evaluate the impact of seasonal climate changes on the human body and ensure the comprehensiveness and representativeness of the data. The physiological data is monitored in real time through sensors and time series analysis is carried out to evaluate the immediate impact of the thermal environment on physiological responses. The collected physiological data will be used to establish a physiological database of regional personnel, which contains the physiological response data of people in different climate regions and different age groups. Through long-term monitoring and data accumulation, it can provide a scientific basis for subsequent building design and help better optimize thermal comfort and energy efficiency.

[0094] The specific content of step 1.2 is as follows:

[0095] In step S1.2, based on the data collected by the recording device and the near-infrared functional brain imaging (fNIRS) device, through language emotion recognition tools such as OpenSMILE, time series analysis, frequency domain analysis, event-related analysis, and optical path correction algorithms, the facial expressions, language expressions, and brain activity states of regional personnel under different seasons, usage scenarios, and thermal environment conditions are analyzed to evaluate their emotional states and cognitive abilities. Specifically, the recording device is used to record the language expressions of the subjects in the thermal environment, and the emotional analysis of the voice signals is carried out through the OpenSMILE tool to evaluate the language emotion changes of the subjects; the near-infrared functional brain imaging device is used to monitor the brain activity states of the subjects in the thermal environment, combined with electroencephalogram analysis and cerebral blood flow change data, and time series analysis and frequency domain analysis methods are used to evaluate the cognitive states and mental loads of the subjects; at the same time, event-related analysis technology is applied to analyze the response patterns of the subjects to thermal environment changes to further confirm the relationship between their emotional fluctuations and cognitive changes.

[0096] In addition, data is collected through a combination of on-site surveys and online questionnaires. Analysts conduct subjective thermal sensation, thermal comfort, relevant cognitive ability tests, and emotion questionnaires under different thermal environment conditions. Specifically, when implementing, a multi-dimensional questionnaire is designed and distributed, including the thermal sensation of the subjects under different thermal environments, self-evaluation of thermal comfort, evaluation of work efficiency, and emotional state, etc., to evaluate the adaptability of the subjects to the current environment. Combined with cognitive ability tests (such as reaction time, memory, attention concentration, etc.), the impact of the thermal environment on the thinking and attention of the subjects is further analyzed; at the same time, the fatigue of the subjects is investigated to evaluate the physiological and psychological fatigue conditions that may be caused by long-term exposure to a specific thermal environment. Through the integration of the above multiple data sources, a database of thermal sensation and related emotional cognitive states of regional personnel is finally constructed, providing scientific data support for the subsequent personalized thermal comfort prediction model.

[0097] Specifically, step 1.3 is as follows:

[0098] In step S1.3, based on the data collected by the multi-sensor fusion technology, devices such as temperature sensors, humidity sensors, wind speed sensors, and radiant temperature sensors are used to collect the outdoor thermal environment data of the region. Specifically, the temperature sensor is used to collect the air temperature data in the environment in real time, the humidity sensor is used to monitor the change of air humidity, the wind speed sensor is used to detect the fluctuation of wind speed, and the radiant temperature sensor is used to obtain the distribution of radiant heat energy. These data will jointly reflect the current thermal environment state of the region. By fusing these different types of sensor data and using the multi-sensor data fusion algorithm for data preprocessing, noise filtering, and signal integration, high-precision environmental parameter data can be obtained.

[0099] Next, a time series data prediction algorithm is constructed using the combined autoregressive integrated moving average (ARIMA) model, long short-term memory network (LSTM), and convolutional neural network (CNN). Specifically, when implementing, the ARIMA model is used to model the long-term trend of environmental data and identify and fit the long-term change laws of variables such as regional temperature, humidity, wind speed, and radiation; the LSTM network is used to capture the long-term dependencies in time series data, which is particularly suitable for predicting the dynamic changes of climate data; the CNN is used to extract the local features in multi-dimensional sensor data to further optimize the prediction accuracy of the model. By combining these three methods, the constructed regional climate model can efficiently perform deep learning and analysis on multi-dimensional environmental variables, thereby predicting the thermal environment changes under different seasons and climate conditions.

[0100] By analyzing the changing trends of environmental variables such as regional temperature, humidity, wind speed, and radiation, and combining ARIMA's modeling of long-term trends, CNN's extraction of local features, and LSTM's capture of long-term dependencies, this model can accurately predict the changes in the thermal environment over a period of time in the future. Finally, the predicted results output by the model will be used to provide accurate regional climate predictions to assist in making decisions for thermal environment control and optimization.

