Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy

Trend Feature Extraction in Condition Monitoring by a New Piecewise Linear Representation Method

Authors
Changfeng Yan, Cheng Yi, Lixiao Wu, Jianfang Fang
Corresponding Author
Changfeng Yan
Available Online July 2015.
DOI
10.2991/icismme-15.2015.294How to use a DOI?
Keywords
Trend Feature Extraction; Condition Monitoring; Piecewise Linear Representation; Local Maximum Minimum and Slope.
Abstract

To extract the trend of condition monitoring data set effectively, piecewise linear representation is one of the most potential strategies. A new trend feature extraction method is presented based on the local maximum minimum and slope in this paper. The results of experiments are shown that it can extract the multiscale of trend feature and ensure acceptable fitting error. The process of extracting trend feature focuses on identification of rules and patterns and discovering the relevant and interesting information from condition monitoring system. It can provide a certain reference for condition trend analysis.

Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy
Series
Advances in Intelligent Systems Research
Publication Date
July 2015
ISBN
978-94-62520-67-7
ISSN
1951-6851
DOI
10.2991/icismme-15.2015.294How to use a DOI?
Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Changfeng Yan
AU  - Cheng Yi
AU  - Lixiao Wu
AU  - Jianfang Fang
PY  - 2015/07
DA  - 2015/07
TI  - Trend Feature Extraction in Condition Monitoring by a New Piecewise Linear Representation Method
BT  - Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy
PB  - Atlantis Press
SP  - 1377
EP  - 1382
SN  - 1951-6851
UR  - https://doi.org/10.2991/icismme-15.2015.294
DO  - 10.2991/icismme-15.2015.294
ID  - Yan2015/07
ER  -