CN116911148A - Method and system for evaluating earthquake damage of sedimentary basin building group - Google Patents
Method and system for evaluating earthquake damage of sedimentary basin building group Download PDFInfo
- Publication number
- CN116911148A CN116911148A CN202211446398.2A CN202211446398A CN116911148A CN 116911148 A CN116911148 A CN 116911148A CN 202211446398 A CN202211446398 A CN 202211446398A CN 116911148 A CN116911148 A CN 116911148A
- Authority
- CN
- China
- Prior art keywords
- basin
- neural network
- seismic
- parameters
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000006378 damage Effects 0.000 title claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 claims abstract description 71
- 230000004044 response Effects 0.000 claims abstract description 43
- 230000001133 acceleration Effects 0.000 claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 20
- 230000005405 multipole Effects 0.000 claims abstract description 12
- 238000004062 sedimentation Methods 0.000 claims description 59
- 238000012549 training Methods 0.000 claims description 36
- 238000012360 testing method Methods 0.000 claims description 29
- 239000013049 sediment Substances 0.000 claims description 18
- 238000006073 displacement reaction Methods 0.000 claims description 17
- 239000002245 particle Substances 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 12
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 230000003321 amplification Effects 0.000 claims description 10
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000013016 damping Methods 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 5
- 238000011158 quantitative evaluation Methods 0.000 claims description 5
- 238000012038 vulnerability analysis Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 239000011435 rock Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 12
- 230000002265 prevention Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 11
- 238000004088 simulation Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 230000005669 field effect Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000004613 tight binding model Methods 0.000 description 3
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 230000001808 coupling effect Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The application discloses a method and a system for evaluating earthquake damages of a settlement basin building group, which belong to the technical field of engineering disaster prevention and are characterized in that the method for evaluating the earthquake damages of the settlement basin building group comprises the following steps: s1, determining a target site and characteristic input parameters; s2, establishing a three-dimensional sedimentary basin model, and acquiring an earthquake response; s3, establishing an improved data set: s4, optimizing an artificial neural network; s5, acquiring a sample: s6, determining earthquake motion parameters; s7, prediction and evaluation. According to the method, the calculation efficiency of constructing a data set and evaluating the influence of the uncertainty of the site medium parameters on the basin vibration is sequentially improved through the rapid multipole algorithm and the proxy model, the peak acceleration statistical moment and the probability information of any position of the basin surface can be given out, and the method is applied to rapid prediction and evaluation of the earthquake damage of the building group and serves for toughness cities.
Description
Technical Field
The application belongs to the technical field of engineering disaster prevention, and particularly relates to a method and a system for evaluating earthquake damages of a sediment basin building group.
Background
The scientific determination of the earthquake motion parameters is particularly critical when the determination of the earthquake motion parameters of complex site engineering and the design and analysis of engineering structures are carried out. A large number of towns in China, such as Beijing, uruxole, lanzhou, and the like, are located in sedimentary basins. Because the rock-soil characteristics in the basin are greatly different from those of the outer bedrock, the scattering of seismic waves is caused, the time, space and strong distribution of the ground surface seismic vibration are obviously influenced, and the characteristics of the central focusing effect, the edge amplifying effect, the long period characteristic and the like are particularly shown. Many seismic injury and theoretical studies have shown that basin effects will exacerbate building injury. Due to the soil test conditions, the field medium parameters are often uncertain, and uncertainty transmission occurs in the seismic wave propagation process, so that the building group is uncertain in earthquake damage. Therefore, the development of the evaluation of the earthquake damage of the sedimentary basin building group, which considers the uncertainty of the site medium, has important significance.
The premise of developing prediction and evaluation of earthquake damages of sedimentary basin building groups is to scientifically determine earthquake motion parameters which can consider basin effects and uncertainty of field media. The scholars at home and abroad research the earthquake response and characteristics of the earth surface of the sedimentary basin by using an analytic method and a numerical method. The analytic method is suitable for basins with simple geometric and material conditions, and has wider applicability to sedimentary basins with complex geometric shapes or wave velocity structures based on the numerical simulation method of the three-dimensional fluctuation theory. The existing research results show that the incident wave characteristics and the field medium properties have obvious influence on the seismic response of the sedimentary basin, but the classical regression technology is difficult to quantify the highly nonlinear relation and the multifactor characteristics between the incident wave and the field medium properties and the seismic response of the sedimentary basin, and the numerical simulation method is often required to analyze the problem of uncertainty of the three-dimensional sedimentary basin seismic vibration, so that the regional risk assessment cannot be rapidly performed. Thus, there is a need for a three-dimensional sedimentary basin seismic response solution that can take into account both field effects and field medium uncertainty.
Disclosure of Invention
The application provides a method and a system for evaluating earthquake damages of a settlement basin building group, which are used for solving the technical problems in the prior art, and provides a settlement basin building group earthquake damage evaluation scheme taking the uncertainty of a field medium into consideration for improving the calculation efficiency of a conventional method. According to the scheme, abstract features of complex field effects can be automatically extracted and embodied, a mapping relation based on data driving is constructed, the mapping relation is parameterized by a neural network, and efficient response simulation is carried out on target problems on the premise of ensuring accuracy.
