148 results about "Kriging" patented technology

The invention discloses an urban water supply management data trend analysis method based on space-time analysis, and relates to the field of data processing, and the method comprises the steps: collecting data in real time through an urban water supply pipe network sensor network, building a space-time unified coordinate system, building a space-time Kriging interpolation model based on pipe network topology, and achieving the space-time alignment of multi-source data; dividing an adaptive space-time grid by using a Voronoi diagram and a sliding window mechanism, and calculating multi-dimensional features; constructing a dynamic space-time diagram by taking a grid as a node, performing multi-step prediction in combination with a space-time diagram convolution circulation network, fusing a Kriging interpolation result, and evaluating an abnormal probability and a confidence interval through a Bayesian neural network; a monitoring layer, a prediction layer and a risk layer are overlaid in a three-dimensional GIS, a dynamic thermodynamic diagram is generated, an early warning path is optimized based on a Dijkstra algorithm, and a minimum risk topology path is output. The method has the advantages that through space-time analysis and accurate prediction, the intelligence, stability and emergency response efficiency of urban water supply management are remarkably improved, and powerful support is provided for smart city construction.

The invention discloses a water quality safety monitoring and early warning method based on big data, and relates to the technical field of monitoring and early warning. Setting sampling points according to areas, pasting scene labels, and arranging sensors to obtain water quality information; establishing a water quality evaluation model based on a support vector machine improved model, inputting the water quality information into the water quality evaluation model, outputting to obtain a water quality category, and dividing the sampling points into normal sampling points and key sampling points according to the water quality category; based on the normal point data, using LSTM to predict water quality safety and performing graded early warning; based on the key point data, positioning a pollution source by using space-time Kriging interpolation, and simulating a pollution diffusion path by using multivariable collaborative interpolation; and combining normal point early warning and key point diffusion simulation to obtain a water quality safety monitoring early warning result. According to the method, a global risk grading report is generated by fusing a normal sampling point early warning result and a key sampling point diffusion path, and emergency response and long-term treatment strategies are matched.

The invention provides a structure reliability analysis method based on an adaptive variable fidelity model, and the method comprises the steps: generating an initial sample point set which is uniformly distributed and has representativeness through an improved random sampling method KMODMC, enabling the initial sample point set to comprise a low-fidelity sample set and a high-fidelity sample set, training a BP neural network through employing the low-fidelity sample set, and carrying out the training of the BP neural network through employing the high-fidelity sample set; a low-fidelity BP neural network model is obtained; meanwhile, based on an error training Kriging model of a high-fidelity sample set and a low-fidelity model predicted value, an error correction Kriging model is constructed, the low-fidelity BP neural network model and the error correction Kriging model are combined to form a multi-fidelity mixed agent model, and adaptive iterative optimization is performed through a double-model alternate point adding sampling strategy. And finally obtaining a high-precision multi-fidelity hybrid agent model for structural reliability evaluation. According to the method, the problems of high cost of high-fidelity simulation calculation and insufficient precision of a low-fidelity model are solved, and the adaptive capacity and prediction precision of the model in a complex nonlinear problem are effectively improved.

The invention discloses a turbine disc baffle structure optimization method and device, equipment, a medium and a product and relates to the field of turbine rotors, and the method comprises the steps that actual structure information of a turbine disc-baffle rotor system is obtained; performing finite element modeling on the actual structure information to obtain a finite element model; transient thermal analysis and transient stress analysis are sequentially carried out according to the finite element model, and the most dangerous time step where the maximum equivalent stress and the maximum contact stress are located is obtained; establishing a response surface model based on a Kriging model according to the most dangerous time step where the maximum equivalent stress and the maximum contact stress are located and actual structure information; according to the response surface model, a multi-target genetic algorithm is used for optimization, and optimized turbine disc baffle structure information is obtained. Stress concentration is effectively reduced, and the fatigue life is prolonged.

The invention relates to the technical field of complex industrial equipment monitoring and digital twinning, and discloses a gas turbine data visualization and intelligent interaction system which comprises a sensor array, a computing unit, a force feedback device, an eye tracker and a display terminal. The system constructs a three-dimensional physical field and corrects a velocity vector by using Kriging interpolation and Euler equation momentum balance, and generates a variable radius flow tube reflecting the compressibility of fluid; calculating mass, momentum and energy conservation residual errors to construct a generalized potential energy field, and generating gradient guide force and self-adaptive damping force by driving force feedback equipment; and dynamically adjusting solving precision and rendering parameters through sight tracking. According to the method, the flow field is reconstructed through physical constraint, multi-modal feedback is introduced, the problem that discrete data feature distortion and single visual interaction are difficult to perceive physical consistency is solved, and high-fidelity reduction of the gas turbine flow field and visual touch synchronous accurate diagnosis of fault types are achieved.

