Water source identification in mines combining LIF technology and ResNet
作者机构：State Key Laboratory of Deep Coal Mine Exploitation Response and Disaster PreventionAnhui University of Science andTechnologyHuainan 232001China School of Electrical and Information EngineeringAnhui University of Science and TechnologyHuainan 232001China Collaborative Innovation Center of Mine Intelligent Equipment and TechnologyAnhui University of Science&TechnologyHuainan 232001China
出 版 物：《Journal of Mountain Science》 (山地科学学报（英文）)
年 卷 期：2023年第20卷第11期
页 面：3392-3401页
核心收录：
学科分类：0819[工学-矿业工程] 081903[工学-安全技术及工程] 08[工学]
基 金：the Collaborative Innovation Center of Mine Intelligent Equipment and Technology,Anhui University of Science&Technology(CICJMITE202203) National Key R&D Program of China(2018YFC0604503) Anhui Province Postdoctoral Research Fund Funding Project(2019B350)
主 题：Water source identification Mine safety LIF technology CT PCA ResNet
摘 要：The problem of mine water source has always been an important hidden danger in mine safety *** water source under the mine working face may lead to geological disasters,such as mine collapse and water *** research background of mine water source identification involves many fields such as mining production,environmental protection,resource utilization and technological *** is a comprehensive and interdisciplinary subject,which helps to improve the safety and sustainability of mine ***,timely and accurate identification and control of mine water source is very important to ensure mine production ***-Induced Fluorescence(LIF)technology,characterized by high sensitivity,specificity,and spatial resolution,overcomes the time-consuming nature of traditional chemical *** this experiment,sandstone water and old air water were collected from the Huainan mining area as original *** types of mixed water samples were prepared by varying their proportions,in addition to the two original water samples,resulting in a total of seven different water samples for *** preprocessing methods,namely,MinMaxScaler,StandardScaler,Standard Normal Variate(SNV)transformation,and Centering Transformation(CT),were applied to preprocess the original spectral data to reduce noise and *** was determined as the optimal preprocessing method based on class discrimination,data distribution,and data *** maintain the original data features while reducing the data dimension,including the original spectral data,five sets of data were subjected to Principal Component Analysis(PCA)and Linear Discriminant Analysis(LDA)dimensionality *** comparing the clustering effect and Fisher s ratio of the first three dimensions,PCA was identified as the optimal dimensionality reduction ***,two neural network models,CT+PCA+CNN and CT+PCA+ResNet,were constructed by combining Convolutional Neural Networks(
维普期刊数据库
同方期刊数据库