Earthquake early warning oriented high-rise building earthquake response real-time prediction method, device and equipment

Abstract

The application provides a high-rise building earthquake response real-time prediction method, device and equipment for earthquake warning, which comprises the following steps: obtaining strong motion data, a target high-rise building model and building attributes of the target high-rise building model; extracting seismic motion parameters and earthquake parameters from an initial seismic waveform of the strong motion data; the seismic motion parameters comprise peak acceleration, peak velocity, cumulative absolute velocity, important duration and Arias intensity; the earthquake parameters comprise magnitude, epicentral distance and site parameters; inputting the seismic motion parameters, the earthquake parameters and the building attributes into a high-rise building earthquake response real-time prediction model to obtain an earthquake response, and making a warning according to the earthquake response. The method, device and equipment provided by the application can predict the earthquake response of a high-rise building in real time, efficiently and accurately, provide important technical support for earthquake warning and disaster risk reduction, and have good practical value and wide application prospect.

Description

Technical Field

[0001] This invention relates to the field of disaster prevention and mitigation engineering technology, and in particular to a method, device and equipment for real-time prediction of seismic response of high-rise buildings for earthquake early warning. Background Technology

[0002] Real-time prediction of seismic response of high-rise buildings is of great significance for the assessment of their seismic performance.

[0003] Due to the highly nonlinear nature of processes such as earthquake motion propagation and building dynamic amplification, traditional PBEE-based (Performance Based Earthquake Engineering) methods, which are based on fixed function forms, struggle to capture the complex relationships involved. In other words, traditional PBEE-based methods based on fixed function forms have low accuracy in predicting the seismic response of high-rise buildings. Summary of the Invention

[0004] This invention provides a method, apparatus, and equipment for real-time prediction of seismic response of high-rise buildings for earthquake early warning, in order to solve the problem of low prediction accuracy of traditional PBEE-based methods based on fixed function forms for the seismic response of high-rise buildings.

[0005] This invention provides a method for real-time prediction of seismic response of high-rise buildings for earthquake early warning, comprising the following steps:

[0006] Acquire strong ground motion data and a target high-rise building model, and obtain the building attributes of the target high-rise building model; the target high-rise building model is constructed based on a high-rise building model with strong ground motion monitoring data;

[0007] Seismic ground motion parameters and earthquake parameters are extracted from the initial seismic waveform of the strong ground motion data; the seismic ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, significant duration, and Arias intensity; the earthquake parameters include magnitude, epicentral distance, and site parameters.

[0008] The ground motion parameters, earthquake parameters, and building attributes are input into the real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model for the seismic response of high-rise buildings, and an early warning is issued based on the seismic response.

[0009] The real-time seismic response prediction model for high-rise buildings is constructed based on a deep neural network.

[0010] The real-time prediction model for the seismic response of high-rise buildings includes multiple fully connected hidden layers. The number of neurons and the activation function of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise buildings.

[0011] According to the present invention, a real-time prediction method for the seismic response of high-rise buildings for earthquake early warning is provided. The training steps of the real-time prediction model for the seismic response of high-rise buildings include:

[0012] Sample ground motion parameters and sample earthquake parameters are obtained from the strong ground motion database, and sample building attributes are obtained, as well as the labeled earthquake responses corresponding to the sample ground motion parameters, sample earthquake parameters and sample building attributes;

[0013] Obtain an initial real-time prediction model of the seismic response of high-rise buildings;

[0014] The sample ground motion parameters, the sample earthquake parameters, and the sample building attributes are input into the initial high-rise building seismic response real-time prediction model to obtain the predicted seismic response output by the initial high-rise building seismic response real-time prediction model.

[0015] Based on the difference between the predicted seismic response and the labeled seismic response, a target loss is determined, and the parameters of the initial high-rise building seismic response real-time prediction model are iterated based on the target loss to obtain the high-rise building seismic response real-time prediction model.

[0016] According to the present invention, a real-time prediction method for seismic response of high-rise buildings for earthquake early warning is provided, wherein the step of obtaining the labeled seismic response includes:

[0017] Based on the urban seismic elastoplastic analysis method, the labeled seismic response of the target high-rise building under seismic motion is determined.

[0018] According to the present invention, a real-time prediction method for the seismic response of high-rise buildings for earthquake early warning is provided. The method, based on urban seismic elastoplastic analysis, determines the labeled seismic response of a target high-rise building model under seismic motion, including:

[0019] Based on the multi-degree-of-freedom shear layer model, the floor mass of the target high-rise building model is concentrated in a single mass point, and the nonlinear behavior between floors in the target high-rise building model is simulated using a trilinear skeleton line and a single-parameter hysteresis model.

[0020] The skeleton line parameters of the trilinear skeleton line are calibrated using a calibration method based on the HAZUS capability curve database.

[0021] According to the present invention, a real-time prediction method for seismic response of high-rise buildings for earthquake early warning is provided. The strong ground motion database is constructed based on ground motion data with magnitudes between 4 and 8, epicentral distances less than 200 km, and site parameters between 100 and 900 m / s.

[0022] According to the present invention, a real-time prediction method for the seismic response of high-rise buildings for earthquake early warning is provided, wherein the extraction of ground motion parameters and seismic parameters from the initial seismic waveform of the strong ground motion data includes:

[0023] The P-wave arrival time in the initial waveform of the strong ground motion data is detected by using an automatic P-wave identification algorithm.