The invention provides an aerosol concentration inversion method and system under a transient working condition, and the method comprises the steps: 1, carrying out the time processing and time sequence feature construction of a transient aerosol concentration data sequence obtained by a monitoring point, and obtaining a time covariance matrix; 2, based on the time covariance matrix and the space information of the monitoring points and the target inversion points, initial inversion is carried out through a space-time Kriging model, and an initial inversion concentration value is obtained; 3, constructing and solving a nonlinear correction coefficient based on the preliminary inversion concentration value and the corresponding actual observation concentration value, and performing secondary correction on the preliminary inversion concentration value to obtain a weighted space-time Kriging inversion concentration value; and 4, carrying out local peak value matching on the weighted space-time Kriging inversion concentration value and an actual observation concentration value, and amplifying and correcting the inversion concentration value in a successfully matched peak value region to obtain a final aerosol concentration inversion result. According to the method, the precision and stability of pollutant concentration field reconstruction under the transient working condition are improved.

The invention provides an urban storm surge forecasting method based on multi-source information coupling, and the method comprises the steps: taking multi-source typhoon driving element data as the input information of a preset typhoon structure reconstruction model, and outputting typhoon key physical parameters through the typhoon structure reconstruction model; based on a Kriging interpolation and radial basis function mixing method, carrying out fusion processing on the multi-source topographic data, and constructing topographic grid information; extracting tide harmonic constants of a specified number of partial tides from the multi-source tide factor data; based on the typhoon key physical parameters, the terrain grid information and the tide harmonic constants, determining input information of a predetermined urban storm surge forecasting model; and outputting a storm surge level abnormal value and a horizontal flow velocity component corresponding to the multi-source prediction associated data through the urban storm surge prediction model. According to the scheme, the precision of urban storm surge forecasting is improved.

The invention relates to the technical field of agricultural Internet of Things, and discloses an edible mushroom growth environment regulation and control method and system based on multi-source sensing data, and the method comprises the steps: deploying a multi-source sensor network, unifying time synchronization, and carrying out event-driven space-time alignment and three-dimensional mapping. Carrying out multi-dimensional reliability evaluation and environment correction, and obtaining an environment parameter fusion data set by adopting a fuzzy logic reasoning method; performing space-time Kriging interpolation, and obtaining a heterogeneous microenvironment feature database by adopting a multi-source data collaborative correction method; carrying out cross-modal attention fusion; performing multi-scale convolution and time sequence attention classification; carrying out deep reinforcement learning and multi-objective optimization; carrying out online incremental learning optimization to obtain a self-adaptive optimized partition collaborative regulation and control strategy; according to the method, the technical problems of insufficient multi-source data fusion precision, lack of environment spatial and temporal distribution modeling, inaccurate parameter coupling prediction, lack of self-adaptability of regulation and control strategies and the like are solved.

The invention provides an efficient and high-precision prediction method for the minimum failure probability of an aviation structure system based on an exponential penalty learning mechanism, and relates to the technical field of structural reliability analysis. Respectively generating an initial sample and a candidate sample according to the probability density function of the random variable of the performance function to be analyzed; real performance function responses corresponding to the initial samples are calculated to form an initial training sample set, and an initial Kriging agent model is constructed; selecting an optimal sample point from the candidate sample set through the proposed EPAL function; merging the optimal sample and the real response thereof into the initial training sample set, and iteratively updating the Kriging model until an error-based stopping criterion is met; judging whether the failure probability variation coefficient meets the requirement or not; and finally, calculating the failure probability of the structure based on a trained Kriging model and a Monte Carlo method.

