42 results about "Failure assessment" patented technology

The invention discloses a cross-platform power transaction data interaction optimization method, and particularly relates to the technical field of power transaction data digital twinning. Simulation transaction data of market participants is generated based on an antagonistic neural network model; identifying a causal relationship among market variables from the simulation transaction data of the digital twin through a causal discovery algorithm, and constructing a causal graph; modeling spatial dependence and causal conduction paths among market participants by using a graph neural network model, and performing anti-factual reasoning in a single external impact scene in a digital twinborn body by intervening key variables in a causal graph; simulating dynamic game behaviors of market participants in an extreme weather parameter distribution scene; the power market failure assessment is carried out by combining the causal conduction path to obtain the power market failure assessment index, and early warning is carried out based on the power market failure assessment index, so that the adaptability and stability of the power market in extreme weather scenes are improved.

The invention relates to the technical field of bridge engineering, in particular to a probabilistic failure assessment method and system for a floating object impacting a bridge in a flood season, and the method comprises the following steps: collecting floating object data and river hydrological information in the flood season, and obtaining a water velocity condition and a floating object movement condition; a floater dragging force prediction model is established according to the water flow speed condition and the floater movement condition, and the dragging force generated by the flood to the floater is analyzed according to the model; setting a bridge damage assessment mechanism based on the flood season floating object data and the river hydrological information, and obtaining an assessment parameter analysis result according to the assessment mechanism; and a probabilistic failure judgment model is established, a probabilistic failure evaluation result is obtained by combining the dragging force, the evaluation parameter analysis result, the flood season floating object data and the river hydrological information, and the risk prediction and evaluation of the collision of the floating object on the bridge in the flood season are realized. By analyzing the failure mechanism of the bridge impacted by the floating object, the risk degree of bridge damage under different water flow conditions and floating object characteristics is quantified.

The invention provides a crack-containing pipeline failure analysis software system, and belongs to the field of crack-containing pipeline failure evaluation. The system comprises a parameter import module, a random sampling module, a penetration crack length module, a leakage rate module, a failure analysis module and a display module. The parameter import module imports pipeline material parameters, operation environment parameters and the like into the computer; the random sampling module is used for carrying out random sampling according to a common distribution function on the basis of importing parameters; the fatigue crack propagation module is used for calculating a stress intensity factor and fatigue crack propagation; the leakage rate module is used for calculating a detectable leakage length; and the result analysis module is used for integrating all calculation results and input parameters into a failure probability analysis chart. According to the method, the probability fracture mechanics method is adopted, the detection accuracy is improved, and the failure probability of equipment can be evaluated more quickly and visually.

The invention relates to the technical field of offshore wind turbine generator operation and maintenance, and discloses a failure evaluation system based on an offshore wind turbine generator. Comprising a sensor data acquisition module, a data preprocessing module, a failure feature extraction unit, a failure probability calculation module, a maintenance decision module and the like. The system obtains parameters such as vibration and temperature of the wind turbine generator in real time, after preprocessing, failure features are extracted through a deep convolutional neural network, and a dynamic Bayesian network model is constructed to calculate the component failure probability. An optimal maintenance path is generated by using an improved ant colony optimization algorithm, and meanwhile, a dynamic risk assessment module, an abnormal signal detection module and a maintenance strategy optimization module are arranged. The method can accurately evaluate the unit failure risk, timely discover abnormity, optimize the maintenance decision, improve the operation reliability of the offshore wind turbine generator, reduce the operation and maintenance cost, and guarantee the stability and high efficiency of offshore wind power generation.

A multi-material gradient interface microscopic crack path prediction method comprises the following steps: S1, according to material similarity or geometric adjacency, orienting to form an edge, and generating an interface diagram; s2, extracting an energy release rate, a principal stress gradient and a temperature; s3, the three field quantities are mapped back to the graph through KD-Tree nearest neighbor and differentiable Gaussian interpolation, and node and edge embedding features are obtained; s4, the temperature-stress-energy cascade gating message passing network calculates a crack initiation probability and an edge probability, and extracts a crack path according to the maximum cumulative probability; s5, the path is gridded into an indication tensor, and an error gradient for the probability and the energy density is generated; s6, synchronously correcting the network weight and the local energy density according to the gradient, and circulating the steps S2 to S5 until the score is converged; s7, freezing the weight, screening crack initiation nodes, performing spline smoothing on a path, formatting an energy field and a reliability label, and outputting the energy field and the reliability label; according to the method, high-precision failure evaluation is obtained with less calculation amount, and the crack initiation position, the three-dimensional crack curve and the reliability level are output.

