Fault diagnosis of wind turbine based on rough set and BP network
Xinli Li, Wanye Yao, Qingjie Zhou, Jianming Wang, Jingzhi Liu
Available Online April 2015.
- https://doi.org/10.2991/icmra-15.2015.171How to use a DOI?
- Rough set; BP neural network; Fault niagnosis;Pitch system
- Because of wind turbines institutional complexity, many operating parameters, fuzziness,randomness and uncertainty between the cause of the fault and the fault symptom, so direct application of BP neural network for fault diagnosis can lead to the issues of slow convergence of neural network and long training time, therefore we need take some method reducing the speed and improve accuracy of diagnosis. for this case, the fault diagnosis method for wind turbine based on rough set and BP neural network is presented in this paper. Firstly ,rough set theory is a effective tool to deal with vagueness and uncertainty of knowledge, it can simplify the decision-making rules, and can get rid of redundant information with the classification ability unchanged,then put the simplified information into the BP neural network for training,this method can reducing the input dimension of BP neural network to improve diagnostic accuracy and reduce training time. Simulation results show that: the use of this diagnostic method in the wind turbine pitch system, the relationship between the established model accuracy is relatively high, it can make a rapid and accurate diagnosis for the operating status and the fault of turbine pitch system.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Xinli Li AU - Wanye Yao AU - Qingjie Zhou AU - Jianming Wang AU - Jingzhi Liu PY - 2015/04 DA - 2015/04 TI - Fault diagnosis of wind turbine based on rough set and BP network BT - Proceedings of the 3rd International Conference on Mechatronics, Robotics and Automation PB - Atlantis Press SP - 877 EP - 883 SN - 2352-538X UR - https://doi.org/10.2991/icmra-15.2015.171 DO - https://doi.org/10.2991/icmra-15.2015.171 ID - Li2015/04 ER -