| Abstract | Modeling system behavior plays a vital role in controlling systems and in monitoring systems health. Recently machine learning-enabled modeling technology has become a powerful technique and tool for developing models for explaining, predicting, and describing system behaviors. In particular, the machine learning-enabled predictive modeling methods have been widely applied to develop the data-driven models from the “big” data in different applications such as system prognostics, system control, and system health management. Over last decade, we have worked on a research program, machine learning-enabled modeling technologies, focusing on the application of machine learning to real-world problems such as prognostics, predictive maintenance, and fault diagnostics. This paper presents the developed machine learning-enabled modeling approaches for predictive maintenance, address-ing the challenges such as machine learning algorithm selection, model evaluation, model deployment and decision-making support. The developed models can predict the failure before it occurs and estimate the remaining useful life for predictive maintenance decision-making support. After briefing introduction of the machine learning-ena-bled frameworks/methodologies, the paper will present a show case of real-world applications, train predictive maintenance decision making support, to demonstrate the feasibility and usefulness of the proposed approaches for predictive maintenance decision making support. |
|---|
