53 results about "Aftershock" patented technology

The invention discloses a main shock and aftershock full-life vulnerability analysis method based on active learning, and belongs to the field of structural anti-seismic safety evaluation. The method solves the problems that an existing full-life analysis method needs high calculation cost and does not consider the influence of environmental factors and main shock and aftershock coupling effects on the initial damage of the structure. The agent model is constructed based on high-precision and low-precision data fusion, and a meta-learning mechanism is introduced to describe internal association among different degradation states, so that the sample utilization efficiency is improved; a generalized learning function is combined with a two-stage active learning strategy to dynamically select a training sample point with the most information amount, efficient refinement of a prediction model in each degradation scene is gradually realized, the calculation cost is further reduced, and the agent model prediction precision is improved. And finally, through a time-varying two-dimensional limit state equation, explicitly considering the correlation between the initial damage evolved along with time and the structure residual capacity, and effectively fusing the coupling effect of environmental degradation and the seismic sequence. The method can be applied to structure vulnerability analysis.

The invention provides a main shock and aftershock sequence side slope vulnerability analysis method and system based on double response indexes, and relates to the technical field of earthquake side slope vulnerability analysis, and the method comprises the steps: building a GeoStudio side slope model according to the physical parameters of a side slope soil body, and obtaining the initial static safety coefficient and critical acceleration of the side slope; performing incremental dynamic time history analysis according to the main earthquake ground motion data, the slope model and the initial static safety coefficient of the slope to obtain a soil shear strength parameter value after the main earthquake; updating the initial critical acceleration of the side slope to obtain the critical acceleration of the side slope after the main earthquake; performing aftershock increment dynamic time history analysis according to the aftershock oscillation data and the critical acceleration of the side slope after the main shock to obtain a safety coefficient value and an accumulated displacement result of the soil body after the aftershock; and defining a vulnerability function based on the logarithmic normal cumulative distribution function to obtain a multi-level slope vulnerability curve. According to the method, the slope risk assessment precision and the visual decision-making capability are improved.

The invention discloses a multi-source data fusion-based power transmission tower earthquake damage assessment and emergency response method and system. The method comprises the steps of collecting and preprocessing multi-source data of geological disasters of a power transmission tower; constructing a multi-modal fusion-digital twinborn driven dynamic transmission tower earthquake damage evaluation model, and evaluating the preprocessed multi-source data; and generating a corresponding emergency response strategy based on the evaluation result. According to the method, the multi-source data of the geological disaster of the power transmission tower is analyzed and processed by using the multi-modal fusion-digital twinning driven dynamic power transmission tower earthquake damage assessment model, so that the current damage can be comprehensively assessed according to the multi-source data, the evolution trend under aftershock and secondary disaster can be accurately predicted, and prospective early warning is realized.

The invention relates to the technical field of slope stability prediction, in particular to a slope stability evolution prediction method of a main shock and aftershock sequence cumulative damage mechanism. The method comprises the following steps: determining an initial strength parameter of a slope sliding surface rock-soil body and a dynamic strength attenuation parameter under the action of a main shock and aftershock sequence through an indoor cyclic load test, and establishing a cumulative damage model; three-dimensional side slope geometric features are obtained, and the spatial orientation and the stress direction of a potential sliding surface are determined; calculating a dynamic sliding force in combination with seismic oscillation parameters, and updating an effective strength parameter and a dynamic anti-sliding force of the sliding surface in real time; and carrying out staged calculation and dynamic evolution analysis by adopting a limit equilibrium method or a strength reduction method. According to the method, by introducing a rock-soil body strength accumulated damage and progressive attenuation mechanism under the cyclic action of the main and aftershock sequences, the damage accumulation process and the stability evolution law of the slope stability along with the development of the main and aftershock sequences are described, so that the progressive instability process and the accumulated instability risk driven by the aftershock after the main shock is triggered can be identified.

