50 results about "Seismic risk" patented technology

Disclosed in the present invention is an anti-seismic simulation method for an existing building by considering a real damage state. The method comprises: determining a quantified component damage index on the basis of an observed component damage state; determining a material damage index of a damaged component on the basis of the component damage index; determining key parameters of a constitutive law for a damaged material on the basis of the material damage index; establishing a finite element model of a damaged building on the basis of the constitutive law for the material of the damaged component; and assessing the seismic risk and anti-seismic performance of the damaged building on the basis of the finite element model. In the present invention, a constitutive law for a damaged material is incorporated into a fiber model in OpenSEES, so that rapid modeling of a damaged building can be realized, thereby effectively reproducing the real damage of an existing building; and by using a seismic vulnerability analysis method, rapid assessment of the seismic risk and anti-seismic capability of the existing building can be realized, thereby further providing support for formulating reasonable reinforcement and reconstruction strategies by related departments.

The embodiment of the invention provides a pipeline seismic data quality optimization and risk evaluation grade prediction method, which can solve the technical problem of poor pipeline seismic risk evaluation capability. The pipeline seismic data quality optimization and risk evaluation grade prediction method comprises the following steps: acquiring risk data to obtain a first risk data set, a second risk data set and a third risk data set; training a plurality of risk models based on the first risk data set; inputting the second risk data set into each risk model to obtain a risk result output by each risk model; obtaining an error data set based on the risk result of each risk model; eliminating an error data set in the third risk data set to obtain a fourth risk data set; and based on the fourth risk data set, training each risk model to obtain a target risk model. According to the method, through multi-model cross validation, the pipeline seismic data collection quality is improved, a model with higher prediction precision is obtained, and accurate and dynamic prediction of the pipeline seismic risk level is realized.

The invention provides an earthquake risk assessment method and system for a medium-strong earthquake region, and belongs to the technical field of earthquake risk assessment, and the method comprises the steps: carrying out the partitioning construction of an earthquake region, and obtaining a plurality of structural regions; fitting data of historical earthquakes and modern small and medium earthquakes in each structural area to obtain an earthquake magnitude-frequency relational expression, and calculating to obtain an incidence rate, an earthquake generation probability and a recurrence interval of any level of earthquake in each structural area; and for each structural area, a spatial smoothing method is used to distribute weights such as the occurrence rate, the earthquake generation probability and the recurrence interval of any grade of earthquake in each earthquake grade, and the like, to each fault zone. According to the method, the seismic activity model is established by using the spatial smoothing method, after smoothing processing, the earthquake risk is generally improved and is close to the historical earthquake occurrence situation, and for the areas with unclear earthquake-generating structures and weak seismic activities, the earthquake with large energy release occupies a more important position in distribution, so that the seismic activity is improved. And the potential danger of the earthquake activity can be reflected more accurately.

The invention relates to the technical field of building anti-seismic risk assessment, and discloses a building anti-seismic potential safety hazard assessment method and system based on multi-factor coupling, and the method comprises the following steps: collecting key factors of potential safety hazards of a to-be-assessed building, and endowing each piece of key factor information with a discrete value; constructing a nonlinear coupling model through key factor construction and an interaction effect between key factors; building state information is monitored in real time through a sensor, a damage or collapse possibility index is corrected according to monitoring data to obtain a correction value, and a second comprehensive risk value is obtained through recalculation; and according to the second comprehensive risk value obtained through calculation, building anti-seismic safety risk grades are divided. According to the method, the damage possibility index and the accident consequence severity index are constructed, the comprehensive risk value is calculated according to the damage possibility index and the accident consequence severity index, quantitative modeling evaluation from static attributes to the risk value is achieved, and the method is more scientific and objective compared with a traditional single-factor evaluation method with high empirical and subjective performance.

