Building indoor overheating risk assessment and early warning method and device in heat waves

Abstract

The invention relates to the technical field of indoor thermal environment prediction, and discloses a building indoor overheating risk assessment and early warning method and device in heat waves, and the method comprises the steps: obtaining historical meteorological monitoring data, and screening the meteorological data of a heat wave event; building parameters of a plurality of preset building types are obtained, and a plurality of thermal environment model calculation parameter combinations are determined based on building parameter distribution and meteorological data of historical thermal wave events; performing simulation calculation on the thermal environment model to obtain a corresponding indoor thermal index; training a preset prediction model to obtain a prediction model; obtaining actual meteorological monitoring data and actual building parameters of the target area, and obtaining a predicted indoor thermal index by using the prediction model; and performing overheating risk assessment and early warning by using the predicted indoor heat index. According to the method, the thermal environment model is constructed by analyzing the historical heat wave events and the building parameters of different building types, the indoor environment overheating risk assessment and early warning are realized, and the speed and accuracy of indoor overheating risk prediction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of indoor thermal environment prediction, and particularly to a method and device for evaluating and warning the overheating risk in buildings during heatwaves. Background Art

[0002] In recent years, climate change has led to a significant increase in the frequency, intensity, and duration of high-temperature heatwave events. During heatwave events, the continuous abnormal high temperature will cause the indoor temperature of buildings to rise and the overheating risk to increase, increasing the risk to human health. In particular, the elderly, children, and residents who stay at home for a long time are more vulnerable to overheating. Early warning of the overheating risk in building interiors is an important technical means that can warn of the overheating risk in residential buildings by monitoring and predicting outdoor meteorological parameters in real time, improving the public's awareness of prevention and response capabilities.

[0003] Currently, some invention patents have studied the early warning of outdoor heatwave risks in buildings, and these studies mainly focus on the impact of outdoor climate characteristics on human comfort and health risks. For example, invention patent 202311200537.8 discloses a method for evaluating human comfort during heatwaves, which is mainly used to evaluate the impact of the outdoor thermal environment on human thermal comfort and health during heatwaves; invention patent 202410448494.3 discloses a health risk assessment method based on climate change, which is mainly used to evaluate the correlation between outdoor heatwaves, cold wave events, and health risks under future climate change scenarios. It can be seen that in the technical field of heatwave risk assessment, risk assessment methods for human thermal comfort or health have been mainly proposed for the outdoor thermal environment, and no methods and technical ideas suitable for evaluating and warning the overheating risk in buildings during heatwaves have been publicly available. Summary of the Invention

[0004] In view of this, the present invention provides a method and device for evaluating and warning the overheating risk in buildings during heatwaves to solve the problem that the prior art lacks the evaluation and warning of the overheating risk in buildings during heatwaves.

[0005] In a first aspect, the present invention provides a method for evaluating and warning the overheating risk in buildings during heatwaves, the method comprising:

[0006] Obtaining historical meteorological monitoring data of a target area at a preset sampling time interval, and screening out the meteorological data of historical heatwave events from the historical meteorological monitoring data;

[0007] Obtaining the building parameters of multiple preset building types respectively, and determining the calculation parameter combinations of multiple thermal environment models based on the meteorological data of historical heatwave events and the building parameters;

[0008] Construct corresponding thermal environment models according to the calculation parameter combinations of multiple thermal environment models, and perform simulation calculations on multiple thermal environment models based on the calculation parameter combinations of multiple thermal environment models to obtain corresponding indoor thermal indices;

[0009] Use the calculation parameter combinations of multiple thermal environment models as inputs and the corresponding indoor thermal indices as outputs to train a preset prediction model to obtain a trained prediction model;

[0010] Obtain the actual meteorological monitoring data and actual building parameters of the target area, and use the prediction model to predict the predicted indoor thermal index of the actual building parameters;

[0011] Use the predicted indoor thermal index to conduct overheating risk assessment and early warning according to the preset evaluation rules.

[0012] The method for assessing and warning the overheating risk of a building indoors during a heatwave provided by the present invention constructs a thermal environment model by analyzing historical heatwave events and building parameters of different building types, and trains a prediction model according to the thermal environment model, so as to realize the overheating risk assessment and early warning of the indoor environment, improve the speed of predicting the overheating risk of the indoor environment, and ensure high prediction accuracy.

[0013] In an alternative embodiment, obtain the historical meteorological monitoring data of the target area at a preset sampling time interval, and screen out the meteorological data of historical heatwave events from the historical meteorological monitoring data, including:

[0014] Continuously obtain historical meteorological monitoring data at a preset sampling time interval of one hour, and the historical meteorological monitoring data includes the outdoor air dry-bulb temperature;

[0015] Determine the daily maximum temperature according to the historical meteorological monitoring data, and screen out historical heatwave events according to the daily maximum temperature;

[0016] Obtain the meteorological data corresponding to the historical heatwave events from the historical meteorological monitoring data.

[0017] The method for assessing and warning the overheating risk of a building indoors during a heatwave provided by the present invention can obtain the weather conditions in different seasons by collecting long-term meteorological monitoring data. By obtaining the meteorological monitoring data every hour, the daily maximum temperature can be determined more accurately, so as to more reliably identify heatwave events and their corresponding meteorological data.

[0018] In an alternative embodiment, the building parameters include: building geometric parameters, envelope thermal parameters, building ventilation rate, indoor heat generation, and personnel and equipment work and rest.

[0019] In an alternative embodiment, determine the calculation parameter combinations of multiple thermal environment models based on the meteorological data and building parameters of heatwave events, including:

[0020] Determine the variation range and distribution of each building parameter according to the preset building parameter specifications;

[0021] Sample and combine each building parameter according to the variation range and distribution of each building parameter, and combine with the meteorological data of historical heat wave events to obtain the calculation parameter combinations of multiple thermal environment models.

