Method and system for predicting structural response of historic building under atmospheric temperature field

Abstract

This invention discloses a method and system for predicting the structural response of historical buildings under atmospheric temperature fields. The method includes: acquiring atmospheric temperature field information, structural temperature field information, and structural response information over a past period; using the atmospheric temperature field information, structural temperature field information, and structural temperature field information and structural response information as training sets, respectively, to establish and train an atmospheric temperature prediction model for structural temperature and a structural temperature prediction model for structural response based on artificial intelligence algorithms; predicting future structural temperature field information based on future atmospheric temperature field information and historical structural temperature field information using the atmospheric temperature prediction model for structural temperature; and predicting the future structural response information of the historical building structure over a future period based on future structural temperature field information and historical structural response information using the structural temperature prediction model for structural response. This invention improves the accuracy and precision of predicting the structural response of historical buildings as atmospheric temperature changes, and has a wide range of applications.

Description

Technical Field

[0001] This invention relates to the field of civil engineering, and in particular to a method and system for predicting the structural response of historical buildings under atmospheric temperature fields. Background Technology

[0002] Existing buildings, including historical buildings, are not only subject to adverse factors such as sun exposure, wind erosion, rain, foundation settlement, steel structure rusting, and concrete shrinkage during use, but also to the effects of stable loads such as temperature changes. Currently, some historical building structures have been equipped with corresponding monitoring equipment to monitor physical quantities such as displacement, stress, and strain. Existing monitoring data shows that the structural response of relevant historical buildings is affected by the surface temperature of the structure, which is also related to the atmospheric temperature field. Existing methods for predicting structural response based on temperature often rely on the finite element method (FEM), establishing a structural temperature-stress model and predicting the structural response from temperature using the FEM. However, due to the age of historical buildings, their structures change over time, and the method of predicting structural response from temperature using the FEM suffers from inaccurate modeling. In addition, the calculation time for a single FEM model is long, and recalculation for different temperature conditions requires more computational resources. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for predicting the structural response of historical buildings under atmospheric temperature fields, in order to solve the problems of traditional finite element analysis methods for temperature-to-structural response, such as the inability to update the modeling in real time over time, long calculation time, the need for repeated calculations under different working conditions, and the requirement for more computing resources.

[0004] To address the aforementioned technical problems, this invention provides a method for predicting the structural response of historical buildings under an atmospheric temperature field, comprising:

[0005] Obtain information on atmospheric temperature field, structural temperature field, and structural response in the area where the historical building structure is located over a certain period of time.

[0006] Using atmospheric temperature field information and structural temperature field information from a certain period of time in the past as training set, and based on the structural temperature field information obtained from changes in atmospheric temperature field information over a certain period of time, an atmospheric temperature prediction structural temperature model is established and trained based on artificial intelligence algorithms.

[0007] Using the structural temperature field information and structural response information within this period as the training set, and based on the structural response information obtained as the structural temperature field information changes within this period, a structural temperature prediction structural response model is established and trained using artificial intelligence algorithms.

[0008] Based on the future atmospheric temperature field information and the historical structural temperature field information of a past period before the future period, the atmospheric temperature field prediction structural temperature model is used to predict the future structural temperature field information and input the predicted future structural temperature field information into the structural temperature prediction structural response model.

[0009] Based on the structural temperature prediction structural response model, the future structural response information of historical building structures is predicted within a certain period of the future, using the future structural temperature field information predicted by the structural temperature prediction structural response model and the historical structural response information within a certain period of the past.

[0010] Furthermore, the present invention provides a method for predicting the structural response of historical buildings under atmospheric temperature fields.

[0011] The atmospheric temperature prediction structure temperature model and the structure temperature prediction structure response model are combined and superimposed to form the atmospheric temperature field prediction structure response model.

[0012] Based on the atmospheric temperature field prediction structural response model, the model predicts the future structural temperature field information within a certain future time period and the historical structural temperature field information and historical structural response information within a certain past time period before the future time period, and predicts the future structural response information of the historical building structure within a certain future time period based on the future atmospheric temperature field information and the historical structural temperature field information.

[0013] Furthermore, the method for predicting the structural response of historical buildings under atmospheric temperature field provided by the present invention obtains atmospheric temperature field information of the area where the historical building structure is located over a certain period of time through weather forecasts or historical weather records, obtains structural temperature field information under atmospheric temperature field information during that period through temperature sensors installed on the historical building, and obtains structural response information under structural temperature field information during that period through structural response sensors installed on the historical building.