The invention relates to the technical field of geothermal pipe network monitoring, in particular to a geothermal pipe network intelligent monitoring method and system based on edge calculation. The method comprises the following steps: acquiring a sound pressure signal, a vibration signal and a pressure signal in real time, and performing first-order difference calculation based on the pressure signal to obtain a pressure difference change sequence; inputting the sound pressure signal and the vibration signal into a micro-seismic intelligent identification model, outputting a micro-seismic risk quantitative scoring index, generating an execution regulation and control instruction, and recording execution feedback data to form a micro-seismic scoring feedback data set; performing time sequence reconstruction on the pressure difference change sequence by using a neural differential equation model, identifying an abnormal propagation source point and a shortest propagation path, and constructing a water hammer propagation response structural body; and the microseismic score feedback data set and the water hammer propagation response structural body are transmitted to a cloud platform, and the state of the geothermal pipe network is monitored and early warned in real time. According to the invention, intelligent monitoring and tracking of the micro-seismic abnormal state and the water hammer effect of the geothermal pipe network are realized.

The present invention discloses a seismic monitoring system, which relates to the technical field of intelligent monitoring. The system includes a data acquisition module, a data analysis module, and a feedback module. A source movement map is constructed to obtain a movement trajectory, and sub-maps are cut. The ratio of the area of the seismic wave range contained in the sub-map to the area of the cutting frame is calculated, the concentration level is divided, the earthquake-prone factor is calculated, the concentration level corresponding to the dangerous sub-map is obtained, the earthquake-prone factor corresponding to the dangerous sub-map is calculated, a warning signal is issued, and warning lights of different brightness and different colors are displayed. By constructing a source movement map through historical data, the present invention improves the timeliness and accuracy of early warning, analyzes the source position and its movement trajectory, improves the response ability to seismic activities, issues corresponding warning signals for different risk-level regions, realizes a more refined early warning service, intuitively displays the seismic risk level, can provide a more comprehensive risk assessment, and improves the scientificity and reliability of the early warning system.

The present application relates to a kind of assembled frame structure earthquake response prediction algorithm based on LSTM algorithm, by establishing full-scale structure model and using ABAQUS to carry out nonlinear time-history analysis, obtain ground motion and inter-story displacement response data, construct structure earthquake response database.Based on the numerical simulation result, establish deep learning architecture, by the sensitivity study of window length, hidden layer and training sample size, use R and RMSE such as index to evaluate model performance, and select the model with minimum validation loss as the final prediction model.In the prediction phase, input any ground motion record can quickly generate complete inter-story displacement time-history through recursive slicing and step-by-step updating mechanism, so as to realize the efficient estimation of aluminum alloy foam concrete structure earthquake response.The present application can replace the high-cost iterative calculation of traditional finite element analysis, and provide fast and reliable decision support for regional seismic risk assessment, structure safety determination and aluminum alloy foam concrete structure seismic design.

The application discloses a seismic risk evaluation method and system, relates to the technical field of seismic numerical simulation, and receives a three-dimensional geometric model of a gridded fault and sets initial conditions; a simulation operation equation is constructed to solve a shear stress loading rate, a normal stress loading rate and a state variable, and a common differential equation system is constructed; based on the three-dimensional geometric model and the initial conditions, the common differential equation system is used to realize accelerated simulation operation of the shear stress loading rate, the normal stress loading rate and the state variable, wherein the method of the accelerated simulation operation comprises: using a method combining an H-matrix and MPI to accelerate simulation operation, comprising obtaining a layered matrix based on a Green function under a half-space condition in combination with an adaptive cross approximation algorithm, comprising a normal stiffness H-matrix and a shear stiffness H-matrix, and using MPI parallel operation matrix-vector multiplication. The application introduces a hierarchical matrix and fuses an MPI parallel computing framework, so that the simulation period is greatly shortened.

The application provides a substation steel structure earthquake risk early warning method and device, equipment and medium, and the method comprises the steps of: constructing a foundation soil-substation steel structure model and a half-space site model; based on an indirect boundary element method, simulating the seismic response according to the half-space site model and the foundation soil-substation steel structure model to determine a risk grade early warning table; acquiring a target displacement response of the substation steel structure in real time; and analyzing the target displacement response and the risk grade early warning table to determine the seismic risk grade of the current substation steel structure. The application simulates and calculates the displacement response of the substation steel structure under different seismic risk grades based on the indirect boundary element method, the half-space site model and the foundation soil-substation steel structure model, can automatically meet the infinite boundary condition, reduces the problem dimension, improves the solving accuracy, thereby obtains more accurate seismic response of the substation steel structure, and can accurately monitor the risk grade of the substation steel structure.

