1. Fault diagnosis of wind bearing based on multi-scale wavelet kernel extreme learning machine
- Author
-
Bin Jiao and Siwen Zhu
- Subjects
History ,Engineering ,Bearing (mechanical) ,Scale (ratio) ,Basis (linear algebra) ,business.industry ,Pattern recognition ,02 engineering and technology ,Fault (power engineering) ,01 natural sciences ,Wavelet kernel ,Turbine ,010305 fluids & plasmas ,Computer Science Applications ,Education ,law.invention ,law ,0103 physical sciences ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,Support vector machine classification ,Extreme learning machine - Abstract
The principle of kernel Extreme Learning Machine (ELM) is demonstrated. On this basis, a multi - scale wavelet kernel extreme learning machine is proposed. The multi-scale wavelet kernel is used as the kernel function of the extreme learning machine. The test shows that it is an achievable extreme learning machine. Experiments show that, using the multi-scale wavelet kernel extreme learning machine in the wind turbine bearing fault diagnosis has higher classification accuracy and speed than the support vector machine classification algorithm, and has excellent application value.
- Published
- 2017
- Full Text
- View/download PDF