Machine learning model to cluster and map tribocorrosion regimes in feature space

TL;DR

This paper introduces a machine learning approach that uses clustering and support vector machines to generate and validate tribocorrosion maps, aiding in predicting tribosystem performance.

Contribution

It presents a novel method combining unsupervised clustering and SVM classification to create tribocorrosion maps from experimental data.

Findings

Clusters successfully identified from experimental data.

SVM-generated maps align with standard literature maps.

Method improves prediction of tribocorrosion regimes.

Abstract

Tribocorrosion maps serve the purpose of identifying operating conditions for acceptable rate of degradation. This paper proposes a machine learning based approach to generate tribocorrosion maps, which can be used to predict tribosystem performance. First, unsupervised machine learning is used to identify and label clusters from tribocorrosion experimental data. The identified clusters are then used to train a support vector classification model. The trained SVM is used to generate tribocorrosion maps. The generated maps are compared with the standard maps from literature.