The present invention provides a method for evaluating the seismic loss probability of a building complex based on the simulation of ground motion intensity random field, belonging to the technical field of seismic loss assessment. The method provided by the present invention first uses the ground motion intensity random field simulation technology to simulate the ground motion of the region, obtains the spatial distribution of ground motion intensity at different sites, and then estimates the loss probability distribution of each building by using the building seismic performance model and the building vulnerability database. This method can more quickly and accurately evaluate the occurrence probability of extreme seismic losses of large-scale building complexes, provide important support for seismic risk assessment and post-disaster emergency decision-making, thereby enhancing the disaster resistance and recovery ability of cities and improving the overall resilience of cities.

The utility model discloses a kind of sleeve joint type multidirectional energy dissipation shock-absorbing cabinets, it is related to cabinet shock-absorbing technical field.The defects that high seismic risk is difficult to deal with by anchoring, limiting for data center cabinet using welding, bolt connection etc. with ground, wall, using scheme includes cabinet body, cylindrical leg, rubber sleeve and connecting sleeve;Cabinet body bottom is integrally connected with at least three vertically arranged cylindrical legs;Rubber sleeve is the double-layer hollow integrated structure of two ends opening, its inner layer and outer layer are fixed as a whole by annular connecting rib, and inner layer and outer layer between pre-reserved deformation gap, to form buffer space;The cylindrical leg extends downward, its outer wall and the inner wall of the inner layer of rubber sleeve are closely attached, form nested connection;Connecting sleeve is fixed downward in bottom surface, is set in the inner layer outside of rubber sleeve upward, and connecting sleeve and rubber sleeve outer layer are relatively fixed by interference fit implementation.The utility model can improve the shock-absorbing performance of cabinet.

The invention discloses a complex terrain seismic oscillation amplification coefficient prediction and correction method and system based on a convolutional neural network model, and belongs to the application of a deep learning method in the field of seismic engineering. The method comprises the following steps: firstly, respectively establishing seismic oscillation databases of isolated terrains and regional complex terrains; training by using a BP neural network to obtain an isolated terrain seismic oscillation amplification coefficient prediction model, and training by using a convolutional neural network to obtain a regional terrain influence coefficient prediction model; and multiplying the isolated terrain prediction coefficient of the to-be-measured site by the regional terrain influence prediction coefficient to obtain an accurately corrected seismic oscillation amplification coefficient. The method overcomes the defect that an existing method neglects the regional terrain coupling effect, effectively improves the prediction precision of the seismic oscillation amplification coefficient under the complex terrain condition, and provides more reliable technical support for engineering aseismic design and seismic risk assessment.

The application provides a seismic special patrol tower intelligent analysis method based on multi-source data fusion and related equipment, and belongs to the technical field of seismic influence analysis of power towers. The application comprises: obtaining seismic information containing epicenter position and magnitude from a remote seismic data source online, and obtaining power transmission tower foundation data containing geographic coordinates; standardizing and converting the geographic coordinates in the power transmission tower foundation data to obtain tower coordinates, and calculating the seismic distances of each tower based on the epicenter position and the tower coordinates; according to the magnitude and the seismic distances of each tower, calling preset risk level classification rules, dynamically evaluating and outputting the seismic risk level of each power transmission tower to obtain a risk judgment result; generating a structured special patrol analysis report containing a risk distribution statistical summary, and saving the report file. The application can improve the accuracy and scientificity of risk evaluation, provide a complete data basis for seismic special patrol analysis, and solve the problems of scattered data sources and different formats in emergency response.

