CN-121995536-A - Intelligent prospecting multisource data fusion analysis method and system for peganite lithium mine

CN121995536ACN 121995536 ACN121995536 ACN 121995536ACN-121995536-A

Abstract

The invention relates to the technical field of intelligent detection and sensors, in particular to a method and a system for analyzing intelligent prospecting multisource data fusion of a pegmatite lithium mine; the method comprises the steps of dividing a continuous ore forming process into a plurality of stages with definite geological significance based on an ore forming mechanism of the peganite lithium ore, abstracting the stages into structural ore forming rhythm units, constructing an ore forming rhythm constraint model representing the evolution sequence and the space dependency relationship among the units, carrying out standardization processing on multi-source ore finding data, carrying out coupling mapping and sensitivity weighting on the multi-source ore finding data according to the rhythm units to form a comprehensive rhythm response matrix, carrying out fusion generation on the comprehensive rhythm consistency index through calculating space consistency and multi-source attribute consistency indexes, identifying and circumscribing a high potential ore forming area, and introducing actual investigation verification information to dynamically correct and optimize a prediction result to form a closed-loop feedback ore finding decision support. The invention realizes the mechanism-driven intelligent prediction from multi-source data to the mining target area.

Inventors

DUAN WEI
ZHANG WEI
ZOU LIN
TANG WENCHUN
BAO WENXIANG
FAN YINGWU

Assignees

四川省综合地质调查研究所

Dates

Publication Date: 20260508
Application Date: 20260205

Claims (10)