The invention belongs to the technical field of earthquake assessment, and particularly relates to an earthquake influence field dynamic assessment method and system based on multi-source information. The invention discloses an earthquake influence field dynamic evaluation method based on multi-source information. Real-time observation data of various earthquake professional sensors are fully utilized, and an earthquake influence field is dynamically evaluated in different time periods. And multi-source information such as seismic basic parameters, a seismic source mechanism solution, a seismic source fracture process, station seismic oscillation parameters and aftershock information is fused to comprehensively evaluate and correct the seismic influence field.

The invention provides a main shock and aftershock type seismic oscillation dimensionality reduction simulation method based on engineering characteristics, and the method comprises the steps: determining simulation parameters of a main shock, and obtaining corresponding aftershock parameters through the main shock parameters based on an attenuation model of the main shock and aftershock parameters; based on the main earthquake parameters and the aftershock parameters, fully non-stationary evolution power spectrum models of the main earthquake and the aftershock are established respectively, and the fully non-stationary evolution power spectrum models reflect the non-stationary characteristics of earthquake oscillation; discretizing the requirements of the established main shock and aftershock fully non-stationary evolution power spectrum model for random variables by adopting a number theory point selection mode to obtain a representative point set of basic random variables; substituting the representative point set into a random function to obtain an orthogonal random variable set which can be used for simulation; obtaining a representative sample set of the main shock and aftershock process based on an orthogonal random variable set by using a spectrum representation theory; and through the representative sample set, generating seismic oscillation time history samples of the main shock and the aftershock, and outputting a simulation result.

The present application relates to the field of earthquake site rescue warning, and relates to a real-time early warning method for secondary collapse risk of RC frame semi-rubble structure under aftershock. The core content of the method includes four modules. Module 1: using the method of seismic simulation shaking table, the whole process of RC frame structure from perfect to semi-rubble to secondary collapse is realized by simulating main-aftershock action, and time history data of dynamic response of secondary collapse structure is obtained. Module 2: high-dimensional continuous horizontal moving time window method is used to process the time history data of dynamic response of structure and obtain the dynamic response characteristics of RC frame semi-rubble secondary collapse structure. Module 3: K-Means machine learning algorithm is used to cluster the secondary collapse risk type of RC frame semi-rubble structure. Module 4: Informer machine learning algorithm is used to realize real-time early warning of secondary collapse risk of RC frame semi-rubble structure. The present application can scientifically and accurately distinguish and real-time predict the secondary collapse risk of RC frame semi-rubble structure under aftershock.

The application discloses a main aftershock induced slope slip prediction method based on multi-parameter regression, aims to utilize a large amount of ground motion data and a Newmark rigid block method to construct an explicit expression for predicting permanent slip displacement of a slope under the action of a main aftershock from peak ground acceleration, peak velocity and slope yield acceleration. The method comprises the following steps: step 1, selecting ground motion data from a ground motion database NGA-West2 and calculating each ground motion parameter and the slope slip displacement under different slope yield accelerations; step 2, identifying optimal ground motion parameters according to effectiveness criteria and applicability criteria; step 3, obtaining a plurality of prediction models through optimal parameters and a multi-parameter nonlinear regression analysis method and then testing the prediction performance to determine a final slip prediction model; and step 4, predicting the permanent slip displacement of the slope under a given seismic scenario and slope condition. Based on the method, the application develops and discloses a main aftershock induced slope slip prediction model with good accuracy, universality and practicability, and has certain guiding significance for slope stability evaluation and seismic design under the action of a main aftershock.

The utility model discloses an elastic anti-aftershock supporting device for a tunnel lining structure, which relates to the technical field of bridge tunnel construction and comprises a supporting frame, two supporting blocks are fixedly arranged on the supporting frame, and a first servo electric cylinder and two second servo electric cylinders are mounted on each supporting block. The two sides of the supporting frame are each provided with two third servo electric cylinders, the output end of the first servo electric cylinder is connected with a first connecting plate through a fixing block, and the output ends of the two second servo electric cylinders and the output ends of the two third servo electric cylinders are connected with second connecting plates through connecting assemblies. The first connecting plate and the second connecting plate are connected with a top plate through buffer assemblies. Pulleys are installed at the lower end of the supporting frame, and fixing mechanisms are installed on the two sides of the supporting frame. The adjustable tunnel supporting device can be adjusted to support different tunnels, can provide stable supporting force in different environments, can be widely applied to various tunnel projects, and meets different construction requirements.