[0024] Based on the arrival time of the P-wave, the ground motion record for the first 3 seconds after the arrival time of the P-wave is extracted;

[0025] Based on the ground motion record of the first 3 seconds, the ground motion parameters and the earthquake parameters are determined.

[0026] The present invention also provides a real-time prediction device for the seismic response of high-rise buildings for earthquake early warning, comprising the following units:

[0027] The acquisition unit is used to acquire strong ground motion data and a target high-rise building model, and to acquire the building attributes of the target high-rise building model; the target high-rise building model is constructed based on a high-rise building model with strong ground motion monitoring data.

[0028] The extraction unit is used to extract ground motion parameters and earthquake parameters from the initial seismic waveform of the strong ground motion data; the ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, duration of significance, and Arias intensity; the earthquake parameters include magnitude, epicentral distance, and site parameters.

[0029] The prediction unit is used to input the ground motion parameters, the earthquake parameters and the building attributes into the real-time prediction model of the earthquake response of high-rise buildings, obtain the earthquake response output by the real-time prediction model of the earthquake response of high-rise buildings, and make an early warning based on the earthquake response;

[0030] The real-time seismic response prediction model for high-rise buildings is constructed based on a deep neural network.

[0031] The real-time prediction model for the seismic response of high-rise buildings includes multiple fully connected hidden layers. The number of neurons and the activation function of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise buildings.

[0032] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the real-time prediction method for earthquake response of high-rise buildings for earthquake early warning as described above.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the real-time prediction method for seismic response of high-rise buildings for earthquake early warning as described above.

[0034] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the real-time prediction method for earthquake response of high-rise buildings for earthquake early warning as described above.

[0035] This invention provides a method, apparatus, and equipment for real-time prediction of seismic response of high-rise buildings for earthquake early warning. It acquires strong ground motion data and a target high-rise building model, and obtains the building attributes of the target high-rise building model. Then, it extracts ground motion parameters and seismic parameters from the initial seismic waveform of the strong ground motion data. Finally, it inputs the ground motion parameters, seismic parameters, and building attributes into the real-time prediction model of the high-rise building's seismic response, obtaining the seismic response output by the model, and issuing an early warning based on the seismic response. Predicting seismic response based on ground motion parameters, seismic parameters, and building attributes can more comprehensively and accurately reflect the impact of earthquakes on high-rise buildings, improving the accuracy and reliability of seismic response prediction. Furthermore, this invention can predict the seismic response of high-rise buildings in real time, efficiently, and accurately, providing important technical support for earthquake early warning, building emergency management, and disaster risk assessment, and has good practical value and broad application prospects. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating the real-time prediction method for seismic response of high-rise buildings for earthquake early warning provided by the present invention.

[0038] Figure 2 This is a graph showing the loss function of the training set and test set provided by this invention.

[0039] Figure 3 This is a comparison chart of the maximum inter-story drift angle, maximum floor acceleration, and top floor acceleration of the model provided by this invention with the actual values ​​on the test set.

[0040] Figure 4 It is the confusion matrix between the measured acceleration data of the top-level model provided by this invention and the prediction results of this model.

[0041] Figure 5 This is a schematic diagram of the DNN-based network architecture EEWnet provided by the present invention.

[0042] Figure 6 This is a schematic diagram of the structure of the real-time prediction device for earthquake response of high-rise buildings for earthquake early warning provided by the present invention.

[0043] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0045] Currently, due to the highly nonlinear processes of earthquake ground motion propagation and building dynamic amplification, traditional PBEE-based methods with fixed function forms struggle to capture the complex relationships involved. Deep learning methods can uncover complex nonlinear patterns in data, providing an important means to address this challenge; however, current real-time prediction of seismic responses of high-rise buildings based on deep learning is relatively limited.

[0046] To address the aforementioned problems, this invention provides a real-time prediction method for the seismic response of high-rise buildings for earthquake early warning. Figure 1 This is a flowchart illustrating the real-time prediction method for seismic response of high-rise buildings for earthquake early warning provided by the present invention. Figure 1 As shown, the method includes steps 110, 120 and 130.

[0047] Step 110: Obtain strong ground motion data and a target high-rise building model, and obtain the building attributes of the target high-rise building model; the target high-rise building model is constructed based on a high-rise building model with strong ground motion monitoring data;

[0048] Step 120: Extract ground motion parameters and earthquake parameters from the initial seismic waveform of the strong ground motion data; the ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, significant duration, and Arias intensity; the earthquake parameters include magnitude, epicentral distance, and site parameters.

[0049] Step 130: Input the ground motion parameters, the earthquake parameters, and the building attributes into the real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model for the seismic response of high-rise buildings, and issue an early warning based on the seismic response.

[0050] Specifically, strong ground motion data and a model of the target high-rise building are acquired, and the building attributes of the target high-rise building model are obtained. The strong ground motion data are the data measured by the acceleration sensor at the location of the high-rise building.

[0051] The target high-rise building model is constructed based on high-rise building models with strong-motion monitoring data. Here, six high-rise building models with strong-motion monitoring data can be selected. Because the target high-rise building model is constructed based on strong-motion monitoring data, it can more accurately reflect the real response of high-rise buildings under extreme conditions such as earthquakes. It is understood that strong-motion monitoring data typically comes from sensors installed on high-rise buildings during an earthquake; these sensors can capture and record key parameters such as acceleration and displacement of the building under seismic action in real time.

