460 results about "Simulated data" patented technology

The invention relates to the technical field of image analysis, and discloses a multi-modal emotion recognition method and system based on hypergraph diffusion and evidence fusion, a terminal and a storage medium, and the method comprises the steps: carrying out the random shielding of a data set through a randomly generated mask, thereby simulating the random data missing condition, and carrying out inverse sampling on the preprocessed simulation data by using a trained conditional diffusion model to obtain a training set in which missing modals are complemented so as to train an emotion classification network, and finally carrying out emotion recognition. According to the method, through dual-channel evidence fusion, uncertainty is estimated at a feature source level and a discrimination level at the same time, so that adaptive evidence fusion is realized, the condition of performance reduction caused by modal loss is reduced, potential features of the lost modal are explicitly recovered in a feature space, and the accuracy of final emotion recognition is improved.

The invention discloses an oil reservoir production dynamic prediction method fusing discrete gradient information, and belongs to the technical field of oil reservoir development and artificial intelligence crossing, and the method comprises the steps: building a heterogeneous oil reservoir oil-water two-phase flow numerical simulation data set based on a numerical simulation method; designing a double-branch network structure and extracting spatial and physical characteristics of input field data in parallel, wherein the spatial and physical characteristics comprise a main characteristic coding branch and a differential operator branch; designing a backbone network to carry out deep nonlinear modeling; an efficient pressure and saturation field prediction neural network model is constructed based on a double-branch network structure and a backbone network, in a model training stage, spatial region observation points of part of time steps are used to participate in data item loss calculation, and meanwhile, physical control equation residuals are introduced into all time steps and a whole space to serve as physical loss items; a trained efficient pressure and saturation field prediction neural network model is obtained, and high-precision prediction of a full-time-sequence pressure field and a saturation field is achieved.

The invention discloses a transformer substation switching operation risk pre-control method and system based on deep reinforcement learning, and relates to the technical field of power system automation, and the method comprises the steps: collecting transformer substation equipment data in real time, processing the collected data, generating a standardized time series data set, building a system topology structure represented by multiple graphs based on the processed data, and carrying out the pre-control of the transformer substation switching operation risk. Integrating dynamic characteristics, based on a system topological structure, generating a switching operation decision sequence, dynamically adjusting a risk boundary threshold, based on a real-time system state, evaluating the security of the decision sequence, intercepting operations which do not conform to a security boundary, performing reward attribution on contributions of operation sequence steps, and constructing a digital twin environment; the model performance is improved through interactive calibration of real data and simulation data. According to the substation switching operation risk pre-control method based on deep reinforcement learning, high-precision risk prediction is realized, the early warning time is sufficient, and the operation sequence is optimized, so that the safety of substation switching operation is remarkably improved.

The invention discloses a method for realizing ocean sound field prediction based on a pre-training optimized physical information neural network, which comprises the following steps of: pre-training: constructing a hypothetical ocean environment, generating simulation data in a sound pressure envelope form by using an acoustic numerical calculation tool, and pre-training the physical information neural network to learn a physical rule of sound field propagation; fine tuning: adjusting an energy scale factor according to the proportion of the sound pressure amplitude of the actual measurement point to the sound pressure amplitude of the pre-trained environment, and performing fine tuning by using the envelope amplitude data of the actual measurement sound field for the pre-trained physical information neural network to obtain an ocean sound field prediction model through a pre-training-fine tuning dual-stage strategy; and ocean sound field prediction: according to the ocean sound field prediction model, obtaining a target position envelope from the to-be-predicted range, and then converting the target position envelope into a sound pressure result to realize ocean sound field prediction. The method can improve the high-frequency sound field modeling precision and training efficiency, and can be widely applied to the fields of ocean sound field modeling, sound source localization and environment inversion.

