Unsupervised machine learning in industrial applications: a case study in iron mining

Abstract

The volume of data collected in the industry has grown rapidly in recent years, transforming into a challenge the task of analyzing this data. To identify patterns and improve industrial processes, several Artificial Intelligence techniques can be used, especially clustering methods. This work applies the technique of clustering and dimensionality reduction in the mining industry, performing a case study in a public database about an iron mining flotation process. The K-means algorithm was used and it was able to identify a statistically significant difference between the clusters in the silica concentration value, an important impurity in the flotation process.