135 results about "Earthquake disaster" patented technology

The invention discloses an earthquake disaster loss dynamic assessment method and system based on multi-source disaster situation data, and relates to the technical field of earthquake disaster loss assessment, and the method comprises the following steps: S1, obtaining the multi-source original data of an earthquake disaster, and carrying out the preprocessing, the multi-source original data comprises seismic oscillation parameter data and multi-source disaster data; and S2, based on the preprocessed multi-source data, constructing a coupling driving model of the earthquake influence field and the multi-source disaster situation data, and generating a regional disaster damage thermodynamic map. According to the earthquake disaster loss dynamic evaluation method and system based on the multi-source disaster situation data, the earthquake multi-source disaster situation data is acquired, the coupling driving model of the earthquake influence field and the multi-source disaster situation data is constructed, and the influence of various factors on the earthquake disaster loss is comprehensively considered, so that the limitation that a traditional method depends on a single data source is overcome; the real situation of earthquake disaster loss can be reflected more comprehensively and accurately, and a more reliable basis is provided for rescue decision making.

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 provides a structure vulnerability analysis method and system based on earthquake magnitude, distance and site conditions, a storage medium and a computer program product. The method comprises the following steps: adopting a preset sampling algorithm to obtain preset earthquake magnitude, distance and site conditions, and acceleration time history samples corresponding to the preset earthquake magnitude, distance and site conditions; based on the acceleration time-history sample, performing nonlinear dynamic time-history analysis on a to-be-evaluated structure by using a finite element analysis method to obtain nonlinear structure seismic response corresponding to the to-be-evaluated structure and the acceleration time-history sample; establishing a change relationship between the statistical parameters of the seismic response of the nonlinear structure and the preset magnitude, distance and site conditions by using a regression fitting method; and constructing a vulnerability curved surface of a to-be-evaluated structure based on the preset earthquake magnitude, distance and site conditions based on the statistical parameters of the seismic response of the nonlinear structure and the change relationship between the preset earthquake magnitude, distance and site conditions. According to the embodiment of the invention, the four elements of a seismic source, a propagation path, a site and a structure can be completely coupled, and the method can be suitable for earthquake disaster risk analysis and rapid evaluation of post-earthquake disasters under various medium-short period structure systems.

The invention discloses a post-disaster recovery large-scale city power grid toughness evaluation method, device and medium, and the method comprises the steps: constructing a large-scale city power grid fault scene and a power transmission line time-varying fault probability model under an earthquake disaster, generating an earthquake-fault combined scene based on Monte Carlo simulation, and selecting k high-risk typical scenes, and then, by taking the maximum weighted load recovery total amount in the system full recovery period as a core optimization target, constructing a power grid post-disaster collaborative recovery model, constructing a multi-dimensional dynamic toughness index system based on the grid robustness, the system self-healing capability and the post-disaster first-aid repair capability, and evaluating the large-scale urban power grid toughness level of power grid post-disaster collaborative recovery. And outputting a good and bad sequence of the optimization strategy. By evaluating the toughness level of the large-scale urban power grid subjected to post-disaster collaborative recovery of the power grid, the performance of the whole recovery process can be comprehensively quantified, the advantages and disadvantages of strategies can be effectively distinguished, and the recovery speed and the recovery degree can be accurately quantified, so that an effective recovery strategy cannot be adopted, and a reliable basis is provided for disaster prevention and emergency of the power grid.

The invention relates to the technical field of power system operation and control, in particular to a power system recovery capability evaluation method, device and equipment considering unconventional risks and a medium, and the method comprises the steps: determining parameters for calculating the occurrence probability of earthquake disasters of different earthquake magnitudes; calculating intensity distribution by using an earthquake intensity diffusion model; calculating transmission tower and transmission line fault probabilities to obtain a fault line set; according to the operation power flow and the maximum allowable power flow, the cascading failure situation is divided into high risk and low risk; aiming at the two conditions, respectively enumerating a first-order fault state set and a second-order fault state set to obtain a system recovery capability initial value; the value serves as input, a convergence threshold value is set, a ULBI-IISE algorithm is adopted for iterative calculation, when the difference value of the upper cut set and the lower complementary set is smaller than the threshold value, the recovery capacity and the interval are output, and the method reduces high-order fault complete enumeration and the calculation amount while guaranteeing the precision, and is suitable for rapid evaluation of emergency scenes such as earthquakes.