[0052] Here, magnitude is a measure of the amount of energy released by an earthquake, epicentral distance is the distance from the observation point to the epicenter of the earthquake, and site parameters usually refer to parameters used to reflect the spatial distribution and dynamic characteristics of modern sediments or soil layers covering the bedrock.

[0053] The building attributes include the number of floors, height, structural type, and construction year, etc., which are not specifically limited in this embodiment of the invention. Common building structure types include brick-concrete structure (mostly used in low-rise or multi-story residential buildings), frame structure (mostly used in mid-rise and high-rise buildings), frame-shear wall structure (used to increase the rigidity and integrity of buildings), shear wall structure (mostly used in mid-rise and high-rise buildings), and steel structure (used in super high-rise buildings).

[0054] After acquiring strong ground motion data, ground motion parameters and seismic parameters can be extracted from the initial seismic waveform of the strong ground motion data. Ground motion parameters include peak ground acceleration (PGA), peak ground velocity (PGV), cumulative absolute velocity (CAV), significant duration, and Arias intensity. Seismic parameters include magnitude, epicentral distance, and site parameters.

[0055] Among them, PGA is the maximum absolute value of the acceleration of ground particles during an earthquake. PGV is the maximum velocity describing ground vibration, usually measured in meters per second (m / s). It is a way of representing earthquake amplitude and, together with PGA, is often used to assess the intensity and destructive potential of earthquakes. CAV is the cumulative absolute value of ground particle velocity during an earthquake. It can reflect the total energy and duration of the earthquake and its impact on buildings. Significant duration is a measure of the duration of an earthquake, used to reflect the duration of its impact. Arias intensity is a parameter used to quantify the magnitude of earthquake energy; Arias intensity reflects the total energy and energy distribution of the earthquake.

[0056] Finally, the ground motion parameters, earthquake parameters, and building attributes are input into the real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model for the seismic response of high-rise buildings, and an early warning is issued based on the seismic response.

[0057] Here, the seismic response includes key response indicators such as inter-story drift angle and floor acceleration, which are not specifically limited in this embodiment of the invention.

[0058] For example, it could be based on the acceleration of one floor (e.g., 0.5 or 1.5 m / s²). 2 This threshold serves as an early warning measure for the floor acceleration of high-rise buildings. If the floor acceleration of a high-rise building exceeds this threshold, an early warning will be issued.

[0059] It should be noted that, considering the characteristics of real-time prediction of seismic response of high-rise buildings, a model architecture and optimization strategy were designed. Key parameters of the model were adjusted based on the distribution characteristics of building response data. Furthermore, the network depth, number of neurons, and activation function type of the model were optimized based on the nonlinear relationship between ground motion parameters, seismic parameters, and building attributes. Under low signal-to-noise ratio seismic recording conditions, regularization methods and data augmentation techniques were used to improve the model's generalization ability. Finally, a comparative analysis method was employed to determine a suitable combination of network hyperparameters for real-time seismic response prediction based on the prediction accuracy and physical rationality of key response indicators for high-rise buildings.

[0060] The method provided in this invention acquires strong ground motion data and a target high-rise building model, and obtains the building attributes of the target high-rise building model. Then, it extracts ground motion parameters and seismic parameters from the initial seismic waveform of the strong ground motion data. Finally, it inputs the ground motion parameters, seismic parameters, and building attributes into a real-time seismic response prediction model for high-rise buildings to obtain the seismic response output by the model, and issues an early warning based on the seismic response. Seismic response prediction based on ground motion parameters, seismic parameters, and building attributes can more comprehensively and precisely reflect the impact of earthquakes on high-rise buildings, improving the accuracy and reliability of seismic response prediction. Furthermore, this invention can predict the seismic response of high-rise buildings in real time, efficiently, and accurately, providing important technical support for earthquake early warning and disaster risk reduction, and has good practical value and broad application prospects.

[0061] Based on the above embodiments, the training steps of the real-time prediction model for the seismic response of high-rise buildings include:

[0062] Step 210: Obtain sample ground motion parameters and sample earthquake parameters from the strong ground motion database, and obtain sample building attributes, as well as the labeled seismic responses corresponding to the sample ground motion parameters, the sample earthquake parameters, and the sample building attributes;

[0063] Step 220: Obtain the initial real-time prediction model of the seismic response of high-rise buildings;

[0064] Step 230: Input the sample ground motion parameters, the sample earthquake parameters, and the sample building attributes into the initial high-rise building seismic response real-time prediction model to obtain the predicted seismic response output by the initial high-rise building seismic response real-time prediction model;

[0065] Step 240: Based on the difference between the predicted seismic response and the labeled seismic response, determine the target loss, and perform parameter iteration on the initial high-rise building seismic response real-time prediction model based on the target loss to obtain the high-rise building seismic response real-time prediction model.

