{"title":"Estimating Pillar Strength for Rock Salt Mines of the Salt Range Pakistan Using Statistical and Artificial Neural Network Modeling Techniques","authors":"Y. Majeed, K. M. Sani, M. Z. Emad","doi":"10.1007/s42461-024-01037-8","DOIUrl":null,"url":null,"abstract":"<p>This research proposes empirical models to estimate pillar strength by adopting multilinear regression and artificial neural network approaches for rock salt mines of the Salt Range, Punjab, Pakistan. The field data of a total of 168 pillars was collected from three (03) selected rock salt mines being operated by Pakistan Mineral Development Corporation. The field work included geometry of pillars, Schmidt rebound hardness (SRH), uniaxial compressive strength (UCS), fracture spacing, fracture condition, joint-orientation, groundwater state, weathering effects, blasting effects, and mining-induced stress. The dataset collected from the field for each rock salt pillar was further utilized to determine rock quality designation (RQD), rock mass rating (RMR), mining rock mass rating (MRMR), design rock mass strength (DRMS), and pillar strength (<span>\\({\\sigma }_{p}\\)</span>). The modeling was done using a dataset of 150 columns, and the remaining data of 18 pillars was left for validation purposes. The proposed ANN and MLR models have <i>R</i>-square (<i>R</i><sup>2</sup>) values of 95.35% and 91.61%, respectively. Further, the prediction performance of the ANN model was also compared with that of multilinear regression (MLR). It was found that the ANN model outperformed the MLR model.</p>","PeriodicalId":18588,"journal":{"name":"Mining, Metallurgy & Exploration","volume":"30 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mining, Metallurgy & Exploration","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1007/s42461-024-01037-8","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
This research proposes empirical models to estimate pillar strength by adopting multilinear regression and artificial neural network approaches for rock salt mines of the Salt Range, Punjab, Pakistan. The field data of a total of 168 pillars was collected from three (03) selected rock salt mines being operated by Pakistan Mineral Development Corporation. The field work included geometry of pillars, Schmidt rebound hardness (SRH), uniaxial compressive strength (UCS), fracture spacing, fracture condition, joint-orientation, groundwater state, weathering effects, blasting effects, and mining-induced stress. The dataset collected from the field for each rock salt pillar was further utilized to determine rock quality designation (RQD), rock mass rating (RMR), mining rock mass rating (MRMR), design rock mass strength (DRMS), and pillar strength (\({\sigma }_{p}\)). The modeling was done using a dataset of 150 columns, and the remaining data of 18 pillars was left for validation purposes. The proposed ANN and MLR models have R-square (R2) values of 95.35% and 91.61%, respectively. Further, the prediction performance of the ANN model was also compared with that of multilinear regression (MLR). It was found that the ANN model outperformed the MLR model.
期刊介绍:
The aim of this international peer-reviewed journal of the Society for Mining, Metallurgy & Exploration (SME) is to provide a broad-based forum for the exchange of real-world and theoretical knowledge from academia, government and industry that is pertinent to mining, mineral/metallurgical processing, exploration and other fields served by the Society.
The journal publishes high-quality original research publications, in-depth special review articles, reviews of state-of-the-art and innovative technologies and industry methodologies, communications of work of topical and emerging interest, and other works that enhance understanding on both the fundamental and practical levels.