[0022] The method for evaluating and warning the risk of overheating indoors in buildings during heat waves provided by the present invention combines the meteorological data of heat wave events with building parameters to construct a thermal environment model, which can accurately simulate the thermal performance of buildings under extreme high temperatures. By sampling and combining different building parameters and combining with the meteorological data of historical heat wave events, calculation parameter combinations of multiple thermal environment models are formed, which are more representative for reflecting urban residential building models.

[0023] In an optional implementation manner, perform simulation calculations on multiple thermal environment models based on the calculation parameter combinations of multiple thermal environment models to obtain the corresponding indoor thermal indices, including:

[0024] Based on the calculation parameter combinations of multiple thermal environment models, use building full-performance simulation software to perform thermal environment simulation on multiple thermal environment models, and calculate the indoor air temperature and indoor relative humidity corresponding to the thermal environment models;

[0025] Calculate the indoor thermal index according to the indoor air temperature and indoor relative humidity.

[0026] The method for evaluating and warning the risk of overheating indoors in buildings during heat waves provided by the present invention is based on multiple thermal environment models, uses building full-performance simulation software to simulate the indoor air temperature and relative humidity, and calculates the indoor thermal index. The thermal environment is calculated in the form of a thermal index, which can accurately evaluate the indoor thermal environment and intuitively reflect the thermal feeling of the occupants.

[0027] In an optional implementation manner, use the calculation parameter combinations of multiple thermal environment models as inputs and the corresponding indoor thermal indices as outputs to train a preset prediction model to obtain a trained prediction model, including:

[0028] Construct a preset prediction model using a machine learning algorithm, and use grid search and cross-validation to determine the hyperparameter value combination of the preset prediction model;

[0029] Use the calculation parameter combinations of multiple thermal environment models as inputs and the corresponding indoor thermal indices as outputs, and perform training and optimization on the preset prediction model based on the hyperparameter value combination to obtain a trained prediction model.

[0030] The method for evaluating and warning the overheating risk in a building interior during a heatwave provided by the present invention constructs a prediction model using a machine learning algorithm, and optimizes the hyperparameters through grid search and cross-validation, which can significantly improve the prediction accuracy, enhance the generalization ability of the model, reduce the computational cost, support real-time prediction and decision-making, and improve the accuracy and efficiency of prediction. The prediction model for the overheating risk in a residential building interior based on machine learning can also be used to determine the optimization strategy for improving measures for the overheating risk subsequently, and can combine with an optimization algorithm to quickly find the optimal improvement measures, so as to help designers clarify the severity of the overheating risk under different combinations of residential building parameters, and further improve the efficiency of the design work.

[0031] In an alternative embodiment, the overheating risk is evaluated and warned by using the predicted indoor heat index according to a preset evaluation rule, including:

[0032] Obtain a plurality of historical indoor heat indices, and divide the indoor thermal environment into a plurality of risk levels according to the plurality of historical indoor heat indices;

[0033] Determine the corresponding risk level according to the predicted indoor heat index, and issue a warning.

[0034] The method for evaluating and warning the overheating risk in a building interior during a heatwave provided by the present invention is beneficial to accurately evaluate the overheating risk of the indoor thermal environment by formulating the mapping relationship between the heat index and the risk level, and timely issue a warning to take measures to reduce the occurrence of potential safety hazards caused by indoor overheating.

[0035] In a second aspect, the present invention provides a device for evaluating and warning the overheating risk in a building interior during a heatwave, and the device includes:

[0036] A heatwave event screening module, configured to obtain historical meteorological monitoring data of a target area at a preset sampling time interval, and screen out the meteorological data of historical heatwave events from the historical meteorological monitoring data;

[0037] A thermal environment model construction module, configured to respectively obtain the building parameters of a plurality of preset building types, and determine the calculation parameter combinations of a plurality of thermal environment models based on the meteorological data and building parameters of historical heatwave events;

[0038] A simulation calculation module, configured to construct corresponding thermal environment models according to the calculation parameter combinations of a plurality of thermal environment models, and perform simulation calculations on the plurality of thermal environment models based on the calculation parameter combinations of the plurality of thermal environment models to obtain the corresponding indoor heat indices;

[0039] A model training module, configured to use the calculation parameter combinations of a plurality of thermal environment models as inputs and the corresponding indoor heat indices as outputs to train a preset prediction model to obtain a trained prediction model;

[0040] A heat index prediction module, configured to obtain the actual meteorological monitoring data and actual building parameters of a target area, and use a prediction model to perform prediction to obtain the predicted indoor heat index of the actual building parameters;

[0041] A risk assessment and early warning module, configured to perform overheating risk assessment and early warning according to a preset assessment rule by using the predicted indoor heat index.

[0042] In a third aspect, the present invention provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the method according to the first aspect or any corresponding embodiment thereof.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored. The computer instructions are used to cause a computer to execute the method according to the first aspect or any corresponding embodiment thereof. Description of the Drawings

[0044] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 is a schematic flowchart of a method for assessing and warning indoor overheating risk in a building during a heat wave according to an embodiment of the present invention;

[0046] Figure 2 is a schematic flowchart of another method for assessing and warning indoor overheating risk in a building during a heat wave according to an embodiment of the present invention;

[0047] Figure 3 is a schematic diagram of building types in a specific embodiment of a method for assessing and warning indoor overheating risk in a building during a heat wave according to an embodiment of the present invention;

[0048] Figure 4 is a schematic diagram of the accuracy of a prediction model in a specific embodiment of a method for assessing and warning indoor overheating risk in a building during a heat wave according to an embodiment of the present invention;

[0049] Figure 5 is a schematic diagram of prediction results in a specific embodiment of a method for assessing and warning indoor overheating risk in a building during a heat wave according to an embodiment of the present invention;

[0050] Figure 6It is a structural block diagram of a device for evaluating and warning of overheating risks in a building interior during a heatwave according to an embodiment of the present invention;

[0051] Figure 7 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed implementation manners

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. 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.