To solve the problem that it is difficult for residents who cannot live in a house due to an earthquake, a tsunami, a fire, or the like to secure a lodging place for a restoration worker because the residents cannot go to a house with electricity and water while being safe against an aftershock and a tsunami and protecting privacy.SOLUTION: A wooden artificial island is floated on the sea adjacent to the land, a plurality of dwellings are installed on the wooden artificial island, and the wooden artificial island is fixed by setting a concrete guide on the sea adjacent to the land, passing a log connected to the wooden artificial island through the concrete guide, and stopping the wooden artificial island with two wooden stoppers so that the wooden artificial island does not move in the horizontal direction (left, right, front, and back) but can move in the vertical direction to cope with the ebb and flow of the tide.SELECTED DRAWING: Figure 1

The invention discloses a post-earthquake evacuation method and system based on image analysis, belongs to the technical field of earthquake engineering, and aims to solve the problems of slow response and inaccurate guidance due to the fact that dynamic changes of secondary disasters such as aftershocks and fire disasters cannot be handled in real time by means of manual guidance and traditional emergency broadcast and static evacuation routes. Comprising the steps of obtaining high-definition image data through an unmanned aerial vehicle, a satellite, a camera, a LiDAR and a spectrum sensor in an earthquake influence area, performing multi-dimensional processing on the image data based on a deep learning model, and generating a risk thermodynamic diagram of a dangerous area; through deep analysis of different types of image data, multiple risk sources in the post-earthquake environment can be identified, the dangerous area thermodynamic diagram is generated according to the risk sources, the system can dynamically plan the optimal evacuation path based on the dangerous area thermodynamic diagram, it is ensured that personnel avoid high-risk areas in the evacuation process, and the personnel evacuation efficiency is improved. Therefore, the evacuation efficiency and the personnel safety are improved.

The invention relates to the technical field of earthquake monitoring, in particular to an intelligent earthquake monitoring system based on the Internet of Things. The adaptive optimization module is used for dynamically generating an aftershock probability density field; the adaptive optimization module is used for configuring a stress release relaxation factor based on a sequence active modal index calculated by a kurtosis characteristic value and a skewness characteristic value of probability space distribution in a current time slice to obtain a primary iteration aftershock probability density field; the structure-oriented constraint adjusting module is used for adjusting the structure-oriented constraint weight based on the deviation degree of the main axis direction of the high-probability aftershock cluster and the fault trend of the known region to obtain a secondary iteration aftershock probability density field; and the aftershock risk assessment module is used for determining whether the reliability of the secondary iteration aftershock probability density field is qualified or not based on the width of the confidence interval of the aftershock occurrence rate, and optimizing the preset active index based on an unqualified condition. The aftershock probability prediction precision is improved.

The invention discloses a maximum aftershock prediction method based on online enhancement, and belongs to the technical field of earthquake prediction. The core of the method is that a personalized prediction model is dynamically generated for a current event through online retrieval of similar historical sequences and data enhancement aiming at a newly occurring main earthquake. Firstly, a historical seismic database is constructed from a global seismic directory, and an initial prediction model is trained. When a new main earthquake occurs, an online process is triggered immediately: based on the characteristics of the new main earthquake, K most similar sequences are quickly retrieved from historical data; then, the similar sequence data are enhanced (such as noise adding and interpolation), so that a diversified enhanced training set is constructed; and finally, performing rapid fine adjustment on the initial model by using the enhancement set to obtain an optimization model for the current main earthquake, and predicting the maximum aftershock magnitude. According to the method, the limitation of one-time cutting of the existing static model is overcome, the problem of inaccurate prediction in an earthquake small sample scene is effectively solved, and the accuracy, robustness and timeliness of prediction are remarkably improved.