The invention discloses a glacier material balance simulation method and system based on feature interaction, and belongs to the technical field of glacier hydrology and climate change monitoring, and the method comprises the steps: sequentially carrying out the uniform format processing and slope feature enhancement of a multi-source data set of a glacier, and dividing the multi-source data set into a simulation data set and an observation data set; training a model based on a trans-attention Transform encoder framework by using the simulation data set to obtain a pre-training model; when one-glacier-leaving cross validation is carried out on the pre-trained model, multi-stage fine tuning training is carried out by using the observation data set to obtain a plurality of fine-tuned models; performing model integration based on performance index screening on the fine-tuned models, and constructing an integrated simulation model; and preprocessing the meteorological dynamic characteristics and the static topographic characteristics of the target glacier, inputting the preprocessed meteorological dynamic characteristics and static topographic characteristics into the integrated simulation model, and carrying out glacier material balance simulation to obtain a glacier material balance simulation result. According to the method, the simulation uncertainty is reduced, and the high-precision simulation of the glacier material balance is realized.

The invention discloses a BIM and block chain-based construction whole process quality tracing method and system, and relates to the technical field of building construction quality management. In a material entering stage, material information is collected through the Internet of Things and is associated with a BIM component identifier, and an initial block is generated by using an intelligent contract; in the process execution stage, BIM 4D / 5D simulation data is associated with a construction log, and a Hash chain algorithm is adopted to generate a process block containing IPFS Hash; in the acceptance inspection stage, the consistency of detection results is verified through zero-knowledge proof, and a new block is generated; checking the block data through a consensus mechanism to obtain a complete data set; constructing a graph database index based on the BIM component tree, and generating a chain path graph; responding to a query request, traversing path diagram nodes, comparing hash values and outputting a tracing result; trusted communication, tamper-proof evidence storage and intelligent tracing of data in the whole construction process are achieved, and the accuracy and reliability of project quality management are remarkably improved.

The invention provides a forest degeneration process identification and degeneration degree division method based on a time sequence, and relates to the field of forest resource degeneration restoration. The method comprises the following steps: acquiring surface reflectance data, and calculating an NBR index after preprocessing; fitting an NBR time sequence through a LandTrendr algorithm, and extracting sample place time sequence data based on random sampling and visual interpretation; generating an adversarial network and expanding sample point fitting data into a simulation data set in combination with a self-supervised learning technology; training CNN, random forest and BOSSVS time sequence classification models, and constructing a hybrid classification model through an integrated voting strategy; and identifying a forest degeneration process by using a hybrid classification model, and generating a degeneration degree diagram through reclassification. The method can achieve the efficient recognition of the complex degradation process of the forest region, has good time sequence adaptability and regional applicability, and provides technical support for the monitoring and management of ecological restoration of regional forests.

The invention discloses a tunnel over-break and under-break prediction method based on numerical simulation and actual measurement data mixed training, which comprises the following steps: step 1, determining RHT constitutive model parameters corresponding to five types of surrounding rocks through physical and mechanical parameters of a rock foundation in combination with a state equation of an RHT constitutive model and an original numerical value of the RHT constitutive model; 2, based on constitutive model parameters, finite element analysis calculation is carried out, and a tunnel back break simulation data set based on a numerical simulation test is obtained; 3, tunnel construction site blasting parameters and tunnel average overexcavation amount are collected to serve as an actual measurement data set; and step 4, carrying out mixed training on the simulation data set and the actually measured data set, and constructing a tunnel back break prediction model. According to the tunnel back-break prediction method based on numerical simulation and actual measurement data mixed training, the problems that a tunnel back-break prediction model is weak in generalization ability and poor in migration ability due to the fact that an existing prediction method is large in calculation amount and small in data sample set due to a numerical simulation method are solved.