[0053] The embodiments of the present invention provide a method and device for evaluating and warning of overheating risks in a building interior during a heatwave. By analyzing historical heatwave events and building parameters of different building types, a thermal environment model is constructed, and a prediction model is trained according to the thermal environment model to achieve overheating risk assessment and warning of the indoor environment, improve the speed of overheating risk prediction in the interior, and ensure a high prediction accuracy.

[0054] According to an embodiment of the present invention, an embodiment of a method for evaluating and warning of overheating risks in a building interior during a heatwave is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0055] In this embodiment, a method for evaluating and warning of overheating risks in a building interior during a heatwave is provided, which can be used in the above computer system. Figure 1 It is a flowchart of a method for evaluating and warning of overheating risks in a building interior during a heatwave according to an embodiment of the present invention. As Figure 1 shown, the process includes the following steps:

[0056] Step S101, obtain historical meteorological monitoring data of a target area at a preset sampling time interval, and screen out meteorological data of historical heatwave events from the historical meteorological monitoring data.

[0057] Specifically, the meteorological monitoring data includes but is not limited to: outdoor air dry-bulb temperature, relative humidity, total solar radiation on a horizontal plane, wind speed, wind direction, and atmospheric pressure. The acquisition methods of each data are mature existing technologies and will not be elaborated here. The historical meteorological monitoring data can be for ten consecutive years or twenty consecutive years, and the preset sampling time interval can be one hour, two hours, just as an example, but not limited thereto.

[0058] Based on long-term meteorological monitoring data, historical heatwave events are identified. A heatwave event refers to a situation where the weather continuously remains excessively hot and may be accompanied by high humidity. Heatwave events are usually associated with regions. A temperature that is normal for a hotter climate region may be a heatwave for a region that is usually colder. Heatwave events can lead to heat-related deaths, especially the elderly are more vulnerable.

[0059] Step S102: Obtain the building parameters of multiple preset building types respectively, and determine the calculation parameter combinations of multiple thermal environment models based on the meteorological data and building parameters of historical heatwave events.

[0060] Specifically, the preset building types can be selected as typical residential building types, including but not limited to: townhouses (1 - 3 floors), multi-story slab buildings (4 - 6 floors), high-rise slab buildings (>7 floors), high-rise tower buildings (>7 floors), and other types.

[0061] To numerically represent the preset building types, it is necessary to obtain the building parameters of each preset building type and determine the calculation parameter combinations of multiple thermal environment models based on the meteorological data and building parameters of historical heatwave events. This is equivalent to placing different types of buildings in the environments of different heatwave events to form the input parameters of the thermal environment models.

[0062] Step S103: Construct the corresponding thermal environment models according to the calculation parameter combinations of multiple thermal environment models, and perform simulation calculations on multiple thermal environment models based on the calculation parameter combinations of multiple thermal environment models to obtain the corresponding indoor thermal indices.

[0063] Specifically, using building performance simulation software, construct multiple thermal environment models based on long-term meteorological monitoring data and the calculation parameter combinations of the thermal environment models of typical residential buildings, and perform thermal environment simulation calculations in the simulation software to obtain the corresponding indoor thermal indices. Representing the indoor thermal environment state with specific numerical values facilitates the subsequent judgment of overheating risks.

[0064] Step S104: Use the calculation parameter combinations of multiple thermal environment models as inputs and the corresponding indoor thermal indices as outputs to train the preset prediction model to obtain the trained prediction model.

[0065] Specifically, a machine learning algorithm can be used to construct a preset prediction model. The thermal environment model of a typical residential building and the corresponding indoor thermal index are used as training samples to train the preset prediction model, and a trained prediction model is obtained for predicting the indoor overheating risk. The input feature variables of the preset prediction model include: meteorological parameters such as hourly outdoor dry-bulb temperature and relative humidity in the thermal environment model, as well as building characteristic parameters such as residential building type, window-wall ratio, exterior wall heat transfer coefficient, exterior window heat transfer coefficient, roof heat transfer coefficient, solar heat gain coefficient of the exterior window, and building ventilation rate. The input prediction variable includes: hourly indoor thermal index.

[0066] Step S105, obtain the actual meteorological monitoring data and actual building parameters of the target area, and use the prediction model to predict the predicted indoor thermal index of the actual building parameters.

[0067] Specifically, in actual applications, when predicting the overheating risk of a target area, directly obtain the actual meteorological monitoring data of the target area and the actual building parameters corresponding to the target building, and input them into the prediction model to predict the predicted indoor thermal index corresponding to the target building.

[0068] Step S106, use the predicted indoor thermal index to conduct overheating risk assessment and early warning according to the preset evaluation rules.

[0069] Specifically, use the prediction model to predict the indoor overheating risk of different residential buildings during a heatwave. The input variables include the hourly dry-bulb temperature and relative humidity given by the weather forecast, as well as the information of the residential building to be predicted. Use the trained prediction model to predict the hourly indoor thermal index of the building to be predicted for the next day, and based on the prediction results, evaluate the indoor overheating risk level of the building for the next day and issue an early warning.

[0070] The method for assessing and warning indoor overheating risk in a building during a heatwave provided in this embodiment constructs a thermal environment model by analyzing historical heatwave events and building parameters of different building types, and trains a prediction model according to the thermal environment model, realizing overheating risk assessment and early warning of the indoor environment, improving the speed of indoor overheating risk prediction, and ensuring high prediction accuracy.

