43 results about "Seismic damage" patented technology

The invention relates to the technical field of earthquake damage prediction, in particular to a mountain fallen layer structure earthquake damage prediction method based on machine learning, and the method comprises the steps: building a numerical model database of a mountain fallen layer structure; applying seismic oscillation excitation of different levels to each structure model in the numerical model database, and obtaining corresponding anti-seismic performance indexes through nonlinear time-history analysis; analyzing an influence rule of the structural design parameters on the anti-seismic performance based on the anti-seismic performance indexes; by taking the structural design parameters and the seismic oscillation parameters as input features and the seismic performance indexes as output features, constructing a mountain fallen layer structure seismic damage prediction model by adopting a machine learning algorithm; performing training optimization on the earthquake damage prediction model; and inputting structural design parameters and seismic oscillation parameters of a to-be-predicted structure into the optimized seismic damage prediction model, and outputting a corresponding seismic damage response prediction result. And the earthquake damage prediction efficiency and accuracy of the mountain building structure are improved.

The invention provides a tunnel system safety evaluation method based on a unit danger coefficient. The tunnel system safety evaluation method comprises the following specific steps that surrounding rock and lining structure unit danger coefficients are defined; an anchor rod unit danger coefficient is defined, and danger coefficients of an anchor rod body and an anchor rod interface are defined; defining a surrounding rock-anchor rod-lining system and a safety evaluation index, defining the surrounding rock-anchor rod-lining system formed by a rock mass, an anchor rod and a lining within an anchor rod reinforcing range, and establishing a danger coefficient index of the surrounding rock-anchor rod-lining system; and a damage grading standard is established, and a tunnel damage grading standard based on the unit danger coefficient EDC is established in combination with a gravity dam earthquake damage analysis result. According to the method, the surrounding rock-anchor rod-lining system can be used for evaluation, the danger degree of the surrounding rock, the anchor rod and the lining of each part of the tunnel and the danger degree of the surrounding rock-anchor rod-lining system can be visually given, the stability of the tunnel can be evaluated very conveniently, and engineering design can be guided.

The application discloses an assembly underground station structure beam slab column joint pseudo-dynamic test device and method, belongs to the field of assembled underground structure seismic resistance technology, and comprises a test specimen model, a counterforce wall, a transverse actuating mechanism, a hinged support, a clamping support and a longitudinal actuating mechanism, the test specimen model is composed of multiple prefabricated components; the counterforce wall comprises vertically arranged counterforce wall vertical walls and horizontally arranged counterforce wall bases; the transverse actuating mechanism is fixedly arranged on the inner side of the counterforce wall vertical wall and connected with the top end of the prefabricated upper column, is used for transmitting reciprocating load to simulate transverse seismic action; the hinged support is fixedly connected on the counterforce wall base; the clamping support is fixedly connected with the test specimen model and is used for simulating earth pressure applied to the test specimen model on both sides of the station structure; the longitudinal actuating mechanism is fixedly connected on the counterforce frame, the longitudinal actuating mechanism acts on the top end of the prefabricated upper column and applies axial compression to simulate top earth pressure and road surface load. The application can intuitively simulate the seismic damage process and the form of the large underground structure joint.

The invention discloses a bridge earthquake damage rapid assessment method and system, and relates to the technical field of bridge earthquake damage assessment. According to the method, the acceleration response data of the key components of the bridge is taken as input, and the overall earthquake damage state of the bridge is quickly judged by constructing an association graph structure among the multiple components of the bridge and utilizing a graph neural network model. The method comprises the following steps: acquiring acceleration time history data of a bridge pier, a bridge abutment and a support under the action of an earthquake; preprocessing the acceleration time history data and extracting time sequence features; constructing a graph structure based on the response correlation of each component; and inputting the component features and the graph structure into the graph neural network model for reasoning, and outputting the earthquake damage level of the bridge. According to the method, multi-component damage information can be fully fused under the condition that the number of sensors is limited, the accuracy and efficiency of bridge post-earthquake damage evaluation are remarkably improved, and the method is suitable for post-earthquake emergency evaluation and bridge safety rapid judgment scenes.