1. The intelligent multi-source data fusion analysis method for the prospecting of the peganite lithium ores is characterized by comprising the following specific implementation steps: S1, surrounding a pegmatite lithium ore forming process, identifying a key ore forming stage, abstractly defining the key ore forming stage as an ore forming rhythm unit, and constructing an ore forming rhythm constraint model for representing an evolution sequence and a space dependency relationship between the units; s2, carrying out standardized processing on remote sensing data, geophysical measurement data, geochemical sampling data, geological survey data and monitoring data streams of an Internet of things sensing network, and carrying out coupling mapping and sensitivity weighting on the processed multi-source ore finding data according to an ore forming rhythm unit to form a comprehensive rhythm response matrix; S3, based on the comprehensive rhythm response matrix, calculating a space consistency index and a multi-source attribute consistency index, and carrying out weighted fusion on the space consistency index and the multi-source attribute consistency index to generate a comprehensive rhythm consistency index, and identifying and circumscribing a high potential ore formation area according to the comprehensive rhythm consistency index; s4, introducing actual investigation verification information, dynamically correcting and optimizing the comprehensive rhythm consistency index and the high potential ore-forming area marked according to the comprehensive rhythm consistency index, and feeding back a new investigation result to the steps to form a closed-loop feedback ore-making decision support.
2. The method for analyzing intelligent prospecting multisource data fusion of the pegmatite lithium ore according to claim 1, wherein in step S1, the construction process of the minescence rhythm constraint model specifically comprises the following steps: Abstracting each identified ore forming stage into an ore forming rhythm unit, wherein the ore forming rhythm unit is characterized by a space response state, a control attribute set and a stage identifier together; Calculating an ore forming stage evolution consistency index among different ore forming rhythm units by utilizing a rhythm sequence consistency function according to the stage identification; calculating the space dependency index between different mineforming rhythm units by utilizing a rhythm space dependency function according to the space response state; And constructing an ore rhythm evolution constraint function based on the ore stage evolution consistency index and the spatial dependency index, wherein the ore rhythm evolution constraint function is used for quantifying the comprehensive constraint intensity between any two ore rhythm units on the ore evolution logic and spatial distribution relation.
3. The method for analyzing intelligent prospecting multisource data fusion of the pegmatite lithium ores according to claim 2, wherein in step S2, the standardization process specifically comprises: Carrying out unified space coordinate registration, dimension normalization and noise filtering treatment on remote sensing image data, aviation or ground geophysical measurement data, geochemical sampling data and geological survey data; And monitoring time sequence data flow of the Internet of things sensing network acquired by intelligent sensors deployed in the investigation region, performing time sequence analysis and feature extraction, and processing the extracted feature values into space grid data matched with analysis time periods of the ore-forming rhythm units.
4. The method for intelligent prospecting multisource data fusion analysis of the pegmatite lithium mine according to claim 3, wherein in the step S2, the specific process of sensitivity weighting is as follows: calculating sensitivity indexes of the class of data sources to each ore-forming rhythm unit and each class of data sources aiming at each ore-forming rhythm unit; determining a weighting coefficient of the data source on the corresponding ore-forming rhythm unit according to the calculated sensitivity index; and carrying out weighted calculation on the response values of various data sources mapped to the ore-forming rhythm unit by using the weighted coefficient, thereby obtaining weighted rhythm response.
5. The method for intelligently searching for ore from the pegmatite lithium ore by multi-source data fusion analysis according to claim 4, wherein in the step S3, the specific method for generating the comprehensive rhythm consistency index is as follows: Calculating a spatial consistency index of response values in local neighborhood of each ore-forming rhythm unit according to the response of each ore-forming rhythm unit at the spatial position (x, y); calculating multi-source attribute consistency indexes of different data source response values according to the response of each ore-forming rhythm unit at the spatial position (x, y); And multiplying the spatial consistency index and the multi-source attribute consistency index by a preset spatial consistency weight coefficient and an attribute consistency weight coefficient respectively, and adding to obtain the comprehensive rhythm consistency index of the position.
6. The method for intelligent prospecting multisource data fusion analysis of the pegmatite lithium ores according to claim 5, wherein in step S3, high potential mineralization areas are identified and delineated, and the method is specifically realized by the following steps: Setting a high potential threshold for the comprehensive rhythm consistency index, wherein the threshold is determined according to the percentile of historical mine point data response values; Extracting all spatial position points with the comprehensive rhythm consistency index higher than the high potential threshold value in the spatial range of each ore-forming rhythm unit to form a single rhythm unit high potential area of the unit; And carrying out spatial superposition and fusion on the single-rhythm unit high-potential areas corresponding to all the ore-forming rhythm units to generate a final comprehensive prediction ore-forming area.
7. The method for analyzing intelligent prospecting multisource data fusion of the pegmatite lithium mine according to claim 6, wherein in step S4, the specific process of dynamic correction comprises the following steps: Mapping the actual investigation verification point into a corresponding ore forming rhythm unit, and calculating the prediction credibility of the ore forming rhythm unit according to the ore finding result label and the comprehensive rhythm consistency index at the verification point; based on the comparison of the prediction reliability and the average reliability of all units, calculating to obtain a rhythm consistency correction factor of the ore-forming rhythm unit; And (3) correcting the original comprehensive rhythm consistency index obtained in the step (S3) by using the rhythm consistency correction factor to obtain a corrected rhythm consistency index.
8. The method for intelligent prospecting multisource data fusion analysis of the pegmatite lithium mine according to claim 7, wherein the step S4 further comprises the following closed-loop optimization process: according to the corrected rhythm consistency index and the change amplitude of the original index, a high potential area with the change smaller than a preset stability threshold value is screened out and used as a stable final optimal prospecting prediction area; generating executable prospecting decisions including drilling priority zone and slot search placement suggestions based on the final preferred prospecting prediction zone; And supplementing the newly acquired investigation verification result after the ore finding decision is executed into an actual investigation verification information set, and triggering an iterative optimization flow from fine tuning of the model parameters in the step S1 to re-correction in the step S4.
9. The method for analyzing the intelligent prospecting multisource data fusion of the pegmatite lithium mine according to claim 3, wherein the sensing network monitoring data of the internet of things in the step S2 specifically comprises time sequence data collected by one or more devices of a high-precision gas sensor, a soil temperature and humidity sensor, a microseismic monitoring node and a groundwater chemistry in-situ monitor.
10. The utility model provides a multi-source data fusion analysis system for intelligent prospecting of peganite lithium ore, which is used for executing a multi-source data fusion analysis method for intelligent prospecting of peganite lithium ore according to any one of claims 1 to 9, and is characterized by comprising the following steps: The multi-source mining data collaborative acquisition and standardization module is used for collaborative acquisition of heterogeneous data from remote sensing, geophysics, geochemistry, geological survey and an internet of things sensing network, and standardization and quality constraint processing under a unified space-time reference; the ore formation indication information structured expression and characteristic evolution module is used for constructing ore rhythm units according to the characteristics of the pegmatite lithium ore formation factor and establishing an evolution and space dependence constraint model among the units; the multi-scale ore forming response association fusion module is used for mapping the standardized multi-source data to an ore forming rhythm unit and carrying out sensitivity weighting fusion to generate a comprehensive rhythm response matrix, so as to calculate a comprehensive rhythm consistency index and outline a high potential ore forming area; And the intelligent reasoning and verification feedback module of the prospecting target area is used for introducing actual investigation verification information to dynamically correct and optimize the prediction result and driving iterative updating of the system model based on verification feedback to form closed-loop decision support.