[0071] In this embodiment, a method for assessing and warning indoor overheating risk in a building during a heatwave is provided, which can be used in the above computer system. Figure 2 It is a flowchart of the method for assessing and warning indoor overheating risk in a building during a heatwave according to an embodiment of the present invention, as Figure 2 shown, and this process includes the following steps:

[0072] Step S201, obtain the historical meteorological monitoring data of the target area at a preset sampling time interval, and screen out the meteorological data of historical heatwave events from the historical meteorological monitoring data.

[0073] Specifically, the above-mentioned step S201 includes:

[0074] Step S2011: Continuously obtain historical meteorological monitoring data at a preset sampling time interval of one hour. The historical meteorological monitoring data includes the outdoor air dry-bulb temperature.

[0075] Specifically, continuously obtain historical meteorological monitoring data at a preset sampling time interval of one hour. Since heatwave events mainly target temperature, the historical meteorological monitoring data at least includes the outdoor air dry-bulb temperature. The dry-bulb temperature refers to the temperature measured by a thermometer freely exposed in ordinary air, representing the actual temperature of the air on the surface of the sphere and not affected by direct sunlight.

[0076] Step S2012: Determine the daily maximum temperature based on the historical meteorological monitoring data, and screen out historical heatwave events according to the daily maximum temperature.

[0077] Specifically, at a preset sampling time interval of one hour, 24 sets of corresponding data will be obtained in a day. Select the maximum value of the outdoor dry-bulb temperature from the 24 sets of data as the daily maximum temperature, and screen out heatwave events according to the daily maximum temperature. A weather process with a daily maximum temperature exceeding 35°C for more than 3 consecutive days can be called a heatwave event, which is only for example and not limited thereto.

[0078] Step S2013: Obtain the meteorological data corresponding to the historical heatwave event from the historical meteorological monitoring data.

[0079] Specifically, obtain the meteorological data corresponding to the heatwave event from the historical meteorological monitoring data, including but not limited to: the outdoor air dry-bulb temperature, relative humidity, total solar radiation on the horizontal plane, wind speed, wind direction, and atmospheric pressure during the heatwave event.

[0080] The method for evaluating and warning the risk of overheating in buildings during heatwaves provided in this embodiment can obtain the weather conditions in different seasons by collecting long-term meteorological monitoring data. By obtaining the meteorological monitoring data every hour, the daily maximum temperature can be determined more accurately, so as to more reliably identify heatwave events and their corresponding meteorological data.

[0081] Step S202: Obtain the building parameters of multiple preset building types respectively, and determine the calculation parameter combinations of multiple thermal environment models based on the meteorological data and building parameters of the heatwave event.

[0082] The building parameters include: building geometric parameters, thermal parameters of the envelope structure, building ventilation rate, indoor heat generation, and work and rest of personnel and equipment.

[0083] Specifically, among the building parameters, the building geometric parameters include, but are not limited to: building plane contour, building height, number of floors, etc.; the thermal parameters of the envelope structure include, but are not limited to: the heat transfer coefficient - K value (W / (m 2 ·K)) of the exterior wall, roof, and exterior window, as well as the solar heat gain coefficient (SHGC) of the exterior window; the building ventilation rate; the indoor heat generation; the schedules of occupants and equipment.

[0084] Specifically, the above step S202 includes:

[0085] Step S2021, determining the variation range and distribution of each building parameter according to the preset building parameter specifications.

[0086] Specifically, due to the large uncertainties in meteorological parameters and building parameters in actual residential buildings, it is difficult to reflect the parameter situation of typical residential buildings in the city using a single value. Therefore, it is necessary to determine possible parameter combinations. The meteorological parameters are the values obtained using professional meteorological equipment and are accurate values. The variation range and distribution of building parameters need to be determined according to the preset building parameter specifications in relevant standards and literature.

[0087] Step S2022, sampling and combining each building parameter according to the variation range and distribution of each building parameter, and combining with the meteorological data of historical heatwave events to obtain the calculation parameter combinations of multiple thermal environment models.

[0088] Specifically, sampling and combining each building parameter to obtain different combinations of building parameters as the parameters of the building model. For example, the parameters of the first building model may include: building height, number of floors; the parameters of the second building model may include: window-wall ratio, heat transfer coefficients of the exterior wall, roof, and exterior window.

[0089] Based on different combinations of building parameters, combining with the meteorological data of historical heatwave events, multiple thermal environment models are determined. The combinations of different building model parameters and the meteorological data combinations of historical heatwave events form the calculation parameter combinations of the thermal environment models. For example, the meteorological data of the first historical heatwave event includes: outdoor air dry-bulb temperature of 36.3°C, relative humidity of 46%, total solar radiation on the horizontal plane of 938 W / m 2 ², wind speed of 2.0 m / s, wind direction of southeast, and atmospheric pressure of 1013 hPa; the meteorological data of the second historical heatwave event includes: outdoor air dry-bulb temperature of 39.5°C, relative humidity of 35%, total solar radiation on the horizontal plane of 774 W / m 2 ², wind speed of 1.7 m / s, wind direction of southeast, and atmospheric pressure of 1013 hPa.

