A New Multivariate Approach for Prognostics Based on Extreme Learning Machine and Fuzzy Clustering

• Published in: IEEE transactions on cybernetics Vol. 45; no. 12; pp. 2626 - 2639
• Main Authors: Javed, Kamran, Gouriveau, Rafael, Zerhouni, Noureddine
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cluster Analysis; Clustering algorithms; Data models; Data-driven; Degradation; Dynamics; Engineering; Estimates; extreme learning machine (ELM); Failure; Fuzzy; fuzzy clustering; Fuzzy Logic; Fuzzy set theory; Machine Learning; Machinery; Mathematical models; Models, Theoretical; Monitoring; Multivariate Analysis; Predictive models; prognostics; Prognostics and health management; remaining useful life (RUL); Data-driven; remaining useful life (RUL); extreme learning machine (ELM); fuzzy clustering; prognostics
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2014.2378056

Prognostics is a core process of prognostics and health management (PHM) discipline, that estimates the remaining useful life (RUL) of a degrading machinery to optimize its service delivery potential. However, machinery operates in a dynamic environment and the acquired condition monitoring data are usually noisy and subject to a high level of uncertainty/unpredictability, which complicates prognostics. The complexity further increases, when there is absence of prior knowledge about ground truth (or failure definition). For such issues, data-driven prognostics can be a valuable solution without deep understanding of system physics. This paper contributes a new data-driven prognostics approach namely, an "enhanced multivariate degradation modeling," which enables modeling degrading states of machinery without assuming a homogeneous pattern. In brief, a predictability scheme is introduced to reduce the dimensionality of the data. Following that, the proposed prognostics model is achieved by integrating two new algorithms namely, the summation wavelet-extreme learning machine and subtractive-maximum entropy fuzzy clustering to show evolution of machine degradation by simultaneous predictions and discrete state estimation. The prognostics model is equipped with a dynamic failure threshold assignment procedure to estimate RUL in a realistic manner. To validate the proposition, a case study is performed on turbofan engines data from PHM challenge 2008 (NASA), and results are compared with recent publications.