Vibrational health risk assessment for truck operators in mining using artificial neural network

Abstract

Operators of mining vehicles are frequently exposed to harmful levels of whole-body vibration (WBV). Long time exposure to WBV causes backache and has non-ergonomic effects on the human body. Exposure levels of the WBV have already been evaluated for different vehicles. Among these vehicles, mining trucks usually operate at the various working phases and also in different haul road conditions. This paper aims to develop a simultaneous integrated model to predict the WBV exposure for mining truck drivers. Considering the effect of the speed level, weight and geometry of load on the WBV exposure for the mining truck drivers are limited. There is not much research to predict the vibrational health risk level in conditions with no or missing data, as well. The root mean squire (RMS) of the vertical vibration of the seat and cabin floor was obtained during different operational conditions of an open pit mine in Iran. Then an artificial neural network was designed for the prediction of the vibrational health risk level. Regarding the results of this study, haul road quality, speed level, and load profile had a significant effect on vibration exposure. The average of the RMS values were 0.942 and 1.176m/s2 for the good and poor road conditions, respectively that are in the high health risk levels. However, there was no significant relationship between the payloads, in the range of 20 to 30 tons, in the RMS values. At speeds higher than 30 km/h, the vibrational health risk was at high level for all conditions. Moreover, there were 93.83% correlation between the measured and simulated RMS values was found in the application of the neural network. This paper helps the mine managers to predict the unsafe conditions and consider the practical approach for the WBV risk reduction.