[0090] The building parameter sampling process makes distribution assumptions and samples for building characteristic parameters. On this basis, taking the meteorological data of various historical heat wave events as meteorological boundary conditions, heat environment simulation calculations are carried out. Therefore, the calculation parameter combinations in the heat environment model include building parameters and meteorological parameters, but meteorological data is not included in the building parameter sampling. The calculation parameter combinations of the heat environment model obtained based on different combinations of building parameters and combined with the meteorological data of historical heat wave events can include:

[0091] (1) The calculation parameter combination of the first heat environment model determined based on the parameters of the first building model and the meteorological data of the first historical heat wave event includes: building height, number of floors, outdoor air dry-bulb temperature of 36.3 °C, relative humidity of 46%, total horizontal solar radiation of 938 W / m 2 , wind speed of 2.0 m / s, wind direction of southeast, atmospheric pressure of 1013 hPa;

[0092] (2) The calculation parameter combination of the second heat environment model determined based on the parameters of the first building model and the meteorological data of the second historical heat wave event includes: building height, number of floors, outdoor air dry-bulb temperature of 39.5 °C, relative humidity of 35%, total horizontal solar radiation of 774 W / m 2 , wind speed of 1.7 m / s, wind direction of southeast, atmospheric pressure of 1013 hPa;

[0093] (3) The calculation parameter combination of the second heat environment model determined based on the parameters of the second building model and the meteorological data of the first historical heat wave event includes: window-wall ratio, heat transfer coefficients of the exterior wall, roof, and exterior window, outdoor air dry-bulb temperature of 36.3 °C, relative humidity of 46%, total horizontal solar radiation of 938 W / m 2 , wind speed of 2.0 m / s, wind direction of southeast, atmospheric pressure of 1013 hPa;

[0094] (4) The calculation parameter combination of the second heat environment model determined based on the parameters of the second building model and the meteorological data of the second historical heat wave event includes: window-wall ratio, heat transfer coefficients of the exterior wall, roof, and exterior window, outdoor air dry-bulb temperature of 39.5 °C, relative humidity of 35%, total horizontal solar radiation of 774 W / m 2 , wind speed of 1.7 m / s, wind direction of southeast, atmospheric pressure of 1013 hPa. For example only, but not limited thereto.

[0095] The method for evaluating and warning the overheating risk in a building interior during a heatwave provided in this embodiment combines the meteorological data of the heatwave event with building parameters to construct a thermal environment model, which can accurately simulate the thermal performance of the building under extreme high temperatures. By sampling and combining different building parameters and forming a calculation parameter combination for multiple thermal environment models based on the meteorological data of historical heatwave events, it is more representative for reflecting the urban residential building model.

[0096] Step S203: Based on the calculation parameter combinations of multiple thermal environment models, perform simulation calculations on the multiple thermal environment models to obtain the corresponding indoor thermal indices.

[0097] Specifically, the above step S203 includes:

[0098] Step S2031: Based on the calculation parameter combinations of multiple thermal environment models, use building full-performance simulation software to perform thermal environment simulations on the multiple thermal environment models, and calculate the indoor air temperature and indoor relative humidity corresponding to the thermal environment models.

[0099] Specifically, using the building full-performance simulation software DeST, construct corresponding multiple thermal environment models based on long-term meteorological data and typical residential building models, and use the simulation software to perform simulation calculations on the indoor thermal environment models of each residential building. The calculated indoor thermal environment parameters include indoor air temperature and relative humidity. The calculation process is a mature technology during the use of the DeST software and will not be elaborated here.

[0100] Step S2032: Calculate the indoor thermal index based on the indoor air temperature and indoor relative humidity.

[0101] Specifically, based on the thermal environment parameters, it is also necessary to quantify the magnitude of the thermal environment risk. Therefore, an evaluation index is required to quantitatively describe the overheating risk. This evaluation index is the indoor thermal index, which facilitates subsequent quantitative prediction of the overheating risk.

[0102] The indoor overheating risk uses the heat index as an evaluation index, and based on the simulated indoor thermal environment parameters, calculate the hourly value of the indoor overheating risk. The calculation formula for this index is:

[0103] Heat index=c1+c2T+c3R+c4TR+c5T 2 +c6R 2 +c7T 2 R+c8TR 2 +c9T 2 R 2

[0104] Among them, T represents the indoor air temperature (°C); R represents the relative humidity (%); the values of each coefficient are: c1 = -8.78469475556, c2 = 1.61139411, c3 = 2.33854883889, c4 = -0.14611605, c5 = -0.012308094, c6 = -0.0164248277778, c7 = 0.002211732, c8 = 0.00072546, c9 = -0.000003582.

[0105] The method for evaluating and warning the risk of indoor overheating in buildings during heatwaves provided in this embodiment is based on multiple thermal environment models. Using building performance simulation software, it simulates the indoor air temperature and relative humidity, calculates the indoor heat index, and calculates the thermal environment in the form of the heat index, which can accurately evaluate the indoor thermal environment and intuitively reflect the thermal sensation of the occupants.

[0106] Step S204: Use the calculation parameter combinations of multiple thermal environment models as inputs and the corresponding indoor heat indices as outputs to train a preset prediction model to obtain a trained prediction model.

[0107] Specifically, the above step S204 includes:

[0108] Step S2041: Construct a preset prediction model using a machine learning algorithm, and use grid search and cross-validation to determine the combination of hyperparameter values of the preset prediction model.

[0109] Specifically, a preset prediction model is constructed using a machine learning algorithm. In this embodiment, five prediction algorithms are compared, including: Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and LightBGM algorithm. During the construction of the indoor overheating risk prediction model, for the hyperparameters that affect the prediction accuracy of the algorithm, the grid search and five-fold cross-validation methods are used to select the combination of hyperparameter values with the smallest prediction error, and this is used as the hyperparameter of the model prediction algorithm.

[0110] Step S2042: Use the calculation parameter combinations of multiple thermal environment models as inputs and the corresponding indoor heat indices as outputs to train and optimize the preset prediction model based on the combination of hyperparameter values to obtain a trained prediction model.

[0111] Specifically, the calculation parameter combinations of the thermal environment model and the corresponding indoor thermal indices are used as training samples, and the training samples are divided into a training set and a test set according to a ratio of 8:2 to train a preset prediction model. After the model training, the performances of each model on the test set are compared, and the accuracy indices of each model are calculated respectively. In this embodiment, the architecture prediction error uses the coefficient of variation of root mean square error (CVRMSE) as the accuracy evaluation index, and the model with the smallest prediction error obtained based on the test set is used as the optimal prediction model.