The invention belongs to the technical field of CFD (computational fluid dynamics) parameter calibration, and discloses a CFD parameter adaptive calibration method and system based on measured data and a double-agent model, and the method comprises the steps: obtaining a CFD input parameter sample, inputting the CFD input parameter sample into a CFD solver, and obtaining an initial simulation result; determining an error evaluation index according to the initial simulation result based on a target actual measurement data result; constructing a double-agent model based on a Kriging model and a radial basis function neural network by taking a CFD input parameter sample as an independent variable and an error evaluation index as a dependent variable; the double-agent model is trained, the trained double-agent model takes the error evaluation index as fitness, and CFD input parameter values are obtained based on a genetic algorithm; the CFD input parameter values are input into the CFD solver for a simulation experiment, a calibrated simulation result is output, the reliability and generalization ability of prediction are improved through a double-agent model, a high-fidelity simulation result is output through the CFD solver, and the number of times of calling the CFD solver is reduced while the calibration precision is guaranteed.

The invention discloses a motor multi-objective optimization design method and system based on a Kriging agent model. Comprising the following steps: constructing an initial data set through an experimental design method and finite element simulation calculation, so as to train an initial Kriging agent model which takes a motor design variable combination as an input variable and takes motor performance as an output response; the proxy model serves as a target function, a multi-target optimization problem is solved, the proxy model is updated, and an updating strategy is as follows: after each round of optimization is finished, a high-error solution in a current Pareto solution set is screened based on a Kriging model prediction mean square error, a finite element response of the high-error solution is obtained and supplemented to a data set, and the proxy model is updated and trained; and repeating the process until the optimization result converges. According to the method, high-uncertainty region samples are selectively supplemented, the calculation cost is remarkably reduced while the local prediction precision of the proxy model at the Pareto leading edge is improved, and the method has good practicability and economical efficiency.

The invention relates to the technical field of data analysis, and discloses a parameterization analysis method and system based on a sea wave spectrum mode. The method comprises the following steps: carrying out abnormal value detection and missing data filling on multi-source ocean data by adopting a 3 sigma criterion and Kriging interpolation, and unifying to a 0.1-degree grid to obtain a standardized data set; decomposing a sea wave energy balance equation source item into three modules for numerical calculation; configuring ST2, ST4 and ST6 schemes for the numerical solutions, and carrying out statistical analysis to obtain performance evaluation indexes; based on the evaluation indexes, a genetic algorithm is combined with particle swarm optimization to carry out parameter optimization; dividing the offshore China into four sub-regions for differential adjustment according to the optimization parameters; and carrying out trend checking and parameter increment updating by adopting a sliding window technology based on region configuration. The technical problems that a sea wave spectrum mode parameterization scheme lacks a systematic comparison and optimization mechanism, parameter configuration cannot adapt to regional marine environment differences, and parameters lacks real-time monitoring and dynamic adjustment capabilities are solved.

The invention discloses an urban atmospheric pollution real-time monitoring method and system. The method comprises the following steps: acquiring pollutant concentration, weather and geographic position data through multi-source monitoring equipment; performing data fusion by adopting space-time Kriging interpolation and wavelet threshold denoising to generate a high-quality urban pollution distribution initial field; a machine learning model of an encoder-decoder structure is used for prediction, an encoder is a convolutional long-short term memory network, a decoder is a dynamic graph convolutional network fused with meteorological factors, and a dynamic pollution situation map is generated; polluted area identification is carried out based on a wind field streamline, and accurate tracing is carried out through combination of reverse simulation of a Lagrange particle diffusion model and a control variable method. The whole process optimization of pollution monitoring from data fusion, accurate prediction to quantitative traceability is realized, and the accuracy and timeliness of urban atmospheric pollution supervision are remarkably improved.

The invention relates to the technical field of power system automation and digital twinning, in particular to a regional power grid static safety risk early warning system and method. Comprising a multi-source heterogeneous data intelligent fusion module, a high-fidelity static security analysis module, a multi-dimensional dynamic risk assessment module, a hierarchical linkage early warning decision module and a full-link result tracing and optimizing module. Uniform access of four kinds of heterogeneous data including SCADA, WAMS, equipment online monitoring and meteorological prediction is supported, a data island of a traditional system is broken through, timestamp alignment is achieved by adopting a dynamic time warping algorithm, spatial deviation is corrected based on GIS Kriging interpolation, the problem of analysis distortion caused by time / space deviation of the traditional system is solved, and the analysis accuracy of the system is improved. A sparse matrix compression technology and an MPI parallel computing framework are adopted, so that the efficiency is improved, the real-time analysis requirement is met, and an N-1 / N-2 fault scene is dynamically generated based on an equipment health index, including N-1 verification of health equipment and N-2 verification of sub-health equipment.