A first object of the present application is to provide a method for evaluating earthquake damage to a settlement basin building group, comprising:
s1, determining a target site and characteristic input parameters:
selecting a sedimentation basin as a target field, determining a seismic vibration frequency band of the sedimentation basin in an actual seismic vibration, a sedimentation basin field medium attribute parameter and a value range, and taking the sedimentation basin as a characteristic input parameter in an artificial neural network basic data set;
s2, establishing a three-dimensional sedimentary basin model, and acquiring seismic response:
establishing a three-dimensional sedimentation basin model, materializing the characteristic input parameters, taking random numbers from each characteristic input parameter in a given value range, and solving the seismic response of the three-dimensional sedimentation basin model under any group of random numbers by adopting a rapid multipole boundary element method, wherein the seismic response under a plurality of groups of random numbers forms an elementary data set;
s3, establishing an improved data set:
on the basis of the first-class data set, the relative position of the earth surface of the sedimentary basin is also used as a characteristic input parameter, and an improved data set is established, wherein the characteristic input parameter is the incidence frequency of the bedrock seismic waves, the attribute of the medium material in the sedimentary basin and the relative position of the earth surface of the sedimentary basin, and the characteristic output parameter is the displacement amplification factor DAF of each position of the earth surface of the sedimentary basin;
s4, optimizing an artificial neural network;
s5, acquiring a sample:
establishing a real case model for solving the target problem, using the trained neural network as a proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin seismic response, solving the basin seismic response corresponding to each sample in the target problem, and rapidly providing the required samples for the Monte Carlo method for analyzing the uncertainty problem;
s6, determining earthquake motion parameters:
according to the actual sediment basin situation, setting uncertain parameters of a field medium, probability distribution and a value range of the uncertain parameters, judging whether a sample overlapped with uncertain characteristics exists in a basic data set, if so, extracting a result from a corresponding improved data set, and if not, calling a proxy model to sequentially calculate uncertain characteristic combinations to obtain the statistical moment of the surface displacement amplification factor, the speed and the acceleration amplitude of the sediment basin; obtaining peak acceleration statistical moment of any position on the surface of the sedimentation basin and peak acceleration corresponding to any confidence coefficient by utilizing inverse fast Fourier transform, and carrying out quantitative evaluation on the influence of the uncertainty of the site medium parameters on the three-dimensional sedimentation basin vibration by utilizing a multi-dimensional result;
s7, prediction and evaluation:
and selecting the peak earthquake vibration acceleration of the ground surface of the sedimentation basin corresponding to different confidence degrees according to actual needs, and carrying out earthquake damage prediction and evaluation of the sedimentation basin building group by combining a local building earthquake vulnerability curve database or vulnerability analysis and considering the uncertainty of the site medium parameters.
Preferably, in S2, the characteristic input parameters are embodied as a bedrock seismic wave incidence frequency, a sedimentary basin internal and external shear wave velocity ratio, a damping ratio and a poisson ratio.
Preferably, S4 is specifically: selecting an artificial neural network structure, dividing the improved data set to obtain a training set, a testing set and a verification set, developing artificial neural network training based on the training set, introducing a differential evolution-particle swarm algorithm to optimize initial weights and thresholds in the training process, and performing parameter selection and network accuracy testing on the artificial neural network based on the testing set and the verification set, wherein the artificial neural network with the best test performance is used as a data driving proxy model for solving the target problem.
A second object of the present application is to provide a sedimentary basin building group seismic hazard assessment system, comprising:
and a data acquisition module: determining a target site and characteristic input parameters, selecting a sedimentation basin as the target site, determining a seismic frequency band of the sedimentation basin in actual seismic, a property parameter and a value range of a medium of the sedimentation basin, and taking the property parameter and the value range as characteristic input parameters in an artificial neural network basic data set;
and a model building module: establishing a three-dimensional sedimentation basin model, acquiring seismic response, establishing the three-dimensional sedimentation basin model, materializing the characteristic input parameters, taking random numbers from each characteristic input parameter in a given value range, solving the seismic response of the three-dimensional sedimentation basin model under any group of random numbers by adopting a rapid multipole boundary element method, and forming an elementary data set by the seismic response under a plurality of groups of random numbers;
a data set improvement module: an improved data set is established, the relative position of the earth surface of the sedimentary basin is also used as a characteristic input parameter on the basis of the first-class data set, the incidence frequency of the base rock seismic waves, the attribute of medium materials in the sedimentary basin and the relative position of the earth surface of the sedimentary basin are used as characteristic input parameters, and the displacement amplification factors DAF of all the positions of the earth surface of the sedimentary basin are used as characteristic output parameters;
and an optimization module: optimizing an artificial neural network;
sample acquisition module: obtaining a sample, establishing a real case model for solving a target problem, using a trained neural network as a proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin seismic response, solving the basin seismic response corresponding to each sample in the target problem, and rapidly providing a required sample for a Monte Carlo method for analyzing the uncertainty problem;
and a parameter determining module: determining earthquake parameters, setting uncertain parameters of a field medium, probability distribution and a value range of the uncertain parameters according to actual sediment basin conditions, judging whether a sample overlapped with uncertain characteristics exists in a basic data set, extracting a result from a corresponding improved data set if the sample is present, and calling a proxy model to sequentially calculate uncertain characteristic combinations if the sample is not present to obtain statistical moments of surface displacement amplification factors, speeds and acceleration amplitudes of the sediment basin; obtaining peak acceleration statistical moment of any position on the surface of the sedimentation basin and peak acceleration corresponding to any confidence coefficient by utilizing inverse fast Fourier transform, and carrying out quantitative evaluation on the influence of the uncertainty of the site medium parameters on the three-dimensional sedimentation basin vibration by utilizing a multi-dimensional result;
the execution module: and (3) predicting and evaluating, namely selecting the earthquake peak acceleration of the ground surface of the sedimentation basin corresponding to different confidence degrees according to actual needs, and combining a local building earthquake vulnerability curve database or vulnerability analysis to develop the earthquake damage prediction and evaluation of the sedimentation basin building group by considering the uncertainty of the site medium parameters.
