Exploring the potentials of online machine learning for predictive maintenance: a case study in the railway industry

This study addresses data-driven predictive maintenance, an area in which machine learning has received considerable attention. Traditionally, a machine learning model is trained on static data before being put into production to predict failures on incoming data. However, new data typically present novelties that were not included in the training data, such as unexpected anomalies or faults. Such novelties reduce the model accuracy and require model retraining, which we consider to be a suboptimal practice.Therefore, we propose to leverage online machine learning as an adaptive and continuous alternative to implement efficient predictive maintenance on systems that produce data continuously. The literature on predictive maintenance concentrates primarily on failure prediction, whereas there are multiple stages in a standard predictive maintenance framework, such as data preprocessing and diagnostics, that require attention. In this study, we propose a modular pipeline consisting of three modules to execute many stages inside a predictive maintenance solution. Each module represents one of our original contributions. Firstly, because a system generates repeating patterns in the form of cycles when performing its functions, we construct an online active learning-based framework to extract these cycles from a stream of sensor data (cycle extraction with InterCE). Secondly, we implement an autoencoder for encoding the extracted cycles into feature vectors (feature learning with LSTM-AE). Thirdly, we develop an adaptive scoring function to compute the health of any system at any time using online clustering on the stream of feature vectors (health detection with CheMoc). These three contributions establish our framework for processing raw sensor data for predictive maintenance. We evaluate our methods using a real-world data set provided by SNCF, the French national railway company. For each experiment, we simulate a data stream consisting of sequentially arriving data from the provided data set to test our online algorithms. The experimental results demonstrate that (i) InterCE is able to extract cycles from a high-speed stream with greater accuracy than a hand-crafted expert system, (ii) LSTM-AE can identify meaningful features from the extracted cycles, and (iii) CheMoc can discover clusters that represent physical anomalies of the systems and capture the health evolution of the monitored systems. Due to a lack of ground-truth data at the time of writing, we have not implemented the prognostics method and will reserve this for future works. This study confirms the potential of online machine learning as an adaptive and lifelong learning solution for predictive maintenance.