The invention discloses an equipment attitude automatic correction method and device and an optical terminal intensity instrument, the equipment attitude automatic correction method is applied to a preset monitoring terminal comprising a triaxial MEMS accelerometer and a magnetometer, and the method comprises the following steps: collecting acceleration and magnetometer data; calculating acceleration stable three-axis offset; calculating roll and pitch angles and determining a horizontal plane; positioning magnetic north and calculating a magnetic north azimuth angle; calculating a magnetic declination angle and a yaw angle by combining longitude and latitude; generating a rotation matrix and converting a coordinate system; judging angle change and updating the matrix; and completing calibration and attitude stabilization. According to the technical scheme provided by the invention, the monitoring terminal equipment can be ensured to automatically and accurately adjust and stably maintain the attitude after being installed, so that the effective operation of the earthquake monitoring and early warning system is ensured, and the earthquake disaster prevention and flooding earthquake (vibration) monitoring performance is improved.

The invention relates to the technical field of large language models, in particular to a large language model anti-seismic report examination method and device based on domain knowledge enhancement, and provides a large language model anti-seismic report examination method based on domain knowledge enhancement. The method comprises the steps that firstly, a building earthquake-proof professional field large language model is trained, then data preprocessing is conducted on an earthquake-proof examination report, and finally examination is conducted on the basis of the trained building earthquake-proof professional field large language model, so that accumulated earthquake-proof special examination experience and the large language model are fused, and a professional LLM of the vertical field is built; strict examination can be carried out according to standards and files, interference of human errors and subjective factors is effectively avoided, accuracy and reliability of examination results are improved, examination efficiency is improved, a more scientific and accurate basis is provided for expert examination and internal pre-examination, the earthquake resistance and disaster prevention capacity of a construction project is further improved, and the earthquake disaster risk is reduced.

The invention provides a federated learning and privacy calculation-based cross-border earthquake risk assessment method, which solves the fundamental contradiction between data sovereignty and privacy security in cross-border data sharing by constructing a federated learning architecture fusing hierarchical desensitization and hybrid encryption. Through the multi-source data cooperative training and CNN-LSTM mixed disaster chain model, the problem that the assessment precision is insufficient due to the fact that a single country model cannot describe a complex cross-border disaster chain is solved; finally, a cross-border disaster scene is constructed, and the defect that a static evaluation tool is disjointed with an actual combat is overcome through a multi-agent dynamic policy simulation system; according to the method, the security collaboration under the condition that the data is not out of the scene is realized, the multi-country collaboration participation rate is improved by 60%, the risk assessment accuracy rate is improved to 92% or above, the policy assessment period is shortened from several months to several hours, a quantifiable scientific basis is provided for cross-border emergency decision making, and the joint prevention and joint control capability of regional earthquake disasters is effectively improved.

The application discloses a correction method and device of a seismic disaster personnel casualty assessment model and a storage medium, and relates to the technical field of disaster emergency management. By constructing an emergency preparedness index and an emergency response index as a nonlinear attenuation correction factor, the traditional assessment model's defects of relying on expert experience for manual correction and lacking in automation and intelligence are overcome. The coupling correction formula takes the nonlinear attenuation correction factor as the core, and through the multiplication coupling of independent double indexes, the synergistic attenuation effect of emergency preparedness and emergency response is accurately reflected. Through a closed-loop optimization mechanism, highly reliable data support is provided for emergency command. The correction process not only outputs personnel casualty prediction values, but also quantitatively diagnoses regional resilience by generating an emergency preparedness index and an emergency response index, so that emergency plans can be optimized, rescue force deployment can be adjusted or popular science drills can be strengthened, thereby directly serving the active prevention and control and rapid recovery goals of a resilient city.