[0066] Specifically, to obtain a better real-time prediction model for the seismic response of high-rise buildings, training can be performed based on the following steps:

[0067] First, sample ground motion parameters and sample earthquake parameters are obtained from the strong-motion database, along with sample building attributes and the corresponding labeled seismic responses. Then, an initial real-time prediction model for the seismic response of high-rise buildings is acquired. The strong-motion database is based on earthquakes with magnitudes between 4 and 8, epicentral distances less than 200 km, and site parameters... It was constructed from ground motion data ranging from 100 to 900 m / s.

[0068] Here, the parameters of the initial high-rise building seismic response real-time prediction model can be preset or randomly generated, and the embodiments of the present invention do not specifically limit this.

[0069] The initial real-time prediction model for the seismic response of high-rise buildings is based on deep neural networks (DNNs). The model contains multiple fully connected hidden layers, and the number of neurons and activation function settings of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise buildings.

[0070] The number of neurons in each fully connected hidden layer is a key parameter that directly affects the model's complexity and learning ability. In practical applications, the number of neurons is usually adjusted based on the characteristics of the seismic response data corresponding to high-rise buildings. For example, if the seismic response data contains rich nonlinear features, it may be necessary to increase the number of neurons in the hidden layers to improve the model's fitting ability.

[0071] Activation functions are used to introduce nonlinear characteristics, enabling the network to learn complex function mappings. In real-time prediction models of seismic responses of high-rise buildings, appropriate activation functions (such as ReLU, Sigmoid, or Tanh) can be selected to enhance the model's nonlinear expressive power. The choice of these activation functions will be based on a trade-off between the characteristics of the seismic response data and the model's training performance.

[0072] After obtaining the sample ground motion parameters, sample seismic parameters, and sample building attributes, these parameters can be input into the initial high-rise building seismic response real-time prediction model to obtain the predicted seismic response output by the initial high-rise building seismic response real-time prediction model.

[0073] Finally, based on the difference between the predicted seismic response and the labeled seismic response, the target loss is determined, and the parameters of the initial real-time prediction model of the seismic response of high-rise buildings are iterated based on the target loss. The initial real-time prediction model of the seismic response of high-rise buildings after parameter iteration is used as the real-time prediction model of the seismic response of high-rise buildings.

[0074] Understandably, the greater the difference between the predicted seismic response and the labeled seismic response, the greater the target loss; conversely, the smaller the difference, the smaller the target loss.

[0075] It should be noted that during the training process, network hyperparameter analysis was conducted on the initial real-time prediction model for the seismic response of high-rise buildings. The parameters used were analyzed, and optimal parameters were determined. The effects of changing the model depth, the number of neurons in each hidden layer, the batch size, the learning rate, and the type of optimizer on the real-time prediction results of the seismic response of high-rise buildings were observed to determine the optimal parameters.

[0076] Specifically, the optimal parameters determined are: batch size = 512, activation function = Leakyrelu, optimizer = Adam optimizer, learning rate = 0.0015, and dropout rate = 0.1.

[0077] Further, the steps for training a real-time prediction model of seismic response of high-rise buildings according to this embodiment of the invention include: dividing all sample data into a training set, a test set, and a validation set according to a reasonable division; using the training set and validation set during training; and using the test set as the dataset for testing the predictive ability of the trained model. The model is then evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), and Coefficient of Determination (R²). 2 The prediction accuracy of the model is measured by the following method: Based on the better model, the entire dataset is trained. The number of training iterations is reasonably designed. When the model can achieve convergence of the validation error after multiple iterations and the mean square error of both the training set and the validation set decreases, it indicates that the training effect has been achieved.

[0078] In one example, this embodiment provides a specific implementation method for obtaining a real-time prediction model of the seismic response of high-rise buildings through training:

[0079] The data used were divided into training set: test set: validation set = 0.8: 0.1: 0.1, and the prediction accuracy of the model was measured by mean absolute error, mean square error, root mean square error, and coefficient of determination. Figure 2 This is a graph showing the loss function of the training set and test set provided by this invention, such as... Figure 2 As shown, the loss function during the training process gradually decreases with the increase of the number of training iterations, and the prediction performance of the model is continuously improving. Furthermore, the loss curves of the training set and the test set are quite similar, indicating that the model does not exhibit obvious overfitting. Thus, a real-time prediction model for the seismic response of high-rise buildings has been established.

[0080] In one specific implementation method, the trained high-rise building seismic response prediction model is evaluated, with a focus on analyzing the model's prediction results for maximum inter-story drift ratio (MIDR), maximum peak floor acceleration (MPFA), and peak top floor acceleration (PTFA) on the test set. Figure 3 This is a comparison chart of the maximum inter-story drift angle, maximum floor acceleration, and top floor acceleration provided by the present invention with the actual values ​​on the test set, such as... Figure 3 As shown, a comparison graph of the predicted and target values ​​for three seismic responses—maximum inter-story drift angle, maximum story acceleration, and top-floor acceleration—is presented on the test set. Further quantitative analysis of the model's comprehensive evaluation indices, including mean absolute error (MAE), root mean square error (RMSE), root mean square error (RMSE), and coefficient of determination (COP), is also presented. The results show that the model exhibits high prediction accuracy across all indices on the test set. Specifically, for the prediction of maximum inter-story drift angle, the MAE is 0.291, the RMSE is 0.379, and the R² value is [missing information]. 2 A value of 0.90 indicates that the model can capture the inter-story deformation characteristics of the structure well. For the maximum floor acceleration and the top floor acceleration, R... 2 The results, reaching 0.96 and 0.95, further demonstrate the model's superior performance in acceleration prediction. Furthermore, the model completes its prediction in just 0.001632 seconds, meeting the requirements for real-time early warning.

