An introduction to genetic algorithms
An introduction to genetic algorithms
Design and analysis of a fuzzy proportional-integral-derivative controller
Fuzzy Sets and Systems
Neurocontrol: towards an industrial control methodology
Neurocontrol: towards an industrial control methodology
Process Control Systems: Application, Design and Tuning
Process Control Systems: Application, Design and Tuning
Adaptive Control Utilising Neural Swarming
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Neural Networks, Fuzzy Logic and Genetic Algorithms
Neural Networks, Fuzzy Logic and Genetic Algorithms
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
| Hi-index | 0.00 |
System modeling and identification is an important tool for analysis, evaluation and prediction in classification, decision analysis and automatic control. Many models have been suggested for noise rejection. The identification of adaptive controllers for practical system is desired for better control and for improved system response even in the presence of the noise. In this paper, a hybrid controller is developed, using Artificial Neural Network and Genetic algorithm, which can provide adaptation. The neuro-controller translates the data (input, output and noise data pertaining to the system) into a control action. A genetic algorithm in integration with neuro-controller is used to determine the weights and biases of the neural network for better response. The performance of these two approaches has been evaluated using data of different plants on a common set of performance indices. The simulations results show that identified GA based Adaptive neuro-controller along with PID controller provides a much better system response under noise condition as compared to using PID controller. The hybrid controller provides a better system response and also helps in maintaining the optimal set point.