Reduced kernel recursive least squares algorithm for aero-engine degradation prediction

•The novel method considers all the constraints generated by the whole training set.•The redundant data is used to modify the coefficients related to each kernel unit.•The structure update and coefficient adjustment are carried out independently.•A more compact network without accuracy deterioration...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Mechanical systems and signal processing Jg. 95; S. 446 - 467
Hauptverfasser: Zhou, Haowen, Huang, Jinquan, Lu, Feng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin Elsevier Ltd 01.10.2017
Elsevier BV
Schlagworte:
Accuracy
Adaptive algorithms
Adaptive filters
Aero-engine
Basis functions
Degradation
Kernel recursive least squares
Least squares method
Markov chains
Mathematical models
Prognostics
Radial basis function
Recursive algorithms
Reduced technique
Redundancy
Remaining useful life
Signal processing
Sparse kernel method
Time series
Training
Reduced technique
Aero-engine
Remaining useful life
Kernel recursive least squares
Prognostics
Sparse kernel method
ISSN:0888-3270, 1096-1216
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•The novel method considers all the constraints generated by the whole training set.•The redundant data is used to modify the coefficients related to each kernel unit.•The structure update and coefficient adjustment are carried out independently.•A more compact network without accuracy deterioration is obtained.•A novel prognostic model based on KAF and HMM is developed. Kernel adaptive filters (KAFs) generate a linear growing radial basis function (RBF) network with the number of training samples, thereby lacking sparseness. To deal with this drawback, traditional sparsification techniques select a subset of original training data based on a certain criterion to train the network and discard the redundant data directly. Although these methods curb the growth of the network effectively, it should be noted that information conveyed by these redundant samples is omitted, which may lead to accuracy degradation. In this paper, we present a novel online sparsification method which requires much less training time without sacrificing the accuracy performance. Specifically, a reduced kernel recursive least squares (RKRLS) algorithm is developed based on the reduced technique and the linear independency. Unlike conventional methods, our novel methodology employs these redundant data to update the coefficients of the existing network. Due to the effective utilization of the redundant data, the novel algorithm achieves a better accuracy performance, although the network size is significantly reduced. Experiments on time series prediction and online regression demonstrate that RKRLS algorithm requires much less computational consumption and maintains the satisfactory accuracy performance. Finally, we propose an enhanced multi-sensor prognostic model based on RKRLS and Hidden Markov Model (HMM) for remaining useful life (RUL) estimation. A case study in a turbofan degradation dataset is performed to evaluate the performance of the novel prognostic approach.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0888-3270
1096-1216
DOI:10.1016/j.ymssp.2017.03.046