Description

Intelligent prospecting multisource data fusion analysis method and system for peganite lithium mine Technical Field The invention relates to the technical field of intelligent detection and sensors, in particular to a method and a system for analyzing intelligent prospecting multisource data fusion of pegmatite lithium ores. Background Currently, mineral resource exploration has entered a new stage characterized by data driving and intelligence, and multi-source data acquisition technologies such as remote sensing, geophysics, geochemistry, geological investigation and the like are becoming mature, and data volume and types are becoming rich, so that a solid information foundation is provided for comprehensively knowing an ore-forming system. The Chinese patent application with the publication number of CN121069525A discloses a mining method based on multisource geological relation data, wherein the method comprises the steps of carrying out space-time alignment and standardization processing on acquired geological historical evolution data, geophysical field data, geochemical migration data and remote sensing alteration information to generate a dynamic knowledge graph, carrying out mining effect phase division processing on the geological historical evolution data to obtain a mining effect phase division result, integrating a fluid migration space-time path network, carrying out three-dimensional dynamic modeling processing to generate a staged three-dimensional mining evolution model, extracting phase specific geological mark combinations from the staged three-dimensional mining evolution model, carrying out knowledge reasoning processing based on a preset historical deposit rule base, outputting a mining target area meeting preset confidence coefficient conditions and mining process constraint basis to improve the accuracy of a construction model, generating a staged hydrodynamic field and enhancing the prediction confidence of the target area. At present, the popularization of the Internet of things technology promotes the wide application of the intelligent sensor in the field environment, can realize the dynamic and in-situ monitoring of the physical and chemical parameters related to the ore formation, and further expands the data dimension; under the background, how to deeply fuse multi-source, static and dynamic investigation data with specific ore forming theory and space evolution rule of pegmatite lithium ore, an intelligent ore finding model which can embody geological mechanism constraint and fully exert data value is constructed, and the intelligent ore finding model becomes a key research direction for improving lithium resource investigation efficiency and accuracy and is an important front edge for promoting geological investigation to intelligent and refined transformation upgrading. Disclosure of Invention The invention aims to solve the problems in the background technology and provides a method and a system for intelligent prospecting multisource data fusion analysis of pegmatite lithium ores. The technical scheme of the invention is that the intelligent mining multisource data fusion analysis method for the pegmatite lithium ores comprises the following concrete implementation steps: S1, surrounding a pegmatite lithium ore forming process, identifying a key ore forming stage, abstractly defining the key ore forming stage as an ore forming rhythm unit, and constructing an ore forming rhythm constraint model for representing an evolution sequence and a space dependency relationship between the units; s2, carrying out standardized processing on remote sensing data, geophysical measurement data, geochemical sampling data, geological survey data and monitoring data streams of an Internet of things sensing network, and carrying out coupling mapping and sensitivity weighting on the processed multi-source ore finding data according to an ore forming rhythm unit to form a comprehensive rhythm response matrix; S3, based on the comprehensive rhythm response matrix, calculating a space consistency index and a multi-source attribute consistency index, and carrying out weighted fusion on the space consistency index and the multi-source attribute consistency index to generate a comprehensive rhythm consistency index, and identifying and circumscribing a high potential ore formation area according to the comprehensive rhythm consistency index; s4, introducing actual investigation verification information, dynamically correcting and optimizing the comprehensive rhythm consistency index and the high potential ore-forming area marked according to the comprehensive rhythm consistency index, and feeding back a new investigation result to the steps to form a closed-loop feedback ore-making decision support. Preferably, in step S1, the process of constructing the ore-forming rhythm constraint model specifically includes: Abstracting each identified ore forming stage into an ore forming rhythm unit, wherei