[0081] In one specific implementation method, the CESMD database provides valuable building monitoring data, including basic building attributes and sensor placement information. Therefore, this paper selects six high-rise buildings with a large amount of measured data (74 sets in total) as case studies for verification. Considering that sensors are installed on the top floors of all buildings, this embodiment selects the monitoring results from the top floors to verify the proposed method. This paper uses acceleration values ​​of 0.5 and 1.5 m / s², referencing the human acceleration perception classification criteria. 2 As a threshold for high-level acceleration warning, if the acceleration exceeds the threshold, people will feel uncomfortable or very uncomfortable. Figure 4 This is the confusion matrix between the measured acceleration data of the top-level model provided by this invention and the prediction results of this model, such as... Figure 4As shown, <Threshold> indicates less than the threshold, ≥Threshold indicates greater than the threshold, True indicates measured, predicted indicates predicted, and the confusion matrix is the accuracy of the predicted classification. By comparing the measured data with the model prediction results in the embodiments of the present invention, it can be seen from the confusion matrix and relevant evaluation indicators that the model adopted in the embodiments of the present invention performs well in the earthquake early warning of high-rise building acceleration, has a high accuracy and precision, up to 94.59% at most, thus determining that the method can better predict the earthquake response of high-rise buildings.

[0082] In summary, Figure 5 is a schematic diagram of the EEWnet network architecture based on DNN provided by the present invention, as Figure 5 shown. The network optimization adopts an adaptive optimization algorithm, combined with a learning rate adjustment strategy to improve the convergence efficiency and prediction accuracy of the model. By adjusting the network architecture, activation function and optimization method, a deep neural network EEWnet (Earthquake Early Warning net) suitable for real-time prediction of high-rise building earthquake responses is constructed. Among them, EEWnet is the real-time prediction model of high-rise building earthquake responses, and EDPs (Engineering Demand Parameters) are the earthquake responses of high-rise buildings.

[0083] The above real-time prediction model and method for high-rise building structure earthquake responses based on deep learning provided in this embodiment establish a real-time prediction model for high-rise building earthquake responses and are verified and tested. Thus, it is determined that the method can better predict the earthquake responses of high-rise buildings, providing an important reference basis for the earthquake early warning of high-rise buildings.

[0084] Based on the above embodiments, the steps for obtaining the labeled earthquake response include:

[0085] Based on the urban seismic elastoplastic analysis method, determine the labeled earthquake response of the target high-rise building under earthquake ground motion.

[0086] Specifically, based on the seismic elastoplastic analysis method, the labeled earthquake response of the target high-rise building under earthquake ground motion can be determined.

[0087] Specifically, based on the multi-degree-of-freedom shear building model, the floor masses of the target high-rise building model are concentrated on a single mass point, and the trilinear backbone curve and single-parameter hysteretic model are used to simulate the nonlinear behavior between floors in the target high-rise building model. Among them, the backbone curve parameters of the trilinear backbone curve are calibrated by a calibration method based on the HAZUS capacity curve database.

[0088] This study employs an open-source seismic damage framework based on urban seismic elastoplastic analysis to calculate the seismic response of high-rise buildings. The model uses a multi-degree-of-freedom shear layer model to simulate the building, concentrating the mass of each floor into a single mass point. The skeleton line of the springs between floors in the multi-degree-of-freedom model adopts the trilinear skeleton line recommended in the HAZUS report, and the hysteresis model adopts a single-parameter hysteresis model. The skeleton line parameters are calibrated using a calibration method based on the HAZUS capacity curve database.

[0089] Based on the above embodiments, step 120 includes:

[0090] Step 121: Use the P-wave automatic identification algorithm to detect the arrival time of the P-wave in the initial waveform of the strong ground motion data.

[0091] Step 122: Based on the arrival time of the P-wave, extract the ground motion record for the first 3 seconds after the arrival time of the P-wave;

[0092] Step 123: Based on the ground motion record of the first 3 seconds, determine the ground motion parameters and the earthquake parameters.

[0093] Specifically, an automatic P-wave identification algorithm is used to detect the arrival time of the P-wave in the initial waveform of strong ground motion data. For example, using P... PHASE P ICKER An algorithm is used to detect the arrival time of the P-wave in the initial waveform of strong ground motion data. PHASE P ICKER The algorithm is an automatic P-wave phase pickup algorithm for single-component acceleration or broadband velocity records. This algorithm converts the seismic signal into the response domain of a viscous damped single-degree-of-freedom (SDOF) oscillator and tracks the rate of change of dissipated damping energy to pick up the P-wave phase. The SDOF oscillator has a short natural period (approximately 0.01 seconds) and a high damping ratio (60%), avoiding resonance. The damping energy is zero at the initial signal stage, approaches zero before the arrival of the P-wave, and increases rapidly upon arrival. Through this energy change, the P-wave phase is automatically picked up. PHASE P ICKER The algorithm can accurately detect the arrival time of the P-wave phase under low signal-to-noise ratio conditions. Using this method to process ground motion records, after identifying the P-wave, the ground motion record of the first 3 seconds is selected, and its ground motion parameters are calculated, including PGA and significant duration (in this embodiment, the time interval between 5% and 95% Arias intensity is selected as the duration indicator, i.e., ...). D S5-95 ), Arias intensity, CAV, PGV, etc.