[0101] The specific content of step 1.5 is as follows:

[0102] In step S1.5, first, collect data on people's subjective thermal sensations, thermal comfort, cognitive ability tests, and emotional responses in different seasons and usage scenarios, combine them with indoor and outdoor thermal environment data (temperature, humidity, wind speed, etc.) at corresponding moments, and use an integrated multi-input system to standardize the data so that data in different dimensions (such as body temperature, emotion, cognitive ability, etc.) are in the same dimension. Then, according to the characteristics of the input variables, define fuzzy sets and define a membership function for each fuzzy set to represent the membership degree of each input variable. Next, construct fuzzy rules based on empirical data and distinguish the differences in thermal demands in different activity situations, and different fuzzy logics need to be applied. Finally, use the Mamdani inference method to derive the fuzzy results of the output variables to obtain a comprehensive thermal comfort index (Comprehensive Comfort Index, CCI).

[0103] Step 2: Construction of a building indoor thermal environment-thermal demand prediction model based on a spatio-temporal graph convolutional network;

[0104] The specific content of step 2 is as follows:

[0105] Step 2.1: Construction of a spatio-temporal thermal environment dataset for typical regional buildings;

[0106] Step 2.2: Collection of regional personnel behavior-thermal demand and construction of a dataset;

[0107] Step 2.3: Deep learning-driven multi-dimensional data feature extraction and preprocessing;

[0108] Step 2.4: Training of a building indoor spatio-temporal thermal environment-thermal demand prediction model based on a spatio-temporal graph convolutional network.

[0109] The specific content of step 2.1 is as follows:

[0110] Step 2.1.1: Obtaining design parameters of typical regional buildings based on lidar;

[0111] Step 2.1.2: Construction of a building form and energy consumption model;

[0112] Step 2.1.3: Simulation of spatial thermal environment parameters based on a high-performance computing (HPC) cluster;

[0113] The specific content of Step 2.1.1 is as follows:

[0114] Apply lidar technology to obtain typical building design parameters of the region. Scan and collect data on the building's exterior facade, spatial structure, and surrounding environment through lidar equipment, extract design parameters such as the geometric shape, dimensions, floor height, and window positions of the building, construct a dataset of typical building design parameters of the region based on this, and through data cleaning and standardization processing, ensure the accuracy and consistency of the building design parameters.

[0115] The specific content of Step 2.2 is as follows:

[0116] Step 2.2.1: On-site collection of regional personnel behavior and physiological indicators;

[0117] Step 2.2.2: Cluster analysis of regional personnel behavior-thermal demand;

[0118] Step 2.2.3: Establishment of the spatio-temporal mapping relationship between regional personnel behavior and thermal demand;

[0119] The specific content of Step 2.2.1 is as follows:

[0120] On-site collect the personnel behavior, clothing wearing conditions, and their physiological indicators (respiration rate and heart rate) of typical buildings in the region throughout the year, and mark the data according to time and space.

[0121] The specific content of Step 2.2.2 is as follows:

[0122] Based on the respiration rate and heart rate, calculate the metabolic rate under different behaviors and clothing wearing conditions, and conduct cluster analysis on it, corresponding different behaviors and clothing wearing conditions to a thermal demand index.

[0123] The specific content of Step 2.2.3 is as follows:

[0124] Correspond the time and space information of the occurrence of regional personnel behavior with the thermal demand coefficient to construct a spatio-temporal matrix of regional personnel behavior-thermal demand.

[0125] Step 2.3 is specifically as follows: Based on the type of input data, technologies such as normalization processing, time series analysis, and convolutional neural networks are applied to construct preprocessing schemes for different types of data, obtaining optimized building design parameters and building floor plan data. Among them, for building design parameters, normalization processing is applied and combined with feature selection methods to remove low-correlation or redundant features, obtaining effective design parameter data. For building floor plans, the floor plans are converted into image data, and convolutional neural networks (CNNs) are used for feature extraction. The CNN model automatically extracts spatial features in the floor plan, such as the shapes, sizes, and positions of different areas such as rooms, corridors, and windows. If the building floor plan is relatively complex or the image data is relatively limited, an image segmentation model can be used to segment different areas to clarify the boundaries of each spatial area in the building.

[0126] Step 2.4 is specifically as follows: Based on the dataset, spatio-temporal graph convolutional networks (ST-GCN) are applied to construct a building indoor spatio-temporal thermal environment-thermal demand prediction model. The building floor plan is converted into a graph structure, with grids as nodes to describe the topological structure of the space. At the same time, the thermal demand, activities, and number of people at each node at different times are used as features for convolutional processing in the time dimension.

[0127] Step 3: Construction of a building space thermal autonomy prediction model based on spatio-temporal Transformer;

[0128] Step 3 is specifically as follows:

[0129] Step 3.1: Construction of a building space thermal autonomy dataset;

[0130] Step 3.2: Concatenation of time encoding, space encoding, and input features;

[0131] Step 3.3: Training of a space thermal autonomy prediction model based on spatio-temporal Transformer (ST-Transformer);

[0132] Step 3.4: Verification of the performance of the space thermal autonomy prediction model.

