Failure Prediction Model for Prognostic Health Management in Machine Systems

This research paper addresses the problem of machine systems' failure prediction. This work is innovative in that it uses machine learning approaches to create a failure prediction model that is accurate for prognostic health management (PHM) in all machine systems: vibration based, and non-vibration based. The authors have employed a variety of well-known machine learning methods: Naïve Bayes (NB), Generalized Linear Model (GLM), Logistic Regression (LR), Decision Trees (DT), Random Forests (RF), and Gradient Boosted Tree (GBT) on Machine Predictive Maintenance Classification Dataset available on Kaggle. DT has given the highest accuracy i.e., 97.3%. The research paper offered insightful information about the suitability of various classifiers for failure prediction in machine systems and highlighted the best-performing classifier among the examined ones based on their predictive accuracy, enabling practitioners in PHM to make well-informed decisions.