A detailed design procedure for fuzzy neural controllers in electromechanical drives is presented. The proposed procedure has one or two stages. The first stage yields the number of fuzzy rules and the rules themselves for the fuzzy neural controller. Initial estimates for centres and widths for membership functions associated with the controller input and output variables are also obtained. From this information a five-layer fuzzy neural controller is configured and the resulting controller may be further tuned using a backpropagation-type of algorithm. Applications of fuzzy neural controllers to DC and AC drives are presented. Results are first presented for a separately excited DC drive incorporating a combined speed and armature current fuzzy neural controller. Results are also presented for the response of a vector controlled induction motor drive with a fuzzy neural controller replacing the PI speed controller. Minimum numbers of fuzzy sets and rules have been established by the self-organising methodology. The drive responses obtained using fuzzy neural controllers are compared to the corresponding drive performances obtained using PI-type speed controllers. It is shown that a high dynamic performance can be obtained from drives incorporating fuzzy neural controllers and that the ad hoc tuning procedures associated with the implementation of PI and conventional fuzzy controllers are eliminated.
[1]
Peter Vas,et al.
Electrical Machines and Drives: A Space-Vector Theory Approach
,
1993
.
[2]
Geoffrey E. Hinton,et al.
Learning representations by back-propagating errors
,
1986,
Nature.
[3]
Stephen A. Billings,et al.
Non-linear system identification using neural networks
,
1990
.
[4]
A. F. Stronach,et al.
Variable-speed drives incorporating interacting multiloop adaptive controllers
,
1995
.
[5]
Li-Xin Wang,et al.
Adaptive fuzzy systems and control
,
1994
.
[6]
Geoffrey E. Hinton,et al.
Learning internal representations by error propagation
,
1986
.
[7]
Derrick H. Nguyen,et al.
Neural networks for self-learning control systems
,
1990
.
[8]
R. Palmer,et al.
Introduction to the theory of neural computation
,
1994,
The advanced book program.
[9]
A. A. Mullin,et al.
Principles of neurodynamics
,
1962
.
[10]
Bart Kosko,et al.
Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence
,
1991
.
[11]
Chin-Teng Lin,et al.
Neural-Network-Based Fuzzy Logic Control and Decision System
,
1991,
IEEE Trans. Computers.
[12]
George W. Irwin,et al.
Neural networks for control and systems
,
1992
.