Preferably, in the model building module, the characteristic input parameters are embodied into the base rock seismic wave incidence frequency, the internal and external shear wave velocity ratio, the damping ratio and the poisson ratio of the sedimentary basin.
Preferably, the optimization process of the optimization module is specifically: selecting an artificial neural network structure, dividing the improved data set to obtain a training set, a testing set and a verification set, developing artificial neural network training based on the training set, introducing a differential evolution-particle swarm algorithm to optimize initial weights and thresholds in the training process, and performing parameter selection and network accuracy testing on the artificial neural network based on the testing set and the verification set, wherein the artificial neural network with the best test performance is used as a data driving proxy model for solving the target problem.
The third object of the application is to provide an information data processing terminal for realizing the method for evaluating earthquake damage of the sedimentary basin building group.
A fourth object of the present application is to provide a computer readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the method of sediment basin building group seismic damage assessment described above.
The application has the advantages and positive effects that:
1) According to the technical scheme provided by the application, the earthquake response of the sedimentary basin under the coupling effect of uncertain factors of various field media can be accurately simulated, and the calculation accuracy and the calculation efficiency can be considered; in order to accurately describe the influence of uncertain parameters of a field medium on the seismic response of a sedimentary basin, a Monte Carlo method is generally adopted, but the calculation samples are more, the calculation cost of a single sample is higher, and the calculation efficiency of the single sample can be greatly improved by adopting an artificial neural network proxy model to replace numerical simulation, so that the uncertainty is efficiently evaluated.
2) The application of the application can reduce the assumption of artificial conditions, obviously reduce the difficulty of analyzing the earthquake motion response of a complex site under the action of uncertain factors, and facilitate the construction engineers to carry out engineering site selection and engineering earthquake motion parameter determination; the method has wide applicability, and other types of complex sites can also be used for constructing proxy models, carrying out the quantification of the vibration uncertainty of the complex sites and the evaluation of the vibration damage of building groups.
Drawings
FIG. 1 is a flow chart of an embodiment of the present application;
FIG. 2 is a flow chart of the ADE-PSO algorithm;
FIG. 3 is a schematic diagram of an artificial neural network
FIG. 4 is a schematic illustration of a sedimentary basin;
FIG. 5 is a graph comparing predicted values to actual values of a neural network;
FIG. 6 is a graph of performance evaluation of a neural network;
FIG. 7 is a graph of statistical moment and probability information of time domain response given by the proxy model;
FIG. 8 is a graph of failure probabilities corresponding to different failure levels of a group of buildings using a peak seismic acceleration of 85% confidence as a seismic intensity indicator.
Detailed Description
For a further understanding of the application, its features and advantages, reference is now made to the following examples, which are illustrated in the accompanying drawings in which:
the following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. Based on the technical solutions of the present application, all other embodiments obtained by a person skilled in the art without making any creative effort fall within the protection scope of the present application.
Related art in the artificial intelligence field is increasingly being used to solve the problem of seismic engineering, with artificial neural networks being most widely used. The artificial neural network is a multi-layer feedforward neural network algorithm combining a back propagation algorithm and a neural network structure, does not need to presuppose a mapping relation, is suitable for constructing a highly nonlinear mapping relation, and can be used as a proxy model for solving related problems. Therefore, the basic idea of the application is to construct a data set required by establishing an artificial neural network proxy model by calculating a small number of samples, introduce a differential-particle swarm algorithm to perform initial optimization on a weight and a threshold, perform three-dimensional sediment basin vibration uncertainty assessment based on a Monte Carlo method after training and testing to obtain a proxy model with good precision, obtain or directly extract the existing result in the data set through the proxy model by a single sample result, not perform numerical simulation any more, reduce the calculation cost of the Monte Carlo method by improving the calculation efficiency of the single sample, realize the three-dimensional sediment basin vibration uncertainty quantification, and be applied to rapid prediction and assessment of building swarm vibration damage. For quickly establishing a data set, a quick multipole boundary element method is adopted to solve the three-dimensional sedimentary basin seismic response under the deterministic parameter condition.
Please refer to fig. 1 to 8.