The present application belongs to the technical field of urban meteorological data processing and spatial information calculation, and particularly relates to a method and device for constructing urban meteorological gridded data based on spatial interpolation. The method comprises meteorological data clustering, partition optimization by using a target function during clustering, partition interpolation, spatial division and processing of regions according to the clustering results of meteorological data, statistics of the number of base stations for each region, determination of the type of a region based on the spatial distribution density of the base stations, determination of a global variation function and a regional variation function for each region, calculation of the estimated value of an interpolation point by using a corresponding Kriging interpolation method based on the variation function for different region types, interpolation of points near the boundary lines of different regions by using the meteorological data of the base stations of the regions involved, and weighting to obtain the final result. Finally, the construction of urban meteorological gridded data based on spatial interpolation is realized.

This invention provides a distributed sensor fault-tolerant collaborative control method and system based on spatial interpolation reconstruction. The method includes: intelligent actuator nodes maintaining a list of neighboring sensors and receiving the measured values ​​and self-confidence levels of each sensor; the actuator nodes dynamically calculating the confidence level of each neighboring sensor; when the confidence level of the master sensor is lower than a fault threshold, the actuator nodes automatically select a set of reliable sensors, reconstruct the environmental parameters of the control point using inverse distance weighted or Kriging interpolation, and use the reconstructed values ​​as feedback for control output; simultaneously, the system continuously monitors failed sensors and automatically switches back to the measured values ​​after the sensor recovers. This invention eliminates the need for redundant hardware, completes fault detection and parameter reconstruction at the edge level in milliseconds, achieves reconstruction accuracy that meets control requirements, significantly reduces system costs, improves fault tolerance, real-time performance, and control continuity, and is suitable for environments such as laboratories and cleanrooms.

The invention provides a geomagnetic daily variation prediction method and system based on sub-band Kriging interpolation, and relates to the technical field of geomagnetic daily variation data processing, and the method comprises the steps: obtaining a measurement geomagnetic daily variation signal in a target region; based on the measured geomagnetic daily variation signal, determining a plurality of frequency data corresponding to the measured geomagnetic daily variation signal by adopting wavelet decomposition; on the basis of the multiple pieces of frequency data, adopting a Kriging interpolation prediction model to predict interpolation data corresponding to each piece of frequency data; based on the plurality of interpolation data, the geomagnetic daily variation prediction value of the geomagnetic daily variation observation station to be solved in the target area is obtained through linear superposition reconstruction, and the precision and reliability of geomagnetic daily variation space prediction are effectively improved.

The invention relates to a magnetic suspension centrifugal fan structure optimization method and system based on machine learning. According to the method, parametric modeling is carried out on a meridian plane profile, a blade setting angle and a torsion angle of an impeller, a sample set is generated by utilizing advanced Latin hypercube sampling (ALHS), and a performance database is constructed in combination with CFD simulation; 9 key geometric parameters which have the maximum influence on isentropic efficiency are screened out through adoption of MOP, and a high-precision Kriging approximation model is established; and with the maximum isentropic efficiency as the target and the inlet and outlet pressure difference as the constraint, iterative optimization is carried out by adopting a genetic algorithm (GA), and optimal impeller parameters are obtained. According to the invention, high-efficiency and low-cost automatic design is realized, and the method is suitable for improving the performance of the small-sized centrifugal blower.

This invention provides a multimodal fusion-based method for correlation analysis of deep-sea environmental data outside the Yangtze River Estuary, belonging to the field of deep-sea environmental analysis technology. This invention achieves accurate data registration by establishing a spatiotemporal standardization model for multi-source data and employing an adaptive spatiotemporal kriging interpolation algorithm. It utilizes a sparse coding marine signal separation algorithm to construct an overcomplete dictionary to separate mixed signals and extract pure features. Based on an attention mechanism, a feature extraction network is constructed to automatically learn deep feature representations of physical, chemical, and biological parameters. A matrix rank deficiency detection algorithm is used to automatically supplement feature compensation vectors to ensure feature integrity. A cross-scale attention mechanism based on wavelet transform is constructed to fuse multi-scale features. A Shapley value interpretability evaluation system is established to quantify the importance of correlated features. This invention solves the technical problem of inaccurate correlated feature extraction during the fusion of multi-source heterogeneous marine environmental data.