The invention provides a mine earthquake master control horizon determination method, which comprises the following steps of: establishing a mine area stratum model, and determining a plurality of key layers which are positioned above a fissure zone in the mine area stratum model and have mine earthquake risks as mine earthquake control layers according to a key layer theory; main control layer analysis is carried out on all the mine earthquake control layers, a step-by-step determination and governance analysis principle is formulated for the mine earthquake control layers, and multi-stage mine earthquake main control layers are determined from all the mine earthquake control layers; and performing logging correction analysis, and dynamically correcting the position of the target rock stratum of the multi-stage mine earthquake main control layer. According to the method, different mine earthquake disaster-causing conditions are analyzed, mine earthquake main control layers under the scene that mine earthquakes generate disaster-causing influence on the ground and under the scene that mine earthquakes generate disaster-causing influence on an underground mining working face are respectively determined, and the target rock layer position of the mine earthquake main control layers is dynamically corrected through logging analysis; and it is guaranteed that the target layer of the mine earthquake main control layer can be subjected to construction treatment.

The invention discloses an earthquake numerical value prediction method based on kernel density and machine learning, and belongs to the technical field of earthquake prediction. The method comprises the steps of performing magnitude standardization and energy association processing on original seismic directory data to form standard seismic directory data, performing completeness processing on the standard seismic directory data to determine a minimum complete magnitude, and performing screening to obtain a complete seismic directory; determining a first bandwidth and a second bandwidth for the complete seismic directory through a nuclear density bandwidth sensitivity test, calculating seismic frequency and energy nuclear density distribution of the target area in combination with a time and magnitude sliding window, and obtaining nuclear density anomaly distribution data by making a difference between the seismic frequency and energy nuclear density distribution and long-term average nuclear density distribution; and inputting the kernel density abnormal distribution data of the target magnitude range under multiple time scales into a pre-trained random forest model, and outputting an occurrence prediction result of a target magnitude earthquake in the target region. According to the method, the spatial accuracy and timeliness of earthquake prediction are improved, and technical support is provided for earthquake disaster risk prevention and control.

This invention discloses an automatic attitude correction method, device, and optical terminal intensity meter for equipment. The automatic attitude correction method is applied to a pre-set monitoring terminal including a triaxial MEMS accelerometer and a magnetometer, and includes the following steps: acquiring acceleration and magnetometer data; calculating acceleration-stabilized triaxial offset; calculating roll and pitch angles and determining the horizontal plane; locating magnetic north and calculating the magnetic north azimuth; calculating magnetic declination and yaw angle using latitude and longitude; generating a rotation matrix and performing coordinate system transformation; judging angle changes and updating the matrix; and completing calibration and attitude stabilization. The technical solution provided by this invention ensures that the monitoring terminal equipment can automatically and accurately adjust and maintain its attitude after installation, thereby guaranteeing the effective operation of the earthquake monitoring and early warning system and improving earthquake disaster prevention and seismic monitoring capabilities.

The invention provides an engineering machinery man-machine cooperative scheduling system and method applied to an earthquake disaster site, and relates to the technical field of man-machine cooperative scheduling, and the system comprises a site environment information obtaining module which is used for obtaining the site environment information of the earthquake disaster site; the rasterization processing module is used for performing area rasterization processing to generate a disaster area grid map; the task execution list generation module is used for performing task allocation evaluation, generating a rescue task execution list and extracting a primary task and a secondary task; the path planning module is used for performing path planning and generating a first rescue path and a second rescue path; and the collaborative rescue scheduling module is used for carrying out collaborative rescue scheduling on earthquake disasters. The technical problems that in the prior art, due to the fact that an effective man-machine cooperative scheduling mechanism is lacked, the collaboration between rescue workers and engineering machinery is poor, rescue resources are wasted, and the rescue efficiency is low are solved.