A method for evaluating earthquake damage of a sedimentary basin building group comprises the following steps:
and step 1, establishing a physical driving model for solving the target problem.
The method is characterized in that a target site is determined, and the geological structure of the sedimentation basin is wide in distribution range, and the planning and design of a large number of cities or building groups also pay attention to the geological feature of the sedimentation basin, so that the semi-ellipsoidal sedimentation basin is selected as the target site. A three-dimensional model is employed to accurately account for the scattering effect of the sedimentary basin on the seismic waves.
And 2, solving the response of the three-dimensional sedimentary basin under seismic excitation by using a numerical simulation method.
FIG. 4 is a numerical model of a sedimentary basin built based on a programming platform. The application adopts a rapid multipole boundary element method to simulate the response of the sedimentary basin under bedrock seismic waves. The fast multipole algorithm can greatly reduce the calculated amount and the storage space and improve the efficiency of establishing a basic data set for the artificial neural network. Firstly, a quick multipole algorithm is utilized to preprocess potential functions, the key steps are that cell nodes in a hierarchical tree structure are introduced, direct actions among units are converted into indirect actions taking the cell nodes as intermediate points, and secondly, the green functions are expanded by adopting taylor series, so that the preprocessing is essentially the rational processing of complex functions. Secondly, carrying out unit division on the surface of the sedimentation basin, the surface of the bedrock and the interface between the bedrock and the sedimentation; then, assuming that the sedimentary basin does not exist, obtaining a free field reaction; then the seismic excitation is equivalent to a virtual load through a green function, the virtual load is applied to a discrete unit, and the fringe field reaction is solved by utilizing boundary conditions and the green function; and finally, synthesizing the free field and the scattered field reaction to obtain the total field reaction. The total field effect is defined as frequency domain displacement amplitude, and the obtained frequency domain displacement amplitude is unfolded by utilizing basic physical relationship, so that frequency domain speed and acceleration amplitude can be obtained. The rapid multipole boundary element algorithm can be directly realized based on an open source programming platform, and the three-dimensional sedimentary basin physical model can also be directly established through programming languages, so that the operation difficulty of various complex software is greatly reduced.
And 3, determining uncertain parameters and value ranges.
The uncertain factors influencing the vibration response of the sedimentary basin and the value range thereof are determined after the comprehensive consideration of the existing database, related documents and national standard are researched, and the model category, modeling mode, site medium attribute, geometric attribute, boundary condition and the like are defined. The application selects the internal and external shear wave speed ratio of the sedimentary basin, the Poisson ratio of the sedimentary basin and the damping ratio as uncertain parameters, namely agent conditions for representing the uncertainty of the field medium attribute, and simultaneously takes the frequency of incident waves as the uncertainty parameters and gives a value range.
And 4, establishing a basic data set of 'uncertain parameters-sedimentary basin seismic response'.
Generating corresponding random data sets for the four random variables determined in the step 3 based on a random seed command of the Matlab programming platform, wherein each data set represents one random variable, the data in the set is required to be within a set reference range, and the dimensions of the four data sets are required to be consistent. Four data sets form a basic data set, the basic data set is input into the physical model established in the step 2, and the three-dimensional sedimentary basin seismic effect under the condition of each data set is calculated sequentially by using a rapid multipole boundary element method; after the simulation is completed, extracting all basin surface point frequency domain displacement amplitude values from the simulation result to reduce the number of output parameters of the artificial neural network, wherein Cartesian coordinates of the basin surface position are also used as input characteristic parameters for constructing a proxy model; orderly combining the basic data set, the frequency domain displacement amplitude of any basin surface point and the position coordinates by using the ordering command to form a group of improved data sets; each sample of the improvement dataset represents the meaning: and under the condition that four uncertain parameters are fixed values, depositing the frequency domain displacement amplitude corresponding to a certain earth surface point of the basin.
And 5, establishing a proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin.
Randomly dividing the improved data set obtained in the step 4 to obtain a training set and a testing set, training the artificial neural network by using the training set, and testing the performance of the artificial neural network by using the testing set; the ratio of training set to test set was 8:2.
FIG. 2 is a flow of a differential evolution-particle swarm optimization algorithm, ADE stands for the differential evolution algorithm, PSO stands for the particle swarm algorithm, and ANN stands for the artificial neural network; the algorithm can optimize the weights and the thresholds of an input layer and a hidden layer in the artificial neural network, and randomly generate a population for corresponding weight and threshold individuals through a differential evolution-particle swarm optimization algorithm. Parameters of the differential evolution-particle swarm optimization algorithm are initialized, including convergence threshold, population size, inertia weight, maximum iteration number, maximum particle count, intersection rate, variation rate, and upper and lower limits of positions.
The artificial neural network is trained and the fitness of each particle is calculated. And comparing the sizes of the adaptation degrees, and selecting local optimal particles and global optimal particles in the particle population. Updating the speed and position of the particles, coding the obtained new population, and carrying out selection, genetic crossover and mutation operation on the particles on the population. Judging whether convergence conditions are met, if so, obtaining optimal weights and thresholds, giving the artificial neural network and training. If the condition is not satisfied, the iteration times are increased, and the related flow of the optimization algorithm is repeated until the convergence condition is satisfied. And obtaining a weight and a threshold meeting the requirements, and giving an artificial neural network to train.
