Fuzzy-C-Mean Based Radial Basis Function Network Application in Machinery Noise Prediction

Abstract

Advanced mechanized in opencast mines in now-a-days expected to intensify more noise problems in working environment. Prolonged exposure of miners to the high levels of noise can cause noise induced hearing loss besides several non-auditory health effects. To maintain the good working environment in mines, appropriate noise survey of machineries should be conducted. Hence in order to improve the environmental condition in working place, it is needed to develop appropriate noise prediction model for finding out the accurate status of noise levels from various surface mining machineries. The measured sound pressure level (SPL) of equipments is not accurate due to instrumental error, attenuation, geometrical aberration, atmospheric attenuation etc. Some of the popular noise prediction models e.g. ISO: 9613-2, ENM, CONCAWE have been applied in mining and allied industries. In this paper, an advanced radial basis neural network (RBFN) has been proposed. Two types of RBFN architectures: Generalized Radial Basis Function Network (GRBFN) and Fuzzy-C-Mean based Radial Basis Function Network (FCMRBFN) were used to predict the machinery noise in a large opencast bauxite mine. The proposed models were designed with ISO: 9613-2 noise prediction guidelines considering 1/1 octave band. From the present investigation, it can be concluded that, the output of FCMRBFN system based noise prediction models closely matches with the ISO: 9613-2 model output.