AutoML for Predictive Maintenance: One Tool to RUL Them All

Abstract

Automated machine learning (AutoML) deals with the automatic composition and configuration of machine learning pipelines, including the selection and parametrization of preprocessors and learning algorithms. While recent work in this area has shown impressive results, existing approaches are essentially limited to standard problem classes such as classification and regression. In parallel, research in the field of predictive maintenance, particularly remaining useful lifetime (RUL) estimation, has received increasing attention, due to its practical relevance and potential to reduce unplanned downtime in industrial plants. However, applying existing AutoML methods to RUL estimation is non-trivial, as in this domain, one has to deal with varying-length multivariate time series data. Furthermore, the data often directly originates from real-world scenarios or simulations, and hence requires extensive preprocessing. In this work, we present ML-Plan-RUL, an adaptation of the AutoML tool ML-Plan to the problem of RUL estimation. To the best of our knowledge, it is the first tool specifically tailored towards automated RUL estimation, combining feature engineering, algorithm selection, and hyperparameter optimization into an end-to-end approach. First promising experimental results demonstrate the efficacy of ML-Plan-RUL.