The invention discloses a post-earthquake disaster sensing emergency path planning method based on reinforcement learning, and the method employs the real disaster information provided by a high-resolution remote sensing image, combines the reinforcement learning theory, models the remote sensing image interpretation information into a reinforcement learning environment, enables a disaster sensing agent to carry out the continuous trial and error interaction with the environment, and achieves the emergency path planning of the post-earthquake disaster sensing. Learning an optimal post-earthquake emergency path planning strategy; according to the method, the problem that rich remote sensing data cannot be fully utilized in an existing post-earthquake emergency path planning method and the problem that disaster situations are not fully considered in the path planning process can be solved, in addition, the proposed post-earthquake emergency response framework is beneficial to optimizing rescue resource allocation, and the rescue efficiency is improved; according to the method, the path covering more disaster centers can be effectively planned in the middle and short distance scene, the rescue efficiency is maximized, and casualties and economic losses caused by earthquake disasters are greatly reduced.

The invention discloses a multi-parameter fusion disaster reduction platform system based on earthquake and strong vibration monitoring, and the system comprises a data collection module which collects multi-source earthquake monitoring data; the data preprocessing module is used for denoising, standardizing and synchronizing the seismic waveform data; the time synchronization and space standardization module is used for ensuring time synchronization and coordinate standardization of the seismic waveform data; the local time window division module divides the waveform data into a fragment set; the dynamic time warping algorithm module is used for executing data alignment and ensuring accurate alignment of waveform fragments; the waveform feature extraction module is used for extracting waveform features; the abnormity detection module is used for identifying and marking an abnormal fluctuation mode; and the propagation path speculation module speculates the epicentral position and the propagation path according to the mark set. According to the method, accurate synchronization and alignment of multi-source earthquake monitoring data are realized, the epicenter position speculation accuracy is improved, and the method is widely applied to earthquake disaster early warning and decision support.

This invention discloses an earthquake disaster simulation training method and system, aiming to solve the problems of low multi-system timing synchronization accuracy, insufficient immersion and training realism, fixed configuration, and high scene adaptation costs in existing earthquake simulation systems. This method initializes the system by loading a structured configuration file, establishing a globally unified time reference for all system control nodes; it uses real-time audio-visual timecodes to drive the calculation of the target magnitude, generating synchronization control commands with unified execution timestamps to achieve timing alignment of vibration, audio-visual, and environmental effects; it implements hierarchical safety control throughout the entire process, and completes system reset through a progressive termination sequence after the process ends. This invention significantly improves the synchronization accuracy and immersion of earthquake simulation, enhances system scalability, reduces scene adaptation costs, and ensures the safety of the training process.

The utility model discloses an operating table for simulating earthquake disasters, which comprises an earthquake simulation vibration table, a house model is arranged at the top of the earthquake simulation vibration table, a support column is fixedly mounted at the bottom of the earthquake simulation vibration table, the bottom of the support column is connected with a bottom support plate, the house model is composed of a plurality of floors, and the floors are connected with the house model. A bridging plate is fixedly mounted at the bottom of the floor, and the earthquake disaster simulation device relates to the technical field of earthquake disaster simulation, a house model is arranged on an earthquake simulation vibration table, and earthquake waves are simulated and emitted through a simulation earthquake signal generator in the earthquake simulation vibration table, so that the disaster condition of the house model under an earthquake can be simulated; a plurality of dampers are jointly hinged between the floors, so that the different floors have corresponding swing amplitudes and directions during earthquake simulation, and the disaster conditions of the floors with different heights can be simulated.