The application relates to the field of data processing, and discloses a main aftershock sequence time-frequency feature fusion deep dimension reduction simulation system and method, wherein the main aftershock sequence time-frequency feature fusion deep dimension reduction simulation method comprises the following steps: adaptively segmenting original waveform data from multiple seismic monitoring nodes according to a non-fixed window; performing cross-window aggregation on local amplitude anomalies and burst energy features existing in preliminary sequence representation; dynamically mapping potential aftershock signals and main shock features by constructing a bidirectional association network; iteratively fusing feature differences in a response evolution diagram and node distribution information; introducing a hierarchical dimension reduction processing mechanism based on a digital constraint model, and performing selective compression on signal modes of different granularities; and dynamically comparing and weighting integrating sequence features of different time segments by using an index system. The application has the advantage of improving the real-time performance of large-scale seismic data processing.

This application belongs to the field of earthquake assessment technology, and in particular relates to a method and system for dynamic assessment of earthquake impact fields based on multi-source information. This method utilizes real-time observation data from various specialized seismic sensors to dynamically assess the earthquake impact field over time periods. It also integrates multi-source information, such as basic earthquake parameters, focal mechanism solutions, focal rupture processes, station ground motion parameters, and aftershock information, to comprehensively assess and correct the earthquake impact field.

The present invention discloses a method and system for evaluating the seismic effect of high-rise shear wall structures, specifically relating to the technical field of high-rise shear walls. By accurately collecting low-cycle fatigue parameters, a concrete and steel degradation model considering fatigue effects is constructed, which is applied to the seismic analysis of shear wall structures, simulating the influence of main earthquake and multiple aftershock loading on structural performance, drawing a bearing capacity degradation curve through multiple loading results, analyzing the abnormal state of degradation rate, combining the changes in residual stiffness and bearing capacity, judging the risk of abnormal structural stiffness and bearing capacity, and dividing the risk into high, medium and low levels, and proposing appropriate reinforcement or preventive measures for different risk levels, effectively making up for the deficiency of existing seismic evaluation that does not fully consider material fatigue effects, and being able to more accurately predict the damage accumulation of high-rise shear wall structures in frequent aftershocks, thereby reducing the risk of premature structural failure and improving the durability and safety of buildings in earthquakes.

According to the building structure beam-column joint, the application and the staged anti-seismic control method, through collaborative design of the joint body and the energy dissipation assembly, the core effects of seismic energy staged dissipation and structure self-adaption are achieved, and the joint body serves as a rigid carrier to stably connect a beam body and a column body; the energy dissipation steel bar sets and the disc spring-steel bar sets which are symmetrically distributed on the energy dissipation steel bar sets form a double-path energy dissipation mechanism, the energy dissipation steel bar sets elastically bear and maintain the initial rigidity of the structure during small earthquakes, the steel bars plastically deform and dissipate energy during medium earthquakes or above, and meanwhile the disc spring-steel bar sets achieve rigidity strengthening intervention in the large earthquake stage through gap control. According to the building structure beam-column joint, the stability and repair feasibility of a building in continuous aftershocks are greatly improved, the building structure beam-column joint is particularly suitable for the anti-seismic requirement of a high-intensity earthquake area, and the technical problems that in the prior art, a building structure beam-column joint cannot achieve multi-stage energy consumption, and the adaptability to multi-stage earthquakes is insufficient are solved.

The application provides a vector primary aftershock risk analysis model construction and early warning method and system, establishes a primary aftershock database of a target engineering structure; at least one characteristic signal related to each primary aftershock is obtained from the primary aftershock database; data analysis is performed on the target engineering structure by using the characteristic signal, and each analysis result is obtained; each analysis result is combined and calculated to determine a vector primary aftershock vulnerability surface and a vector primary aftershock danger surface; the vector primary aftershock vulnerability surface and the vector primary aftershock danger surface are integrated and calculated to determine a vector primary aftershock risk analysis model. The problem that a traditional earthquake risk analysis process cannot consider aftershock events is solved, and a three-dimensional primary aftershock risk surface is obtained. The vector primary aftershock risk analysis method can be used to establish a risk analysis model of a target engineering site under the action of a primary aftershock sequence and evaluate the earthquake risk of the target engineering site under the action of the primary aftershock sequence.