This utility model relates to the field of bridge seismic resistance technology, and particularly to a seismic toughness protection structure for high-speed railway box girder bridges. The structure is installed in the gap between the pier and the main girder. It includes three sets of support blocks, each set comprising two support block units. The two support block units in the same set are spaced apart along the longitudinal direction of the bridge. Each support block unit is located near the top edge of the pier, and the vertical distance between the top surface of each support block unit and the bottom surface of the main girder does not exceed 4 cm. This design provides a displacement of more than 1 m in any horizontal direction after the main girder is dislodged, significantly improving the bridge structure's ability to withstand strong earthquakes. The support blocks ensure that the main girder maintains an upright posture after dislodging, preventing slippage and lateral collisions with the piers, thereby greatly reducing seismic damage to the main girder and pier foundations. Simultaneously, it effectively controls track deformation and damage, maximizing the safety of trains traveling on the bridge.

The invention relates to a structure period segment division method based on structure dynamic response similarity, which is characterized in that on the basis of structure dynamic response under seismic action, objective division of structure period segments is realized by constructing response characteristic matrixes corresponding to different structure periods and introducing a fuzzy clustering mechanism to perform unsupervised classification on the structure periods. According to the method, linear and non-linear structure response characteristics are considered at the same time, the optimal period segmentation number and the boundary threshold are determined in combination with the clustering effectiveness evaluation index, and a more accurate thought and method are provided for more rapidly evaluating seismic damage of the structure in the specific period range and matching input vibration of the structure in the specific period range.

The invention provides an earthquake damage RC component damage assessment method based on eye movement attention, and the method comprises the steps: constructing a damage building image data set containing different damage types and scenes, and carrying out the standardization processing; performing injury assessment by a professional engineer under an eye movement tracking device, and synchronously acquiring eye movement data; performing cleaning, track correction and thermodynamic diagram generation on the eye movement data, and constructing an attention map; a deep learning model fusing eye movement attention is designed, an original image and an attention map are spliced and input, features are extracted through an encoder-decoder structure, a feature pyramid is constructed, a cross entropy loss function and an Adam optimizer are adopted for model training and optimization, and a damage level is output. According to the invention, by introducing an expert eye movement attention mechanism, the reliability and interpretability of the deep learning model in post-earthquake assessment are significantly improved, and an effective technical means is provided for rapid and accurate earthquake damage assessment.

The present application relates to the technical field of railway track inspection, and particularly relates to a high-speed railway intelligent track inspection operation robot operation monitoring method and system, the present application combines track turnout state data and seismic influence data to analyze abnormal conditions of track passage detection conditions, and according to the analysis result, analyzes the threat degree of the execution environment of the robot post-earthquake track inspection operation task; combining the robot's own operation data and track turnout state data, analyzes the abnormal conditions of the robot post-earthquake track inspection operation task's own operation control; based on the execution environment threat degree of the robot post-earthquake track inspection operation task, the abnormal conditions of the robot post-earthquake track inspection operation task's own operation control, the track inspection operation risk of the robot post-earthquake track inspection operation task is evaluated; according to the evaluation result, the robot emergency braking early warning is realized, so as to guarantee the operation safety of the inspection robot in the earthquake destructive environment, and the intelligent level of the high-speed railway post-earthquake track inspection operation is significantly improved.

This invention relates to a seismic design method for a weakly connected structure, mainly comprising the following steps: A cantilever member extends outward from the main tower to provide a support sliding surface for the weakly connected structure; a horizontal steel plate is embedded in the top surface of the cantilever member, and a low-friction coefficient sliding material is laid on the embedded horizontal steel plate; the weakly connected structure is made of steel, with the steel beams of the weakly connected structure having reduced beam height near the support nodes to form a variable cross-section, and the ends of the steel beams resting on the low-friction coefficient sliding material; the floor slabs of the weakly connected structure are connected to the steel beams by studs, and the reinforcing bars of the floor slabs are anchored into the adjacent main towers on both sides. Using this invention for structural design ensures that the connected structure does not experience component failure under minor earthquakes and wind loads; and under major earthquakes, it does not suffer severe seismic damage such as the collapse of the connected structure, effectively protecting the safety of the overall structure.

Provided is an experimental device for analyzing seismic damage to a slope under coupled action of ground motion and bedrock dislocation. The experimental device includes a seismic motion excitation system and a bedrock fault dislocation system. The seismic motion excitation system includes a shaking table, a shaking table platen, a plurality of vertical actuators, and a horizontal actuator, enabling bidirectional seismic motion input. The bedrock fault dislocation system includes a lifting box, a fixed box, a slope adjustment actuator, inclination adjustment reaction devices, and pushing actuators. A required slope gradient is achieved by jacking up the lifting box using the slope adjustment actuator, and relative fault dislocation is realized by pushing a movable bottom plate of the lifting box using the pushing actuators. Operating the seismic motion excitation system and the bedrock fault dislocation system simultaneously enables experimental analysis of seismic damage to a slope under coupled action of ground motion and bedrock dislocation.