[0133] Step 3.1 is specifically as follows:

[0134] Step 3.1.1: Acquisition of a building indoor spatio-temporal thermal environment-thermal demand dataset;

[0135] Step 3.1.2: Prediction of building indoor spatio-temporal thermal comfort index;

[0136] Step 3.1.3: Calculation of building indoor space thermal autonomy.

[0137] Step 3.1.1 is specifically as follows:

[0138] Substitute the typical building design parameters of different functional types in different regions into the building indoor spatio-temporal thermal environment-thermal demand prediction model obtained in Step 2.4 to obtain the building indoor thermal environment-thermal demand spatio-temporal distribution matrix.

[0139] Step 3.1.2 is specifically as follows:

[0140] Substitute the thermal environment parameter characteristics and thermal demand coefficient characteristics in the building indoor thermal environment-thermal demand spatio-temporal distribution matrix into the comprehensive thermal comfort model in Step 1.5 to obtain the building indoor thermal comfort spatio-temporal distribution matrix.

[0141] Step 3.1.3 is specifically as follows:

[0142] Calculate the spatial thermal autonomy according to the hourly thermal comfort situation of grid points. The spatial thermal autonomy is defined as "the percentage of the building area where the hot zone reaches or exceeds the given thermal comfort standard only through passive means", and the spatial thermal autonomy index sTA per hour t , and the calculation formula is as follows:

[0143]

[0144] where A i is the local area of the space represented by grid point i, with the unit of m 2 ; 1 {i∈comfort} is an indicator function, which is equal to 1 if grid point i meets the comfort standard, otherwise 0; A total is the total area of the space, with the unit of m 2 .

[0145] Then calculate the annual spatial thermal autonomy sTA annual , and the calculation formula is:

[0146]

[0147] where τ comfort is the hourly spatial comfort threshold, representing the minimum floor area percentage (or grid point i) that must meet the defined comfort standard for a given area to be considered thermally autonomous at time t; is 1 if the hourly spatial thermal autonomy sTA t is greater than or equal to τ comfort at time t, otherwise 0; T year is the total number of hours in a year (usually 8760h for non-leap years).

[0148] Step 3.2 is specifically as follows:

[0149] Spatial and temporal information is introduced by performing positional encoding on the model input dataset (thermal environment parameters, heat demand coefficients, etc.). Sine-cosine encoding is used to represent time to ensure that the model can recognize the order of time, and spatial coordinates are used to assign a positional encoding to each spatial point.

[0150] Step 3.3 is specifically as follows:

[0151] Based on the time - space distribution data of the indoor thermal environment parameters and the heat demand of the building occupants, combined with the spatio - temporal Transformer model, a prediction model for the thermal autonomy of the indoor space of the building is constructed. First, the Transformer architecture is designed. Through the multi - head attention mechanism, spatial attention is used to capture the heat conduction in space, and temporal attention is used to model the impact of daily and seasonal variations on the thermal environment and the behavior of the occupants. For each time step, a spatio - temporal attention matrix is used to capture the correlation of each spatio - temporal position. Finally, a fully connected layer is applied to map the output of the model to the prediction target - spatial thermal autonomy.

[0152] Step 3.4 is specifically as follows:

[0153] During the training process, the mean squared error (MSE) loss is used to measure the difference between the predicted annual thermal comfort ratio of the model and the true value, and the Adam optimizer is used to train the model, continuously adjusting hyperparameters such as the learning rate to improve the prediction accuracy of the model.

[0154] The present invention also proposes an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method for optimizing the building health performance based on spatial thermal autonomy are implemented.

[0155] The present invention also proposes a computer - readable storage medium for storing computer instructions, and when the computer instructions are executed by a processor, the steps of the method for optimizing the building health performance based on spatial thermal autonomy are implemented.

[0156] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DRRAM). It should be noted that the memory of the method described in the present invention is intended to include but not limited to these and any other suitable types of memories.

[0157] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a high-definition digital video disc (DVD)), or a semiconductor medium (such as a solid state disc (SSD)), etc.

