𝔖 Bobbio Scriptorium
✦   LIBER   ✦

131 EMG pattern recognition by neural networks for prosthetic fingers control: A. Hiraiwa, N. Uchida, K. Shimohara, pp 73–80


Publisher
Elsevier Science
Year
1993
Tongue
English
Weight
116 KB
Volume
1
Category
Article
ISSN
0967-0661

No coin nor oath required. For personal study only.

✦ Synopsis


The contribution of this paper is twofold. First, it focuses on the application of a particular NARMAX (nonlinear ARMAX) model representation based on local models for adaptive decoupling. Second, in order to improve the robusmess of the adaptive control algorithm, a diagonal PI-controller is introduced, in parallel with the adaptive decoupler. These controUers are separated in the frequency domain, such that the decoupler and Plcontroller take care of control actions at higher and lower frequencies, respectively. The parallel control smlcture supports incremental control design, in the sense that improved process knowledge is used to successively upgrade control performance. The concept is illustrated by a semi-realistic simulation example.