Billuroglu, B; Livina, V N (2022) Full-Cycle Failure Analysis Using Conventional Time Series Analysis and Machine Learning Techniques. Journal of Failure Analysis and Prevention, 22 (3). pp. 1121-1134.

Full text not available from this repository.

Abstract

We study time series of dynamical systems for failures, applying data-driven machine learning techniques, such as clustering and tipping point analysis. We consider artificial data with known properties and real systems case studies, demonstrating diverse patterns of time series and discussing applicability of various techniques. The proposed methodology may be useful in various industrial and geophysical applications, where sensor records are available for data-driven failure analysis.

Item Type:	Article
Subjects:	Mathematics and Scientific Computing > Signal Processing
Divisions:	Data Science
Identification number/DOI:	10.1007/s11668-022-01381-1
Last Modified:	01 Mar 2024 14:39
URI:	https://eprintspublications.npl.co.uk/id/eprint/9603