Setting network structure parameters of the artificial neural network. As shown in fig. 3, the artificial neural network of the present application adopts a four-layer network structure, which includes an input layer, two hidden layers, and an output layer. The structural parameters of the artificial neural network comprise the number of nodes of an input layer, the number of nodes of a two-layer hidden layer, the number of nodes of an output layer, the activation function of each layer, a training function, a learning rate, a set convergence error, training times and maximum failure times. The number of nodes of the input layer and the number of nodes of the output layer are determined according to the studied problems, the number of the nodes of the input layer is 6, and the number of the nodes of the output layer is 1. The node number of the two layers of hidden layers is determined by adopting a trial and error method, the node range of the two layers of hidden layers is roughly determined through a large number of experiments, then the neural network in the node range is trained by using the same training sample, the neural network with the minimum test set error is selected as a final proxy model, and the node numbers of the two layers of hidden layers are 38 and 32 respectively. The activation function of each layer is a tanh function, the gradient descent method is adopted to carry out self-adaptive adjustment on errors in the neural network training process, the training function is a traingdm function, and the evaluation functions are MSE and Loss functions. And a regularization technology is added in the training process, so that the occurrence of the over-fitting phenomenon of the neural network is reduced, and other related parameters can be determined according to a large number of experimental methods. A well-trained neural network can be used as a proxy model for analyzing three-dimensional sedimentary basin uncertainty problems. Firstly, carrying out normalization pretreatment on data to be predicted, and then carrying out simulation prediction on the normalized data by using a proxy model to obtain the frequency domain displacement amplitude of each basin surface point under the working condition.
And 6, evaluating the accuracy and the applicability of the artificial neural network.
In order to fully evaluate the generalization capability of the artificial neural network to solve the problem, three indexes are adopted for evaluation. The residual and root mean square errors are calculated as dimension indicators to evaluate the deviation between the predicted and actual values of the individual samples and test sets. The model is also evaluated by using the decision coefficients in the dimensionless index, and the value range is [0,1]. The method aims to measure the degree of the independent variable interpretation dependent variable, and the closer the decision coefficient is to 1, the higher the applicability of the proxy model is, and the complex mapping relation between input and output can be accurately captured. Fig. 5 shows a comparison of the predicted and expected results given by means of an artificial neural network, RMSE representing the root mean square error, it can be seen that the comparison of the two results is good and the root mean square error is small in the sample interval in question. FIG. 6 shows the decision coefficients of the artificial neural network on the training set and the test set, and the decision coefficients of the two sets of data sets are both larger than 0.96, which indicates that the agent model established by the application belongs to an excellent model and has stronger generalization capability on target problems.
And 7, quantifying the vibration uncertainty of the three-dimensional sedimentary basin based on the proxy model.
The result of the uncertainty problem is usually solved by adopting a classical Monte Carlo method, the randomness of data distribution is emphasized in the establishment process of the algorithm, and the result is solved by means of a probability statistics correlation theory. The Monte Carlo method needs to calculate a large number of uncertainty samples, solves moment response and probability information of a target problem by carrying out statistical analysis, has high requirements on the number of the calculated samples, and can reach the number of the samples under the excitation of seismic waves in different frequency bands. The artificial neural network proxy model with good training can be used as a proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin, and has the advantage that compared with the traditional numerical simulation method, the proxy model has remarkable improvement on the calculation efficiency.
After training, the artificial neural network can be directly stored through a programming language, and can be directly called by a relevant platform when needed, and training is not needed. After the call, the proxy model is applied to solve the actual problem. According to the actual sediment basin situation, quantifying the value range of the uncertain factors (the frequency of incident waves, the ratio of internal shear waves to external shear waves, the poisson ratio and the damping), firstly judging whether a sample coincident with the uncertain factors exists in the basic data set, if so, directly extracting the result from the corresponding improved data set, and if not, then calling the neural network to sequentially calculate the uncertain factor combination. According to the application, the output parameters of the proxy model are the frequency domain displacement amplitude of the basin surface point, and the frequency domain velocity and the acceleration amplitude can be obtained through the calculation of the first derivative and the second derivative. The statistical moment of the frequency domain can obtain the acceleration time course and the peak acceleration statistical moment through the inverse Fourier transform technology. Three typical time domain statistical moment results are shown in fig. 7, which show that the agent model established in the research can effectively develop multidimensional indexes to determine the earthquake motion parameters of the sedimentary basin under the influence of uncertain coupling of bedrock earthquake waves and medium parameters.
And 8, carrying out building group earthquake damage assessment by combining a local building structure earthquake vulnerability database.
As shown in fig. 8, the confidence level to be met by the earthquake motion parameters is determined according to the actual requirements, the earthquake motion peak acceleration is taken as the earthquake motion intensity parameter, and the failure probabilities corresponding to different damage levels of regional building groups are obtained by combining the local existing building structure vulnerability database, so that the earthquake motion peak acceleration is used for predicting the unfavorable regions before earthquake or building and rapidly evaluating after earthquake.
