Integrated evolutionary computation neural network quality controller for automated systems

With increasing competition in the global market, more and more stringent quality standards and specifications are being demands at lower costs. Manufacturing applications of computing power are becoming more common. The application of neural networks to identification and control of dynamic processes has been discussed. The limitations of using neural networks for control purposes has been pointed out and a different technique, evolutionary computation, has been discussed. The results of identifying and controlling an unstable, dynamic process using evolutionary computation methods has been presented. A framework for an integrated system, using both neural networks and evolutionary computation, has been proposed to identify the process and then control the product quality, in a dynamic, multivariable system, in real-time.

[1]  J. D. Schaffer,et al.  Combinations of genetic algorithms and neural networks: a survey of the state of the art , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[2]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[3]  D. Haesloop,et al.  Neural networks for process identification , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[4]  Kumpati S. Narendra,et al.  Adaptive control using neural networks , 1990 .

[5]  Bogdan Filipič,et al.  An Interactive Genetic Algorithm for Controller Parameter Optimization , 1993 .