The invention provides a swing wall reinforced concrete structure design method based on toughness, which comprises the following steps: analyzing earthquake damage of an existing concrete structure, and evaluating the anti-seismic toughness level of the existing concrete structure according to an analysis result, so as to determine an anti-seismic toughness improvement target of the existing concrete structure; preliminarily determining design parameters for reinforcing the swing wall; the earthquake damage of the reinforced concrete structure is analyzed, the anti-seismic toughness level of the reinforced concrete structure is evaluated according to the analysis result, so that whether the anti-seismic toughness improvement target of the existing concrete structure is met or not is determined, and the design parameters, meeting the anti-seismic toughness improvement target, of swing wall reinforcement are obtained according to the determination result; the method has the beneficial effects that quantitative toughness evaluation and a reinforcing design scheme are organically combined, and a reinforcing design method of the existing reinforced concrete frame structure and the frame-shear wall structure is established by adopting a novel swing wall technology, so that the anti-seismic toughness level of the existing concrete structure is improved.

The invention belongs to the technical field of post-earthquake power system first-aid repair engineering, and provides a post-earthquake traffic path planning method and system, and the method comprises the steps: determining the probability of different road damage levels through a standard normal distribution function based on the seismic surface peak acceleration and road vulnerability parameters; the maximum traffic flow allowed by the road is obtained by introducing the lane width, the lane number and the earthquake damage correction coefficient; and with the purpose of obtaining the shortest passing time and path between any node pairs of the whole traffic network, updating the passing time matrix and the path recording matrix through iteration, and obtaining the shortest passing time matrix of the whole network and the corresponding path recording matrix through multiple times of iteration. The traffic network state can be rapidly and accurately evaluated after an earthquake by considering earthquake oscillation, road damage and passing time, comprehensively considering multi-stage road damage probability and post-earthquake passing capacity correction and internalizing surface peak acceleration and road vulnerability parameters in a state sensing process.

The invention discloses a seismic damage structure optimal repair decision determination method based on rapid improvement of seismic toughness. The practical and effective optimal repair decision determination method is provided for improving the anti-seismic performance of the earthquake damage structure to the maximum extent. The method comprises the following steps: firstly, extracting end displacement of all beam and column components in an earthquake damage structure, and calculating corners and damage degrees of the beam and column components according to the end displacement; then, calculating the anti-seismic property loss of the components, the floors and the structures by combining the importance coefficients of the components and the floors; on this basis, time and cost required for repairing each component are calculated, and an optimal repairing strategy of the seismic damage structure is determined in combination with a greedy-genetic algorithm; and finally, further determining the optimal repairing sequence of the components on the basis of the optimal repairing strategy by taking the component repairing effect as an evaluation index. The method can provide powerful help for making an actual earthquake damage structure repair decision scheme, and has high engineering application value.

This invention relates to a two-stage intelligent prediction method for seismic damage to underground railway stations, comprising: S1: using a first-stage deep learning prediction model to predict the samples to be predicted, obtaining the first-stage prediction result; S2: calculating the prediction confidence and classification interval based on the prediction probability and the preliminary prediction result of the seismic damage state, and determining whether the first-stage prediction result meets the preset reliability conditions. If it does, the first-stage prediction result is used as the final seismic damage state prediction result; if it does not, proceed to step S3; S3: using a numerical analysis model to perform a verification calculation on the underground railway station to be evaluated, and determining the final seismic damage state prediction result based on the verification calculation result. This invention introduces a second-stage triggering mechanism based on prediction confidence and classification interval, further verifying and analyzing low-confidence samples and class boundary samples, reducing the risk of misjudgment and omission under complex working conditions.

The present application relates to the field of bridge seismic resistance technology, in particular to a bridge transverse quasi-isolation multi-stage ordered seismic resistance construction method, according to the seismic resistance requirement of the bridge structure under different intensity grades of earthquakes, the performance target of three levels is determined, the reasonable mechanical parameter value method of steel block is proposed, the multi-stage seismic resistance mechanism of quasi-isolation bridge is established, the seismic potential of each component is sequentially played, the seismic damage degree of the bridge can be controlled and reduced according to the expected performance target, and the falling beam phenomenon of the bridge superstructure can be effectively prevented, so that the multi-stage ordered seismic resistance mechanism is realized.

