Indonesia Conference Directory

Wet muck forms due to the accumulation of fine material and water in drawbells in a block cave mine system. It results in the potential for mud rushes or wet muck spills, which have a significant influence on safety and production. Butcher, et al (2005, 2007) stated that the wet muck contributing factors are fine materials and water; according to Widodo, et al (2018), wet muck is formed because of the contribution of five factors, namely, fine material, water, height of draw, no mucking days and rainfall. Widodo, et al (2018) focussed on the expert opinions about five wet contributing factors facilitated by fuzzy logic and resulting in the wet muck class, thereby indicating the status of the corresponding drawpoints in terms of the qualitative wet muck spill potential. With the increasing number of wet muck spill occurrences, there is an opportunity for evaluating the expert opinions on data or facts about wet muck spill evidence. In this paper, the process of wet muck class prediction is based on the views of experts, such as those illustrated by Widodo, et al (2018), and strengthened by the system-s learning / training process for wet muck spill occurrence data, which his facilitated by using an adaptive neuro–fuzzy inference system (ANFIS). What is conveyed in this paper is the development of the system presented in Widodo, et al (2018), which is based solely on the opinions of experts; moreover, it involves additional system development that can intelligently recognise the wet muck class from the data of wet muck spill events or wet muck spill history and then used to predict further wet muck spill potential.