[0014] Furthermore, the method for predicting the response of historical building structures under atmospheric temperature field provided by the present invention establishes and trains an atmospheric temperature prediction model for structure temperature based on the structural temperature field information obtained from changes in atmospheric temperature field information and cloud thickness over a certain period of time.

[0015] Furthermore, the method for predicting the response of historical building structures under atmospheric temperature field provided by the present invention establishes and trains an atmospheric temperature prediction structural temperature model based on structural temperature field information obtained from changes in atmospheric temperature field information and rainfall over a certain period of time.

[0016] Furthermore, the method for predicting the response of historical building structures under atmospheric temperature field provided by the present invention establishes and trains an atmospheric temperature prediction model for structural temperature based on structural temperature field information obtained from changes in atmospheric temperature field information, cloud thickness, and rainfall over a certain period of time.

[0017] Furthermore, the method for predicting the structural response of historical buildings under atmospheric temperature field provided by this invention uses the SGD or Adam algorithm to train the model.

[0018] Furthermore, in the method for predicting the structural response of historical buildings under atmospheric temperature field provided by the present invention, both the structural temperature prediction structural response model and the structural temperature prediction structural response model are DNN, RNN, LSTM or Transformer models.

[0019] To address the aforementioned technical problems, this invention also provides a system for predicting the structural response of historical buildings under an atmospheric temperature field, comprising:

[0020] The information acquisition module is used to acquire atmospheric temperature field information, structural temperature field information, and structural response information of the area where the historical building structure is located over a certain period of time.

[0021] The atmospheric temperature prediction structure temperature module uses atmospheric temperature field information and structure temperature field information from a certain period in the past as a training set. Based on the structure temperature field information obtained as the atmospheric temperature field information changes over a certain period in the past, it establishes and trains an atmospheric temperature prediction structure temperature model based on artificial intelligence algorithms. On the atmospheric temperature prediction structure temperature model, it predicts the future structure temperature field information for a certain period in the future based on the input future atmospheric temperature field information and the historical structure temperature field information from a certain period in the past before the future.

[0022] The structural temperature prediction structural response module uses the structural temperature field information and structural response information within the specified time period as a training set. Based on the structural response information obtained as the structural temperature field information changes within the specified time period, it establishes and trains a structural temperature prediction structural response model using artificial intelligence algorithms. Based on the structural temperature prediction structural response model, it predicts the future structural response information of the historical building structure within a certain future time period using the future structural temperature field information predicted by the structural temperature prediction structural response model and the historical structural response information from a certain time period before the future.

[0023] To address the aforementioned technical problems, this invention further provides a system for predicting the structural response of historical buildings under atmospheric temperature fields, comprising:

[0024] The information acquisition module is used to acquire atmospheric temperature field information, structural temperature field information, and structural response information of the area where the historical building structure is located over a certain period of time.

[0025] The atmospheric temperature prediction structure temperature module uses atmospheric temperature field information and structure temperature field information over a certain period of time as a training set. Based on the structure temperature field information obtained as atmospheric temperature field information changes over a certain period of time, it establishes and trains an atmospheric temperature prediction structure temperature model based on artificial intelligence algorithms.

[0026] The structural temperature prediction structural response module uses the structural temperature field information and structural response information within the specified time period as a training set. Based on the structural response information obtained as the structural temperature field information changes within the specified time period, it establishes and trains a structural temperature prediction structural response model based on artificial intelligence algorithms.

[0027] The atmospheric temperature block predicts structural response module, which combines and superimposes the atmospheric temperature predicts structural temperature model and the structural temperature predicts structural response model to form a composite prediction model. Based on the input future atmospheric temperature field information and historical structural temperature field information and historical structural response information for a certain period in the past, the module predicts the future structural temperature field information for a certain period in the future, and predicts the future structural response information of the historical building structure for a certain period in the future.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0029] The present invention provides a method and system for predicting the structural response of historical buildings under atmospheric temperature fields. This method acquires information on the atmospheric temperature field, structural temperature field, and structural response of the area where the historical building is located over a past period. Based on an artificial intelligence algorithm, it establishes and trains an atmospheric temperature prediction model for structural temperature and a structural temperature prediction model for structural response, using the atmospheric temperature field information, structural temperature field information, and structural response information as training sets, respectively. Then, based on future atmospheric temperature field information and historical structural temperature field information, the atmospheric temperature prediction model predicts the future structural temperature field information over a future period. Finally, based on future structural temperature field information and historical structural response information, the structural temperature prediction model predicts the structural response information of the historical building over a future period. Compared with finite element modeling and analysis of the structural response of historical buildings, this method can update the atmospheric temperature prediction model and the structural temperature prediction model for structural response based on real-time updated atmospheric temperature field information, structural temperature field information, and structural response information, improving the accuracy and efficiency of model establishment, thereby enhancing the prediction accuracy of the structural response of historical buildings as atmospheric temperature changes. At the same time, based on updated data, redundant calculations in the finite element solution process are avoided, reducing the amount of computation and eliminating the need to consume a lot of computing resources.