The invention discloses a residual life prediction method applied to a hot end component of an aero-engine, which comprises the following steps of: performing finite element analysis on the hot end component of the aero-engine with cracks, and determining J integral and stress three-axis degree of a crack front edge node under different loads; the representative position of the crack front edge is determined by combining the J integral of the crack front edge and the stress three-axis degree processing result; generating a traditional failure assessment diagram through the J integral of the representative position of the crack front edge; a correlation function of crack driving force and ligament yield parameters under different crack sizes is constructed, and a failure assessment diagram and a damage tolerance failure assessment diagram combined with the crack size effect are generated; and performing allowable crack size and residual fatigue life prediction to obtain a fatigue life prediction result. According to the method, the residual life prediction precision and reliability of the aero-engine hot end component are improved, the service cycle and maintenance strategy of equipment are optimized, and potential safety hazards caused by structural failure are reduced.

The invention provides a power transmission line fitting failure diagnosis method and system considering a near-wind-field airflow field, and relates to the technical field of power transmission line fitting failure assessment, and the method comprises the steps: obtaining a to-be-diagnosed fitting structure finite element model, building a to-be-diagnosed fitting simulation scheme based on the environment characteristics of the near-wind-field airflow field of a power transmission line, determining a stress aggregation region, and obtaining a to-be-diagnosed fitting failure assessment model; and determining a first constraint index for failure diagnosis of the to-be-diagnosed hardware fitting based on the obtained failure diagnosis constraint signal of the stress aggregation region and the stress aggregation region microscopic fatigue aggregation index, performing deviation extraction on the environmental characteristics of the near wind field and airflow field of the power transmission line, and judging the simulation failure diagnosis evaluation level of the to-be-diagnosed hardware fitting. According to the method, the problems that the traditional inspection tour is difficult to meet the accurate prediction requirement of the hardware failure in a complex environment and cannot meet the requirement of the dynamic failure diagnosis, evaluation and response of the power transmission line hardware are solved, the accuracy of fault prediction is greatly improved, and the safety risk caused by sudden fracture is reduced.

The invention discloses a crack tolerance analysis method for a saddle-shaped welding seam of an integral reinforcing connecting pipe of nuclear pressure-bearing equipment, and belongs to the technical field of reliability. The method comprises the following steps: firstly, establishing a three-dimensional model containing a crack structure and defining crack parameters; carrying out finite element analysis after applying a load; and the critical crack size is determined by iteratively adjusting the crack depth in the failure evaluation diagram. Carrying out sampling analysis by taking the load and the material parameters as random variables to obtain a critical crack size set; and finally, the failure probability reaches a target allowable value by adjusting a crack detection threshold value of nondestructive testing. According to the method, finite element simulation is carried out, the critical crack size of the saddle-shaped welding seam of the integral reinforcing connecting pipe of the pressure-bearing equipment under the complex load is checked based on a failure evaluation icon, the relation between the critical crack size and the allowable crack size is established by assuming that the crack size detected by nondestructive testing obeys normal distribution, and the test efficiency is improved while the number of experiments is reduced. And the reliability of a calculation result is ensured.

The invention discloses a method for judging a shaft integrity failure dangerous area in a gas injection and production stage of a gas reservoir type gas storage. According to the method, a stratum-cement sheath-casing geometric model is constructed in finite element simulation software according to design parameters of the gas reservoir type gas storage and geological data of a stratum where the stratum-cement sheath-casing geometric model is located, and the integrity failure process of a shaft in the gas production stage is simulated through the stratum-cement sheath-casing geometric model. The method comprises the following steps: respectively evaluating the integrity failure severity degree of a failed shaft and the integrity failure risk of a non-failed shaft of the gas reservoir based on a shaft integrity failure evaluation standard, and calculating shaft integrity failure danger level judgment indexes corresponding to each depth of the gas reservoir type gas reservoir; based on the dangerous area judgment standard of the integrity failure of the shaft of the gas reservoir type gas storage, the danger level of the integrity failure of the shaft in each area of the shaft in the gas injection and production stage of the gas reservoir type gas storage is comprehensively judged, and shaft integrity failure monitoring of key areas of the gas storage in the later period is facilitated.

