Affiliations: Department of Automatic Test and Control, Harbin Institute of Technology, Harbin, Heilongjiang, China
Correspondence:
[*]
Corresponding author: Yong Xu, 3033#, Science Park of Harbin Institute of Technology, No. 2, YiKuang Street, NanGang District, Harbin 150080, Heilongjiang, China. Tel.: +86 451 86413532-431; Fax: +86 451 86402953; E-mail:[email protected]
Abstract: Feature selection in data-driven modelling is an
important research topic for prognostics. The performance of prediction
model may vary considerably under different feature subsets. Hence it is
important to devise a systematic feature selection method, which offers the
guidance for choosing the most representative features for prognostics.
Nowadays, feature selection algorithms in the field of prognostics are
largely studied to the type of learning: supervised or unsupervised, which
leads to poor generalization between different prognostics applications. In
this paper, a unified feature selection method, called locality structure
preserving based feature selection (LSPFS), is developed to improve the
robustness and accuracy of prognostics under both unsupervised and
supervised learning conditions. In LSPFS, the local structure of original
data is constructed according to the similarity between data points, and the
representative features are selected based on their ability to preserve the
local structure. Moreover, by designing different local structure via local
information and actual degradation information of the data, the introduced
method can unify supervised and unsupervised feature selection, and enable
their joint study under a general framework. Experiments on NASA turbofan
engine simulation dataset and lithium-ion battery dataset are conducted to
test and evaluate the proposed algorithm.
Keywords: Prognostics, health assessment, feature selection, local structure preserving