In summary, the application establishes a physical driving model for solving the target problem, solves the three-dimensional sedimentation basin seismic response under a small amount of deterministic parameters by using a numerical simulation method, establishes an uncertain parameter-sedimentation basin seismic response basic data set, sets the basin surface position coordinates as input characteristic parameters, and establishes an improved data set; based on the improved data set, a high-precision proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin is established by utilizing an artificial neural network; then quantifying the vibration uncertainty of the three-dimensional sedimentary basin based on the proxy model, so that the calculation efficiency of the conventional Monte Carlo method can be greatly improved; finally, the sediment basin building group is subjected to pre-earthquake prediction and post-disaster evaluation by combining with a building earthquake vulnerability database, so that the method has good application value.
The utility model provides a deposit basin building crowd earthquake hazard evaluation system for realize above-mentioned deposit basin building crowd earthquake hazard evaluation method, include:
and a data acquisition module: determining a target site and characteristic input parameters, selecting a sedimentation basin as the target site, determining a seismic frequency band of the sedimentation basin in actual seismic, a property parameter and a value range of a medium of the sedimentation basin, and taking the property parameter and the value range as characteristic input parameters in an artificial neural network basic data set;
and a model building module: establishing a three-dimensional sedimentation basin model, acquiring seismic response, establishing the three-dimensional sedimentation basin model, embodying the characteristic input parameters into bedrock seismic wave incidence frequency, sediment basin internal and external shear wave speed ratio, damping ratio and poisson ratio, taking random numbers from each characteristic input parameter in a given value range, solving the seismic response of the three-dimensional sedimentation basin model under any group of random numbers by adopting a rapid multipole boundary element method, and forming an elementary data set by the seismic response under a plurality of groups of random numbers;
a data set improvement module: an improved data set is established, the relative position of the earth surface of the sedimentary basin is also used as a characteristic input parameter on the basis of the first-class data set, the incidence frequency of the base rock seismic waves, the attribute of medium materials in the sedimentary basin and the relative position of the earth surface of the sedimentary basin are used as characteristic input parameters, and the displacement amplification factors DAF of all the positions of the earth surface of the sedimentary basin are used as characteristic output parameters;
and an optimization module: optimizing an artificial neural network; selecting an artificial neural network structure, dividing the improved data set to obtain a training set, a testing set and a verification set, developing artificial neural network training based on the training set, introducing a differential evolution-particle swarm algorithm to optimize initial weights and thresholds in the training process, and performing parameter selection and network accuracy testing on the artificial neural network based on the testing set and the verification set, wherein the artificial neural network with the best test performance is used as a data driving proxy model for solving the target problem;
sample acquisition module: obtaining a sample, establishing a real case model for solving a target problem, using a trained neural network as a proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin seismic response, solving the basin seismic response corresponding to each sample in the target problem, and rapidly providing a required sample for a Monte Carlo method for analyzing the uncertainty problem;
and a parameter determining module: determining earthquake parameters, setting uncertain parameters of a field medium, probability distribution and a value range of the uncertain parameters according to actual sediment basin conditions, judging whether a sample overlapped with uncertain characteristics exists in a basic data set, extracting a result from a corresponding improved data set if the sample is present, and calling a proxy model to sequentially calculate uncertain characteristic combinations if the sample is not present to obtain statistical moments of surface displacement amplification factors, speeds and acceleration amplitudes of the sediment basin; obtaining peak acceleration statistical moment of any position on the surface of the sedimentation basin and peak acceleration corresponding to any confidence coefficient by utilizing inverse fast Fourier transform, and carrying out quantitative evaluation on the influence of the uncertainty of the site medium parameters on the three-dimensional sedimentation basin vibration by utilizing a multi-dimensional result;
the execution module: and (3) predicting and evaluating, namely selecting the earthquake peak acceleration of the ground surface of the sedimentation basin corresponding to different confidence degrees according to actual needs, and combining a local building earthquake vulnerability curve database or vulnerability analysis to develop the earthquake damage prediction and evaluation of the sedimentation basin building group by considering the uncertainty of the site medium parameters.
An information data processing terminal is used for realizing the method for evaluating the earthquake damage of the sediment basin building group.
A computer readable storage medium comprising instructions that when run on a computer cause the computer to perform the above-described sedimentary basin building crowd earthquake hazard assessment method.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When used in whole or in part, is implemented in the form of a computer program product comprising one or more computer instructions. When loaded or executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the application in any way, but any simple modification, equivalent variation and modification of the above embodiments according to the technical principles of the present application are within the scope of the technical solutions of the present application.
