Abstract
An interval type-2 fuzzy neural network (IT2FNN) control system is proposed to control the position of an X-Y-Theta (X-Y-θ) motion control stage using linear ultrasonic motors (LUSMs) to track various contours. The IT2FNN, which combines the merits of interval type-2 fuzzy logic system (FLS) and neural network, is developed to simplify the computation and to confront the uncertainties of the X-Y-θ motion control stage. Moreover, the parameter learning of the IT2FNN based on the supervised gradient descent method is performed on line. The experimental results show that the tracking performance of the IT2FNN is significantly improved compared to type-1 FNN.
Original language | English |
---|---|
Pages (from-to) | 1138-1151 |
Number of pages | 14 |
Journal | Neurocomputing |
Volume | 72 |
Issue number | 4-6 |
DOIs | |
Publication status | Published - 2009 Jan 1 |
Keywords
- Gradient descent method
- Linear ultrasonic motors
- Type-2 fuzzy logic system
- Type-2 fuzzy neural network
- X-Y-Theta motion control
ASJC Scopus subject areas
- Computer Science Applications
- Cognitive Neuroscience
- Artificial Intelligence