Underground water dam levels and energy consumption prediction using computational intelligence techniques

Abstract

Three computational intelligence algorithms (k-nearest neighbors, a naïve Bayes' classifier, and decision trees) were applied on a double pump station mine to monitor and predict the dam levels and energy consumption. This work was carried out to inspect the feasibility of using computational intelligence in certain aspects of the mining industry. If successful, computational intelligence systems could lead to improved safety and reduced electrical energy consumption. The results show k nearest neighbors' technique to be more efficient when compared with decision trees, and naïve Bayes' classifier techniques in terms of predicting underground dam levels and pumps energy consumption.