The invention relates to the field of data processing, and discloses a main shock and aftershock sequence time-frequency feature fusion depth dimension reduction simulation system and method.The main shock and aftershock sequence time-frequency feature fusion depth dimension reduction simulation method comprises the steps that original waveform data from a plurality of earthquake monitoring nodes are subjected to self-adaptive segmentation according to a non-fixed window; performing cross-window aggregation on local amplitude anomaly and burst energy features existing in the preliminary sequence representation, and performing dynamic mapping on potential aftershock signals and main shock features by constructing a bidirectional association network; carrying out iterative fusion on feature differences in the response evolution diagram and node distribution information; introducing a hierarchical dimension reduction processing mechanism based on the digital constraint model, and executing selective compression on signal modes with different granularities; and performing dynamic comparison and weighted integration on the sequence features of different time slices by using an index system. The method has the advantage of improving the real-time performance of large-scale seismic data processing.

The application provides a main aftershock sequence slope vulnerability analysis method and system based on double response indexes, relates to the technical field of earthquake slope vulnerability analysis, and comprises the following steps: constructing a GeoStudio slope model according to physical parameters of slope soil, obtaining an initial static safety factor and a critical acceleration of the slope; performing incremental dynamic time-history analysis according to main shock ground motion data, the slope model and the initial static safety factor of the slope, and obtaining shear strength parameter values of the soil after the main shock; updating the initial critical acceleration of the slope to obtain a critical acceleration of the slope after the main shock; performing aftershock incremental dynamic time-history analysis according to aftershock ground motion data and the critical acceleration of the slope after the main shock, and obtaining safety factor values and cumulative displacement results of the soil after the aftershock; and defining a vulnerability function based on a lognormal cumulative distribution function to obtain a multilevel slope vulnerability curve. The application improves slope risk assessment precision and visual decision-making capability.

The utility model relates to the technical field of floors, in particular to an anti-seismic integrated house floor structure. The utility model provides an improved integrated house floor structure for seismic resistance. The floor structure comprises a limiting frame, an anti-skid plate, a damp-proof plate, buffering protection pieces and the like, a panel is placed between the inner side of the limiting frame and the top of a lifting frame, the anti-skid plate and the damp-proof plate are connected to the upper side and the lower side of the panel in a clamped mode respectively, and the buffering protection pieces used for resisting shock are arranged at the bottom of the lifting frame at intervals. The floor structure is formed by clamping and combining the panel, the anti-skid plate and the moisture-proof plate, so that the floor structure can be conveniently and quickly mounted between the limiting frame and the lifting frame to form a stable integral structure; and through the special buffering piece structure and the cooperation effect of the crisscrossed rubber strips and the base, the anti-seismic performance and the buffering protection capacity of the floor structure can be effectively improved, then impact force caused by an earthquake can be effectively absorbed and dispersed when the earthquake or aftershock occurs, and therefore the purpose of protecting the safety of residents is achieved.

This invention belongs to the field of seismic information processing technology and discloses a method and system for constructing a three-dimensional model of seismogenic faults based on aftershock precision location data. The method includes: acquiring seismic geological data of the study area; establishing a high-resolution three-dimensional crustal velocity model of the study area and determining precise source parameters; obtaining tectonic stress field characteristics through source mechanism solutions and GNSS observation data; and studying the seismogenic mechanism of the study area and obtaining information on potential strong earthquake hazards. This invention combines two grid intervals, 0.2°×0.2° and 0.1°×0.1°, to obtain both the velocity structure of the non-source area with a 0.2°×0.2° grid interval and the velocity structure of the source area with a 0.1°×0.1° grid interval. This is suitable for studying the velocity structure of source areas with a relatively small number of stations.