The invention provides an insurance premium evaluation method and device for an intelligent driving vehicle, equipment and a medium. The method comprises the following steps: acquiring multi-level data of a sensor; generating a first sensing parameter based on the sensor multi-level data; generating a second sensing parameter based on the sensor service life and the sensor quality guarantee period; performing simulation scene configuration based on the first sensing parameter and the second sensing parameter to obtain a target simulation scene, and performing driving decision simulation on the intelligent driving vehicle in the target simulation scene to obtain risk loss simulation data corresponding to different driving scenes; determining scene accident loss of the intelligent driving vehicle based on the risk loss simulation data; and determining an intelligent driving scene occurrence probability based on the intelligent driving scene mileage and the total mileage of the vehicle, and evaluating the reference premium of the intelligent driving vehicle based on the intelligent driving scene occurrence probability, the scene accident loss of the intelligent driving vehicle, the premium rate and the expected mileage of the intelligent driving vehicle. Therefore, rapid and accurate premium evaluation of the vehicle is effectively realized.

A system and method include learning a topological order of a plurality of variables in a directed acyclic graph based on real data, computing parameter estimate values corresponding to the real data, computing error values based on the real data, the topological order, and the parameter estimate values, generating simulated data from the parameter estimate values and the error values, such that simulated variables in the simulated data preserve a causal relationship between variables in the real data, and the simulated variables in the simulated data preserve a correlation relationship between the variables in the real data, and reorganizing and outputting the simulated data based on the topological order.

The invention relates to the technical field of open channel gate flow prediction, and discloses an open channel gate flow prediction method based on multivariate data fusion driving, and the method comprises the following steps: carrying out the hour-level processing and preprocessing of actually measured water regimen data, and generating a basic data set; simulating gate water regimen data based on the hydrodynamic model, and constructing a supplementary data set; the basic data set and the supplementary data set are fused, and a BiLSTM multi-factor flow prediction model is constructed; inputting the fused data set into the model, and fitting a traffic prediction model through iterative training; and carrying out traffic prediction by using the trained model, and carrying out reverse normalization to output a final result. According to the method, the actually measured water regimen data and the hydrodynamic model simulation data are subjected to multivariate fusion, so that the problems of precision and robustness of a single data source in gate flow prediction are solved. The simulation data of the hydrodynamic model is used as an effective supplement for actually measured data, and comprehensive gate water regimen information is provided, so that the accuracy and generalization ability of the prediction model are improved.

The invention discloses a simulation data analysis method for long-distance tunneling of a shield in a complex stratum, and relates to the technical field of underground engineering and intelligent construction, and the method comprises the following steps: multi-source data fusion and dynamic modeling: integrating geological exploration data, real-time shield construction sensor data and historical engineering data, constructing and dynamically updating a digital twinborn body in the shield tunneling process, wherein the digital twinborn body is used for simulating mechanical response in the tunneling process in real time; mechanical characteristic enhanced extraction: extracting a stress-strain tensor field of a key part based on a simulation result of the digital twin, and performing differential geometric transformation on the tensor field; by constructing a system of multi-source data fusion, digital twin dynamic modeling, differential geometric mechanics feature extraction, three-dimensional risk intelligent identification, multi-target parameter optimization and visual closed-loop execution, the pain points of traditional shield analysis data fragmentation, feature surface and difficulty in risk positioning are broken through.

The invention discloses a method for data inversion by utilizing a multipoint geological statistical structure constraint direct current electric method, which belongs to the field of geophysical exploration, and comprises the following steps: based on geological drilling data, establishing a model containing geological structure information by adopting a multipoint geological statistical algorithm, and constructing an underground stratum structure operator by utilizing the model; a structure operator is added to a regularization term, an initial resistivity model is given to calculate a data residual term, and an inversion objective function with structure constraint is formed; in the inversion process, a finite memory quasi-Newton optimization algorithm is adopted to carry out iterative optimization on a target function until the difference between forward modeling simulation data and actually measured data reaches a set threshold value, and constraint inversion is completed; and finally, outputting the resistivity inversion model. According to the method, the problems of fuzzy stratum boundary, reduced resolution and the like caused by regularization smooth constraint in a traditional method are reduced, and the method is suitable for subsurface stratum structure detection and fine imaging in a complex geological environment and has wide application value.