Claims (8)
1. A method for evaluating earthquake damage to a settlement basin building group, comprising the steps of:
s1, determining a target site and characteristic input parameters:
selecting a sedimentation basin as a target field, determining a seismic vibration frequency band of the sedimentation basin in an actual seismic vibration, a sedimentation basin field medium attribute parameter and a value range, and taking the sedimentation basin as a characteristic input parameter in an artificial neural network basic data set;
s2, establishing a three-dimensional sedimentary basin model, and acquiring seismic response:
establishing a three-dimensional sedimentation basin model, materializing the characteristic input parameters, taking random numbers from each characteristic input parameter in a given value range, and solving the seismic response of the three-dimensional sedimentation basin model under any group of random numbers by adopting a rapid multipole boundary element method, wherein the seismic response under a plurality of groups of random numbers forms an elementary data set;
s3, establishing an improved data set:
on the basis of the first-class data set, the relative position of the earth surface of the sedimentary basin is also used as a characteristic input parameter, and an improved data set is established, wherein the characteristic input parameter is the incidence frequency of the bedrock seismic waves, the attribute of the medium material in the sedimentary basin and the relative position of the earth surface of the sedimentary basin, and the characteristic output parameter is the displacement amplification factor DAF of each position of the earth surface of the sedimentary basin;
s4, optimizing an artificial neural network;
s5, acquiring a sample:
establishing a real case model for solving the target problem, using the trained neural network as a proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin seismic response, solving the basin seismic response corresponding to each sample in the target problem, and rapidly providing the required samples for the Monte Carlo method for analyzing the uncertainty problem;
s6, determining earthquake motion parameters:
according to the actual sediment basin situation, setting uncertain parameters of a field medium, probability distribution and a value range of the uncertain parameters, judging whether a sample overlapped with uncertain characteristics exists in a basic data set, if so, extracting a result from a corresponding improved data set, and if not, calling a proxy model to sequentially calculate uncertain characteristic combinations to obtain the statistical moment of the surface displacement amplification factor, the speed and the acceleration amplitude of the sediment basin; obtaining peak acceleration statistical moment of any position on the surface of the sedimentation basin and peak acceleration corresponding to any confidence coefficient by utilizing inverse fast Fourier transform, and carrying out quantitative evaluation on the influence of the uncertainty of the site medium parameters on the three-dimensional sedimentation basin vibration by utilizing a multi-dimensional result;
s7, prediction and evaluation:
and selecting the peak earthquake vibration acceleration of the ground surface of the sedimentation basin corresponding to different confidence degrees according to actual needs, and carrying out earthquake damage prediction and evaluation of the sedimentation basin building group by combining a local building earthquake vulnerability curve database or vulnerability analysis and considering the uncertainty of the site medium parameters.
2. The sedimentary basin building group seismic damage assessment method of claim 1, wherein in S2, the characteristic input parameters are embodied as bedrock seismic wave incidence frequency, sedimentary basin internal and external shear wave velocity ratio, damping ratio and poisson ratio.
3. The method for evaluating earthquake damage to a sedimentary basin building group according to claim 2, wherein S4 is specifically: selecting an artificial neural network structure, dividing the improved data set to obtain a training set, a testing set and a verification set, developing artificial neural network training based on the training set, introducing a differential evolution-particle swarm algorithm to optimize initial weights and thresholds in the training process, and performing parameter selection and network accuracy testing on the artificial neural network based on the testing set and the verification set, wherein the artificial neural network with the best test performance is used as a data driving proxy model for solving the target problem.
4. A sedimentary basin building crowd-hazard assessment system, comprising:
and a data acquisition module: determining a target site and characteristic input parameters, selecting a sedimentation basin as the target site, determining a seismic frequency band of the sedimentation basin in actual seismic, a property parameter and a value range of a medium of the sedimentation basin, and taking the property parameter and the value range as characteristic input parameters in an artificial neural network basic data set;
and a model building module: establishing a three-dimensional sedimentation basin model, acquiring seismic response, establishing the three-dimensional sedimentation basin model, materializing the characteristic input parameters, taking random numbers from each characteristic input parameter in a given value range, solving the seismic response of the three-dimensional sedimentation basin model under any group of random numbers by adopting a rapid multipole boundary element method, and forming an elementary data set by the seismic response under a plurality of groups of random numbers;
a data set improvement module: an improved data set is established, the relative position of the earth surface of the sedimentary basin is also used as a characteristic input parameter on the basis of the first-class data set, the incidence frequency of the base rock seismic waves, the attribute of medium materials in the sedimentary basin and the relative position of the earth surface of the sedimentary basin are used as characteristic input parameters, and the displacement amplification factors DAF of all the positions of the earth surface of the sedimentary basin are used as characteristic output parameters;
and an optimization module: optimizing an artificial neural network;
sample acquisition module: obtaining a sample, establishing a real case model for solving a target problem, using a trained neural network as a proxy model for analyzing the uncertainty problem of the three-dimensional sedimentary basin seismic response, solving the basin seismic response corresponding to each sample in the target problem, and rapidly providing a required sample for a Monte Carlo method for analyzing the uncertainty problem;
and a parameter determining module: determining earthquake parameters, setting uncertain parameters of a field medium, probability distribution and a value range of the uncertain parameters according to actual sediment basin conditions, judging whether a sample overlapped with uncertain characteristics exists in a basic data set, extracting a result from a corresponding improved data set if the sample is present, and calling a proxy model to sequentially calculate uncertain characteristic combinations if the sample is not present to obtain statistical moments of surface displacement amplification factors, speeds and acceleration amplitudes of the sediment basin; obtaining peak acceleration statistical moment of any position on the surface of the sedimentation basin and peak acceleration corresponding to any confidence coefficient by utilizing inverse fast Fourier transform, and carrying out quantitative evaluation on the influence of the uncertainty of the site medium parameters on the three-dimensional sedimentation basin vibration by utilizing a multi-dimensional result;
the execution module: and (3) predicting and evaluating, namely selecting the earthquake peak acceleration of the ground surface of the sedimentation basin corresponding to different confidence degrees according to actual needs, and combining a local building earthquake vulnerability curve database or vulnerability analysis to develop the earthquake damage prediction and evaluation of the sedimentation basin building group by considering the uncertainty of the site medium parameters.
