418 results about "Uncertainty analysis" patented technology

The invention discloses an acousto-optic multi-view-field detection device and method for underwater defects of a hydraulic structure, and the method comprises the steps: obtaining original data, carrying out the filtering processing of the original data, and obtaining the filtered original data; based on the filtered original data, constructing a preprocessed multi-modal data tensor; performing spatial registration processing on the multi-modal data to obtain multi-modal data under a unified coordinate system; a self-adaptive tensor decomposition method is adopted for processing, and real-time position coordinates and movement track data of the robot are obtained; processing by adopting a multi-scale feature analysis method to obtain a target position coordinate and a target feature description; and processing by adopting a space-time optimization method and an uncertainty analysis method to obtain a final target positioning result and a confidence evaluation result. According to the method, the detection precision and the system robustness are improved, the detection accuracy is improved, the system positioning precision reaches the centimeter level, and the method is particularly suitable for intelligent defect detection in a complex hydraulic environment.

An icing detection method based on tension and tilt angle sensors. Two kinds of sensor data are comprehensively utilized, cross validation and mutual compensation are realized, and the precision of an icing monitoring result is improved; compared with a single sensor, data fusion of a multi-source heterogeneous sensor improves the robustness and the anti-interference ability of ice volume assessment, and improves the reliability of icing detection; an uncertainty analysis model for icing thickness is established, a confidence interval of a monitoring result is given, and more sufficient reference information is provided for related decisions; by setting a scientific and reasonable monitoring and early-warning mechanism, intelligent monitoring and early-warning of an icing condition are realized, and the intelligent level of the technology is improved; and by establishing an icing monitoring model, the icing condition of wires can be accurately predicted, and the early-warning and monitoring capabilities are improved to ensure the safe operation of a power grid. Also disclosed are an icing detection system based on tension and tilt angle sensors, a computer device and a computer-readable storage medium.

The invention discloses a deep learning-based intelligent identification method and system for rock and soil mechanical parameters, and aims to accurately identify the elastic modulus, strength parameter and permeability coefficient of rock and soil and support the decision and design of engineering projects under complex geological conditions. And starting from data demand analysis, determining a parameter identification target and planning a field test layout. A basic data set is constructed by comprehensively collecting and integrating multi-source data including laboratory and field test data, remote sensing information and the like. The data is pre-processed and analyzed to remove noise and explore associations between the data. The method comprises the following core steps: constructing a rock-soil mechanical model by using a deep learning algorithm, and realizing high-precision inversion of parameters by defining and optimizing an objective function. And verifying an inversion result and carrying out uncertainty analysis. According to the method, an analysis result is fed back to engineering design adjustment and decision support, and scheme optimization is achieved. The model and strategy are dynamically adjusted through continuous monitoring and real-time data, and safety and high efficiency of engineering implementation are guaranteed.

The invention belongs to the technical field of atmospheric pollution monitoring, and discloses a method for realizing VOCS inversion of satellite remote sensing column concentration by using machine learning. Comprising the following steps: preprocessing multi-source data to obtain a multi-source feature data set; performing feature hierarchical extraction and association analysis based on the multi-source feature data set to obtain a feature association graph; performing dynamic feature embedding and relation modeling based on the feature association graph to obtain a component feature space; based on the component feature space, constructing a multi-task deep learning inversion model, and performing weight optimization to obtain an optimized inversion model; based on the optimized inversion model, space-time interpolation and uncertainty analysis are carried out on satellite remote sensing column concentration data, and a high-resolution VOCs component inversion graph is obtained; and multi-scale verification and dynamic correction are carried out based on the high-resolution VOCs component inversion graph and the ground VOCs component monitoring data, and a VOCs component inversion result is finally obtained, so that the refinement level of regional atmosphere quality management is improved.

The invention discloses a regional risk prediction method and system based on toxic gas diffusion analysis, and provides a regional risk prediction method based on toxic gas diffusion analysis on the basis of source item traceability prediction of a leakage source. The content of the invention mainly relates to development and improvement of a gas diffusion model, data acquisition and processing, construction of a risk prediction model, uncertainty analysis, research of an emergency response strategy, case analysis and verification and system integration and demonstration application, and through comprehensive consideration of factors such as gas properties, meteorological conditions and topographic features, prediction accuracy is improved, and the risk of the gas diffusion model is predicted. Scientific basis is provided for risk management, and practicability and popularization of the prediction system are finally realized.