The embodiment of the utility model provides an oil and gas storage tank earthquake damage monitoring and alarming system, and relates to the field of oil and gas storage tank monitoring. The oil and gas storage tank earthquake damage monitoring and alarming system comprises a sensor assembly, a control module and an alarming module. The sensor assembly is used for being arranged on the oil and gas storage tank so as to detect acceleration parameters and / or deformation parameters generated by seismic oscillation on the oil and gas storage tank. The control module is in communication connection with the sensor assembly and the alarm module. The control module can control the alarm module according to a comparison result between the acceleration parameter and / or the deformation parameter obtained by the sensor assembly and a preset threshold value of the control module. The system can detect the oil gas storage tank in real time and give an alarm in time when the oil gas storage tank is damaged by seismic oscillation, so that the emergency disposal efficiency is improved, and harm is reduced.

The application relates to a knowledge graph-based seismic-damaged building structure reinforcement scheme recommendation method and equipment, and belongs to the technical field of computers.The method comprises the following steps: based on a knowledge graph, rule reasoning and similar case matching are performed to determine a first reinforcement technology node candidate set corresponding to a damage mode node of a building structure subjected to seismic damage; constraint condition nodes triggered by the damage mode node are determined according to engineering input parameters, the first reinforcement technology node candidate set is filtered according to the constraint condition nodes, and a second reinforcement technology node candidate set is obtained; the applicability score of each reinforcement technology node in the second reinforcement technology node candidate set is calculated for the reinforcement of the building structure; the second reinforcement technology node candidate set is sorted according to the applicability score, at least one second reinforcement technology node ranking at the front is determined according to the sorting result, and a reinforcement scheme recommendation list is further determined.The application realizes intelligent reinforcement scheme recommendation based on a knowledge graph.

The invention discloses an earthquake vulnerability analysis method based on a rock fracture degree, and the method comprises the following steps: building a finite difference numerical calculation model of a deep underground structure, and selecting a series of seismic oscillation records as the input vibration of the finite difference numerical calculation model, based on the finite difference numerical calculation model and input vibration, determining a seismic oscillation intensity factor and a damage performance index suitable for the deep underground structure, dividing the deep underground structure seismic damage level, and based on the seismic oscillation intensity factor and the structure loss performance index, adopting an incremental dynamic analysis method to analyze the deep underground structure seismic damage level. And acquiring an earthquake vulnerability calculation sample set of the deep underground structure, and based on the earthquake vulnerability calculation sample set, analyzing the earthquake vulnerability of the deep underground structure by establishing an earthquake vulnerability function. The deep underground structure seismic vulnerability analysis precision and applicability are high under the complex seismic geological conditions.

The application discloses a sedimentary basin building group earthquake disaster evaluation method and an evaluation system, belongs to the technical field of engineering disaster prevention, and is characterized in that the sedimentary basin building group earthquake disaster evaluation method comprises the following steps: S1, determining a target site and characteristic input parameters; S2, establishing a three-dimensional sedimentary basin model and obtaining a seismic response; S3, establishing an improved data set; S4, optimizing an artificial neural network; S5, obtaining samples; S6, determining seismic motion parameters; S7, prediction and evaluation. The application improves the calculation efficiency of building the data set and evaluating the influence of site medium parameter uncertainty on basin seismic motion by means of a fast multipole algorithm and a surrogate model in sequence, can give statistical moment and probability information of peak acceleration of the basin ground surface at any position, and is applied to rapid prediction and evaluation of building group earthquake disaster, and serves a resilient city.

The invention relates to the technical field of railway track inspection, in particular to an operation monitoring method and system for a high-speed railway intelligent track inspection operation robot. Track turnout state data and earthquake influence data are combined, abnormal conditions of track passing detection conditions are analyzed, and according to the analysis result, the track turnout state data and the earthquake influence data are analyzed; analyzing the execution environment threat degree of the post-earthquake track inspection task of the robot; in combination with the body operation data of the robot and the track turnout state data, the body operation control abnormal condition of the post-earthquake track inspection operation task of the robot is analyzed; based on the execution environment threat degree of the post-earthquake track inspection operation task of the robot and the body operation control abnormal condition, the track inspection operation risk of the post-earthquake track inspection operation task of the robot is evaluated; the robot emergency braking early warning is realized according to the evaluation result, so that the operation safety of the inspection robot in an earthquake destructive environment is guaranteed, and the intelligent level of the high-speed railway post-earthquake rail inspection operation is remarkably improved.