[0094] Based on any of the above embodiments, a method for real-time prediction of seismic response of high-rise buildings for earthquake early warning includes the following steps:

[0095] The first step, training steps for the real-time prediction model of seismic response of high-rise buildings, includes:

[0096] Sample ground motion parameters and sample earthquake parameters are obtained from the strong ground motion database, along with sample building attributes and the labeled seismic responses corresponding to the sample ground motion parameters, sample earthquake parameters, and sample building attributes. The strong ground motion database is constructed based on ground motion data with magnitudes between 4 and 8, epicentral distances less than 200 km, and site parameters between 100 and 900 m / s.

[0097] Obtain an initial real-time prediction model of the seismic response of high-rise buildings;

[0098] The sample ground motion parameters, sample earthquake parameters, and sample building attributes are input into the initial high-rise building seismic response real-time prediction model to obtain the predicted seismic response output by the initial high-rise building seismic response real-time prediction model.

[0099] Based on the difference between the predicted seismic response and the labeled seismic response, the target loss is determined, and the parameters of the initial real-time prediction model of the seismic response of high-rise buildings are iterated based on the target loss to obtain the real-time prediction model of the seismic response of high-rise buildings.

[0100] The steps for obtaining the labeled seismic response include:

[0101] Based on urban seismic elastoplastic analysis methods, the labeled seismic response of a target high-rise building under seismic action is determined. For example, based on a multi-degree-of-freedom shear layer model, the floor mass of the target high-rise building model is concentrated in a single mass point, and the nonlinear behavior between floors in the target high-rise building model is simulated using a trilinear skeleton line and a single-parameter hysteresis model. The skeleton line parameters of the trilinear skeleton line are calibrated using a calibration method based on the HAZUS capacity curve database.

[0102] The second step is to acquire strong ground motion data and a target high-rise building model, and then acquire the building attributes of the target high-rise building model, which is constructed based on a high-rise building model with strong ground motion monitoring data.

[0103] Among them, the real-time prediction model for the seismic response of high-rise buildings is constructed based on a deep neural network. The real-time prediction model for the seismic response of high-rise buildings contains multiple fully connected hidden layers. The number of neurons and the activation function settings of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise buildings.

[0104] The third step involves employing an automatic P-wave identification algorithm to detect the arrival time of the P-wave in the initial waveform of the strong ground motion data. Based on the P-wave arrival time, the ground motion record for the first 3 seconds following the P-wave arrival time is extracted. Finally, based on this first 3-second ground motion record, the ground motion parameters and earthquake parameters are determined. The ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, duration of significance, and Arias intensity; the earthquake parameters include magnitude, epicentral distance, and site parameters.

[0105] The fourth step involves inputting the ground motion parameters, earthquake parameters, and building attributes into the real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model for the seismic response of high-rise buildings, and issuing early warnings based on the seismic response.

[0106] The following describes the real-time earthquake response prediction device for high-rise buildings for earthquake early warning provided by the present invention. The real-time earthquake response prediction device for high-rise buildings for earthquake early warning described below can be referred to in correspondence with the real-time earthquake response prediction method for high-rise buildings for earthquake early warning described above.

[0107] Based on any of the above embodiments, the present invention provides a real-time prediction device for the seismic response of high-rise buildings for earthquake early warning. Figure 6 This is a structural schematic diagram of the real-time earthquake response prediction device for high-rise buildings for earthquake early warning provided by the present invention, as shown below. Figure 6 As shown, the device includes:

[0108] The acquisition unit 610 is used to acquire strong ground motion data and a target high-rise building model, and to acquire the building attributes of the target high-rise building model; the target high-rise building model is constructed based on a high-rise building model with strong ground motion monitoring data.

[0109] Extraction unit 620 is used to extract ground motion parameters and earthquake parameters from the initial earthquake waveform of the strong ground motion data; the ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, duration of significance, and Arias intensity; the earthquake parameters include magnitude, epicentral distance, and site parameters;

[0110] The prediction unit 630 is used to input the ground motion parameters, the earthquake parameters and the building attributes into the real-time prediction model of the earthquake response of high-rise buildings, obtain the earthquake response output by the real-time prediction model of the earthquake response of high-rise buildings, and make an early warning based on the earthquake response.

[0111] The real-time seismic response prediction model for high-rise buildings is constructed based on a deep neural network.

[0112] The real-time prediction model for the seismic response of high-rise buildings includes multiple fully connected hidden layers. The number of neurons and the activation function of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise buildings.

[0113] The apparatus provided in this invention acquires strong ground motion data and a target high-rise building model, and obtains the building attributes of the target high-rise building model. It then extracts ground motion parameters and seismic parameters from the initial seismic waveform of the strong ground motion data. Finally, the ground motion parameters, seismic parameters, and building attributes are input into a real-time seismic response prediction model for high-rise buildings to obtain the seismic response output by the model, and an early warning is issued based on the seismic response. Seismic response prediction based on ground motion parameters, seismic parameters, and building attributes can more comprehensively and precisely reflect the impact of earthquakes on high-rise buildings, improving the accuracy and reliability of seismic response prediction. Furthermore, this invention can predict the seismic response of high-rise buildings in real time, efficiently, and accurately, providing important technical support for earthquake early warning and disaster risk reduction, and has good practical value and broad application prospects.

