Noise identification, modeling, and control in mining industry

Abstract

Prolonged exposure of miners to the high levels of noise in opencast and underground mines can cause noise induced hearing loss and non-auditory health effects. To minimize noise risk, it is imperative to identify machinery noise and their impacts on miners at the work place and adopt cost effective and appropriate noise control measures at the source, path, and at the receiver. In this paper, authors have summarized the noise levels generated from different machineries used in opencast and underground mines and elaborated on frequency dependent noise prediction models, e.g., ISO 9613-2, ENM, CONCAWE, and non-frequency based noise prediction model VDI-2714 used in mining and allied industries. The authors illustrated the applications of innovative soft computing models, viz., Fuzzy Inference System [Mamdani and Takagi Sugeno Kang (T-S-K)], MLP (multi-layer perceptron, RBF (radial basis function) and adaptive network-based fuzzy inference systems (ANFIS) for predicting machinery noise in two opencast mines. The paper highlights the developments and research conducted on effective noise control measures being adopted for mining machineries and implemented in mines to minimize the noise menace so that noise levels generated in mines are within the prescribed noise standards and rules.