Assessment of effective parameters on dilution using approximate reasoning methods in longwall mining method, Iran coal mines

TL;DR

This study analyzes key parameters affecting dilution in Iranian longwall coal mining using Rough Set Theory and Neuro-Fuzzy methods, identifying the most sensitive factors influencing dilution to improve mining efficiency.

Contribution

The paper introduces the application of RST and SONFIS to identify and predict influential parameters on dilution in longwall mining, providing a novel approach for industry analysis.

Findings

Layer thickness, stope length, advance rate, miner count, and advancing type are highly sensitive variables.

RST reduced data complexity by extracting core rules.

SONFIS successfully predicted dilution cases.

Abstract

Approximately more than 90% of all coal production in Iranian underground mines is derived directly longwall mining method. Out of seam dilution is one of the essential problems in these mines. Therefore the dilution can impose the additional cost of mining and milling. As a result, recognition of the effective parameters on the dilution has a remarkable role in industry. In this way, this paper has analyzed the influence of 13 parameters (attributed variables) versus the decision attribute (dilution value), so that using two approximate reasoning methods, namely Rough Set Theory (RST) and Self Organizing Neuro- Fuzzy Inference System (SONFIS) the best rules on our collected data sets has been extracted. The other benefit of later methods is to predict new unknown cases. So, the reduced sets (reducts) by RST have been obtained. Therefore the emerged results by utilizing mentioned methods shows that the high sensitive variables are thickness of layer, length of stope, rate of advance, number of miners, type of advancing.