[0112] The method for evaluating and warning the overheating risk in a building interior during a heatwave provided by the embodiments of the present invention constructs a prediction model using a machine learning algorithm and optimizes hyperparameters through grid search and cross-validation, which can significantly improve the prediction accuracy, enhance the model generalization ability, reduce the calculation cost, support real-time prediction and decision-making, and improve the accuracy and efficiency of prediction. The prediction model for the overheating risk in a residential building interior based on machine learning can also be used to determine the optimization strategy for improving measures of the overheating risk subsequently, and can combine with an optimization algorithm to quickly search for the best improvement measures, so as to help designers clarify the severity of the overheating risk under different combinations of residential building parameters, and further improve the efficiency of the design work.

[0113] Step S205: Obtain the actual meteorological monitoring data and actual building parameters of the target area, and use the prediction model to predict the predicted indoor thermal index of the actual building parameters. For details, please refer to Figure 1 Step S105 of the embodiment shown, which will not be elaborated here.

[0114] Step S206: Use the predicted indoor thermal index to conduct overheating risk assessment and warning according to a preset assessment rule.

[0115] Specifically, the above step S206 includes:

[0116] Step S2061: Obtain multiple historical indoor thermal indices, and divide the indoor thermal environment into multiple risk levels according to the multiple historical indoor thermal indices.

[0117] Specifically, obtain multiple historical indoor thermal indices, and divide the thermal environment into multiple risk levels according to the multiple historical indoor thermal indices. For example, if the range of the historical indoor thermal index is 20°C - 60°C, the divided risk levels are shown in Table 1, which is only for illustration and not limited thereto.

[0118] Table 1

[0119]

[0120] Step S2062: Determine the corresponding risk level according to the predicted indoor thermal index and issue a warning.

[0121] Specifically, according to the predicted indoor heat index, the overheating risk level is determined, and early warnings are issued based on the risk level. For example, when the risk level is level 3, it is a medium risk, and the household is prompted to cool down in time by using methods such as fans and air conditioners. This is only an example and is not limited thereto.

[0122] The method for evaluating and warning the overheating risk of a building interior in a heatwave provided by this embodiment is conducive to accurately evaluating the overheating risk of the indoor thermal environment and promptly issuing early warnings and taking measures to reduce the occurrence of potential safety hazards caused by indoor overheating by formulating the mapping relationship between the heat index and the risk level.

[0123] In a specific embodiment, four common residential building types are selected: row houses, multi-story slab buildings, high-rise slab buildings, and high-rise tower buildings. As Figure 3 shown, they are schematic structural diagrams of each building type. Among them, the row house has 2 floors, a building area of 930 m 2 , a shape factor of 0.48, and a window-wall ratio of 0.27; the multi-story slab building has 4 floors, a building area of 1703 m 2 , a shape factor of 0.36, and a window-wall ratio of 0.26; the high-rise slab building has 9 floors, a building area of 3947 m 2 , a shape factor of 0.31, and a window-wall ratio of 0.26; the high-rise tower building has 24 floors, a building area of 10459 m 2 , a shape factor of 0.3, and a window-wall ratio of 0.25.

[0124] Taking the target area as an example of City A, the meteorological data is from the monitoring data of the past 20 years (2004 - 2023), and the heatwave events in the past 20 years are identified based on the definition of heatwave events.

[0125] This embodiment selects parameters related to the building, including building type, window-wall ratio, heat transfer coefficients of the exterior wall / exterior window / roof, solar heat gain coefficient of the exterior window, air change rate, personnel work and rest, lighting and equipment power density, and personnel density. Among them, except for the building type, the variation range and distribution of the remaining input parameters are determined according to relevant national standards and literature, as shown in Table 2. The Latin hypercube sampling method is used to generate 1000 simulation cases of the indoor thermal environment of residential buildings, representing possible combinations of actual building parameters with a small number of sampling sample quantities.

[0126] Table 2

[0127]

[0128] Import the 1000 indoor thermal environment models of typical residential buildings generated in this embodiment into the building performance simulation software DeST, and use the meteorological data of City A in the past 20 years to conduct natural room temperature simulation calculations to obtain the indoor temperature and relative humidity of all residential building models in City A in the past 20 years, and calculate the indoor heat index therefrom.

[0129] Based on the dataset composed of the building input parameters and indoor overheating risk of all simulation cases, use the residential building type, window-wall ratio, heat transfer coefficients of exterior walls / exterior windows / roofs, solar heat gain coefficient of exterior windows, building ventilation rate, personnel schedule, and indoor heat release parameters as input feature variables, and use the hourly indoor heat index as the model output. Based on the machine learning algorithm, construct an indoor overheating risk prediction model. The indoor overheating risk prediction model proposed in this embodiment is compared with 5 prediction algorithms, including: Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and LightBGM algorithm.

[0130] After preparing the dataset, divide the dataset into a training set and a test set at a ratio of 8:2. During the model training process, the hyperparameter tuning process involved in each algorithm can refer to the corresponding steps in the invention content and will not be elaborated here. After model training, compare the performance of each model on the test set, and calculate the accuracy index CVRMSE of each model respectively. In this embodiment, the indoor overheating risk prediction model based on the XGBoost algorithm has the highest accuracy, and the CVRMSE result is 6.71%. Therefore, select the indoor overheating risk prediction model constructed by the XGBoost algorithm. The comparison between the prediction result of this model and the actual value is as Figure 4 shown.