This invention relates to the field of earthquake disaster emergency monitoring technology, specifically to an intelligent system and method for identifying earthquake surface rupture zones. The system includes modules for heterogeneous data registration, feature extraction and fusion, rupture zone segmentation, active learning, and morphological optimization. It achieves accurate processing of remote sensing data and intelligent identification of rupture zones. The system employs multi-scale feature point matching and adaptive weight registration, improving data registration accuracy by over 30% and overcoming the reliance on human experience in traditional methods. Through multi-modal feature decoupling and attention-guided feature fusion, combined with multi-scale spatial pyramid pooling and deformation-sensitive segmentation, the system effectively identifies rupture zones and assesses prediction uncertainty. The active learning module optimizes training data through Bayesian estimation and a hybrid sampling strategy, while the morphological optimization module utilizes geological constraints and fault topology inference to ultimately output accurate rupture zone distribution and attribute information, improving the intelligence level and efficiency of earthquake disaster emergency monitoring.

The application belongs to the technical field of earthquake disaster scenario construction, and discloses a method for constructing an earthquake disaster scenario based on big data, and the specific steps are as follows: step one: multi-source heterogeneous data acquisition and preprocessing ground structure data acquisition: the spatial distribution characteristics of urban building groups are obtained by using multi-platform remote sensing technology. By integrating multi-source data, a three-dimensional coupling model of underground pipe network and ground building is constructed, the defects of isolated analysis of ground and underground systems in traditional methods are solved, the synchronous simulation of the dynamic correlation process of pipe network rupture and building damage is realized, the additional influence of pipe network failure on building foundation stability and the chain effect of soil erosion caused by leakage fluid are accurately analyzed, and the space-time correlation rules of pipe network rupture events, building fire, fire fighting failure and other types of secondary disasters are established, the building group function paralysis risk and disaster diffusion range under different damage degrees are dynamically predicted, and the disaster evolution path is displayed in real time through a visual platform.

The invention discloses a rock burst danger full space-time prediction method based on induced fracture imaging, and the method comprises the steps: solving a seismic source fracture parameter for micro-seismic monitoring data through an automatic inversion method of a mine seismic source fracture parameter, and then forming micro-seismic induced fracture imaging based on the seismic source parameter through a graph theory; obtaining the energy density of each fracture through fracture imaging, obtaining the fracture energy density probability of different positions through a statistical theory, and achieving the position prediction of a strong mine earthquake disaster source through setting a threshold value. Meanwhile, according to the data, time sequence data needed by training is generated, a precursor mode sequence is constructed, then a CNN-Transform early warning model is constructed, and after the CNN-Transform early warning model is trained, a rock burst danger occurrence probability prediction model is obtained and used for predicting the occurrence probability of impact dangers at different positions; and the two predictions are combined to realize full space-time cooperative early warning of the rock burst danger. The method has the advantages of clear calculation model, high universality and high prediction accuracy, and can effectively predict the impact display area.

The invention specifically discloses an optimal selection method for a seismic oscillation intensity index of an underground diaphragm wall-subway station system, and relates to the technical field of underground structure anti-seismic performance evaluation. The method comprises the following steps: constructing a diaphragm wall-subway station two-dimensional nonlinear finite element model; obtaining an engineering demand parameter EDP through nonlinear time-history analysis, calculating a candidate seismic oscillation intensity index set IMs, forming an original database of IMs and EDP, and dividing a training set and a test set; generating an optimal candidate IM combination on the training set by using a filtering method, an embedding method and a wrapping method; building a multi-model verification platform, and evaluating the generalization performance of each combination based on a model-independent evaluation standard; comprehensively analyzing and determining the combination of the optimal scalar IM and the optimal vector IM; and verifying the whole optimization method through vulnerability analysis. According to the method, the limitation of a traditional method is broken through, the accuracy of earthquake resistance evaluation is improved, the adaptability of the method is defined, and reliable technical support is provided for earthquake disaster prediction and vulnerability analysis.