The invention discloses a method for quantifying the influence of climate change and human activity on watershed vegetation, which comprises the following steps: acquiring data of a research area from a plurality of data sources, performing time-space consistency processing, and calculating saturation vapor pressure difference; performing feature extraction on the processed data, and constructing a high-dimensional feature tensor; constructing a space-time diagram based on the high-dimensional feature tensor, performing dimension reduction and dynamic modeling by applying a map embedding technology, and analyzing space-time dynamic features of watershed vegetation; separating and quantifying direct influence of climate and human activities on vegetation by adopting a causal network and a regression decomposition method; comprehensive evaluation is carried out, and uncertainty analysis is carried out. According to the method, the ability of understanding the dynamic state of a complex ecosystem is remarkably improved, powerful scientific support is provided for watershed ecosystem management, and more accurate, reliable and comprehensive decision support can be provided.

The invention discloses a flowmeter self-calibration method and system based on big data analysis. The method comprises the steps that multi-source data collection is conducted, and multiple kinds of data are collected and stored in a big data platform with a block chain evidence storage function; data preprocessing: adopting multiple algorithms to improve data quality; feature extraction and analysis: identifying key factors and monitoring fluid states by means of multiple technologies; calculating calibration parameters, and considering various coefficients and uncertainty analysis; performing automatic calibration, encrypting and writing parameters after digital twin simulation, and reserving a copy; and verifying the calibration effect by adopting a multi-mode verification mechanism. The system comprises a plurality of functional modules which work cooperatively. According to the invention, the data acquisition comprehensiveness is improved, the calibration period is shortened, the production efficiency is improved, the data integrity and reliability are ensured, key factors are accurately identified, the fluid state is monitored in real time, the calibration parameter adjustment is simulated, and the calibration effect is verified in a multi-mode manner, so that the reliability and accuracy of a flowmeter measurement system are improved.

The invention provides an aviation transient electromagnetic fast Bayesian inversion method, device and equipment, and relates to the technical field of geophysical signal processing and analysis, and the aviation transient electromagnetic fast Bayesian inversion method comprises the steps: obtaining a resistivity model and the height of a transmitting coil; the resistivity model and the transmitting coil height serve as input data, electromagnetic response data serve as output data, a deep learning network model is trained, and a forward modeling model is obtained; coupling the forward modeling simulation model to a parallel Bayesian inversion framework to generate a target network model; and performing resistivity inversion and quantitative uncertainty analysis on to-be-analyzed aviation transient electromagnetic data based on the target network model to obtain an analysis result. By integrating a deep learning forward simulator into a Bayesian inversion framework, rapid Bayesian inversion and quantitative uncertainty estimation of aviation transient electromagnetic data can be realized, and the inversion efficiency is greatly improved.

The invention provides a method and system for measuring resistance in an underwater vehicle towing test, and relates to the technical field of underwater vehicle hydrodynamic performance testing, and the method comprises three links of gravity center adjustment, measurement data processing and uncertainty analysis. Firstly, it is ensured that the gravity center and the buoyancy center of a test model are consistent in height, model attitude stability is ensured, and resistance measurement errors caused by attitude changes are eliminated. Secondly, measuring the sailing resistance of the test model in the towing test, and post-processing the measured data to obtain the total resistance coefficient of the test model at the test temperature; and finally, quantizing errors of each link and synthesizing expansion uncertainty by adopting a deviation limit and precision limit combined uncertainty analysis method. Compared with a traditional single-index evaluation method, the method not only can reveal error sources and quantify the influence of each link on the measurement result, but also can accurately reflect the composite effect of errors, and ensures the reliability of the resistance measurement result.

The invention relates to the technical field of remote sensing technology and forest ecological system carbon sink monitoring, and particularly discloses a forest carbon sink dynamic monitoring method based on near-surface multi-source remote sensing data, which comprises the steps of S1, data acquisition, S2, data processing, S3, forest change information monitoring, S4, forest carbon reserve estimation, S5, forest carbon sink dynamic analysis and S6, result verification and uncertainty analysis. By integrating multi-source information such as the multispectral data, the laser radar data and the field survey data, the structure and functional characteristics of the forest ecosystem can be comprehensively and accurately reflected. Compared with a single data source, the comprehensive data acquisition mode has the advantages that the precision and reliability of forest parameter extraction can be remarkably improved, and a solid foundation is provided for subsequent forest carbon reserve estimation and carbon sink dynamic analysis.