[0158] In the implementation process, the steps of the above method can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware processor, or executed and completed by a combination of the hardware and software modules in the processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0159] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiments can be completed by the integrated logic circuit in the hardware of the processor or instructions in the form of software. The above-mentioned processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0160] The above has introduced in detail a method for optimizing the building health performance design based on spatial thermal autonomy proposed by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A building health performance optimization design method based on spatial thermal autonomy, characterized in that: The method comprises the following steps: S1. Construction of thermal comfort model combining multimodal deep learning and fuzzy neural network; The step S1 is specifically as follows: S1.1: Collection of regional personnel’s physiological indicators and database construction based on high-precision physiological sensing technology; S1.2: Construction of a database of regional personnel’s emotions, cognitive states, and thermal sensations that integrates subjective and objective perceptions; S1.3: Construction of regional climate time series prediction model based on multi-sensor fusion data; S1.4: Collection of indoor thermal environment parameters of typical buildings in the region; S1.5: Construction of a comprehensive thermal comfort model for regional personnel based on multimodal data; S2. Construction of building indoor thermal environment-heat demand prediction model based on spatiotemporal graph convolutional network; The step S2 is specifically as follows: S2.1: Construction of a spatiotemporal thermal environment dataset of typical buildings in the region; S2.2: Regional personnel behavior-heat demand collection and data set construction; S2.3: Deep learning driven multi-dimensional data feature extraction and preprocessing; S2.4: Training of indoor spatiotemporal thermal environment-heat demand prediction model for buildings based on spatiotemporal graph convolutional network; S3, Construction of a prediction model for thermal autonomy of building space based on spatiotemporal Transformer; The step S3 is specifically as follows: S3.1: Construction of a dataset on thermal autonomy of building spaces; S3.2: Temporal encoding and spatial encoding and input feature concatenation; S3.3: Spatial thermal autonomy prediction model training based on spatiotemporal Transformer; S3.4: Verification of spatial thermal autonomy prediction model performance.

2. The method according to claim 1, characterized in that In step S1.2, based on the data collected by the recording equipment and near-infrared brain functional imaging equipment, the language expression and brain activity status of the regional personnel under different seasons, usage scenarios, activity status and thermal environment conditions are analyzed through language feature recognition tools, time series analysis, frequency domain analysis, event correlation analysis and optical path correction algorithm. Combined with the subjective thermal sensation, thermal comfort, related cognitive ability test and emotional state of the personnel under different thermal environment conditions collected through subjective questionnaire surveys, a database of thermal sensation and related emotional cognitive state of regional personnel is established.

3. The method according to claim 1, characterized in that In step S1.5, a multimodal data set is constructed based on the indoor and outdoor thermal environment conditions, physiological indicators, subjective thermal perception, emotions and cognitive states collected in the previous steps; a fuzzy logic system is applied to comprehensively analyze all thermal comfort-related indicators in the multimodal data by defining fuzzy rules and membership functions, and a comprehensive indicator thermal comfort model for regional personnel is established to achieve a comprehensive evaluation based on objective physiological and psychological health data, cognitive ability, and subjective evaluation data.

4. The method according to claim 1, characterized in that: The step S2.1 is specifically as follows: S2.1.1: Acquisition of typical regional building design parameters based on LiDAR; S2.1.2: Construction of building form and energy consumption model; S2.1.3: Simulation of spatial thermal environment parameters based on high performance computing (HPC) cluster.

5. The method according to claim 1, characterized in that The step S2.2 is specifically as follows: S2.2.1: On-site collection of behavioral and physiological indicators of regional personnel; S2.2.2: Cluster analysis of regional personnel behavior-thermal demand; specifically: cluster analysis of different behavior types of regional personnel, and determine the thermal demand coefficient for different groups of people, different activity intensities, their physiological states and clothing thermal resistance conditions in combination with physiological indicators; S2.2.3: Establish the spatial-temporal mapping relationship between regional personnel behavior and heat demand; specifically: correspond the time and space information of regional personnel behavior with the heat demand coefficient, and construct the spatial-temporal matrix of regional personnel behavior-heat demand.

6. The method according to claim 1, characterized in that The step S2.4 is specifically as follows: based on the data set, a spatiotemporal graph convolutional network is used to construct a building indoor spatiotemporal thermal environment-heat demand prediction model, the building floor plan is converted into a graph structure, the grid is used as a node, the topological structure of the space is described, and the heat demand, activity, and number of people of each node at different times are used as features to perform convolution processing on the time dimension.

7. The method according to claim 1, characterized in that The step S3.1 is specifically as follows: S3.1.1: Acquisition of building indoor spatiotemporal thermal environment-heat demand dataset; S3.1.2: Prediction of indoor spatiotemporal thermal comfort index of buildings; S3.1.3: Calculation of thermal autonomy of building interior spaces.

8. The method according to claim 1, characterized in that The step S3.3 is specifically as follows: based on the time-space distribution data of the thermal environment parameters of the building's indoor space and the thermal demand of the personnel, combined with the spatiotemporal Transformer model, a thermal autonomy prediction model for the building's indoor space is constructed; through the multi-head attention mechanism, spatial attention is used to capture the heat conduction in space, and temporal attention is used to model the impact of daily and seasonal changes on the thermal environment and personnel behavior, and for each time step, the space-time attention matrix is ​​used to capture the correlation of each spatiotemporal position.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images