Clustering Mining Equipment Productivity Data Using K-Means Algorihtm

Abstract

There are many factors that affect the productivity of mining equipment, one of which is the condition of the mining equipment when it is used. Knowing the condition of the machines on mining equipment is mandatory for supervisors in mining activities. In analyzing data on the condition of mining equipment in large quantities requires a lot of energy and time, so a classification model is needed that can categorize the mining equipment based on its performance. Data Mining is a process that uses statistical, mathematical, artificial intelligence and machine learning techniques to extract information. The results of data mining for mining productivity data are obtained duration of mining equipment work has a impact on productivity based on correlation value between work duration and maintenance duration of a tool. Data mining analysis is also carried out by clustering mining equipment using the K-Means model. The results obtained a conclusion that supports mining equipment with less working duration affects to productivity. The result shows variables that affect the productivity of mining equipment and divide mining equipment categories based on tool performance with data mining clustering techniques.