The invention relates to a safety assessment method for pressure-bearing special equipment with crack defects based on health monitoring and digital twinning. Various sensors are installed at key parts of the equipment to collect running state data in real time, a parameterized digital reconstruction technology is adopted to establish high-precision twin bodies of the equipment, and stress distribution and crack propagation trend of the structure are automatically simulated and analyzed by means of cloud computing. A two-stage Bayesian optimization algorithm is innovatively used to realize self-correction of simulation result errors, and adaptive accurate mapping of a digital model to physical equipment is realized. And in a crack defect-containing area, an instability critical dimension prediction model is constructed based on an extended finite element method and a failure evaluation diagram technology, and the crack instability critical dimension is dynamically calculated. According to the invention, real-time, efficient and automatic safety assessment and early warning can be carried out on pressure-bearing special equipment, and scientific data support and decision basis are provided for safe operation and maintenance of the equipment.

The invention relates to optimized handling of adjacent plane interference problems, and provides a data storage device and a method. The memory blocks of the meta-block are analyzed and tested to determine whether the plurality of memory blocks have not passed the first failure assessment. If more than one memory block does not pass the first failure assessment, the memory blocks are allocated to a retry pool. When in the retry pool, a second fault assessment is performed on the memory block. If one or more of the memory blocks pass the second failure assessment, the memory blocks are placed in a pool of memory blocks and relinked to other memory blocks to form a new meta-block. However, if one or more of the memory blocks do not pass the second failure assessment, the memory blocks are withdrawn.

The present invention relates to the field of pipeline testing, and specifically provides a service life prediction method applicable to natural gas hydrogen - blended pipelines. The service life prediction method applicable to natural gas hydrogen - blended pipelines includes establishing a failure assessment diagram, and drawing a load ratio cut - off line and a toughness ratio cut - off line in the failure assessment diagram to form a reference line and a safety zone. Based on the calculated depth a of i cracks, the load ratio #imgabs0# and the toughness ratio #imgabs1# are respectively calculated and the corresponding coordinate points (#imgabs2#, #imgabs3#) are formed to obtain the critical crack depth #imgabs4#. When the circumferential stress direction applied to the pipeline is the principal stress direction of the crack, the service life of the pipeline is calculated according to #imgabs5#, and when the axial stress direction applied to the pipeline is the principal stress direction of the crack, the service life of the pipeline is calculated according to #imgabs6#. The service life prediction method applicable to natural gas hydrogen - blended pipelines of the present invention has high accuracy.

The application relates to the technical field of offshore wind turbine operation and maintenance, and discloses a system for evaluating the failure of an offshore wind turbine, which comprises a sensor data acquisition module, a data preprocessing module, a failure feature extraction unit, a failure probability calculation module, a maintenance decision module and the like. The system can acquire parameters such as the vibration and temperature of the wind turbine in real time, extract failure features by using a deep convolutional neural network after preprocessing, and calculate the failure probability of components by constructing a dynamic Bayesian network model. An improved ant colony optimization algorithm is used to generate an optimal maintenance path, and a dynamic risk evaluation module, an abnormal signal detection module and a maintenance strategy optimization module are simultaneously provided. The system can accurately evaluate the failure risk of the unit, timely discover abnormalities, optimize maintenance decisions, improve the operation reliability of the offshore wind turbine, reduce operation and maintenance costs, and ensure the stable and efficient operation of offshore wind power generation.

The invention discloses a safety evaluation method for a defective PE (Poly Ethylene) pipeline under a point load, which comprises the following steps of: determining a defect form of the PE pipeline under the action of the point load by acquiring constitutive model parameters, fracture toughness and other mechanical parameters of a PE pipe material; selecting a failure evaluation curve used by the failure evaluation diagram; the fracture ratio Kr is calculated based on the M integral, the load ratio Lr is calculated based on the elastic-plastic J integral, and parameters are corrected through experiments and simulation verification. Establishing a three-dimensional simulation model of the PE pipe under the point load according to different analysis parameters; extracting a crack front edge stress intensity factor KI and a J integral maximum value Jmax, and calculating a failure evaluation point; and finally, drawing according to the failure evaluation curve and the failure evaluation points, and judging whether the pipeline is safe or not. According to the method, the actual working condition can be comprehensively considered, the safety of the defective PE pipe under the action of the point load is scientifically evaluated, and the method also has reference significance for safety evaluation of pipelines made of other thermoplastic polymer materials.