The invention discloses an earthquake sand liquefaction deformation prediction method based on machine learning, and relates to the technical field of earthquake engineering and machine learning. Missing value processing, abnormal value detection, feature selection and standardization processing are carried out on the multi-source coupling seismic data set to obtain a seismic sand liquefaction deformation data set, a seismic sand liquefaction deformation prediction model is constructed according to the seismic sand liquefaction deformation data set, the root-mean-square error, the mean absolute error and the decision coefficient of the model are calculated, and the seismic sand liquefaction deformation prediction result is obtained. And according to corresponding threshold judgment, carrying out hyper-parameter adjustment on the model through Bayesian optimization or carrying out model packaging through Flask, processing the obtained new seismic sand liquefaction characteristic data, and inputting the processed data into the packaged model to obtain a seismic sand liquefaction deformation prediction result. The method can effectively predict earthquake sand liquefaction deformation, and provides support for earthquake disaster prevention and engineering design.

The application discloses a method and a program product for automatically generating a three-dimensional geological finite element model, which determines a horizontal reference surface based on the maximum height difference of the ground surface, determines a first grid size and a second grid size based on a shear wave velocity, and then comprehensively determines the number of ground surface part grids and divides hexahedral units; according to the first grid size, equally divides a base part into horizontal slices with the same height, and determines the grid size of the horizontal slices in combination with a corrected minimum shear wave velocity; according to the grid size and thickness requirement, combines adjacent horizontal slices to obtain a final rock layer division scheme, and then comprehensively determines the number of rock layer grids and divides the rock layer into hexahedral units; and according to the three-dimensional center coordinates of each hexahedral unit, compares the three-dimensional center coordinates with an original geological model, and sets the stratum category of the hexahedral unit. The application greatly reduces the modeling time and cost of a three-dimensional non-uniform field finite element model of a complex terrain, has high grid quality, and is beneficial to the application of the three-dimensional geological model in the simulation and analysis of earthquake disasters.

The application discloses a strong earthquake disaster area prediction method and system based on crustal interior and seismic frequency analysis, and relates to the technical field of strong earthquake disaster area prediction. The method comprises the following steps: determining a land crustal interior depth model according to seismic literature data of a research area; the seismic literature data comprises aviation magnetic method measurement data; determining a seismic frequency distribution map of the research area according to historical earthquake catalog data; determining a seismic frequency superimposed crustal interior depth map of the research area according to the land crustal interior depth model and the seismic frequency distribution map; determining an Ms >= 7 strong earthquake potential risk area in the research area based on the seismic frequency superimposed crustal interior depth map of the research area; determining an Ms >= 7 strong earthquake potential disaster area marking map of the research area according to the Ms >= 7 strong earthquake potential risk area in the research area; and using the Ms >= 7 strong earthquake potential disaster area marking map to determine the strong earthquake potential disaster area of the research area.

The invention discloses an intelligent emergency evacuation guidance method, device and equipment and a medium, and relates to the technical field of earthquake disaster emergency management, and the method comprises the following steps: constructing a digital twin emergency body model of a target area; receiving sensing data uploaded by the sensor network of the target area in real time; the sensing data is synchronized to the digital twin emergency body model, disaster dynamic simulation is performed based on the sensing data and a disaster deduction model, a dangerous area is identified, and the real-time risk of an evacuation path is evaluated; based on the personnel distribution data, the real-time risk and the optimization target, dynamically generating an optimal evacuation path for different partitions; and according to the optimal evacuation path, controlling a multi-mode guide terminal in the target area to carry out adaptive emergency evacuation guide. A virtual emergency command center is constructed through a digital twinborn technology, multi-source data are fused in real time, and an optimal evacuation path is dynamically planned by applying a swarm intelligence algorithm, so that a guiding scheme is adjusted in real time according to disaster evolution, and the risk avoiding success rate is improved.

The invention provides an earthquake scene simulation system and method and computer equipment, and relates to the technical field of earthquake emergency. The system comprises a natural language interaction layer, a central scheduling module, a multi-source data fusion layer, a professional calculation layer and a visualization and decision support layer. The earthquake scene simulation system receives a natural language instruction based on a natural language interaction layer under the condition of earthquake scene simulation; the central scheduling module is used for sequentially sending trigger instructions to other levels of the system based on the structured instruction; the multi-source data fusion layer is used for querying seismic data and obtaining a unified seismic feature data set based on association integration of a knowledge graph; the professional calculation layer is used for generating a structured decision scheme and determining seismic intensity and seismic loss evaluation results; and the visualization and decision support layer is used for constructing a city-level three-dimensional scene and generating multi-class earthquake thematic maps. The system can improve scientificity and timeliness of earthquake disaster response decisions.

