Research On Fault Diagnosis Of Wind Turbine Gearbox Based On IFA-ELM

DOI

10.2991/iceeecs-16.2016.153How to use a DOI?

Keywords

wind turbine; fault diagnosis; extreme learning machine; firefly algorithm

Abstract

In order to effectively improve the accuracy of fault diagnosis of wind turbine gearbox, a fault diagnosis model based on improved firefly algorithm for extreme learning machine is proposed in this paper. The extreme learning machine overcomes the shortcomings of traditional neural network, such as slow convergence rate and easy to fall into local minimum points, however, the weights and thresholds of the input layer and the hidden layer are generated in a random way, this can lead to excessive number of nodes in the hidden layer, resulting in over fitting in the training process. In view of this problem, the firefly algorithm with high searching speed and high efficiency is used to optimize the parameters of the extreme learning machine. However, because of the fixed step size, the firefly algorithm is easy to fall into the local optimum in the early stage and slows down in the late convergence. Therefore, the step size of the firefly algorithm is improved to make it change with the change of the objective function in the search process so as to improve the performance of the firefly algorithm. The experimental results show that compared to the standard ELM, GA-ELM, and FA-ELM networks, the improved firefly algorithm for extreme learning machine that proposed in this paper has a higher prediction accuracy.

Copyright

© 2016, 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  - Shaomin Zhang
AU  - Jia Wei
AU  - Baoyi Wang
PY  - 2016/12
DA  - 2016/12
TI  - Research On Fault Diagnosis Of Wind Turbine Gearbox Based On IFA-ELM
BT  - Proceedings of the 2016 4th International Conference on Electrical & Electronics Engineering and Computer Science (ICEEECS 2016)
PB  - Atlantis Press
SP  - 775
EP  - 780
SN  - 2352-538X
UR  - https://doi.org/10.2991/iceeecs-16.2016.153
DO  - 10.2991/iceeecs-16.2016.153
ID  - Zhang2016/12
ER  -