[0131] In this embodiment, the residential building to be predicted and the recent weather forecast results are given. Among them, the residential building to be predicted is a high-rise tower building, and the window-wall ratio, heat transfer coefficients of exterior walls / exterior windows / roofs, solar heat gain coefficient of exterior windows, building ventilation rate, personnel schedule, indoor heat release, and recent weather forecast of the residential building to be predicted are recorded. According to the above input parameters, the indoor overheating risk prediction model based on the XGBoost algorithm can predict the hourly indoor heat index of the day to be predicted. According to the prediction result of the heat index (determined within the temperature range), divide the indoor thermal environment into different risk levels 1-4, as shown in Table 1. Among them, the smaller the level, the higher the corresponding overheating risk, so as to realize the risk warning of the indoor thermal environment. Finally, the maximum value of the indoor overheating risk level on the day to be predicted is level 3, that is, medium risk, and the duration is from 10 am to 20 pm, as Figure 5 shown. People who stay at home for a long time during the day need to pay attention to health protection, especially sensitive groups such as children, pregnant women, the elderly, and patients with chronic underlying diseases need to be focused on.

[0132] In this embodiment, a device for evaluating and warning the overheating risk of a building interior in a heatwave is further provided. This device is used to implement the above-mentioned embodiments and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" may be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0133] This embodiment provides a device for evaluating and warning the overheating risk of a building interior in a heatwave, such as Figure 6 shown, including:

[0134] A heatwave event screening module 601, configured to obtain historical meteorological monitoring data of a target area at a preset sampling time interval, and screen out meteorological data of historical heatwave events from the historical meteorological monitoring data.

[0135] A thermal environment model construction module 602, configured to respectively obtain building parameters of a plurality of preset building types, and determine a combination of calculation parameters of a plurality of thermal environment models based on the meteorological data and building parameters of historical heatwave events.

[0136] A simulation calculation module 603, configured to construct corresponding thermal environment models according to the combination of calculation parameters of a plurality of thermal environment models, and perform simulation calculations on the plurality of thermal environment models based on the combination of calculation parameters of the plurality of thermal environment models to obtain corresponding indoor thermal indices.

[0137] A model training module 604, configured to use the combination of calculation parameters of a plurality of thermal environment models as input and the corresponding indoor thermal indices as output to train a preset prediction model to obtain a trained prediction model.

[0138] A thermal index prediction module 605, configured to obtain actual meteorological monitoring data and actual building parameters of a target area, and use the prediction model to predict the predicted indoor thermal index of the actual building parameters.

[0139] A risk assessment and warning module 606, configured to perform overheating risk assessment and warning according to a preset assessment rule using the predicted indoor thermal index.

[0140] In some alternative implementation manners, the heatwave event screening module 601 includes:

[0141] A data sampling unit, configured to continuously obtain historical meteorological monitoring data at a preset sampling time interval of one hour, and the historical meteorological monitoring data includes the outdoor air dry-bulb temperature.

[0142] A heatwave event determination unit, configured to determine the daily maximum temperature according to the historical meteorological monitoring data, and screen out historical heatwave events according to the daily maximum temperature.

[0143] A heatwave data acquisition unit for acquiring meteorological data corresponding to historical heatwave events from historical meteorological monitoring data.

[0144] In some alternative embodiments, the thermal environment model construction module 602 includes:

[0145] A building parameter characteristic determination unit for determining the variation range and distribution of each building parameter according to a preset building parameter specification.

[0146] A parameter sampling and combination unit for sampling and combining each building parameter according to the variation range and distribution of each building parameter, and obtaining a calculation parameter combination for multiple thermal environment models by combining with the meteorological data of historical heatwave events.

[0147] In some alternative embodiments, the simulation calculation module 603 includes:

[0148] A simulation unit for performing a thermal environment simulation on multiple thermal environment models using building full-performance simulation software based on the calculation parameter combinations of multiple thermal environment models, and calculating the indoor air temperature and indoor relative humidity corresponding to the thermal environment models.

[0149] A heat index calculation unit for calculating the indoor heat index according to the indoor air temperature and indoor relative humidity.

[0150] In some alternative embodiments, the model training module 604 includes:

[0151] A model construction unit for constructing a preset prediction model using a machine learning algorithm, and determining a combination of hyperparameter values for the preset prediction model using grid search and cross-validation.

[0152] A model training unit for using the calculation parameter combinations of multiple thermal environment models as inputs, and the corresponding indoor heat index as outputs, and training and optimizing the preset prediction model based on the combination of hyperparameter values to obtain a trained prediction model.

[0153] In some alternative embodiments, the risk assessment and warning module 606 includes:

[0154] A risk level classification unit for obtaining multiple historical indoor heat indices, and classifying the indoor thermal environment into multiple risk levels according to the multiple historical indoor heat indices.

[0155] A prediction evaluation unit for determining the corresponding risk level according to the predicted indoor heat index and giving a warning.

[0156] The further function descriptions of the above-mentioned various modules and units are the same as those in the corresponding embodiments above, and will not be elaborated here.

[0157] In this embodiment, the device for evaluating and warning the risk of overheating in a building interior during a heatwave is presented in the form of functional units. Here, the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0158] An embodiment of the present invention further provides a computer device having the above Figure 6 device for evaluating and warning the risk of overheating in a building interior during a heatwave as shown.

[0159] Please refer to Figure 7 , Figure 7 which is a schematic structural diagram of a computer device provided by an alternative embodiment of the present invention. As shown in Figure 7 , the computer device includes: one or more processors 10, a memory 20, and an interface for connecting each component, including a high-speed interface and a low-speed interface. Each component communicates with each other using different buses and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some alternative embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Figure 7 In

[0160] FIG. 14, one processor 10 is taken as an example.

