Evaluating time series encoding techniques for Predictive Maintenance. (30th December 2022)

• Record Type: Journal Article
• Authors: De Santo, Aniello; Ferraro, Antonino; Galli, Antonio; Moscato, Vincenzo; Sperlì, Giancarlo
• Is Part Of: Expert systems with applications. Volume 210(2022)
• Publication Date: 2022-12-30
• Subjects: Predictive maintenance -- Time series Encoding techniques -- Failure prediction -- Deep learning; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.118435
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Predictive Maintenance has become an important component in modern industrial scenarios, as a way to minimize down-times and fault rate for different equipment. In this sense, while machine learning and deep learning approaches are promising due to their accurate predictive abilities, their data-heavy requirements make them significantly limited in real world applications. Since one of the main issues to overcome is lack of consistent training data, recent work has explored the possibility of adapting well-known deep-learning models for image recognition, by exploiting techniques to encode time series as images. In this paper, we propose a framework for evaluating some of the best known time series encoding techniques, together with Convolutional Neural Network -based image classifiers applied to predictive maintenance tasks. We conduct an extensive empirical evaluation of these approaches for the failure prediction task on two real-world datasets ( PAKDD2020 Alibaba AI OPS Competition and NASA bearings ), also comparing their performances with respect to the state-of-the-art approaches. We further discuss advantages and limitation of the exploited models when coupled with proper data augmentation techniques. Highlights: We analyze Predictive Maintenance task aiming to minimize down-times of an equipment. We use time series encoding techniques with CNN-based models in different scenarios. An extensive evaluation has been performed for HDD and bearings failure prediction. Performance has been evaluated w.r.t. other benchmarking neural network models.