Feature Extraction Method for Fault Diagnosis of Rotating Machinery Based on Wavelet and LLE
Guangtao Zhang, Yuanchu Cheng, Xingfang Wang, Na Lu
Available Online April 2016.
- https://doi.org/10.2991/emim-16.2016.241How to use a DOI?
- Feature extraction; Rotating machinery; Fault diagnosis; Wavelet; LLE
- Feature extraction is an important procedure in the process of fault diagnosis for rotating machinery. Based on wavelet and local linear embedding (LLE), a method is proposed in this paper to extract features from vibration signals of rotating machinery. Firstly, multiple features were extracted from the original vibration signals and their wavelet decomposition coefficients to construct a high feature set. Then, to reduce the dimension of the high feature set initially, detection index (DI) was taken as an index to select several features from the extracted features. After that, LLE was employed to conduct feature fusion on the initial obtained feature set and obtain low dimension fault features for fault diagnosis of rotating machinery. To validate the proposed method, fault extraction experiment was conducted, and the result shows that the proposed method can extract better features for fault classification of rotating machinery.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Guangtao Zhang AU - Yuanchu Cheng AU - Xingfang Wang AU - Na Lu PY - 2016/04 DA - 2016/04 TI - Feature Extraction Method for Fault Diagnosis of Rotating Machinery Based on Wavelet and LLE BT - 6th International Conference on Electronic, Mechanical, Information and Management Society PB - Atlantis Press SP - 1181 EP - 1185 SN - 2352-538X UR - https://doi.org/10.2991/emim-16.2016.241 DO - https://doi.org/10.2991/emim-16.2016.241 ID - Zhang2016/04 ER -