Path Optimization of Multi-source Signal Feature Factor Decomposition and Its Application

DOI

10.2991/icmcs-18.2018.4How to use a DOI?

Keywords

Feature Factor; Decomposition Path; Optimization Algorithm; Fault Diagnosis

Abstract

The non-linear process mechanical state is characterized by multivariate, strong coupling, many vibration sources, large signal noise and various random factors. The mechanical structure generates corresponding nonlinear faults and multi-source characteristic signals under nonlinear excitation. Multi-source characteristic signal propagation is complex and varied, and it also has a strong nonlinear signal decomposition relationship. The intrinsic relationship of the directional path of the multi-source matrix signal feature and the overall consistency optimization is a brand-new study of multi-source dynamic feature signal identification. This project proposes a feature factor signal propagation path optimization algorithm based on nonlinear system identification theory. Under the guidance of matrix signal analysis theory, the vector analysis, spatial geometry, optimization theory, denoising principle and error theory are applied to analyze and discuss the intrinsic relationship of the optimal decomposition path of multi-source signal feature factors. It is established that the optimal nonlinear relationship between state variables, failure modes and feature signals in time, frequency and space. Then, the optimization of feature factor decomposition path is applied to feature extraction of ultrasonic fault detection signals.

Copyright

© 2018, 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)

TY  - CONF
AU  - Liu Yang
AU  - Hanxin Chen
AU  - Wenjian Huang
AU  - Jinmin Huang
AU  - Chenghao Cao
PY  - 2018/10
DA  - 2018/10
TI  - Path Optimization of Multi-source Signal Feature Factor Decomposition and Its Application
BT  - Proceedings of the 8th International Conference on Management and Computer Science (ICMCS 2018)
PB  - Atlantis Press
SP  - 20
EP  - 25
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmcs-18.2018.4
DO  - 10.2991/icmcs-18.2018.4
ID  - Yang2018/10
ER  -