The invention discloses a 10kV overhead line adaptive evaluation method and system for non-power-cut operation, and the method comprises the following steps: obtaining the field data of a target line, and constructing the field data into a multi-dimensional evaluation feature vector according to a preset evaluation dimension system for non-power-cut operation; inputting the multi-dimensional evaluation feature vector into a non-power-cut operation adaptability evaluation model to obtain a comprehensive evaluation score and an optimization suggestion of the target line; outputting the comprehensive evaluation score and the optimization suggestion; wherein the non-power-cut operation adaptability evaluation model is constructed by the following steps: training to obtain an initial machine learning model; simulating a preset non-power-cut operation task flow in the digital twinborn body; and performing incremental training and parameter optimization on the initial machine learning model by using operation effect data fed back after actual operation of the simulation data vector. The problems of single evaluation dimension, model stiffness and the like in the prior art can be solved.

The invention relates to the field of intelligent water affairs, and discloses a precise flow control system for intelligent water affairs, which comprises the steps of collecting local water flow change data in real time, extracting flow velocity disturbance characteristics and pipe network transient pressure response, and judging whether unexpected disturbance trigger exists or not; constructing a local disturbance label library based on disturbance trigger source features and a historical operation model, and identifying disturbance sources and flow direction tendentiousness by using fuzzy discrimination and variable weight filtering algorithms; according to the pipe section hydraulic characteristics corresponding to the mismatching behavior, the flow of the target pipe section is corrected through a high-resolution electric proportional valve set and a two-way feedback control unit; constructing a cross-section response chain through the intelligent edge control node, and generating a multivariable adjustment gradient according to the multi-period callback simulation data; flow state data and peripheral environment variables before and after the current round of regulation and control intervention are collected, and system model parameters are dynamically corrected through the integrated evolutionary prediction network. The stability of the intelligent water affair system is improved.

The invention discloses a rice chlorophyll content prediction method, device, medium and equipment, and relates to the technical field of crop growth, and the method comprises the following steps: obtaining canopy spectral data and physicochemical parameters of rice in a to-be-detected area; dividing the rice canopy into three concentric circle areas based on the leaf inclination angles of different leaves of the rice, and obtaining the layered rice canopy; constructing a hierarchical radiation transfer model HRTM for simulating a rice hierarchical spectrum, and inputting the physical and chemical parameters into the hierarchical radiation transfer model HRTM to generate hierarchical spectrum data; constructing a lookup table LUT based on the physicochemical parameters and the layered spectral data, taking the lookup table LUT as an analog data set, improving the analog data set by adopting a quartile method, and determining analog spectral data; based on the simulated spectrum data, constructing an inversion model for acquiring the chlorophyll content of the rice layers layer by layer; and inputting hyperspectral data to be measured into the inversion model, and determining a corresponding chlorophyll content prediction result.

The invention provides an avalanche risk assessment method and device, electronic equipment and a readable storage medium. The method comprises the following steps: acquiring accumulated snow data of an accumulated snow area; in the digital elevation model, performing avalanche simulation on the snow accumulation area based on the snow accumulation data to obtain snow falling simulation data; determining action information of the snowfall simulation data on the target road unit in the digital elevation model; and determining the risk of the target road unit when the avalanche occurs based on the action information. According to the invention, avalanche simulation is carried out based on the actual snow area, so that the snow falling simulation data after the simulated avalanche occurs can be obtained, the effect of the avalanche on the target road unit is determined based on the snow falling simulation data, and the influence of the avalanche on the target road unit is obtained. Before avalanche, the risk of the target road unit in the avalanche type is predicted, so that disaster management and control can be performed in advance aiming at the risk of the road unit, and powerful data support is provided for risk management before the avalanche disaster.

