Echo state kernel recursive least squares algorithm for machine condition prediction

•A combination of reservoir computing and kernel adaptive filter.•The fixed reservoir facilitates the capability of performing long-term prediction.•The novel online learning method still maintains the simplicity of the training process.•A online prognostic method based on KAF and a Bayesian techniq...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mechanical systems and signal processing Ročník 111; s. 68 - 86
Hlavní autoři: Zhou, Haowen, Huang, Jinquan, Lu, Feng, Thiyagalingam, Jeyarajan, Kirubarajan, Thia
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin Elsevier Ltd 01.10.2018
Elsevier BV
Témata:
Adaptive algorithms
Adaptive filters
Algorithms
Bayesian analysis
Convexity
Data points
Dependence
Dynamic characteristics
Kernel adaptive filter
Least squares
Life prediction
Long-term prediction
Machine learning
Mathematical models
Neural networks
Numerical analysis
Principal components analysis
Prognostics
Remaining useful lifeprediction
Reservoir computing
Signal processing
Time series
Turbofan engines
Kernel adaptive filter
Remaining useful lifeprediction
Reservoir computing
Prognostics
Long-term prediction
ISSN:0888-3270, 1096-1216
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•A combination of reservoir computing and kernel adaptive filter.•The fixed reservoir facilitates the capability of performing long-term prediction.•The novel online learning method still maintains the simplicity of the training process.•A online prognostic method based on KAF and a Bayesian technique is developed. Kernel adaptive filter (KAF) has been widely utilized for time series prediction due to its online adaptation scheme, universal approximation capability and convexity. Nevertheless, KAF’s ability to handle temporal tasks is limited, because it is essentially a feed-forward neural network that lacks dynamic characteristics. Traditionally, a sliding widow that contains consecutive data points is constructed to deal with the temporal dependency between data points at neighboring time steps, but the restricted widow length may be incapable of capturing temporal patterns on a larger time scale. To manage this issue, a novel sequential learning approach called echo state KRLS (ES-KRLS) algorithm is proposed by incorporating a dynamic reservoir into kernel recursive least squares (KRLS) algorithm. The reservoir, consisting of a large number of sparsely interconnected hidden units, is treated as a temporal function that transforms the history of the time series into a high-dimensional reservoir state space. Subsequently, the spatial relationship between the reservoir state and the target output is effectively approximated by KRLS algorithm. With the utilization of the fixed reservoir, our novel method not only maintains the simplicity of the learning process but also leads to a significant improvement in the capability of modeling dynamic systems. Numerical results on benchmark tasks demonstrate the excellent performance of the novel method with respect to long-term prediction. Finally, an online prognostic method that combines ES-KRLS and a Bayesian technique is developed for tracking the health status of a degraded system and predicting remaining useful life (RUL). This prognostic method is applied to a turbofan engine degradation dataset to demonstrate its effectiveness.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0888-3270
1096-1216
DOI:10.1016/j.ymssp.2018.03.047