[0114] Based on any of the above embodiments, a training unit is further included, wherein the training unit is specifically used for:

[0115] Sample ground motion parameters and sample earthquake parameters are obtained from the strong ground motion database, and sample building attributes are obtained, as well as the labeled earthquake responses corresponding to the sample ground motion parameters, sample earthquake parameters and sample building attributes;

[0116] Obtain an initial real-time prediction model of the seismic response of high-rise buildings;

[0117] The sample ground motion parameters, the sample earthquake parameters, and the sample building attributes are input into the initial high-rise building seismic response real-time prediction model to obtain the predicted seismic response output by the initial high-rise building seismic response real-time prediction model.

[0118] Based on the difference between the predicted seismic response and the labeled seismic response, a target loss is determined, and the parameters of the initial high-rise building seismic response real-time prediction model are iterated based on the target loss to obtain the high-rise building seismic response real-time prediction model.

[0119] Based on any of the above embodiments, a tag seismic response acquisition unit is further included, wherein the tag seismic response acquisition unit is specifically used for:

[0120] Based on the urban seismic elastoplastic analysis method, the labeled seismic response of the target high-rise building under seismic motion is determined.

[0121] Based on any of the above embodiments, the prediction unit 630 is specifically used for:

[0122] Based on the multi-degree-of-freedom shear layer model, the floor mass of the target high-rise building model is concentrated in a single mass point, and the nonlinear behavior between floors in the target high-rise building model is simulated using a trilinear skeleton line and a single-parameter hysteresis model.

[0123] The skeleton line parameters of the trilinear skeleton line are calibrated using a calibration method based on the HAZUS capability curve database.

[0124] Based on any of the above embodiments, the strong ground motion database is constructed based on ground motion data with magnitudes between 4 and 8, epicentral distances less than 200 km, and site parameters between 100 and 900 m / s.

[0125] Based on any of the above embodiments, the extraction unit 620 is specifically used for:

[0126] The P-wave arrival time in the initial waveform of the strong ground motion data is detected by using an automatic P-wave identification algorithm.

[0127] Based on the arrival time of the P-wave, the ground motion record for the first 3 seconds after the arrival time of the P-wave is extracted;

[0128] Based on the ground motion record of the first 3 seconds, the ground motion parameters and the earthquake parameters are determined.

[0129] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 7As shown, the electronic device may include: a processor 710, a communications interface 720, a memory 730, and a communications bus 740, wherein the processor 710, the communications interface 720, and the memory 730 communicate with each other through the communications bus 740. The processor 710 can call logical instructions in the memory 730 to execute a real-time prediction method for the seismic response of high-rise buildings for earthquake early warning. This method includes: acquiring strong ground motion data and a target high-rise building model, and acquiring the building attributes of the target high-rise building model; the target high-rise building model is constructed based on a high-rise building model with strong ground motion monitoring data; extracting ground motion parameters and seismic parameters from the initial seismic waveform of the strong ground motion data; the ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, duration of significance, and Arias intensity; the seismic parameters include magnitude, epicentral distance, and site parameters; inputting the ground motion parameters, the seismic parameters, and the building attributes into the real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model, and issuing an early warning based on the seismic response; the real-time prediction model for the seismic response of high-rise buildings is constructed based on a deep neural network; the real-time prediction model for the seismic response of high-rise buildings contains multiple fully connected hidden layers, and the number of neurons and the activation function settings of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise building.

[0130] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0131] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the real-time prediction method for seismic response of high-rise buildings for earthquake early warning provided by the above methods. The method includes: acquiring strong ground motion data and a target high-rise building model, and acquiring the building attributes of the target high-rise building model; the target high-rise building model is constructed based on a high-rise building model with strong ground motion monitoring data; extracting ground motion parameters and seismic parameters from the initial seismic waveform of the strong ground motion data; the ground motion parameters include peak values. The seismic parameters include ground motion acceleration, peak velocity, cumulative absolute velocity, significant duration, and Arias intensity; the seismic parameters include magnitude, epicentral distance, and site parameters; the ground motion parameters, the seismic parameters, and the building attributes are input into the real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model for the seismic response of high-rise buildings, and an early warning is issued based on the seismic response; the real-time prediction model for the seismic response of high-rise buildings is constructed based on a deep neural network; the real-time prediction model for the seismic response of high-rise buildings contains multiple fully connected hidden layers, and the number of neurons and the activation function settings of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise building.

[0132] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a real-time prediction method for the seismic response of high-rise buildings for earthquake early warning, as provided by the methods described above. This method includes: acquiring strong ground motion data and a target high-rise building model, and acquiring the building attributes of the target high-rise building model; the target high-rise building model is constructed based on a high-rise building model with strong ground motion monitoring data; extracting ground motion parameters and seismic parameters from the initial seismic waveform of the strong ground motion data; the ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, duration of significance, and Arias intensity; the seismic parameters include magnitude, epicentral distance, and site parameters; inputting the ground motion parameters, the seismic parameters, and the building attributes into a real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model, and issuing an early warning based on the seismic response; the real-time prediction model for the seismic response of high-rise buildings is constructed based on a deep neural network; the real-time prediction model for the seismic response of high-rise buildings includes multiple fully connected hidden layers, and the number of neurons and the activation function settings of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise building.

