Open Mining Dataset Modeling at PT. United Tractors Semen Gresik with Artificial Neural Network Method

Abstract

The Mining industry in Indonesia plays a vital role as a source of state income and an integral part of the industrial progress of the nation. The majority of the mining industry in Indonesia employs open-pit mining. One of the weather factors that can be an obstacle in open-pit mining is rainfall. Therefore, this research focused on modelling data from rainfall, working hours and production outcomes. It applied the Artificial Neural Network algorithm with an input layer consisting of two neurons, a hidden layer with two neurons, and an output layer. The data on Rainfall working hours, and production results were trained to produce a model that, later on, will be used to predict the value of production results. For model testing, this study uses two parameters, namely learning rate and epoch. From 90 times of testing, the best model was obtained with a learning rate value of 0.3 and an epoch of 1000 which resulted in an RMSE error of 0.004838259401280330