The invention discloses a method for converting an elevation system contour line of a stock place to a 85 elevation datum, which comprises the following basic steps of: discretizing the contour line based on an adaptive sampling method of contour line curvature, and extracting node data on the contour line; elevation points are properly encrypted in a place with sparse contour lines by using a method for improving Kriging interpolation by using a gradient boosting tree, and elevation point data obtained by arrangement is converted into 85 elevation; according to a weighted soft constraint Delaunay triangulation algorithm, a triangulated irregular network is constructed by using 85-elevation point data, and contour lines are generated. The method provided by the invention has the advantages of being scientific, reasonable, easy to implement, high in production efficiency, wide in application range and the like, the curvature and characteristics of the contour lines are analyzed one by one by fully utilizing the contour lines of the elevation system of the stock place, and the variation characteristics of the complex space are captured more accurately; and the accuracy of conversion from the elevation line contour line of the stock place to the 85 elevation datum can be further improved.

A method of semiconductor manufacturing process parameter optimization based on Bayesian average Kriging and evidence theory is proposed. By introducing Bayesian model averaging into the basic Kriging model, different variance functions are adaptively weighted, which effectively improves the robust estimation of spatial correlation structure and alleviates the bias caused by model mis-specification under small sample conditions. At the same time, the introduction of evidence theory not only realizes the fusion of multi-source model prediction results, but also explicitly describes the cognitive uncertainty at the model level, enhancing the interpretability of the prediction results and the value of process diagnosis. The method shows good applicability in high-cost and data-scarce manufacturing systems, and can provide reliable proxy modeling support for complex processes such as semiconductor etching.

This disclosure relates to the field of reliability technology, specifically to a method for global sensitivity analysis of a radome structure. The method includes: obtaining important sampled samples of the input variables of the radome structure and a sample pool of the distribution parameters of the input variables; obtaining a training set for a Kriging failure model of the radome structure based on the important sampled samples, and training the Kriging failure model using the training set; when it is determined that each sample in the sample pool meets preset conditions, substituting the samples of the distribution parameters into the Kriging failure model to obtain the global sensitivity analysis result of the radome structure. This disclosure can improve the performance and reliability of radome structures.

The application relates to the technical field of mineral exploration, and discloses a deposit grade prediction method, device, equipment and medium. The method comprises the following steps: performing a pretreatment operation on deposit exploration data, and constructing a feature data set according to the processed deposit exploration data; training an XGBoost main regression model based on the feature data set, and constructing a hybrid residual model; generating an intermediate prediction result by adopting a two-level fusion mechanism, and establishing a mapping relationship between a spatial structure, a variation function and a prediction error; adaptively selecting and dynamically adjusting variation function parameters according to the mapping relationship, so as to obtain an optimized variation function; performing Kriging interpolation by using the optimized variation function, so as to obtain a preliminary grade prediction result with spatial continuity; and fusing the intermediate prediction result and the preliminary grade prediction result, so as to obtain a final grade prediction result. By means of the technical scheme, the accuracy and stability of deposit grade prediction are significantly improved.

The invention discloses a method for analyzing the reliability of a gunpowder igniter in a low-temperature ignition failure mode, which comprises the following steps of: firstly, carrying out characterization analysis on the ignition failure mode of the gunpowder igniter in a low-temperature environment, identifying main uncertain factors influencing the low-temperature ignition reliability by adopting a fault tree method (FTA), and determining the probability distribution characteristic of the main uncertain factors; then, an implicit performance function of the failure mode is established. In order to clarify a deterministic relationship between a performance parameter and a design variable, an inner ballistic simulation model for low-temperature ignition of a gunpowder igniter is constructed based on an inner ballistic theory, and a Kriging agent model is further established by using the simulation model. And finally, sampling and solving the Kriging model through an MCS method (Monte Carlo simulation) to obtain the failure probability and reliability of the low-temperature ignition failure mode of the gunpowder igniter. The reliability of the gunpowder igniter under the low-temperature condition can be accurately evaluated, and a theoretical basis is provided for product improvement design.

The invention relates to the technical field of intelligent weather forecast, in particular to a rainfall multi-source seamless fusion method and device based on dynamic error perception, electronic equipment and a storage medium, and the method comprises the steps: dynamically sensing the influence of a weather situation on a multi-source data error through a task-driven VQ-VAE model, adaptively optimizing a fusion weight, and improving the fusion precision; spatial optimal interpolation is realized in combination with a dynamic collaborative Kriging framework, continuous transition of an analysis field and a forecasting field in time and space is ensured by using a time-varying weight fusion technology, and a product jumping phenomenon is eliminated; the adopted semi-supervised mechanism maintains the physical interpretability of the model while reducing the dependence on the labeled data; and finally, through terrain constraint and independent site deviation correction, the product has both physical rationality and quantitative precision, and a reliable data basis is provided for meteorological and hydrological services.

