Machine Learning for the Predictive Maintenance of a Jaw Crusher in the Mining Industry

Abstract

Diagnosis and prognosis are both crucial and interlinked steps in the context of predictive maintenance of rotating machines. Risk management correlated with machine Reliability within time intervention. In this paper, the most popular machine learning algorithms are tested and compared to serve Predictive maintenance purposes. The use case of this paper is an industrial jaw crusher from the mining industry production process. Azure machine learning studio platform made it possible to simulate the proposed approaches. The relevance of Machine Learning models for predicting components’ health states is proved while achieving high accuracies.