The invention relates to the technical field of seismic engineering and geological disaster prevention and control, and discloses a slope seismic oscillation comprehensive risk assessment method considering gradient-incident angle-back-facing slope three-dimensional coupling, and the method comprises the steps: building a three-dimensional double-sided slope dynamic response model, laying monitoring points on a flat ground in front of a slope and slope surfaces at two sides, and carrying out the construction of a three-dimensional double-sided slope dynamic response model; setting free field boundaries around the model, inputting seismic waves subjected to polynomial baseline correction processing, and calculating peak acceleration amplification coefficients under the conditions of different gradients, incident angles and slope orientations; on the basis, a sensitive incident angle threshold weight and a back-facing slope asymmetric weight are introduced, a normalized amplification coefficient is combined, a gradient-incident angle-back-facing slope three-dimensional coupling comprehensive risk index is constructed, and unified quantification and grading evaluation of risk intensity under the conditions of different gradients, different incident angles and different slopes are achieved. The method can systematically reveal the coupling rule of the double-slope seismic oscillation amplification effect, and provides a scientific basis for the seismic design of mountainous engineering and regional seismic damage risk assessment.

The application discloses a kind of based on the fusion of multiple remote sensing and LiDAR point cloud linear structure intelligent identification and segmentation system and method of fracture zone.It is extracted to construct tensor by the deformation anomaly guided LiDAR acquisition, input three-dimensional attention deformable convolution network to output fracture probability body after the system obtains InSAR and LiDAR data, realizes kinematic segmentation after tracking fracture main line and time series clustering and mutation point detection.The method breaks through the limitation of single data source, improves the identification accuracy and segmentation quantification level under complex terrain, and adapts to the needs of seismic risk assessment.

The invention discloses a structure earthquake risk assessment method based on WiBS-PLS-RSM. Firstly, design parameters of structural earthquake risk assessment and damage indexes of a to-be-assessed structure are determined; then, a training set (TrainX, TrainY) is determined, and the training set (TrainX, TrainY) is input into a width-adjustable basic spline partial least square response surface model (WiBS-PLS-RSM) for training; a test set (TestX, TestY) is input into the trained WiBS-PLS-RSM, verification is carried out through a decision coefficient R2, and finally, a total data set input variable sample TotalX is input into the verified WiBS-PLS-RSM to obtain a damage index considering design parameter uncertainty. According to the method, the problem of over-fitting or under-fitting of a traditional response surface model in earthquake risk assessment which is high in nonlinearity, multi-dimension and strong in data correlation and considers parameter uncertainty is effectively solved.

The invention relates to an RSM-based bridge anti-seismic multi-objective optimization method, equipment, a medium and a program product, and belongs to the technical field of bridge engineering anti-seismic design. The method comprises the following steps: determining design parameters and value ranges of bridge piers; designing a test by adopting a CCD method; establishing a finite element model; establishing a vulnerability curve; establishing an earthquake risk curve; the anti-seismic reliability is calculated through a PEER total probability anti-seismic risk assessment framework, the seismic oscillation randomness and the structural parameter uncertainty can be comprehensively considered, and the scientificity and the reliability of a subsequent optimization result are ensured; constructing an anti-seismic RSM model and each coefficient estimation value; and carrying out multi-objective optimization analysis by adopting an NSGA-II algorithm. According to the method, the problem that the calculated amount is too large in traditional anti-seismic optimization design is effectively solved, the optimization efficiency is remarkably improved while the precision is guaranteed, balance optimization of the anti-seismic reliability and the construction cost is achieved, the method has important practical value for improving the anti-seismic performance of the bridge and reducing the engineering construction cost, and multiple feasible optimization schemes are provided for engineering design.

The application discloses a seismic regional safety evaluation system based on data warehousing and three-dimensional visualization, which comprises a data acquisition module, a data preprocessing module, a three-dimensional visualization establishing module, a seismic safety evaluation module and a result output module, and relates to the technical field of data processing. The seismic regional safety evaluation system based on data warehousing and three-dimensional visualization extracts image data and parameter data, establishes a geological three-dimensional model by using drilling parameters, image data and geological feature data, establishes a ground three-dimensional model by using building parameters and geological feature data, and fuses the geological three-dimensional model and the ground three-dimensional model to form a grade evaluation model for evaluating the safety of a seismic region. By means of advanced three-dimensional modeling technology, the system can intuitively display the spatial distribution characteristics of underground rock layers and simultaneously establish an intelligent correlation mechanism among multidimensional data, so that a more scientific and efficient solution strategy is provided for seismic risk evaluation work.

