.png){kind=icon}
Return
Evaluating time series encoding techniques for Predictive Maintenance
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2022.118435.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Predictive Maintenance has become an important component in modern indus-trial 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 require-ments 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 exten-sive 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.
Keywords:
Predictive maintenance
Time series Encoding techniques
Failure Prediction
Deep Learning
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W
Organization
View more organizations
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSaveShareSaveShareSaveShareSaveShareSave View more