The invention relates to the field of tunnel water flow simulation, in particular to a tunnel group water flow simulation method under the coupling action of tide and rainstorm. The method comprises the following steps: firstly, obtaining water level data of different monitoring positions in a tunnel group at each moment in a preset time period, and obtaining a tunnel structure influence coefficient of a target monitoring position according to a change difference of the water level data of different monitoring positions in a preset neighborhood of the target monitoring position at the same moment; according to the change of the water level data of the target monitoring position at each moment and the serial number corresponding to each moment, and in combination with the tunnel structure influence coefficient of the target monitoring position, obtaining the data feedback influence degree of the target monitoring position, and based on the data feedback influence degree, determining the position of the target monitoring position. Dividing the water level data of each monitoring position into a training data set and a simulation data set; and constructing a tunnel group water flow simulation model based on a training data set and the simulation data set. According to the invention, the accuracy of tunnel group water flow simulation can be improved.

The invention provides a Kovar alloy nano-indentation and nano-friction simulation method based on molecular dynamics. The technical key points are as follows: carrying out initial setting on a simulation system and establishing a model; defining a potential function; performing model initialization, including energy minimization, temperature initialization and system relaxation; performing nanoindentation simulation and extracting data; performing nanometer friction simulation and extracting data; and processing and analyzing simulated data, namely outputting a depth-load curve, calculating hardness, fitting and calculating an elastic modulus, calculating a friction force and a friction coefficient, and analyzing wear morphology and dislocation evolution in the alloy through a simulation process file. By analyzing the mechanical properties and the frictional wear properties of the Kovar alloy at different environment temperatures, stable and reliable simulation data is obtained, the actual experiment cost is greatly reduced, and technical guidance is provided for application of the Kovar alloy in the field of vacuum sealing elements.

The invention discloses a high-precision identification method and system for a noise source of an asynchronous motor, and relates to the technical field of asynchronous motor detection, and the method comprises the following steps: constructing a finite element model of a to-be-analyzed asynchronous motor, dividing the surface into a plurality of detection sub-regions, and carrying out the operation simulation of the finite element motor, analyzing vibration speed and sound pressure signal data of each sub-region, synchronously acquiring actual signals, calculating relative differences with simulation data, evaluating detection priorities by combining historical fault times, forming a detection sequence according to the priorities, and sequentially performing sound-vibration coherence analysis and coherence function calculation to obtain a sound-vibration coherence detection result; according to the method, noise frequency bands are classified into structural noise and air noise, order tracking analysis is performed on the structural noise obtained through classification, an amplitude stability index and an amplitude change gradient are calculated, automatic classification and identification of electromagnetic noise and mechanical noise are realized based on a preset threshold value, and the efficiency and accuracy of fault processing are remarkably improved.

The invention is suitable for the cross field of artificial intelligence and natural language processing, and provides a user intention recognition method and system based on user behavior data. In the embodiment, for a target user needing intention recognition, a multi-modal data set composed of behaviors, texts, audios, videos and the like of the user is firstly obtained, and then the multi-modal data set is processed through a world model used for reinforcement learning to obtain simulation data of the user. The method comprises the steps of obtaining a multi-modal data set, performing intention recognition on a user through the multi-modal data set and simulation data to obtain an initial intention recognition result and a corresponding evaluation index, and finally adjusting the initial intention recognition result through the evaluation index to determine a final target intention recognition result. According to the method and the device, for the data with relatively small data volume in the multi-modal data set, simulation expansion is carried out based on the multi-modal data set through the world model, so that the accuracy of the intention recognition model obtained by training can still be remarkably improved even under the condition that behavior samples are insufficient, and thus the accuracy of intention recognition of the user is improved.

The invention provides a deep foundation pit monitoring method based on BIM-physical model hybrid simulation. The method comprises the steps that real-time monitoring data and BIM model parameters of a deep foundation pit are collected; inputting a first model parameter in the BIM model parameters as an initial geometric condition into the initial physical model for simulation calculation to obtain first simulation data, and verifying the first simulation data based on the real-time monitoring data to obtain a verification result index; optimizing the soil mass mechanical parameters in the initial physical model based on the verification result index until the verification result index output in the optimization process meets a preset requirement, and obtaining an optimized physical model; simulating the construction process of the deep foundation pit on the basis of the optimized physical model in combination with a second model parameter in the BIM model parameters, and outputting second simulation data; and performing monitoring and early warning on the deep foundation pit based on the deep foundation pit knowledge graph in combination with the real-time monitoring data and the second simulation data to obtain a monitoring and early warning result. According to the invention, comprehensive monitoring of the deep foundation pit is realized.