The application discloses a method for accurately evaluating the contribution of meteorological bias based on multi-technology integration of atmospheric pollutants simulation bias, which solves the technical problems of insufficient correlation and quantification of meteorological bias and pollution simulation bias, insufficient depth of bias analysis, and missing spatiotemporal contribution rule representation in the prior art. The WRF-CMAQ coupling mode is used to obtain meteorological and pollutant concentration simulation data, and combined with the observation data of the national control site, a standardized bias feature variable data set containing meteorological bias and pollutant concentration bias is constructed. The VIF factor is used to screen and eliminate parameter collinearity, and an XGBoost bias model is constructed to quantify the nonlinear correlation between meteorological bias and pollutant concentration bias. The SHAP model is introduced to analyze the contribution weight of each meteorological bias parameter. Combined with the spatiotemporal information of the site, the Kriging interpolation is used to generate the global spatiotemporal distribution atlas of the contribution of each meteorological bias parameter. The application provides a precise quantitative basis for the targeted optimization of the WRF meteorological field and the improvement of the simulation accuracy of atmospheric pollution.

The application provides a tunnel three-dimensional laser point cloud data denoising interpolation method, system and device, relates to the application technical field of mountain tunnel three-dimensional laser scanning, and the method comprises the following steps: obtaining initial point cloud data of excavation, primary support and secondary lining section, calculating the azimuth angle and overbreak and underbreak value of each point in the point cloud data, removing noise through the difference method and the mean value method, performing interpolation processing based on the improved Kriging interpolation method, and calculating parameters such as overbreak and underbreak value, overbreak and underbreak area and underbreak intrusion position number. Through the method provided by the application, the noise point group and discrete noise points can be effectively removed, the precision and accuracy of tunnel section overbreak and underbreak detection are improved, the misjudgment of underbreak and intrusion position is avoided, the point cloud data at the missing position can be automatically completed, the precision of overbreak and underbreak detection is further improved, and the calculation result is more suitable for engineering practice.

The invention discloses a possibility-based optimization design method for an aero-engine thrust augmentation cylinder, which comprises the following steps of: firstly, analyzing and identifying an important region of interest of the thrust augmentation cylinder, cutting the region by utilizing a sub-model technology, and realizing parametric modeling and finite element modeling; calculating the low-cycle fatigue life of the position with the maximum stress by adopting a local stress-strain method; the method comprises the following steps: representing geometric configuration, material attributes and load environment parameters of a stress application cylinder as fuzzy variables, and carrying out reliability analysis through a method of combining fuzzy simulation and adaptive Kriging to obtain a failure possibility degree; and finally, by taking the minimum volume of the stress application cylinder as a target and the design value of the failure possibility degree as a constraint, solving an optimization design model based on the failure possibility degree by adopting a method based on an enhanced expectation improvement learning function and combining an active constraint criterion and an adaptive Kriging model, so as to obtain design parameters of the stress application cylinder. According to the method, the problem that a traditional optimization algorithm is poor in adaptability under multi-constraint and fuzzy uncertainty is solved.

The invention discloses a cold region tunnel disaster multi-field coupling deduction and lining response prediction method and device, and the method comprises the steps: collecting temperature, stress and seepage pressure monitoring data containing time sequence and space dimensions; finishing data intelligent repair and anomaly recognition by adopting an algorithm of combining a deep learning model-Kriging interpolation based on time sequence analysis with an isolated forest-mahalanobis distance to obtain preprocessed data; constructing a multi-field coupling deduction model based on a finite element-lattice Boltzmann method; using a support vector machine and fuzzy logic to diagnose disaster types and severity, and determining disaster risk levels based on Monte Carlo simulation and a risk matrix; and finally, predicting the evolution trend of the lining structure of the medium-high risk part under different time scales by adopting a physical information neural network and taking the risk level as a constraint. According to the method, the accuracy and multi-scale of multi-field coupling deduction and lining response prediction of the tunnel in the cold region are realized, and reliable technical support is provided for tunnel construction monitoring, operation and maintenance scheduling and disaster prevention and control.