The present invention discloses a method for seismic simulation of existing buildings that takes into account the actual damage state, including: determining a quantitative component damage index based on the observed component damage state; determining the material damage index of the damaged component based on the component damage index; determining key parameters of the damaged material constitutive structure based on the material damage index; establishing a finite element model of the damaged building based on the material constitutive structure of the damaged component; and evaluating the seismic risk and seismic performance of the damaged building based on the finite element model. By assigning the constitutive structure of the damaged material to the fiber model of OpenSEES, the present invention can achieve rapid modeling of the damaged building, effectively restoring the actual damage to the existing building; combined with the seismic vulnerability analysis method, it can achieve rapid assessment of the seismic risk and seismic resistance of the existing building, providing further support for relevant departments to formulate reasonable reinforcement and renovation strategies.

A method and system for assessing the seismic risk of a transformer substation main transformer, comprising: based on a pre-established earthquake damage index system, conducting experiments on the main transformer to be assessed under different earthquake intensities and according to different performance level requirements; evaluating the obtained experimental results with the safety critical values ​​under different earthquake intensities and performance level requirements to obtain the probability of vulnerability; and assessing the risk of the main transformer based on the probability of vulnerability. The present invention divides the seismic resistance level into three indicators, proposes the range of each seismic performance indicator corresponding to each indicator, and realizes a comprehensive and accurate risk assessment of many components of the main transformer in earthquake-prone areas.

The invention discloses a safety early warning method based on while-mining seismic detection, a storage medium and electronic equipment. The method comprises the following steps: determining the position of a while-mining area; according to the position of the mining-following area, a first safety radius with the mining-following area as the center is configured; arranging a first seismic sensing edge network on the first safety radius, performing real-time detection according to the first seismic sensing edge network, and outputting a first seismic sensing signal set corresponding to the first safety radius; performing signal restoration on the first seismic sensing signal set by using a signal restoration module, and outputting a seismic restoration signal set; and inputting the earthquake restoration signal set into an earthquake safety early warning module for safety analysis, outputting an earthquake risk index, and generating a safety early warning signal based on the earthquake risk index. According to the invention, the technical effect of improving the accuracy of seismic signal identification and the monitoring stability is achieved.

Method for assessing the seismic risk on existing buildings, comprising the following steps:a) identifying a set (N) of existing buildings to assess;b) acquiring for all existing buildings belonging to said set (N) qualitative data relating to the formal and construction features of said buildings;c) processing said qualitative data with a rapid analysis method based on qualitative criteria to assess the seismic vulnerability, and the related basic seismic risk, of all existing buildings belonging to the set (N);d) selecting in an organized manner a subset(S) comprising 25% to 33% of buildings of the set (N);e) acquiring for all the buildings of the subset(S) a plurality of analytical parameters;f) processing said plurality of analytical parameters with a scientific analysis method based on quantitative criteria to assess the vulnerability and the basic seismic risk of all the buildings of the subset(S);g) selecting in an organized manner a learning sample (A) comprising 70% to 80% of the buildings of the subset(S), and deriving by subtraction a verification sample (V) comprising 20% to 30% of buildings of the subset(S);h) using an AI-based machine learning model entering into an algorithm, for each building included in said learning sample (A), at least a part of said plurality of analytical parameters and the corresponding seismic vulnerability and basic seismic risk results already obtained with the scientific analysis method referred to in step f), to generate a statistical model for predicting seismic vulnerability and basic seismic risk universally applicable to any building in the set (N);i) applying said statistical prediction model to the buildings of the verification sample (V) using as input data the same part of said plurality of analytical parameters used for learning sample (A), and obtaining as output data calculated values of seismic vulnerability and basic seismic risk;l) comparing said values calculated as output from said statistical prediction model referred to in step i) with the corresponding values of seismic vulnerability and basic seismic risk obtained by applying the scientific analysis method referred to in step f), and determining a degree of accuracy, precision and sensitivity APS of the statistical prediction model;m) if said degree of APS has a value greater than a pre-established value, applying the same validated statistical prediction model to the remaining part of the buildings of the set (N) on which the scientific analysis method has not been applied;n) if said degree of APS has a value lower than said pre-established value, increasing the number of existing buildings belonging to the subset(S) and reiterating steps e) to l) until the statistical prediction model is validated.