Systems, methods, and devices that relate to assessing uncertainty associated with entities are disclosed. In one example aspect, the method receives artifacts relating to an entity and categories for assessing uncertainty. For each category, a generative model retrieves and standardizes data points from the artifacts. A rule-based model inputs the standardized data points to output a rating. The generative model then generates an assessment of the rating and data points according to a predefined structure. The method outputs a summary, rating, and standardized data points for each category. These outputs can be used by other systems for assessing the uncertainty of the entity and taking action based on the assessment.

The invention relates to the technical field of exploration, and discloses a water depth inversion method and system based on a multispectral remote sensing image, which utilizes an independent verification sample set to carry out hierarchical precision evaluation, and analyzes model performance differences according to dimensions such as a water depth range and a substrate type. Error propagation of links such as atmospheric correction and water level correction is quantified through full-chain uncertainty analysis, an uncertainty quantification model of ensemble learning is constructed, and a pixel-level precision distribution diagram is generated. Therefore, according to the technical scheme, a closed-loop dynamic adaptation framework is formed by systematically integrating multi-temporal data dynamic modeling and an uncertainty quantification mechanism, a spatio-temporal variation compensation mechanism is embedded in the whole process from data acquisition to result verification, the interference of spatial-temporal heterogeneity of water optical characteristics on water depth inversion is effectively dealt with, and the accuracy of water depth inversion is improved. The problems of parameter mismatch and precision reduction of the water depth inversion model caused by dynamic change of optical characteristics of a coastal water body in seasonal and tidal scales are solved.

The invention discloses an in-structure sound field bounded uncertainty analysis method based on a physical information neural network. The method comprises the following steps: establishing a physical information loss function and establishing a physical information driven neural network; obtaining an input uncertain parameter value range of the internal sound field, obtaining a plurality of parameter levels, and training a sound pressure prediction model under the parameter levels; acquiring sound pressure of a sample point and establishing a data set; establishing a data driving residual error based on the data set, establishing an overall loss function by using the data driving residual error and a physical information loss function, and training a parameter-containing physical information driving neural network to obtain a parameter-containing internal sound field sound pressure prediction model; and establishing an interval model, and obtaining an internal sound field sound pressure uncertainty distribution range by using a global search algorithm and the parameter-containing internal sound field sound pressure prediction model. The method can solve the problem of prediction of the sound field in the structure containing uncertain parameters, and can effectively improve the calculation efficiency on the premise of ensuring that the calculation precision meets the engineering requirements.

The invention discloses a coal power multi-path transformation and new energy combination decision-making method under low-carbon transformation. The method comprises the following steps: firstly, constructing a system comprising first-level effect indexes such as environmental influence, economic benefit, energy safety and technical innovation and corresponding second-level indexes; then, alternative schemes of various coal power transformation technology and new energy project type combinations are generated; then quantitatively evaluating the effect index of each scheme, and calculating a comprehensive utility value by using multi-criterion decision analysis; identifying potential risk factors, and performing uncertainty analysis through Monte Carlo simulation; and finally, according to the low-carbon transformation target and policy evaluation scheme conformity, selecting a scheme which most conforms to the policy target, and continuously monitoring and adjusting. The coal-electricity multi-path transformation and new energy combination decision-making method under low-carbon transformation is beneficial to promoting energy low-carbon transformation, optimizing resource allocation, improving economic benefits, promoting technical innovation, enhancing risk management capability and ensuring that a project is consistent with policy orientation.

The invention discloses an ecological restoration effect evaluation method and system based on satellite remote sensing, and the method comprises the steps: collecting the satellite remote sensing data and field soil data of a preset region, and taking the remote sensing data of the preset region within a specified time as to-be-analyzed data; calculating a time sequence deviation and a contrast ratio based on the satellite remote sensing data to obtain a grading region; performing deviation correction on the satellite remote sensing data according to the field soil data in the grading region, and inputting the corrected satellite remote sensing data into a space-time ecological development prediction model to obtain ecological development prediction data; performing restoration uncertainty analysis according to the ecological development prediction data and the field soil data to obtain an ecological restoration effect confidence coefficient, and performing elastic capability analysis according to the ecological restoration effect confidence coefficient and the satellite remote sensing data to obtain an ecological elastic index; and constructing a time-varying ecological restoration effect evaluation model according to the ecological elasticity index, and outputting an evaluation result based on the to-be-analyzed data.

