Mohseni, M., Ataei, M. (2016). Risk prediction based on a time series case study: Tazareh coal mine. Journal of Mining and Environment, 7(1), 127-134. doi: 10.22044/jme.2016.514

M. Mohseni; M. Ataei. "Risk prediction based on a time series case study: Tazareh coal mine". Journal of Mining and Environment, 7, 1, 2016, 127-134. doi: 10.22044/jme.2016.514

Mohseni, M., Ataei, M. (2016). 'Risk prediction based on a time series case study: Tazareh coal mine', Journal of Mining and Environment, 7(1), pp. 127-134. doi: 10.22044/jme.2016.514

Mohseni, M., Ataei, M. Risk prediction based on a time series case study: Tazareh coal mine. Journal of Mining and Environment, 2016; 7(1): 127-134. doi: 10.22044/jme.2016.514

Risk prediction based on a time series case study: Tazareh coal mine

^{}School of Mining, Petroleum & Geophysics Engineering, Shahrood University of Technology, Shahrood, Iran

Abstract

In this work, the time series modeling was used to predict the Tazareh coal mine risks. For this purpose, initially, a monthly analysis of the risk constituents including frequency index and incidence severity index was performed. Next, a monthly time series diagram related to each one of these indices was for a nine year period of time from 2005 to 2013. After extrusion of the trend, seasonality, and remainder constituents of the time series modeling, the final time series model of the indices was determined with high precision. The precision level of the resulting model was evaluated using the root mean square error (RMSE) method. The values obtained for the severity index and accident frequency index were 0.001 and 6.400, respectively. Evaluation of the seasonal time series constituent of the frequency index showed that, yearly, most number of accidents occurred in April, and the least one took place in January. Additionally, evaluation of the seasonal time series constituent of the severity index showed that, every year, the severest accidents occurred in October, and the least ones happened in January. Using the final model, a monthly prediction of indices was performed for a four year period of time from 2014 to 2017. Subsequently, using the known mean work hours in the mine, predictions of the number of accidents and the number of work days lost within a similar time period were made. The prediction results showed that in the future, the number of accidents and the number of work days lost would have a down-going trend such that for similar months, annually, an average 22% decrease in the number of accidents and an average 24% decrease in the number of work days lost are expected.