The application discloses a method for seismic vulnerability analysis of underground structures, comprising the following steps: obtaining an initial sample set of seismic demand of underground structures and an initial sample set of limit state threshold; obtaining a sample set of parameters for describing statistical uncertainty of seismic vulnerability of underground structures; obtaining an edge probability density function of the parameters for describing statistical uncertainty of seismic vulnerability; obtaining a joint probability density function of the parameters for describing statistical uncertainty of seismic vulnerability; obtaining a mean value of seismic failure probability and a standard deviation of seismic failure probability; and obtaining a failure probability interval of underground structures, and evaluating seismic performance of the underground structures. The statistical uncertainty of sample data of seismic demand and sample data of limit state threshold is quantified, and the seismic vulnerability of underground structures is expressed as an interval value with certain dispersion degree, so that evaluators can more reasonably consider the variability of seismic vulnerability of underground structures, and the seismic risk evaluation result of the underground structures is more accurate.

The invention provides a dam body earthquake damage risk assessment method, system and equipment, and the method comprises the steps: constructing a numerical model of an assessment object dam body for calculation, and analyzing the relation between the dam body damage degree and the earthquake intensity under different structure damage indexes through a logarithmic distribution function model and an incremental dynamic method; predicting the probability of each earthquake magnitude in the future based on earthquake damage historical data of the region where the dam body is located and a Monte Carlo method; coupling the relationship between the dam body damage degree and the earthquake intensity and the probability of occurrence of each earthquake in the future, and calculating the risk probability of the dam body facing different damage degrees in the future; based on a cloud model algorithm, evaluating the importance of different structural damage indexes in earthquake damage risk assessment, and calculating a dam body earthquake damage risk comprehensive probability; finally, the dam body earthquake damage risk is evaluated through the dam body earthquake damage risk comprehensive probability, the cloud model theory is introduced, index weight analysis is carried out through the processing uncertainty and the data conversion capacity of the cloud model theory, and earthquake damage risk evaluation of the dam body is improved and optimized.

The invention relates to the technical field of seismic engineering, in particular to a method and a system for predicting a surface peak acceleration amplification coefficient. The method comprises the following steps: establishing a regional seismic intensity attenuation relation model based on a single random variable weighted least square method for carrying out regression analysis, and establishing a regional bedrock seismic oscillation attenuation relation model based on a step-by-step regression conversion method, proposing estimation of the amplification coefficient of the peak acceleration of the earth surface based on the average shear wave velocity prediction within 30 meters below the earth surface of the hybrid model; by adopting the above mode, the precision and reliability of seismic intensity and bedrock seismic oscillation attenuation prediction are improved, the efficient and accurate estimation of the earth surface peak acceleration amplification coefficient is realized, and the scientificity and effectiveness of earthquake risk assessment and aseismic design can be enhanced.

The present invention discloses a method for analyzing the seismic performance of ultra-high voltage transmission line towers in high-intensity earthquake zones. The method includes establishing a finite element model of the transmission tower system and extracting an equivalent single-tower-mass analysis model taking into account the spatial effects of earthquakes. Based on different earthquake intensities and regions, the single-tower-mass analysis model is subjected to response spectrum analysis to obtain a single-tower design response spectrum. Seismic motion time history analysis is performed on the finite element model of the transmission tower system, taking into account the spatial effects of earthquake motion, as well as the coherence and traveling wave effects of earthquake motion. Simultaneously, an IDA analysis is performed on the single-tower-mass analysis model to obtain IDA curves at different intensities. The seismic performance of the towers is then analyzed based on the single-tower design response spectrum and the IDA curves. The present invention can provide a scientific and systematic seismic performance evaluation tool for the design of ultra-high voltage transmission line towers in high-seismic risk areas, thereby guiding engineering practice and ensuring the safe and stable operation of power systems.

