Properties of generalized predictive control
Automatica (Journal of IFAC) - Identification and systems parameter estimation
IEEE Spectrum
Adaptive fuzzy systems and control: design and stability analysis
Adaptive fuzzy systems and control: design and stability analysis
Advanced algorithms for neural networks: a C++ sourcebook
Advanced algorithms for neural networks: a C++ sourcebook
Using fuzzy logic: towards intelligent systems
Using fuzzy logic: towards intelligent systems
Fuzzy adaptive learning control network with on-line neural learning
Fuzzy Sets and Systems - Special issue on fuzzy control
Long-range predictive adaptive fuzzy relational control
Fuzzy Sets and Systems - Special issue on modern fuzzy control
Fuzzy-neural control: principles, algorithms and applications
Fuzzy-neural control: principles, algorithms and applications
Probabilistic neural networks and general regression neural networks
Fuzzy logic and neural network handbook
Computer-controlled systems (3rd ed.)
Computer-controlled systems (3rd ed.)
Fuzzy logic control of a solar power plant
IEEE Transactions on Fuzzy Systems
Fire-rule-based direct adaptive type-2 fuzzy H∞ tracking control
Engineering Applications of Artificial Intelligence
| Hi-index | 0.00 |
Recently, adaptive control systems utilizing artificial intelligenttechniques are being actively investigated in many applications. Neuralnetworks with their powerful learning capability are being sought as thebasis for many adaptive control systems where on-line adaptation can beimplemented. Fuzzy logic, on the other hand, has proved to be rather popularin many control system applications due to providing a rule-base likestructure. In this paper, an adaptive neuro-fuzzy control system is proposedin which the Radial Basis Function neural network (RBF) is implemented as aneuro-fuzzy controller (NFC) and the General Regression neural network(GRNN) as a predictor. The adaptation of the system involves the followingthree procedures: (1) tuning of the control actions or rules, (2) trimmingof the control actions, and (3) adjustment of the controller output gain.The tuning method is a non-gradient descent method based on the predictedsystem response which is able to self-organize the control actions from theinitial stage. The trimming scheme can help to reduce the aggressiveness ofthe particular control rules such that the response is stabilized to theset-points more effectively, while the controller gain adjustment scheme canbe applied in the cases where the appropriate controller output gain isdifficult to determine heuristically. To show the effectiveness of thismethodology, its performance is compared with the well known GeneralizedPredictive Control (GPC) technique which is a combination of both adaptiveand predictive control schemes. Comparisons are made with respect to thetransient response, disturbance rejection and changes in plant dynamics. Theproposed control system is also applied in controlling a single linkmanipulator. The results show that it exhibits robustness and goodadaptation capability which can be practically implemented.