[0133] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for real-time prediction of seismic response of high-rise buildings for earthquake early warning, characterized in that, include: Acquire strong earthquake data and a model of the target high-rise building, and obtain the building attributes of the target high-rise building model; The target high-rise building model is constructed based on a high-rise building model with strong seismic monitoring data; Seismic ground motion parameters and earthquake parameters are extracted from the initial seismic waveform of the strong ground motion data; the seismic ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, significant duration, and Arias intensity; the earthquake parameters include magnitude, epicentral distance, and site parameters. The ground motion parameters, earthquake parameters, and building attributes are input into the real-time prediction model for the seismic response of high-rise buildings to obtain the seismic response output by the real-time prediction model for the seismic response of high-rise buildings, and an early warning is issued based on the seismic response. The real-time seismic response prediction model for high-rise buildings is constructed based on a deep neural network. The real-time prediction model for the seismic response of high-rise buildings includes multiple fully connected hidden layers. The number of neurons and the activation function of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise buildings.

2. The method for real-time prediction of seismic response of high-rise buildings for earthquake early warning as described in claim 1, characterized in that, The training steps for the real-time prediction model of seismic response of high-rise buildings include: Sample ground motion parameters and sample earthquake parameters are obtained from the strong ground motion database, and sample building attributes are obtained, as well as the labeled earthquake responses corresponding to the sample ground motion parameters, sample earthquake parameters and sample building attributes; Obtain an initial real-time prediction model of the seismic response of high-rise buildings; The sample ground motion parameters, the sample earthquake parameters, and the sample building attributes are input into the initial high-rise building seismic response real-time prediction model to obtain the predicted seismic response output by the initial high-rise building seismic response real-time prediction model. Based on the difference between the predicted seismic response and the labeled seismic response, a target loss is determined, and the parameters of the initial high-rise building seismic response real-time prediction model are iterated based on the target loss to obtain the high-rise building seismic response real-time prediction model.

3. The method for real-time prediction of seismic response of high-rise buildings for earthquake early warning as described in claim 2, characterized in that, The steps for obtaining the labeled seismic response include: Based on the urban seismic elastoplastic analysis method, the labeled seismic response of the target high-rise building under seismic motion is determined.

4. The method for real-time prediction of seismic response of high-rise buildings for earthquake early warning as described in claim 3, characterized in that, The method based on urban seismic elastoplastic analysis determines the labeled seismic response of the target high-rise building model under seismic motion, including: Based on the multi-degree-of-freedom shear layer model, the floor mass of the target high-rise building model is concentrated in a single mass point, and the nonlinear behavior between floors in the target high-rise building model is simulated using a trilinear skeleton line and a single-parameter hysteresis model. The skeleton line parameters of the trilinear skeleton line are calibrated using a calibration method based on the HAZUS capability curve database.

5. The method for real-time prediction of seismic response of high-rise buildings for earthquake early warning as described in claim 2, characterized in that, The strong ground motion database is constructed based on ground motion data with magnitudes between 4 and 8, epicentral distances less than 200 km, and site parameters between 100 and 900 m / s.

6. The method for real-time prediction of seismic response of high-rise buildings for earthquake early warning according to any one of claims 1 to 5, characterized in that, The extraction of ground motion parameters and earthquake parameters from the initial earthquake waveform of the strong ground motion data includes: The P-wave arrival time in the initial waveform of the strong ground motion data is detected by using an automatic P-wave identification algorithm. Based on the arrival time of the P-wave, the ground motion record for the first 3 seconds after the arrival time of the P-wave is extracted; Based on the ground motion record of the first 3 seconds, the ground motion parameters and the earthquake parameters are determined.

7. A real-time prediction device for the seismic response of high-rise buildings for earthquake early warning, characterized in that, include: The acquisition unit is used to acquire strong earthquake data and a target high-rise building model, and to acquire the building attributes of the target high-rise building model. The target high-rise building model is constructed based on a high-rise building model with strong seismic monitoring data; The extraction unit is used to extract ground motion parameters and earthquake parameters from the initial seismic waveform of the strong ground motion data; the ground motion parameters include peak ground acceleration, peak ground velocity, cumulative absolute velocity, duration of significance, and Arias intensity; the earthquake parameters include magnitude, epicentral distance, and site parameters. The prediction unit is used to input the ground motion parameters, the earthquake parameters and the building attributes into the real-time prediction model of the earthquake response of high-rise buildings, obtain the earthquake response output by the real-time prediction model of the earthquake response of high-rise buildings, and make an early warning based on the earthquake response; The real-time seismic response prediction model for high-rise buildings is constructed based on a deep neural network. The real-time prediction model for the seismic response of high-rise buildings includes multiple fully connected hidden layers. The number of neurons and the activation function of each fully connected hidden layer are adjusted based on the characteristics of the seismic response data corresponding to the high-rise buildings.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the real-time prediction method for earthquake response of high-rise buildings for earthquake early warning as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the real-time prediction method for seismic response of high-rise buildings for earthquake early warning as described in any one of claims 1 to 6.

Images