The invention discloses a reflected wave travel time difference measurement method and system based on transverse constraint, and the method comprises the steps: carrying out the migration imaging of observed seismic data under a given speed model, obtaining an imaging result through the cross-correlation of a seismic source end wave field and a receiving end wave field, and obtaining the information of an underground reflection structure based on a multi-attribute Markov decision process. And then solving a background wave field and a primary reflection wave field in a given speed model and an underground reflection structure, and extracting a simulated seismic record at a detection point position. And calculating zero-offset travel time by using the depth of the reflection horizon, and executing transverse tracking in the reflection event direction by taking the travel time as a seed to obtain simulated travel time of each offset position. A local transverse constraint time window is constructed based on simulation travel time, cross-correlation operation is performed on observation data and simulation data in the time window, and a local extreme point is extracted. And finally, performing transverse tracking by taking the zero-offset travel time position as a starting point to obtain continuous and consistent reflected wave travel time difference, thereby realizing stable and accurate measurement of the reflected travel time.

The invention provides a multi-algorithm fusion-based water-based scratch-resistant plastic gloss oil formula optimization method, which comprises the following steps of: obtaining coating component data and environment variable data from a preset material database, and constructing an initial data set; performing crossover mutation operation on the initial formula parameters by adopting a genetic algorithm to generate a formula candidate set; according to the component proportion in the formula candidate set, obtaining a hardness index and a flexibility index through simulation, and performing grouping processing on the candidate set to obtain a grouped candidate set; for the grouped candidate set, adopting a support vector machine to carry out classified training on flexibility indexes of the high-hardness group, extracting performance deviation characteristics, and determining an adjustment vector; the formula parameters of the low-hardness group are corrected according to the adjustment vector, and the scratch resistance simulation data and the bending resistance simulation data are fused to obtain a corrected formula set; the coating performance under the environment variable change is sampled by adopting Monte Carlo simulation, performance fluctuation distribution is extracted, and an optimization formula and a process combination are determined.

The invention provides a rain and snow enhancement ecological benefit dynamic evaluation method, device and equipment and a storage medium, and relates to the field of agricultural planting, and the method comprises the steps: extracting a plurality of key ecological index data based on obtained multi-source data, and constructing a coupling model; the coupling model obtains a simulation data set based on the key ecological index data corresponding to the data before operation, corrects the simulation data set based on the multi-source data to obtain analysis state data, and generates an optimal ecological benefit index based on the analysis state data and the simulation data set; a comprehensive ecological benefit index is obtained through calculation based on a continuous time sequence generated by the multi-source data within a preset time step length, and the optimal ecological benefit index and the comprehensive ecological benefit index form an ecological benefit evaluation result. According to the technical scheme of the embodiment of the invention, the optimal ecological benefit index is generated from multiple dimensions, the ecological benefit of the artificial rain and snow enhancement operation on the ecological system is comprehensively evaluated, the simulation data set is corrected, and the precision of the optimal ecological benefit index is improved.

The invention relates to an embankment leakage risk early warning method and device based on multi-modal data. The method comprises the following steps: accurately constructing a three-dimensional model through surface data such as embankment surface temperature, LiDAR and embankment surface state; then, based on the geometric parameters of the dike body provided by the three-dimensional model, generating simulation data capable of reflecting the dike seepage process by adopting a physical rule, and generating coupling data based on simulation of the three-dimensional model; then, on the basis of a space-time diagram convolutional neural network based on coupling data in combination with multilevel feature fusion, and on the basis of a prediction result of the space-time diagram convolutional neural network constrained by simulation data, space-time correlation analysis of leakage abnormity can be realized, and the accuracy of leakage risk prediction can be improved; and finally, a corresponding emergency early warning response is matched based on the dike early warning parameters. According to the method, efficient fusion of multi-source data and data driving combination of physical rules can be realized, the accuracy and timeliness of leakage early warning are effectively improved, and finally the risk of dike leakage danger is reduced.