The invention discloses a pre-earthquake reinforcing and post-earthquake damaged area determining method and device for a fabricated building. The method comprises the steps that a plurality of natural seismic wave vibration curves of main earthquakes and afterearthquakes are decomposed into a plurality of types of sub-vibration curves; obtaining a probability density function of each characteristic parameter of the sub-vibration curve; amplifying the number of the sub-vibration curves of each type to form an artificial seismic wave vibration curve of the main shock and the aftershock; inputting the seismic wave vibration curve into a structural dynamic analysis model to calculate a structural damage index; and establishing a mapping function relationship between the structural damage index and the seismic wave vibration curve characteristic parameters, and forming a probability density function of the structural damage index based on the generation probability value of the seismic wave vibration curve and the mapping function relationship. Recognizing a vulnerable area and reinforcing the vulnerable area based on the damage probability of the structural damage index before an earthquake; and outputting the layer-by-layer damage state of the building in real time through the mapping function relationship after the earthquake so as to quickly determine the damaged area. According to the invention, closed-loop management and control of pre-earthquake accurate defense and post-earthquake rapid assessment can be realized.

This invention discloses an SMA plate damper and its seismic resistance method for self-resetting rocking structures. The damper includes an SMA core plate, strip heating units, C-shaped strips, and a buckling restraint plate. The SMA core plate is martensitic and dumbbell-shaped with openings at both ends. The C-shaped strips are arranged on both sides of the SMA core plate along its thickness direction, extending in the same direction as the SMA core plate. Two strip heating units are respectively arranged in the narrow grooves of the two C-shaped strips and are in close contact with the SMA core plate. The C-shaped strips and the buckling restraint plate provide buckling restraint for the SMA core plate. This invention utilizes the unique temperature-performance relationship of SMA material to form a self-reinforcing SMA plate damper. When applied to a self-resetting rocking structure, it can enhance the structure's seismic resistance under the combined action of main and aftershocks.

The utility model discloses an anti-seismic composite damper based on self-healing-metal buckling-eddy current coupling. The anti-seismic composite damper comprises a connecting rod assembly, a damping wall assembly and a rotating support. The connecting rod assembly comprises a rigid connecting section, a slidable inserting section and a permanent magnet, and the rigid connecting section and the slidable inserting section form buckling guide fit through a preset path; the damping wall assembly is of a multi-layer composite structure and comprises a shell, a cooling layer and a magnetic conductive layer, and an inner cavity of the damping wall assembly wraps the connecting rod assembly to form a magnetic flux loop. The rotating support is provided with a rotating limiting structure, and the two ends of the rotating limiting structure are connected with the connecting rod assembly and an external structure correspondingly. According to the utility model, the elliptical cavity is preset in the plastic base body, and the elliptical cavity is broken to release the self-healing agent when the displacement of the connecting rod exceeds a threshold value; after the self-healing agent flows out, the self-healing agent chemically reacts with the plastic matrix to be cured into a solid, and displacement is hindered through mechanical occlusion; the phase change resistance generated in the curing process achieves self-adaptive adjustment of small-earthquake low resistance and large-earthquake high resistance, and the damping force can be remarkably enhanced during strong earthquakes and aftershocks.

The application belongs to the technical field of structural seismic resistance, and particularly relates to a replaceable coupling beam energy dissipation structure convenient to repair, which comprises: steel deep beams embedded in wall limbs, and a energy dissipation beam section detachably connected between the two steel deep beams; the steel deep beam comprises a buried fixing assembly and a fixed end face, the fixed end face is fixedly connected to one end of the buried fixing assembly, two rows of first long circular holes for the second bolts to pass through are formed in the fixed end face, the two rows of first long circular holes are symmetrically arranged, and the end of the energy dissipation beam section is fixedly connected to the fixed end face through the second bolts; the size of the first long circular hole is larger than the diameter of the second bolt. The application is based on a new concept of ductile building structure recovery that can be imperfectly repaired, can remove and replace the damaged energy dissipation beam section in a short time after the earthquake, can restore the building seismic resistance function in a short time before the aftershock, can improve the urban resilience through the rapid repair of the building group, can reduce the repair cost, can also be perfectly repaired on the basis of imperfect repair, and can completely restore the building bearing capacity.

