基于深度学习的矿井时移电阻率监测数据特征提取与智能筛选方法

打开文本图片集

中图分类号：TD745 文献标志码：A 文章编号：1671−251X（2025）07−0059−07

Abstract：The time-lapseresistivity monitoringdata inmines isahigh-dimensional dataset that includes atributes suchasrecoverydirection，working faceextensiondirection，depthdirection，andresistivityvalues.Its true distributionisunknown，and blindly applying existing dimensionalityreductionmethods may diminish certain high-dimensionalatributes thatarecloselyrelatedtodataquality.Atpresent，dataselectionrelies heavily on manual experience，resulting ina low level of automation.To address these issues，a deep learning-based feature extraction and intelligent screening method for time-lapse resistivity monitoring data in mines was proposed.First， high-dimensional discrete data containing spatial 3Dcoordinate information and resistivity values were subjected to dimensionality reduction to capture essntial features of the data，eliminate redundancy，and achieve multi-scale feature extraction.Then， the ResNet10 convolutional neural network was used to extract 2D features from each slice and compute their structural similarity to assess the spatial continuityand smoothness of resistivity anomalies. A Transformer network was used to extract 3D features from the resistivity monitoring data. Finall，spectral clustering Was applied in the feature space to perform intelligent screening of the monitoring data. The proposed method and manual selection method were used to extract features and perform quality selection on 16 monitoring datasets colected in a single day from a coal mine area.The results showed that manual selection bydierent personnelproducedcompletelydiferentresults，indicatingstrong subjectivity，poorrepeatability，lack of fixed evaluation criteria， and took an average of 3O minutes，leading to poor real-time performance. The proposed method achieved 100% consistency in the experimental results， and each selection took less than 30 seconds， indicating that the selection results were objective， stable， reliable，and fast.

Key words： time-lapse resistivity monitoring;ResNetlO convolutional neural network；Transformer network; spectral clustering; coal mine geological transparency; deep learning; structural similarity

0 引言

矿井时移电阻率监测是煤矿地质透明化和水害隐患监测预警的有效手段[1-3]。（剩余12005字）