Methods, computer systems, and computer-readable memory media for determining a warp function. An as-designed watertight spline model of an object is received. A point cloud and the as-designed watertight spline model are used to construct a model of the object. The point cloud is obtained from a physical or virtual (simulated) inspection and / or manufacturing process. A warp function is determined based on a difference between the as-designed watertight spline model and the constructed model. The warp function is a continuous function quantifying differences between the as-designed model and the constructed model. As-preprocessed instructions for a simulation or analysis process of the object are determined based on metadata of the as-designed watertight spline model and the warp function. The simulation or analysis process is performed on the object according to the as-preprocessed instructions to produce as-simulated data, and the as-simulated data is stored in a non-transitory computer-readable memory medium.

The invention relates to the technical field of urban traffic management, in particular to a traffic simulation data generation method and system based on a data distillation and knowledge distillation technology, and the method comprises the steps: obtaining original data of a real traffic scene, carrying out the cleaning, standardization and spatial-temporal feature extraction of the obtained original data, and obtaining a structured feature set; performing data distillation analysis on the structured feature set to obtain an initial simulation data set conforming to real distribution; inputting the initial simulation data set into a knowledge distillation model, and outputting the knowledge distillation model to obtain knowledge distillation parameters; performing fusion processing on the knowledge distillation parameters and the initial simulation data set to obtain a fusion enhanced data set; and performing dynamic scene adaptability verification and multi-dimensional distribution correction on the fusion enhanced data set to obtain a final simulation data set.

The invention discloses a strike-slip fault zone activity ability evaluation method based on a finite element method, and the method comprises the steps: determining the three-dimensional space distribution characteristics of a strike-slip fault zone, determining the evaluation range of the activity ability of the strike-slip fault zone, determining the ground stress state of a research region, carrying out the finite element stress analysis, and carrying out the simulation data of the ground stress distribution, thereby achieving the evaluation of the activity ability of the strike-slip fault zone. The method comprises the following steps: calculating the acting force of different parts of a strike-slip fault zone, calculating two parameters for evaluating the activity capability of the strike-slip fault zone, optimizing the data distribution range of the two parameters according to the strike-slip fault zone activity capability evaluation threshold values of the two parameters, and screening the data capable of being used for evaluating the activity capability of the strike-slip fault zone by utilizing a cumulative multiplication method, so as to evaluate the activity capability of the strike-slip fault zone. The invention relates to a method for finely evaluating active parts of strike-slip fault zones and activity of different parts. According to the method, the activity capability difference of different parts of the strike-slip fault zone can be quantitatively judged, and an effective scheme is provided for professional technicians for researching activity capability evaluation of the strike-slip fault zone and well location deployment.

The invention discloses a cutting slope reliability assessment method considering fracture spatial variability. The method comprises the following steps: step 1, generating a three-dimensional slope model with soil parameter spatial variability by using a Latin hypercube sampling method; 2, averagely selecting M two-dimensional sections from the three-dimensional slope model constructed in the step 1, calculating 2DFS, and reconstructing a plurality of 2DFS signals from sparse 2DFS data by using a BCS method; step 3, taking the plurality of 2DFS signals obtained in the step 2 as machine learning model input, taking the 3DFS as output, and training machine learning models of the 2DFS and the 3DFS; 4, generating 2DFS random field simulation data by adopting a KL series expansion method; and 5, predicting the 3DFS of the random field data by using a machine learning model, and calculating the reliability. According to the method, only a small number of three-dimensional slope samples and sparse two-dimensional sections need to be calculated, and the efficiency of three-dimensional reliability analysis is greatly improved.