The invention discloses a photovoltaic output probability modeling method and system for describing photovoltaic multi-dimensional correlation based on R-Vine Copula, relates to the field of uncertainty analysis of a power system, and aims to adapt to different actual use conditions and precision requirements by flexibly selecting a kernel density estimation bandwidth, so that a nonparametric model based on kernel density estimation can better provide an ideal marginal distribution model. Various Copula functions are hierarchically combined to more accurately represent the nonlinear correlation of photovoltaic output, and the description precision of the photovoltaic dependent structure is improved. According to the method, the defects that an existing traditional photovoltaic probability modeling method is single in marginal distribution and correlation form, large in fitting error, difficult to adapt to a nonlinear photovoltaic power generation scene and large in modeling and actual operation condition deviation are overcome, the randomness and correlation of photovoltaic output can be represented more accurately, and the method is suitable for large-scale popularization and application. Therefore, reliable and stable operation of the power system under the background of large-scale photovoltaic access is ensured.

The invention provides a contaminated site remediation technology scoring system which comprises a multi-dimensional evaluation index system construction module, a situational weight dynamic adjustment module, a remediation technology applicability scoring module, an uncertainty analysis and sensitivity test module, a scoring result visualization module, a technical scheme sorting and screening unit and the like. Through four innovations of a dynamic weight adaptation mechanism, a multi-model fusion scoring algorithm, a technology combination scheme evaluation module and uncertainty robust analysis, the problems of single dimension, weight solidification, difficulty in quantification of a synergistic effect and the like in pollution remediation technology evaluation are systematically solved; and an objective, efficient and transparent intelligent decision-making tool is provided for repairing a complex polluted site.

The invention discloses a power load prediction method, apparatus and device, and a storage medium. The method comprises the steps of obtaining a first power load sequence of a power system; performing uncertainty analysis on the first power load sequence to obtain uncertainty characteristic data; predicting a power load according to the first power load sequence and the uncertainty feature data to obtain a first predicted power load sequence, and predicting a power load predicted value at the target prediction moment; determining a power load residual sequence according to the first power load sequence and the first predicted power load sequence; predicting a power load residual error according to the power load residual error sequence to obtain a power load residual error prediction value; and determining a target power load prediction result according to the power load prediction value and the power load residual prediction value. According to the method and the device, the uncertainty analysis is performed on the historical power load sequence, and the power load is predicted based on the uncertainty analysis result, so that the accuracy of power load prediction is improved.

The invention provides an island shoreline erosion risk prediction method based on computer vision, and belongs to the technical field of island shoreline erosion risk analys.The island shoreline erosion risk prediction method comprises the steps that firstly, a high-resolution remote sensing image is obtained, island contour information is extracted, and a shoreline initial model is constructed through a small grid approximation method; generating multi-level grid representation through grid merging operation and storing the multi-level grid representation as a shoreline feature matrix; then collecting a multi-time sequence remote sensing image, calculating a change matrix set of adjacent time points, and analyzing a shoreline evolution mode; establishing a coast erosion kinetic equation model by combining the wave action intensity, the tide amplitude, the sea level rising rate, the geological structure coefficient and the shoreline slope angle; a shoreline change rule is analyzed by applying a map attention grid evolution model, and finally, an uncertainty analysis module is introduced, a multi-scale erosion risk assessment map is generated, a high-risk area is identified and output as a prediction result, so that the technical problem that the complicated island shoreline erosion risk is difficult to accurately predict is solved.

The invention provides a turbine case connection part reliability analysis and verification method considering uncertainty, and the method comprises the steps: building a finite element analysis model of a local connection structure of a turbine case, and achieving the representation of the uncertainty of connection rigidity; establishing a turbine casing structure uncertainty analysis model considering the connection rigidity uncertainty; determining a failure mode of the turbine case connecting part, defining a failure performance function, and performing reliability analysis on the turbine case structure; according to the finite element analysis result of the turbine case, designing a feature simulation piece of the connection part; processing a characteristic simulation part of the turbine case connecting part and carrying out a fatigue test; and obtaining a finite element analysis result of the turbine case of the processed characteristic simulation piece, and verifying the processed characteristic simulation piece in combination with the dispersibility of the fatigue life data. According to the method, the precision and engineering of the reliability analysis of the connection part of the turbine case are realized, and the precision of reliability evaluation is improved.

