The Journal of Korea Institute of Information, Electronics, and Communication Technology (한국정보전자통신기술학회논문지)
- Volume 6 Issue 4
- /
- Pages.238-242
- /
- 2013
- /
- 2005-081X(pISSN)
- /
- 2288-9302(eISSN)
DOI QR Code
Input-Output Linearization of Nonlinear Systems via Dynamic Feedback
비선형 시스템의 동적 궤환 입출력 선형화
- 조현섭 (청운대학교 전자공학과)
- Received : 2013.10.04
- Accepted : 2013.12.01
- Published : 2013.12.28
Abstract
We consider the problem of constructing observers for nonlinear systems with unknown inputs. Connectionist networks, also called neural networks, have been broadly applied to solve many different problems since McCulloch and Pitts had shown mathematically their information processing ability in 1943. In this thesis, we present a genetic neuro-control scheme for nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.