The invention relates to the technical field of building earthquake damage index prediction, in particular to a building earthquake damage index prediction method based on an optimized XGBoost regression model, and provides a reverse correction algorithm for the limitation problem of discrete data. The algorithm is based on a prediction model, effective information in sample errors is deeply mined, real information of samples is mined by means of a closed-loop mechanism of reverse tracing-dynamic correction-loop optimization, the sample quality is systematically improved from a data source, and a solid foundation is laid for establishment of the prediction model. The problems that a traditional earthquake damage prediction method depends on rough classification and is large in deviation due to insufficient high-intensity data, and an existing machine learning model is insufficient in data preprocessing and discrete data processing are solved, the prediction precision and applicability are remarkably improved, the earthquake resistance difference of a single building can be reflected more accurately, and the prediction accuracy is improved. And reliable technical support is provided for earthquake disaster assessment and disaster prevention and reduction.

The invention discloses a reinforced concrete member earthquake damage detection method based on an improved U-Net deep neural network, and belongs to the technical field of reinforced concrete nondestructive testing. According to the method, the problems of poor accuracy and robustness of earthquake damage detection of the reinforced concrete member by an existing model are solved. In a coding stage, image features are extracted through multilayer convolution and pooling operation, the spatial resolution of a feature map is gradually reduced, and deep semantic information is captured; in the decoding stage, the resolution of the feature map is recovered by using transpose convolution and jump connection, and the detail features in the encoding stage are fused to realize multi-scale feature fusion; a channel attention and space attention mechanism is introduced to enhance the sensitivity of the model to damage characteristics such as cracks and spalling, the attention ability of the model to key areas is improved, and efficient, accurate and automatic detection of various damages of the reinforced concrete member is realized by using the improved U-Net deep neural network. The method can be applied to the field of earthquake damage detection.

The present application relates to the technical field of submarine pipeline performance test, and discloses a submarine pipeline earthquake damage effect underwater shaking table simulation device and method, which comprises a water pool provided with a wave generator at one end and a wave absorbing net at the other end; a shaking table, which is concave downward at the bottom of the water pool to form a mounting groove, is arranged in the mounting groove and located between the wave generator and the wave absorbing net; a soil model box, which is arranged on the shaking table, has an opening at the top and is filled with test soil to form a seabed foundation, which is flush with the bottom of the water pool; and a pipeline model, which is arranged on the seabed foundation. The device can accurately simulate the propagation process of seismic waves in the seabed, fully consider the interaction between the submarine pipeline, soil and seawater, and has multiple working conditions and adjustability, so that the seismic response of the submarine pipeline under different working conditions can be accurately monitored and analyzed, and reliable basis can be provided for the seismic design and safety evaluation of the submarine pipeline.

The invention provides an earthquake damage RC component residual performance evaluation method based on small sample data, and relates to the technical field of concrete structure earthquake damage evaluation, and the method comprises the steps: constructing an image data set with a fine label; constructing an image data set with a coarse label; a two-stage progressive optimization network is constructed, in the first stage, a deep residual shrinkage network is trained with a fine annotation image as input, in the second stage, parameters in the first stage are copied, a coarse annotation image is input, binary errors are generated according to whether a predicted value falls into a coarse annotation interval or not, and the sum of the errors in the two stages is used for parameter updating; converting the binary error of the coarse annotation network in the second stage into an auxiliary supervision signal, fusing the auxiliary supervision signal with the continuous error of the fine annotation network in the first stage according to a specific proportion, and jointly guiding the parameter updating of the two-stage progressive optimization network; and performing weighted fusion on the trained two-stage progressive optimization network parameters according to channel importance to generate a single inference model, and reducing repeated calculation through static calculation graph multiplexing and soft threshold CUDA kernel optimization so as to output a damage index of the seismic damage RC component and a corresponding residual performance evaluation result.