The application discloses a kind of based on coal-bearing strata store-release energy's impact-mining earthquake disaster-causing horizon determination method, comprising the following steps: one, construct geomechanical model;Two, collect physical and mechanical parameters and ground stress parameters;Three, based on ground stress environment and rock mass characteristics energy storage characteristic evaluation;Four, based on the energy release characteristic evaluation of rock mass breaking characteristic;Five, determine disaster-causing horizon;Six, determine disaster control parameters.The application constructs a comprehensive determination model by organic integration of the physical and mechanical properties of coal-bearing strata, ground stress field environment and geological structure conditions, and introduces the dual constraint mechanism of energy storage characteristic and energy release characteristic, which can accurately lock the main disaster-causing horizon with high energy storage and high energy release by coupling quantitative indicators, to realize more scientific and more accurate identification of impact ground pressure disaster-causing horizon, and provide reliable key parameter design basis for targeted disaster control.

The present application belongs to the field of urban power system operation and maintenance technology, and discloses a city power system earthquake disaster resilience determination method and system based on multi-dimensional data analysis. The present application obtains the earthquake parameters, power facility information, geographic data and social economic data of each county in the city, and constructs a multi-source heterogeneous evaluation database. Based on the seismic motion parameters and the power facility vulnerability function, the damage probability and the expected loss rate of the function of different voltage level substations and transmission lines are calculated, and the residual function matrix of regional power supply is generated. Combined with the real-time power demand model and the power supply capacity recovery curve, the post-earthquake power supply gap rate is calculated, and the influence of the terrain characteristics on the transmission line repair cost is evaluated to quantify the influence of the earthquake on the economic loss, the affected population and the social stability. The present application can effectively improve the resilience and risk management capability of the power system in the earthquake disaster, and provide technical support for the post-earthquake power rapid recovery and resource optimization allocation.

The application discloses a strong ground motion risk assessment method and system fusing multi-source data, relates to the technical field of multi-source data fusion, and calculates the time offset relationship of a satellite positioning sequence Gns and a radar deformation sequence Ins relative to a unified time reference Tref by using the unified time reference Tref, and performs time correction processing on a multi-source original set Dor by constructing a time offset matrix Tmx, so that a corrected data set Dsc with a unified time structure is formed. Fusion analysis is performed on the corrected data set Dsc to form a fusion feature set Fus, and the vibration propagation relationship is calculated based on the fusion feature set Fus to obtain a propagation path Pth, and finally, a risk result Rsk and a corresponding risk level Lev are output. The problem of misjudgment of the vibration propagation order caused by the time record difference of different observation systems can be avoided, and more reliable data basis is provided for earthquake disaster warning and emergency decision-making.

This invention discloses a machine learning-based method for predicting earthquake-induced sand liquefaction deformation, relating to the fields of earthquake engineering and machine learning. The method constructs a multi-source coupled earthquake dataset using engineering survey reports and monitoring data from historical earthquake cases. This dataset undergoes missing value processing, outlier detection, feature selection, and standardization to obtain an earthquake-induced sand liquefaction deformation dataset. Based on this dataset, a prediction model is constructed. The root mean square error, mean absolute error, and coefficient of determination of the model are calculated. Based on corresponding thresholds, the model is adjusted for hyperparameters using Bayesian optimization or encapsulated using Flask. New earthquake-induced sand liquefaction feature data is then processed and input into the encapsulated model to obtain the predicted earthquake-induced sand liquefaction deformation results. This method can effectively predict earthquake-induced sand liquefaction deformation, providing support for earthquake disaster prevention and engineering design.