5. The sedimentary basin building group seismic damage assessment system of claim 4, wherein the characteristic input parameters are embodied in a model building module as bedrock seismic wave incidence frequency, sedimentary basin internal and external shear wave velocity ratio, damping ratio and poisson ratio.
6. The sedimentation basin group seismic damage evaluation system of claim 5, wherein the optimization process of the optimization module is specifically: selecting an artificial neural network structure, dividing the improved data set to obtain a training set, a testing set and a verification set, developing artificial neural network training based on the training set, introducing a differential evolution-particle swarm algorithm to optimize initial weights and thresholds in the training process, and performing parameter selection and network accuracy testing on the artificial neural network based on the testing set and the verification set, wherein the artificial neural network with the best test performance is used as a data driving proxy model for solving the target problem.
7. An information data processing terminal, characterized by being used for realizing the method for evaluating earthquake damage of a sedimentation basin building group according to any one of claims 1-3.
8. A computer readable storage medium comprising instructions that when run on a computer cause the computer to perform a method of performing the sedimentary basin building group seismic damage assessment method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211446398.2A CN116911148A (en) | 2022-11-18 | 2022-11-18 | Method and system for evaluating earthquake damage of sedimentary basin building group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211446398.2A CN116911148A (en) | 2022-11-18 | 2022-11-18 | Method and system for evaluating earthquake damage of sedimentary basin building group |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116911148A true CN116911148A (en) | 2023-10-20 |
Family
ID=88367403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211446398.2A Pending CN116911148A (en) | 2022-11-18 | 2022-11-18 | Method and system for evaluating earthquake damage of sedimentary basin building group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911148A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117972437A (en) * | 2024-03-29 | 2024-05-03 | 四川省建筑设计研究院有限公司 | Regional building earthquake damage prediction method and system aiming at complex terrain geological conditions |
-
2022
- 2022-11-18 CN CN202211446398.2A patent/CN116911148A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117972437A (en) * | 2024-03-29 | 2024-05-03 | 四川省建筑设计研究院有限公司 | Regional building earthquake damage prediction method and system aiming at complex terrain geological conditions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108491931B (en) | Method for improving nondestructive testing precision based on machine learning | |
| CN105893669A (en) | Global simulation performance predication method based on data digging | |
| Wen et al. | Rapid seismic response prediction of RC frames based on deep learning and limited building information | |
| CN113687433A (en) | Bi-LSTM-based magnetotelluric signal denoising method and system | |
| CN115270635A (en) | Bayes-neural network high-rise building earthquake demand and vulnerability prediction method | |
| CN115130375A (en) | Rock burst intensity prediction method | |
| CN111709072B (en) | Underground vibration amplitude parameter prediction method | |
| CN105044775A (en) | Seismic fluid inversion identification method and apparatus | |
| CN113009553A (en) | Interpretable seismic motion parameter probability density distribution prediction method based on NGboost and SHAP values | |
| CN114792020B (en) | Quick evaluation method and system for building anti-seismic toughness based on machine learning | |
| CN115654381A (en) | Water supply pipeline leakage detection method based on graph neural network | |
| Lu et al. | Regional ground‐motion simulation using recorded ground motions | |
| Al-saffar et al. | Prediction of soil's compaction parameter using artificial neural network | |
| CN115221793A (en) | Tunnel surrounding rock deformation prediction method and device | |
| Fayaz et al. | Assessment of ground motion amplitude scaling using interpretable Gaussian process regression: Application to steel moment frames | |
| YiFei et al. | Metamodel-assisted hybrid optimization strategy for model updating using vibration response data | |
| Karimzadeh et al. | Stochastic simulation of earthquake ground motions for the seismic assessment of monumental masonry structures: Source‐based vs site‐based approaches | |
| CN104102716A (en) | Imbalance data predicting method based on cluster stratified sampling compensation logic regression | |
| CN116911148A (en) | Method and system for evaluating earthquake damage of sedimentary basin building group | |
| CN111382908A (en) | Earthquake random event set simulation method considering large earthquake time correlation | |
| CN116992522A (en) | Deep foundation pit support structure deformation prediction method, device, equipment and storage medium | |
| Guo et al. | The back propagation based on the modified group method of data-handling network for oilfield production forecasting | |
| Wei | Genetic Algorithm Optimization of Concrete Frame Structure Based on Improved Random Forest | |
| CN115482882A (en) | Pipeline corrosion data acquisition and pipeline corrosion rate prediction model construction method | |
| CN114117753A (en) | Vulnerability-based probabilistic earthquake slope slip risk analysis method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |