论文信息 - Competitive Decentralized Autonomous Neural Net Controllers

Competitive Decentralized Autonomous Neural Net Controllers

A simple and effective method is proposed for controlling a system consists of small processes. Each process is controlled by a decentralized autonomous neural network controller. These controllers compete with each other in order to increase their performances. As a result of the competition, the performance of whole system is kept at a suboptimal level. A control of example system consist of lots of processes is performed.

Masaru Ishida | Takehiro Ohba

[1] Anthony J. Calise,et al. Decentralized control of large-scale systems using single hidden layer neural networks , 2001, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[2] Chyi-Tsong Chen,et al. Multivariable Process Control Using Decentralized Single Neural Controllers , 1998 .

[3] Masaru Ishida,et al. Application of a neural network to evaluation of interactions in a MIMO process , 1998 .

[4] S. Jain,et al. Decentralized adaptive output feedback design for large-scale nonlinear systems , 1997, IEEE Trans. Autom. Control..

[5] Lin Shi,et al. Decentralized adaptive controller design for large-scale systems with higher order interconnections , 1992 .

[6] Changyun Wen,et al. Decentralized model reference adaptive control without restriction on subsystem relative degrees , 1999, IEEE Trans. Autom. Control..

[7] D. R. Lewin,et al. A constrained genetic algorithm for decentralized control system structure selection and optimization , 2003, Autom..