The invention discloses a multi-scale modeling method for a ballastless track on a bridge, which belongs to the technical field of railway bridge modeling analysis and comprises the following steps of: establishing a multi-scale finite element model of a bridge system, and defining a nonlinear constitutive model of each component of the ballastless track on the bridge according to stress damage characteristics; establishing the base plate and the roadbed slab into an elastic entity unit model; establishing a simplified model of the contact between the base plate and the roadbed slab and the geotechnical cloth, the elastic base plate and the vertical cohesive force; establishing a steel rail multi-scale model and contact between the steel rail multi-scale model and a sleeper Establishing a fastener system multi-scale model and coupling between the fastener system multi-scale model and a steel rail and a sleeper; and assembling the models in finite element software to form a ballastless track-bridge system multi-scale finite element model, and performing model verification. According to the method, the problem that a traditional multi-scale model cannot represent strong nonlinear damage behaviors of earthquake damage such as ballastless track steel rail fracture, fastener failure and roadbed slab separation is solved.

The invention provides a building earthquake damage monitoring method based on deep learning and sparse monitoring data. According to the method, modeling is carried out on a seismic response mode of a structure along a height direction through spline interpolation, data dimensions of global seismic response of buildings with different floor numbers are unified through equidistant sampling, and then monitoring data features of two sensors installed on different floors are extracted through a multi-scale convolutional neural network. And combining monitoring data features with building features extracted based on a multi-layer perceptron, and inputting the combined features into an attention-enhanced long-short-term memory neural network for feature fusion, so as to reconstruct earthquake responses of all layers of the building, thereby realizing earthquake damage monitoring of the building. The method can be applied to any building with a layer structure.

The invention relates to the technical field of buried gas pipe network disaster simulation, in particular to a buried gas pipe network disaster dynamic simulation method. Comprising the following steps: constructing an urban buried gas pipe network spatial topology database and a three-dimensional visual model thereof; determining seismic oscillation time history data encountered by each pipeline in the buried gas pipe network, and integrating the seismic oscillation time history data into the urban buried gas pipe network spatial topology database; obtaining section combined stress evolution data of each pipeline in the whole earthquake process; the earthquake damage level of the pipeline at each moment in the whole earthquake process is judged and given; and constructing a three-dimensional dynamic visualization model of the earthquake disaster of the urban buried gas pipe network under the non-uniform excitation, and giving out the damage evolution process of each pipeline in the earthquake. According to the method, earthquake disaster simulation of the urban buried gas pipe network under non-uniform excitation can be realized, the earthquake disaster simulation result better conforms to the actual situation, and the damage evolution process of each pipeline in an earthquake can be given.

The application discloses a seismic damage steel reinforced concrete structure intelligent evaluation method and relates to the field of intelligent construction, and comprises the following steps: obtaining pre-earthquake point cloud data containing all monitoring points through three-dimensional laser scanning; obtaining post-earthquake point cloud data of a steel reinforced concrete component; calculating the inter-story drift index of the steel reinforced concrete component based on the post-earthquake point cloud data, and determining that the steel reinforced concrete component is macroscopically damaged when the inter-story drift index exceeds a limited threshold; obtaining the buckling parameter of the steel reinforced concrete component by comparing the horizontal displacement of the post-earthquake point cloud data relative to the pre-earthquake point cloud data for the rest of the steel reinforced concrete components; establishing a damage coefficient evaluation model based on a neural network, inputting the buckling parameter and the design parameter of the component into the damage coefficient evaluation model, and calculating the damage coefficient of the steel reinforced concrete component; and determining the damage state corresponding to the steel reinforced concrete component and the component repair scheme corresponding to the steel reinforced concrete component, so that the post-earthquake performance of the component can be accurately predicted and classified.

The invention discloses an urban water supply system anti-seismic performance evaluation method considering function decline of a water treatment plant, and belongs to the technical field of urban water supply pipe network anti-seismic analysis. The method comprises the following steps that Monte Carlo simulation sampling is utilized, and earthquake damage scenes of various pipelines in the water supply network under the earthquake action are generated; quantitatively determining the residual function state of the water treatment plant after the earthquake through the vulnerability curve of the water treatment plant; establishing a coupling analysis model of the water treatment plant and the water supply pipe network to realize coupling of function changes between the water treatment plant and the pipe network; and calculating the anti-seismic performance index of the urban water supply system by integrating the pipe network damage and the water plant function attenuation. According to the method, the water plant vulnerability curve is introduced to quantitatively reflect the function attenuation of the water plant after the earthquake, and the water plant-pipe network coupling model is combined, so that the overall anti-seismic performance of the urban water supply system under the earthquake disaster can be more scientifically and comprehensively evaluated; the method has important theoretical and practical significance for guiding seismic design, toughness improvement and emergency decision-making of the urban water supply system.