The present invention relates to a method for predicting and analyzing corrosion failure of naval equipment, and the specific steps are: 1. Analysis and judgment of corrosion failure modes; 2. Determination of statistical functions of naval equipment under typical corrosion failure modes; 3. Analysis of life function based on MATLAB: through the first and second analyses, and through test data or actual ship data, the corrosion basic parameters of the analysis object are obtained, the Weibull distribution function is analyzed, and the statistical laws of corrosion failure are obtained through numerical analysis, and then prediction and judgment are carried out. The method for predicting and analyzing corrosion failure of naval equipment provided by the present invention is based on experimental test data and software analysis. Compared with existing prediction methods, the prediction results are more accurate and can be used for systematic analysis of corrosion failure assessment under typical corrosion failure modes of key systems of naval equipment, providing key step support for life prediction, failure risk prediction, accelerated testing and process monitoring and monitoring, and long-term failure mode correction of equipment during its service period.

The present disclosure relates to a power device failure evaluation method and device, the method comprising: obtaining an operating state parameter of the power device; determining whether a stress event occurs to the power device based on whether the operating state parameter meets a first preset condition, and recording a stress parameter corresponding to the stress event; determining whether a stress failure occurs to the power device based on whether a duration of the stress event exceeds a preset time; in the case that the stress failure does not occur to the power device, calculating an aging characteristic parameter of the power device based on the operating state parameter; and determining whether an aging failure occurs to the power device based on whether one of the aging characteristic parameter and the stress parameter meets a corresponding second preset condition. The present disclosure can evaluate the stress failure and the aging failure of the power device occurring in the actual operation process.

This application discloses a method and apparatus for determining the grade of a non-volatile memory chip. The method includes: acquiring current test data of frequency, capacity, and timing of the non-volatile memory chip, as well as failure assessment test data; determining a dynamic weighting matrix based on the usage scenario information of the non-volatile memory chip; mapping the current test data to a pre-constructed first chip feature space based on the dynamic weighting matrix and calculating the corresponding likelihood probability; determining the current data score grade based on the likelihood probability; calculating a personalized degradation rate parameter based on the failure assessment test data and a pre-constructed chip degradation trajectory curve; determining the failure assessment data based on the personalized degradation rate parameter; and determining the comprehensive grade corresponding to the current data score grade and the binary grading interval to which the failure assessment data belongs as the target comprehensive grade of the non-volatile memory chip. This technical solution achieves automated, multi-dimensional, and high-precision grade classification of non-volatile memory chips.

The invention belongs to the technical field of riser system risk assessment, and discloses a drilling riser system failure assessment method and related device.The drilling riser system failure assessment method comprises the steps that uncertain factor sources of a riser system are obtained; data sampling is carried out on uncertain factor sources of the riser system, and a preset dynamic response index calculation value of the riser system under the storm condition is obtained through analysis; the failure state is judged, and an uncertainty factor source which has the most obvious influence on the vulnerability of the riser system under the extreme storm condition is obtained through analysis; carrying out data sampling on an uncertain factor source which has the most obvious influence on the vulnerability of the marine riser system under the extreme storm condition, and analyzing to obtain a preset dynamic response index calculation value of the marine riser system under the extreme storm condition; the failure state is judged, and uncertain factor indexes which have the most remarkable influence on the vulnerability of the riser system are obtained through analysis; the method breaks through the limitation that a traditional failure assessment method only pays attention to environmental loads, and ensures the accuracy of a failure assessment result.

This invention belongs to the field of rotating machinery condition monitoring and fault diagnosis technology. It proposes a bearing failure assessment method and system. The method involves acquiring bearing vibration signals and performing mean and absolute value removal processing to obtain the signal to be processed. Next, a lower threshold for the tail is determined, and a set of tail samples with amplitudes greater than this threshold is selected. Then, a soft-truncated power-law distribution model is constructed based on the tail sample set, and the distribution parameters, including the power-law tail exponent, truncation scale parameter, and truncation smoothing exponent, are solved using maximum likelihood estimation. Furthermore, an analytical expression for the improved Gini index is constructed based on the distribution parameters, and the bearing degradation degree index is calculated. Finally, a bearing degradation curve is constructed based on the degradation degree index for different time periods. This invention accurately characterizes the tail impact features of vibration signals using a soft-truncated power-law model and quantifies the degradation degree using an improved Gini index, effectively assessing the health status and failure trend of rolling bearings.