The invention discloses a forest carbon sink acquisition method and system for driving an ecological carbon mode through remote sensing observation, and the method and system are corresponding schemes: in the scheme, a set of high-precision and multi-dimensional satellite-ground collaborative observation data system is formed by combining multi-source observation data, and a solid foundation is laid for subsequent carbon sink inversion; a high-resolution prior carbon concentration field of a research area can be generated by using a machine learning method, and a high-precision posterior carbon concentration field can be obtained; on the basis, through inversion analysis and a correction link, high-precision, wide-coverage and low-uncertainty analysis of forest carbon sequestration in a research area is finally realized, and the problems that an existing carbon sequestration estimation method is insufficient in space coverage, high in model uncertainty, limited in multi-source data fusion and the like are solved.

The invention relates to the technical field of power system scheduling, and discloses an intra-day look-ahead scheduling rapid solving method considering large-scale new energy cluster power generation volatility. Comprising the following steps of S1, new energy cluster space-time fluctuation scene generation based on a neuron cellular automaton, S2, power grid dynamic security domain definition and simplification based on a physical information neural network, S3, scheduling rapid optimization solution based on model prediction path integration, and S4, scheduling scheme dynamic elasticity and stability evaluation based on a Kupman operator theory. The new energy cluster space-time fluctuation scene generation method based on the neuron cell automaton can effectively generate a space-time scene reflecting large-scale new energy cluster power generation volatility, supports uncertainty analysis, has the advantages of being high in calculation efficiency and scene authenticity, and is suitable for large-scale new energy cluster power generation. The problem that scene generation is inaccurate due to the fact that a traditional statistical model ignores space-time coupling is solved.

The invention discloses a liquid cooling adaptive control method and system based on a single-phase immersion liquid cooling data center, and relates to the technical field of liquid cooling control, and the method comprises the steps: reading real-time power consumption data of the data center, and synchronously starting a temperature monitoring sensor to read chip temperature data and environment temperature data; configuring a short-time predictor by using the historical load sequence, and executing information gain ratio and prediction uncertainty analysis of preset candidate granularity; performing matching evaluation of single-phase immersion liquid cooling and the data center by using the calibrated prediction granularity; and if the triggering threshold value is met, self-adaptive optimization under local-global control coordination constraint of single-phase immersion liquid cooling control is executed, and a liquid cooling response scheme is output. The technical problems that in the prior art, the cooling capacity of single-phase immersion liquid cooling is low in matching degree with the load requirement, response lags behind, and energy consumption control is insufficient are solved, and the technical effects of self-adaptive optimization control based on real-time and prediction data, energy consumption reduction and heat dissipation efficiency and temperature control precision improvement are achieved.

The invention provides a dangerous rock early warning method, system and device and a medium. Extracting local features of the geological point cloud data, aggregating the local features to generate global features, and obtaining dangerous rock features according to the global features; constructing a dangerous rock three-dimensional model according to the dangerous rock characteristics; performing stability and change trend prediction according to the dangerous rock three-dimensional model to obtain dangerous rock early warning information; according to the method, the change trend can be accurately predicted by using the dangerous rock three-dimensional model, the accuracy of dangerous rock early warning is improved, the uncertainty analysis of dangerous rock disaster time is met according to the dynamic expression of the personalized characteristics of the dangerous rock hidden danger, the reliability and accuracy of dangerous rock disaster early warning are improved, and a data basis is provided for disaster prevention and reduction work of geological disasters.

The invention discloses a hydrogen fuel cell hybrid electric vehicle energy management method based on robust optimization, and the method comprises the following steps: building a vehicle model: building a longitudinal dynamic model of a hydrogen fuel cell hybrid electric vehicle, determining a vehicle demand power model, and building an evaluation function of instantaneous hydrogen consumption, constructing an output power model of the hydrogen fuel cell and the capacitor; performing uncertainty analysis on the hydrogen fuel cell hybrid electric vehicle, determining uncertain parameters in the vehicle model, and constructing an uncertainty set of the uncertain parameters; the method comprises the following steps: constructing an sLSTM vehicle speed prediction model through vehicle historical speed data, predicting a future driving speed, analyzing the uncertainty of the prediction model, and outputting a prediction speed error in a current prediction time domain; and according to the optimization target, constructing a target function for minimizing the hydrogen consumption, solving the target function by applying a robust optimization algorithm, and outputting a first control result of the optimal control sequence.