[0030] The present invention provides a method and system for predicting the structural response of historical buildings under atmospheric temperature field. Starting from the weather, it considers the influence of climate temperature conditions on the temperature of historical building structures, and then infers the structural response of historical buildings to atmospheric temperature through structural temperature. Compared with the finite element analysis method for predicting structural response through temperature, it has a wider range of applications. Attached Figure Description

[0031] Figure 1 This is a flowchart of the method for predicting the structural response of historical buildings under atmospheric temperature field in Example 1;

[0032] Figure 2 This is a schematic diagram of the structural composition relationship of the historical building structure response prediction system under atmospheric temperature field in Example 1;

[0033] Figure 3 This is a flowchart of the method for predicting the structural response of historical buildings under atmospheric temperature field in Example 2;

[0034] Figure 4 This is a schematic diagram of the structural composition relationship of the historical building structure response prediction system under atmospheric temperature field in Example 2. Detailed Implementation

[0035] The present invention will now be described in detail with reference to the accompanying drawings. The advantages and features of the present invention will become clearer from the following description. It should be noted that the drawings are all in a very simplified form and use non-precise proportions, and are only used to facilitate and clarify the illustration of the embodiments of the present invention.

[0036] Example 1

[0037] Please refer to Figure 1 Embodiment 1 of the present invention provides a method for predicting the structural response of historical buildings under atmospheric temperature fields, which may include:

[0038] Step 501: Obtain atmospheric temperature field information, structural temperature field information, and structural response information for the area where the historical building structure is located over a certain period of time. To obtain these information, the method for predicting the structural response of historical buildings under an atmospheric temperature field, as provided in Embodiment 1 of this invention, obtains atmospheric temperature field information for the area where the historical building structure is located over a certain period of time through weather forecasts or historical weather records. It then obtains structural temperature field information under the atmospheric temperature field information using temperature sensors installed on the historical building, and obtains structural response information under the structural temperature field information using structural response sensors installed on the historical building. Weather forecasts or historical weather records can be obtained through queries on relevant meteorological websites or by web scraping. The structural temperature field information can be 24-hour time-division temperature measurement data.

[0039] Step 502: Using atmospheric temperature field information and structural temperature field information from a past period as the training set, and based on the structural temperature field information obtained as the atmospheric temperature field information changes over a past period, an atmospheric temperature prediction model for structural temperature is established and trained using an artificial intelligence algorithm. The input to this model is daily atmospheric temperature field information (maximum and minimum temperatures, cloud and precipitation conditions, etc. within that period), and the temperature sequence of the historical building structure several days prior to the prediction time. The model output is the daily structural temperature field information of the historical building structure within the prediction period (usually one day). The types of this structural temperature prediction model for structural response include, but are not limited to, the following four models:

[0040] 1. DNN (Deep Neural Networks) model.

[0041] 2. RNN (Recurrent Neural Network) model.

[0042] 3. LSTM (Long Short Term Memory) recurrent neural network model.

[0043] 4. Transformer model (self-attention model).

[0044] The model training process can employ optimization algorithms such as SGD (Stochastic Gradient Descent) and Adam (Adaptive Moment Estimation) until the target loss function reaches a pre-set expected value, at which point training can stop. After training, an atmospheric temperature prediction structural temperature model is obtained.

[0045] To improve data accuracy, considering the impact of varying cloud thickness and rainfall on the structural temperature of historical buildings, an atmospheric temperature prediction model for structural temperature can be established and trained based on structural temperature field information obtained over a past period, taking into account changes in the atmospheric temperature field and cloud thickness. Alternatively, this model can be used to further enhance data accuracy by flexibly establishing atmospheric temperature prediction models that consider the influence of other parameters on the structural temperature of historical buildings.