This invention relates to the field of flexible riser risk assessment technology, and more particularly to a method for risk assessment of marine dynamic flexible risers based on fuzzy rule inference networks. The method includes: acquiring a set of historical failure data for flexible risers; conducting a failure assessment on the historical failure data set based on a five-level risk scoring standard to obtain a first assessment result; performing feature fusion processing on the first assessment result based on a preset expert weight standard to obtain a second assessment result; obtaining fuzzy feature values ​​based on a Gaussian fuzzy mechanism and the second assessment result; inputting the fuzzy feature values ​​into a preset fuzzy rule inference network model to obtain a fuzzy set output by the fuzzy rule inference network model; and defuzzifying the fuzzy set to obtain the flexible riser risk assessment result. This invention, through the processing of a fuzzy rule inference network model, can effectively handle the multi-factor nonlinear coupling effects in flexible riser systems, thereby improving the accuracy of risk assessment.

The invention discloses a power transmission network cascading failure risk assessment device and method based on an optimization domain, and belongs to the technical field of power transmission network failure assessment, and the device comprises a cascading failure optimization domain generation module which is used for constructing a cascading failure risk assessment model based on historical data, and generating an optimization domain; the off-network judgment module is used for judging on-network states of all generators in the power transmission network based on the current operation state; the cascading fault deduction module is used for judging a cascading line fault caused by a single fault and updating an optimization domain based on a current topological state; and the cascading failure evaluation module is used for constructing mapping from an operation space to an optimization domain based on all potential renewable energy source scenes so as to realize rapid cascading failure evaluation. According to the power transmission network cascading failure risk assessment device and method based on the optimization domain, the influence of a large-scale scene on cascading failures can be effectively assessed, and the cascading failure assessment speed and efficiency can be remarkably improved.

The invention relates to the technical field of flexible riser risk assessment, in particular to an ocean dynamic flexible riser risk assessment method based on a fuzzy rule inference network, which comprises the following steps: acquiring a historical failure data set of a flexible riser, performing failure assessment on the historical failure data set based on a five-level risk scoring standard to obtain a first assessment result, and performing risk assessment on the first assessment result to obtain a second assessment result; and performing feature fusion processing on the first evaluation result based on a preset expert weight standard to obtain a second evaluation result, obtaining a fuzzy feature value based on a Gaussian fuzzy mechanism and the second evaluation result, inputting the fuzzy feature value into a preset fuzzy rule reasoning network model to obtain a fuzzy set output by the fuzzy rule reasoning network model, and obtaining a fuzzy set output by the fuzzy rule reasoning network model. And performing defuzzification processing on the fuzzy set to obtain a flexible riser risk assessment result. According to the method, the multi-factor nonlinear coupling effect in the flexible riser system can be effectively processed through fuzzy rule reasoning network model processing, so that the accuracy of risk assessment is improved.

The present invention relates to a method and system for assessing the damage tolerance of a high-temperature pipeline under creep fatigue load, and relates to the field of damage tolerance. The method comprises: establishing a pipeline finite element model containing cracks of different sizes and performing numerical calculations to obtain the stress intensity factor of the crack tip in the pipeline; obtaining a crack propagation model and pipeline crack size; determining the creep fatigue crack propagation rate according to the pipeline crack size; calculating the crack propagation life according to the stress intensity factor and the creep fatigue crack propagation rate; determining the fracture toughness according to the pipeline crack size; calculating the residual strength of the pipeline according to the fracture toughness and the pipeline crack size; constructing a damage tolerance assessment diagram of the high-temperature pipeline under creep fatigue load according to the crack propagation life and the residual strength. The present invention can provide ideas for the damage tolerance assessment of pipeline structures, assist in the fracture assessment and residual life prediction of pipelines, and provide guidance and suggestions for the maintenance and overhaul of their structures.

The application discloses a power station boiler high-temperature component with defects remaining life calculation method, device, equipment and medium, relates to the field of boiler risk analysis, and the method comprises the following steps: according to the basic information of the power station boiler component with defects, determining the initial material yield strength, the reference stress at the defect position, the load ratio, the fracture ratio, the creep damage before the defect is generated, the load ratio cutoff line and the failure evaluation curve; when the initial state of the defect is safe, the entire service cycle of the component with defects is divided into multiple time load steps, the creep crack propagation damage, the load ratio and the fracture ratio of each time load step are calculated; and when a certain time load step does not pass the safety assessment, the remaining service life of the component with defects is determined according to the cracking time corresponding to the time load step and the running time of the component with defects. The application improves the calculation accuracy and efficiency of the remaining service life of the power station boiler high-temperature component with defects.