[0161] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0162] The memory 20 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some alternative embodiments, the memory 20 may optionally include a memory remotely provided with respect to the processor 10, and these remote memories may be connected to the computer device through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0163] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk, or a solid-state drive; the memory 20 may further include a combination of the above-mentioned types of memories.

[0164] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0165] Embodiments of the present invention further provide a computer-readable storage medium. The methods according to the embodiments of the present invention can be implemented in hardware, firmware, or be implemented as computer code that can be recorded on a storage medium, or be implemented as computer code originally stored in a remote storage medium or a non-transitory machine-readable storage medium and downloaded through a network and to be stored in a local storage medium, so that the methods described herein can be stored in such software processes on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid-state drive, etc.; further, the storage medium may also include a combination of the above-mentioned types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the methods shown in the above embodiments are implemented.

[0166] Although the embodiments of the present invention are described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for assessing and warning the overheating risk in a building interior during a heat wave, characterized in that, The method includes: Obtaining historical meteorological monitoring data of the target area at a preset sampling time interval, and screening out meteorological data of historical heatwave events from the historical meteorological monitoring data; Respectively obtaining building parameters of multiple preset building types, and determining calculation parameter combinations of multiple thermal environment models based on the meteorological data of the historical heatwave events and the building parameters; Constructing corresponding thermal environment models according to the calculation parameter combinations of the multiple thermal environment models, and performing simulation calculations on the multiple thermal environment models based on the calculation parameter combinations of the multiple thermal environment models to obtain corresponding indoor thermal indices; Using the calculation parameter combinations of the multiple thermal environment models as inputs and the corresponding indoor thermal indices as outputs to train a preset prediction model to obtain a trained prediction model; Obtaining actual meteorological monitoring data and actual building parameters of the target area, and using the prediction model to predict the predicted indoor thermal index of the actual building parameters; Performing overheating risk assessment and early warning according to the preset evaluation rules using the predicted indoor thermal index.

2. The method according to claim 1, wherein Obtaining historical meteorological monitoring data of the target area at a preset sampling time interval, and screening out meteorological data of historical heatwave events from the historical meteorological monitoring data, including: Continuously obtaining historical meteorological monitoring data at a preset sampling time interval of one hour, and the historical meteorological monitoring data includes outdoor air dry-bulb temperature; Determining the daily maximum temperature according to the historical meteorological monitoring data, and screening out historical heatwave events according to the daily maximum temperature; Obtaining the meteorological data corresponding to the historical heatwave events from the historical meteorological monitoring data.

3. The method according to claim 1, wherein The building parameters include: building geometric parameters, thermal parameters of the envelope structure, building ventilation rate, indoor heat generation, and personnel and equipment work and rest.

4. The method according to claim 3, wherein Determining calculation parameter combinations of multiple thermal environment models based on the meteorological data of the historical heatwave events and the building parameters, including: Determining the change range and distribution of each building parameter according to the preset building parameter specifications; Sampling and combining each building parameter according to the change range and distribution of each building parameter, and combining with the meteorological data of the historical heatwave events to obtain calculation parameter combinations of multiple thermal environment models.

5. The method according to claim 1 or 4, characterized in that, Performing simulation calculations on multiple thermal environment models based on the calculation parameter combinations of the multiple thermal environment models to obtain corresponding indoor thermal indices, including: Based on the calculation parameter combinations of the multiple thermal environment models, using building performance simulation software to perform thermal environment simulation on the multiple thermal environment models, and calculating the indoor air temperature and indoor relative humidity corresponding to the thermal environment models; Calculating the indoor thermal index according to the indoor air temperature and the indoor relative humidity.

6. The method according to claim 1, wherein Using the calculation parameter combinations of the multiple thermal environment models as inputs and the corresponding indoor thermal indices as outputs to train a preset prediction model to obtain a trained prediction model, including: Constructing a preset prediction model using a machine learning algorithm, and determining the hyperparameter value combination of the preset prediction model using grid search and cross-validation; Using the combined calculation parameters of the multiple thermal environment models as input and the corresponding indoor thermal index as output, the preset prediction model is trained and optimized based on the combination of hyperparameter values to obtain a trained prediction model.

7. The method according to claim 1 or 4, characterized in that, Using the predicted indoor thermal index to conduct overheating risk assessment and early warning according to the preset evaluation rules, including: Obtaining multiple historical indoor thermal indices, and dividing the indoor thermal environment into multiple risk levels according to the multiple historical indoor thermal indices; Determining the corresponding risk level according to the predicted indoor thermal index and giving an early warning.

8. An indoor overheating risk assessment and early warning device for buildings in a heatwave, characterized in that, The device includes: A heatwave event screening module, configured to obtain historical meteorological monitoring data of a target area at a preset sampling time interval, and screen out the meteorological data of historical heatwave events from the historical meteorological monitoring data; A thermal environment model construction module, configured to respectively obtain building parameters of multiple preset building types, and determine a combination of calculation parameters of multiple thermal environment models based on the building parameters and the meteorological data of historical heatwave events; A simulation calculation module, configured to construct corresponding thermal environment models according to the combination of calculation parameters of the multiple thermal environment models, and perform simulation calculations on the multiple thermal environment models based on the combination of calculation parameters of the multiple thermal environment models to obtain corresponding indoor thermal indices; A model training module, configured to use the combination of calculation parameters of multiple thermal environment models as input and the corresponding indoor thermal index as output to train a preset prediction model to obtain a trained prediction model; A thermal index prediction module, configured to obtain actual meteorological monitoring data and actual building parameters of a target area, and use the prediction model to predict the predicted indoor thermal index of the actual building parameters; A risk assessment and early warning module, configured to use the predicted indoor thermal index to conduct overheating risk assessment and early warning according to the preset evaluation rules.

9. A computer device, characterized in that, Including: A memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Computer instructions are stored on the computer-readable storage medium, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 7.

Images