The invention discloses a post-earthquake building semi-ruin structure collapse probability prediction method based on image recognition and deep learning. The method comprises the following steps of: (1) acquiring a building ruin image capable of representing key damage characteristics such as a concrete peeling area (S), a steel bar buckling degree (Y), a structure overall inclination angle (alpha), a component node cracking and local falling degree (F), ruin overall integrity and residual support degree (E) and the like through an unmanned aerial vehicle; (2) constructing a deep learning model CVCB-Net fusing a convolutional neural network, a visual Transform, a convolutional long-short term memory network and a Bayesian network; and (3) based on the quantized multi-dimensional damage characteristics, generating a collapse probability curve and risk distribution under different aftershock peak acceleration conditions by adopting Bayesian inference, and carrying out risk rating division. According to the method, non-contact, rapid and intelligent safety assessment of the post-earthquake semi-ruin structure can be realized, and a scientific basis is provided for emergency rescue and reinforcement decision during aftershock.

The present application relates to the technical field of earthquake risk and earthquake damage prediction analysis, and particularly relates to a post-earthquake time-varying aftershock risk analysis method based on aftershock swarm, comprising the following steps: identifying parameters of an ETAS model by maximum likelihood estimation through earthquake catalog information; generating a large number of simulated aftershock swarm sequences based on the ETAS model; converting magnitude information of the simulated aftershock swarm sequences into ground motion intensity through a ground motion prediction equation; selecting a main aftershock sequence, solving aftershock vulnerability parameters under different damage states by maximum likelihood estimation, and performing damage state related aftershock vulnerability analysis; and performing post-earthquake time-varying aftershock risk analysis. The present application simulates the aftershock activity model of a site by using the ETAS model, forms a post-earthquake risk analysis model which can consider the action of multiple aftershocks after the main earthquake over time, and solves the defect that only a single main earthquake and a single aftershock can be considered in the existing earthquake risk analysis.

The invention discloses a tunnel disaster monitoring method and blocking method based on earthquake damage-flood cooperation, and relates to the field of earthquake engineering and intelligent disaster prevention and control, and the method comprises the steps: carrying out the decoupling based on the DOFS data of a section, and obtaining a damage feature, a seepage feature and an aftershock feature; simulating to obtain water pressure data according to the multi-source sensing data in the section; based on each feature and historical data, determining a current damage variable, a damage-seepage coupling index and a fracture hydraulic opening degree; according to the water pressure value of each section, the seepage pressure gradient between the sections is determined, and the seepage velocity vector between the sections is determined by combining the fracture hydraulic opening degree and the damage-seepage coupling index of the sections; determining a system cascade failure risk index according to the damage variables of the sections and the dynamic risk propagation weight between the sections; and determining a disaster chain propagation intensity index of the current tunnel by using an entropy weight method. According to the invention, real-time monitoring and risk assessment of secondary flood disasters after tunnel earthquakes can be realized.

The present disclosure provides a prediction model training method, a seismic prediction method, a device and an electronic device, and relates to the technical field of earthquake monitoring and earthquake prediction. The training method comprises: synthesizing a plurality of aftershock data in historical seismic waveform data of a target area with preset noise data respectively to obtain a seismic precursor data set; intercepting a plurality of continuous waveform data containing small earthquake group events from the historical seismic waveform data to obtain a random event data set; determining a noise data set by generating a white noise sequence or selecting a plurality of noise segment waveform data with a magnitude below a preset seismic magnitude from the historical seismic waveform data; and training a neural network by applying the seismic precursor data set, the random event data set and the noise data set to obtain a seismic prediction model. The present disclosure improves the identification accuracy of seismic precursor anomalies.