The invention discloses an undercarriage retracting and releasing mechanism wear prediction method based on digital twinning, and the method comprises the steps: firstly building an undercarriage three-dimensional model containing geometric dimensions and material characteristics, building a multi-body dynamics simulation model, and simulating the stress and wear process of a pin shaft under the actual working condition; and adopting an Archard wear calculation model considering key parameters to calculate the wear of the pin shaft in the simulation model in real time. On the basis, uncertainty analysis of parameters in Archard is carried out, the parameters are considered to obey normal distribution, and a prediction model under multivariate uncertainty is established by setting reasonable mean values and standard deviations. And finally, based on the digital twin model, by using a particle filtering method, initializing a particle swarm, changing a particle weight by virtue of a state and an observation equation, re-sampling to approach a real state, iteratively updating a curve, calibrating model parameters and a state, improving prediction precision, improving prediction accuracy and reliability, discovering a potential wear problem in advance, and providing a basis for a maintenance plan.

The invention discloses an intelligent prediction and uncertainty analysis method for pose errors of a six-degree-of-freedom motion platform, and the method comprises the steps: taking an expected pose in a high-precision six-degree-of-freedom motion platform control system as network input data, and obtaining an actual pose through employing a binocular vision measurement system; collecting multiple groups of data, normalizing the data, and dividing the data into a training set and a test set; constructing a pose error prediction network model taking a gated circulation unit neural network as a basic framework, designing a translation and rotation feature coupling attention module, introducing a sparse attention mechanism guided by domain knowledge, and improving the capturing capability of the model for the real mechanical coupling characteristics of the six-degree-of-freedom platform; and inputting a test set into the trained model, and evaluating data of the test set by adopting a Monte Carlo Dropout method to obtain a pose error prediction result and an uncertainty analysis result. According to the method, the static pose precision of the six-degree-of-freedom motion platform can be effectively improved, a visual and reliable network prediction confidence level is provided, and the precision measurement requirement in the metering field is met.

The invention provides an uncertainty analysis method and device for a livestock target detection model. The method comprises the following steps: acquiring an RGB image of a livestock target; constructing an uncertainty analysis model of the livestock target detection model, and calling the uncertainty analysis model to detect the livestock target in the RGB image to obtain the category of the livestock target and a detection frame coordinate; and respectively calculating a cognitive uncertainty index and a random uncertainty index of the livestock target detection model according to the category and the coordinates of the detection frame. The method is used for solving the problems that in the prior art, an uncertainty analysis method is not comprehensive enough, uncertainty result attribution is lacked, and the uncertainty evaluation effect is poor.

The invention relates to a Bayesian KAN fused aircraft rapid multidisciplinary uncertainty analysis method, and belongs to the technical field of spacecraft manufacturing and application. According to the method, Bayesian learning is combined with a Colmogorov-Arnodel network, a Bayesian KAN neural network which can cope with high-dimensional input uncertainty, can quantify model cognitive uncertainty and is higher in fitting capacity is provided, a BKAN network agent model is constructed for a subsubject analysis model, time-consuming numerical simulation of each subsubject is replaced, and the calculation amount is reduced; with reference to a basic framework of a global sensitivity equation GSE of a deterministic field coupling multidisciplinary system, input random input and model cognition uncertainty are introduced, and expressions of mean values and covariances of disciplinary coupling variables and system responses are deduced on the GSE framework; a rapid semi-analytical multidisciplinary random and model cognition hybrid uncertainty propagation method is established, efficient multidisciplinary uncertainty analysis is achieved, and the problems that an existing method is poor in precision and large in calculation amount are solved.

The invention discloses a mineral resource metallogenic law simulation and target prediction system based on big data, and relates to the technical field of geological exploration. The multi-source data acquisition and standardization module supports acquisition of five types of data, and the data are preprocessed and then transmitted to the distributed database; mining key elements by using an improved Apriori algorithm, and constructing a correlation graph; building a model based on Unity 3D, and integrating three types of dynamic simulation; performing three-level prediction by using a CNN-LSTM model; three-dimensional rendering and multifunctional display are supported; and automatically updating data, models and rules to form an optimized closed loop. According to the method, multi-source data is integrated to improve ore-forming element recognition comprehensiveness, dynamic simulation fits geological reality, AI prediction is accurate, uncertainty analysis is included, visual interaction is practical, iterative optimization continuously improves efficiency, invalid exploration cost is reduced, and mineral exploration is efficiently guided.