This invention discloses a failure assessment method, system, and device for spiking neural network circuits, relating to the field of spiking neural network circuit technology. The method includes: injecting a pre-set fault into the spiking neural network unit of the spiking neural network circuit to change the stability of the spiking neural network circuit, obtaining a faulty spiking neural network circuit; then, based on a pre-set sample set, calculating the first accuracy of the spiking neural network deployed in the spiking neural network circuit before the fault injection, and the second accuracy of the spiking neural network in the faulty spiking neural network circuit after the fault injection; finally, optimizing the spiking neural network circuit based on the first accuracy, the second accuracy, and a pre-set optimization strategy. This solves the technical problem that existing neural network circuit evaluation and optimization methods cannot effectively improve the reliability of the spiking neural network circuit itself.

The invention relates to the technical field of bridge steel structure anti-breaking design, and particularly discloses a method for calculating the minimum acceptable CTOD value of high-strength bridge steel, which comprises the following steps: carrying out a steel tensile test at the minimum service environment temperature of a bridge structure to obtain the mechanical property of the steel at the corresponding temperature, and drawing a failure assessment diagram FAD; assuming the possible defect form and size of the bridge steel member, considering the maximum service load of the bridge steel member, determining the design stress, calculating the abscissa value Lr'of the failure assessment graph FAD, calculating the ordinate value Kr 'corresponding to the Lr', and regarding the points (Lr 'and Kr') as the critical points of the fracture failure of the bridge steel member; according to the method, the minimum acceptable CTOD value of the steel under the corresponding service condition can be calculated under different working conditions, the fracture toughness level of the steel can be evaluated more visually and conveniently, and anti-fracture design of a bridge steel structure is facilitated.

This invention provides a method for assessing internal failure of orthotropic laminates based on strain measurement, relating to the field of orthotropic composite materials technology. The method includes the following steps: S1, fabricating a strain gauge test model of the laminate; S2, connecting the strain gauge test model to a data acquisition instrument, conducting a working condition test on the structure under test, and using a host computer to calculate the stress in each layer and principal direction of each angle within the laminate; S3, acquiring the strength limit of the orthotropic single-layer laminate material, and based on the strength limit of the orthotropic single-layer laminate material and the stress in each layer and principal direction of each angle within the laminate, performing failure assessment for each ply at different angles. Due to the special characteristics of orthotropic laminates, different ply failures can occur under different stress states. This invention provides a method that can calculate the failure assessment of ply in different directions within the laminate structure based on the surface strain measurement values ​​of the composite laminate.

The embodiment of the invention provides a vehicle function failure assessment method and system and a vehicle, and relates to the technical field of function failure probability assessment and automatic driving. The method comprises the steps that initial scene data corresponding to a vehicle are acquired, and the initial scene data are used for representing a real-time scene where the vehicle is located; performing parameter dimension reduction processing on the initial scene data to obtain target scene data; based on target failure probability distribution, adaptive sampling is carried out on the target scene data, a target sampling result is obtained, and the target failure probability distribution is used for representing scene information corresponding to a function failure event of the vehicle; and performing evaluation calculation according to the target sampling result to obtain the function failure probability of the vehicle in the real-time scene. According to the method and the device, the technical problems of low efficiency and low accuracy of a vehicle function failure evaluation method caused by dependence on a Monte Carlo method in related technologies are solved.

The invention belongs to the field of pipeline failure assessment, and relates to a double-competition failure assessment method based on pipe body strain and circumferential weld fracture toughness. According to the method, based on the high-grade steel pipeline containing the circumferential weld cracks under the action of the landslide, the J integral critical index of the circumferential weld material fracture toughness of the high-grade steel pipeline is determined through a three-point bending test, and a structural strain and fracture toughness calculation model of the high-grade steel pipeline containing the circumferential weld cracks under the action of the landslide is established; the method comprises the following steps: determining influence laws of pipeline, crack and landslide parameters on strain and J integral, respectively establishing pipe body strain and circumferential weld crack J integral prediction models by adopting particle swarm optimization (PSO) and a long short term memory neural network (LSTM) embedded algorithm (PSO-LSTM), and finally establishing a double-competition failure assessment method based on pipe body strain and circumferential weld fracture toughness. And a pipeline safety evaluation series atlas is formed. The landslide pipeline failure evaluation method integrating the pipe body strain and the circumferential weld fracture toughness is formed, the landslide pipeline double-competition failure evaluation method is optimized, the safety state of the landslide pipeline can be scientifically and accurately evaluated through field verification, and practicability is high.