[0046] Step 503: Using the structural temperature field information and structural response information within this time period as the training set, and based on the structural response information obtained as the structural temperature field information changes during this time period, a structural temperature prediction model for structural response is established and trained using an artificial intelligence algorithm. The input to this model is the temperature information of the structural temperature field within a certain time period, and the response sequence of the structural response information from the days preceding the predicted structural response time. The output is the structural response information within the time period to be predicted. The model form is not limited; DNN, RNN, LSTM, and Transformer models can all be used to model the structural temperature prediction process for structural response. The model training process can employ optimization algorithms such as SGD and Adam until the objective loss function reaches the pre-set expected value, at which point training can stop. After training, the structural temperature prediction model for structural response is obtained.

[0047] Step 504: Based on the future atmospheric temperature field information and the historical structural temperature field information of a certain period in the past, the atmospheric temperature prediction structural temperature model is used to predict the future structural temperature field information and input the predicted future structural temperature field information into the structural temperature prediction structural response model.

[0048] Step 505: Based on the structural temperature prediction structural response model, predict the future structural temperature field information of the historical building structure in a future period of time by combining the future structural temperature field information predicted by the structural temperature prediction structural response model with the historical structural response information in the past period of time before a future period of time.

[0049] Please refer to Figures 1 to 2 Embodiment 1 of the present invention also provides a system for predicting the structural response of historical buildings under atmospheric temperature fields, comprising:

[0050] Information acquisition module 1 is used to acquire atmospheric temperature field information, structural temperature field information, and structural response information of the area where the historical building structure is located over a certain period of time.

[0051] The atmospheric temperature prediction structure temperature module 2 uses atmospheric temperature field information and structure temperature field information from a certain period in the past as a training set. Based on the structure temperature field information obtained as the atmospheric temperature field information changes over a certain period in the past, it establishes and trains an atmospheric temperature prediction structure temperature model based on artificial intelligence algorithms. On the atmospheric temperature prediction structure temperature model, it predicts the future structure temperature field information for a certain period in the future based on the input future atmospheric temperature field information and the historical structure temperature field information from a certain period in the past before the future.

[0052] The structural temperature prediction structural response module 3 uses the structural temperature field information and structural response information within the specified time period as a training set. Based on the structural response information obtained as the structural temperature field information changes within the specified time period, it establishes and trains a structural temperature prediction structural response model using artificial intelligence algorithms. Based on the structural temperature prediction structural response model, it predicts the future structural response information of the historical building structure within a certain time period in the future using the future structural temperature field information predicted by the structural temperature prediction structural response model and the historical structural response information within a certain time period in the past.

[0053] Example 2

[0054] Please refer to Figure 3 Embodiment 2 of the present invention provides a method for predicting the structural response of historical buildings under an atmospheric temperature field. It is an improvement on Embodiment 1, the difference being that after step 503, steps 504 to 505 are not executed, and the following steps are executed instead:

[0055] Step 506 involves combining and superimposing the atmospheric temperature prediction structural temperature model and the structural temperature prediction structural response model to form an atmospheric temperature field prediction structural response model. This creates a composite model. Once trained, both the atmospheric temperature prediction structural temperature model and the structural temperature prediction structural response model can be used to predict the structural response of historical buildings under atmospheric temperature fields.

[0056] Step 507: Based on the atmospheric temperature field prediction structural response model, using the input future atmospheric temperature field information for a certain future period and the historical structural temperature field information and historical structural response information for a certain past period, the model predicts the future structural temperature field information for that period, and then predicts the future structural response information of the historical building structure for that period. Specifically, first, the future atmospheric temperature field information for the next predicted period (obtainable from future weather forecasts) and the structural temperature field information of the historical building structure a few days before the predicted time (i.e., the temperature sequence) are input to predict the future structural temperature field information; then, the future structural temperature field information for the next predicted period and the structural response information a few days before the predicted time (i.e., the response sequence) are input to predict the future structural response information for the specified time. At this point, the structural response and prediction work is complete.

[0057] In Example 2, steps 501 to 503 are the model building stage, and steps 506 to 507 are the model prediction stage.

[0058] Please refer to Figures 3 to 4 Embodiment 2 of the present invention also provides a system for predicting the structural response of historical buildings under atmospheric temperature fields, comprising:

[0059] Information acquisition module 1 is used to acquire atmospheric temperature field information, structural temperature field information, and structural response information of the area where the historical building structure is located over a certain period of time.

