Toggle Main Menu Toggle Search

Open Access padlockePrints

An improved empirical wavelet transform study based on wind turbine condition monitoring signals

Lookup NU author(s): Dr Pu Shi, Dr Wenxian YangORCiD, Dr Wenye Tian


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


© 2016, British Institute of Non-Destructive Testing. All rights reserved. Reliable condition monitoring (CM) highly relies on the correctness of fault-related features extraction from CM signals. The conventional EWT adopts default method to pre-define values for both mode number and mode boundaries in spectrum. It is not adaptive to the signals being inspected. As a consequence, it would lead to inaccurate feature extraction thus unreliable WT CM result sometimes. For this reason, an improved EWT method is investigated in this paper to precisely extract features. The main contribution of this paper focuses on the development of data-driven adaptive spectrum segment method to perform improved EWT. The experiments have shown that thanks to the use of optimization algorithm, the fault-related features buried in WT CM signals have been extracted out successfully.

Publication metadata

Author(s): Shi P, Yang W, McKeever P, Tian W, Lee H, Ng C

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: 13th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies, CM 2016/MFPT 2016

Year of Conference: 2016

Acceptance date: 02/04/2016

Publisher: British Institute of Non-Destructive Testing

Notes: 138