The invention discloses a hidden active fault geometric parameter discrimination method based on multi-track InSAR and stress field constraint, and belongs to the technical field of remote sensing. The method comprises the following steps of: extracting a spatial connecting line with a maximum deformation gradient value as a fault agent trace by acquiring a rising and falling InSAR co-seismic deformation diagram of a target area; constructing a mutual exclusion tendency hypothesis based on the trace, and screening a reasonable tendency by predicting and comparing multi-track deformation symbol distribution; and meanwhile, in combination with a local main pressure stress axis P orientation of field geological inversion, whether the maximum uplift area is located on a P-axis pointing side is judged so as to constrain the sliding type. According to the method, a fault model does not need to be preset, high-confidence-coefficient judgment of the tendency and the mechanism is achieved through the physical self-consistency of the multi-view InSAR and the actually-measured stress field, the problem of geometric multiplicity of solutions of the fault under the condition of no surface fracture is effectively solved, seismic structure interpretation reliability is remarkably improved, and key parameter support is provided for seismic risk assessment.

This application discloses an integrated assessment method and device for multivariate seismic vulnerability of tunnels that incorporates physical priors, relating to the technical field of seismic analysis and seismic risk probability assessment of underground engineering structures. The method includes: generating predicted samples based on a logarithmic domain joint distribution description; inputting each predicted sample into a heteroscedastic moment estimation substitution model to obtain predicted values ​​of the conditional mean and conditional variance of the logarithmic domain demand response; reconstructing and dynamically anchoring the conditional marginal distributions of each response based on the predicted values ​​and residual information, and coupling each anchored conditional marginal distribution to obtain a multi-response joint probability model; calculating the point-state failure probability of each projected sample under a preset damage state based on the multi-response joint probability model, constructing discrete sample pairs; and fitting each discrete sample pair to obtain seismic vulnerability curves under each preset damage state. This application improves the accuracy, robustness, and engineering usability of tunnel seismic vulnerability assessment.

The invention discloses a large-scale liquefaction disaster rapid response analysis method and system based on a Bayesian network, and relates to the technical field of geotechnical engineering earthquake resistance, and the method comprises the steps: carrying out the earthquake risk decoupling of a to-be-analyzed region based on CPSHA, and determining the magnitude and epicentral distance of a plurality of earthquake events; simulating by adopting a kinematics mixed seismic source model of fault physical fracture to obtain seismic oscillation parameters of the to-be-analyzed area; constructing a liquefied sample library; constructing a soil liquefaction evaluation parameter, and carrying out standardization processing on the soil liquefaction evaluation parameter to obtain raster data; extracting numerical values from the raster data and the liquefied sample library to form a sampling table; performing accuracy analysis and data training on the sampling table to form a conditional probability table; and based on the conditional probability table, through a naive Bayes probability model and a weighted naive Bayes probability model, calculating the liquefaction probability and the non-liquefaction probability of the to-be-analyzed area. The technical problems of high cost and time consumption in the prior art are relieved.

The application belongs to the technical field of fatigue damage and seismic risk assessment of high-rise steel structure, and discloses a wind-induced fatigue damage high-rise steel structure full-life seismic vulnerability assessment method based on Bayesian theory. By introducing the cross-wind vibration response into the fatigue damage assessment, the calculation precision of the full-life cycle fatigue damage accumulation of the key components of the high-rise building is significantly improved. By establishing a time-varying seismic demand model based on Bayesian updating, the cognitive uncertainty of unknown model parameters in the seismic demand is effectively quantified and constrained, so that the defect of large dispersion of the traditional deterministic vulnerability analysis results is overcome. Finally, the time-varying seismic vulnerability curve with a clear confidence boundary is generated, which provides a reliable probabilistic basis far beyond the traditional method for the life cycle safety assessment and risk decision of the high-rise building under multiple disaster scenarios.