[0060] The atmospheric temperature prediction structure temperature module 2 uses atmospheric temperature field information and structure temperature field information from a certain period of time in the past as a training set. Based on the structure temperature field information obtained as atmospheric temperature field information changes over a certain period of time, it establishes and trains an atmospheric temperature prediction structure temperature model based on artificial intelligence algorithms.

[0061] The structural temperature prediction structural response module 3 uses the structural temperature field information and structural response information within this period as a training set. Based on the structural response information obtained as the structural temperature field information changes within this period, it establishes and trains a structural temperature prediction structural response model based on artificial intelligence algorithms.

[0062] The atmospheric temperature block predicts the structural response module 4, which combines the atmospheric temperature predicts the structural temperature model and the structural temperature predicts the structural response model to form a composite prediction model. Based on the input future atmospheric temperature field information and historical structural temperature field information and historical structural response information from a certain period in the past, the module predicts the future structural temperature field information for a certain period in the future, and predicts the future structural response information of the historical building structure for a certain period in the future.

[0063] The method and system for predicting the structural response of historical buildings under atmospheric temperature fields provided in the above embodiments of the present invention acquires atmospheric temperature field information, structural temperature field information, and structural response information of the area where the historical building structure is located over a certain period of time. Based on artificial intelligence algorithms, an atmospheric temperature prediction model and a structural temperature prediction model are trained using the atmospheric temperature field information, structural temperature field information, and structural temperature field information and structural response information as training sets, respectively. Then, based on future atmospheric temperature field information and historical structural temperature field information, the atmospheric temperature prediction model predicts the future structural temperature field information over a certain period of time. Finally, based on future structural temperature field information and historical structural response information, the structural temperature prediction model predicts the structural response information of the historical building over a certain period of time. Compared with the finite element model modeling and analysis method for the structural response of historical buildings, this method can update the atmospheric temperature prediction model and the structural temperature prediction model based on real-time updated atmospheric temperature field information, structural temperature field information, and structural response information, improving the accuracy and efficiency of model building, thereby improving the prediction accuracy and precision of the structural response of historical buildings as atmospheric temperature changes. At the same time, based on updated data, redundant calculations in the finite element solution process are avoided, reducing the amount of computation and eliminating the need to consume a lot of computing resources.

[0064] The method and system for predicting the structural response of historical buildings under atmospheric temperature field provided in the above embodiments of the present invention start from the weather, consider the influence of climate temperature conditions on the temperature of historical building structures, and then infer the structural response of historical building structures by the structural temperature. Compared with the finite element analysis method for predicting structural response by temperature, it has a wider range of applications.

[0065] This invention is not limited to the specific embodiments described above. Obviously, the embodiments described above are only a part of the embodiments of this invention, not all of them. All other embodiments obtained by those skilled in the art based on the described embodiments of this invention are within the scope of protection of this invention. Those skilled in the art can make other modifications and variations to this invention. Therefore, if these modifications and variations of this invention fall within the scope of the claims of this invention, then this invention also intends to include these modifications and variations.

Claims

1. A method for predicting the structural response of historical buildings under an atmospheric temperature field, characterized in that, include: Obtain information on atmospheric temperature field, structural temperature field, and structural response in the area where the historical building structure is located over a certain period of time. Using atmospheric temperature field information and structural temperature field information from a certain period of time in the past as training set, and based on the structural temperature field information obtained from changes in atmospheric temperature field information over a certain period of time, an atmospheric temperature prediction structural temperature model is established and trained based on artificial intelligence algorithms. Using the structural temperature field information and structural response information within this period as the training set, and based on the structural response information obtained as the structural temperature field information changes within this period, a structural temperature prediction structural response model is established and trained using artificial intelligence algorithms. Based on the future atmospheric temperature field information and the historical structural temperature field information of a past period before the future period, the atmospheric temperature field prediction structural temperature model is used to predict the future structural temperature field information and input the predicted future structural temperature field information into the structural temperature prediction structural response model. Based on the structural temperature prediction structural response model, the future structural response information of historical building structures is predicted within a certain period of the future, using the future structural temperature field information predicted by the structural temperature prediction structural response model and the historical structural response information within a certain period of the past.

2. The method for predicting the structural response of historical buildings under atmospheric temperature field according to claim 1, characterized in that, The atmospheric temperature prediction structure temperature model and the structure temperature prediction structure response model are combined and superimposed to form the atmospheric temperature field prediction structure response model. Based on the atmospheric temperature field prediction structural response model, the model predicts the future structural temperature field information within a certain future time period and the historical structural temperature field information and historical structural response information within a certain past time period before the future time period, and predicts the future structural response information of the historical building structure within a certain future time period based on the future atmospheric temperature field information and the historical structural temperature field information.

3. The method for predicting the structural response of historical buildings under atmospheric temperature field according to claim 1, characterized in that, Information on the atmospheric temperature field of the area where the historical building structure is located during a certain period of time is obtained by using weather forecasts or historical weather records. Information on the structural temperature field under the atmospheric temperature field information during that period is obtained by using temperature sensors installed on the historical building. Information on the structural response under the structural temperature field information during that period is obtained by using structural response sensors installed on the historical building.

4. The method for predicting the structural response of historical buildings under atmospheric temperature field according to claim 1, characterized in that, Based on the structural temperature field information obtained from changes in atmospheric temperature field information and cloud thickness over a certain period of time, an atmospheric temperature prediction structural temperature model is established and trained.

5. The method for predicting the structural response of historical buildings under atmospheric temperature field according to claim 1, characterized in that, Based on the structural temperature field information obtained from changes in atmospheric temperature field information and rainfall over a certain period of time, an atmospheric temperature prediction structural temperature model is established and trained.

6. The method for predicting the structural response of historical buildings under atmospheric temperature field according to claim 1, characterized in that, Based on the structural temperature field information obtained from changes in atmospheric temperature field information, cloud thickness, and rainfall over a certain period of time, an atmospheric temperature prediction structural temperature model is established and trained.

7. The method for predicting the structural response of historical buildings under atmospheric temperature field according to claim 1, characterized in that, The model is trained using either SGD or Adam algorithms.

8. The method for predicting the structural response of historical buildings under atmospheric temperature field according to claim 1, characterized in that, Both the atmospheric temperature prediction structure temperature model and the structure temperature prediction structure response model are DNN, RNN, LSTM, or Transformer models.

9. A system for predicting the structural response of historical buildings under an atmospheric temperature field, characterized in that, include: The information acquisition module is used to acquire atmospheric temperature field information, structural temperature field information, and structural response information of the area where the historical building structure is located over a certain period of time. The atmospheric temperature prediction structure temperature module uses atmospheric temperature field information and structure temperature field information from a certain period in the past as a training set. Based on the structure temperature field information obtained as the atmospheric temperature field information changes over a certain period in the past, it establishes and trains an atmospheric temperature prediction structure temperature model based on artificial intelligence algorithms. On the atmospheric temperature prediction structure temperature model, it predicts the future structure temperature field information for a certain period in the future based on the input future atmospheric temperature field information and the historical structure temperature field information from a certain period in the past before the future. The structural temperature prediction structural response module uses the structural temperature field information and structural response information within the specified time period as a training set. Based on the structural response information obtained as the structural temperature field information changes within the specified time period, it establishes and trains a structural temperature prediction structural response model using artificial intelligence algorithms. Based on the structural temperature prediction structural response model, it predicts the future structural response information of the historical building structure within a certain future time period using the future structural temperature field information predicted by the structural temperature prediction structural response model and the historical structural response information from a certain time period before the future.

10. A system for predicting the structural response of historical buildings under an atmospheric temperature field, characterized in that, include: The information acquisition module is used to acquire atmospheric temperature field information, structural temperature field information, and structural response information of the area where the historical building structure is located over a certain period of time. The atmospheric temperature prediction structure temperature module uses atmospheric temperature field information and structure temperature field information over a certain period of time as a training set. Based on the structure temperature field information obtained as atmospheric temperature field information changes over a certain period of time, it establishes and trains an atmospheric temperature prediction structure temperature model based on artificial intelligence algorithms. The structural temperature prediction structural response module uses the structural temperature field information and structural response information within the specified time period as a training set. Based on the structural response information obtained as the structural temperature field information changes within the specified time period, it establishes and trains a structural temperature prediction structural response model based on artificial intelligence algorithms. The atmospheric temperature field prediction structure response module is used to combine and superimpose the atmospheric temperature prediction structure temperature model and the structure temperature prediction structure response model to form a composite prediction model. Based on the input future atmospheric temperature field information and historical structure temperature field information and historical structure response information for a certain period in the future, the module predicts the future structure temperature field information for a certain period in the future, and predicts the future structure response information of the historical building structure for a certain period in the future.

Images