Title :
Optimal neurocontrollers for discretized distributed parameter systems
Author :
Prokhorov, Danil V.
Author_Institution :
Res. & Adv. Eng., Ford Motor Co., Dearborn, MI, USA
Abstract :
We propose to use the framework of backpropagation through time (BPTT) to create optimal feedback neurocontrollers for distributed parameter systems (DPS). DPS are systems distributed in space while evolving in time. Unlike the lumped parameter systems, DPS are represented by a set of partial differential equations in the state space. Our neurocontrollers obtained for discretized DPS in the infinite-horizon regulator setting are applicable to a broad set of initial states (an envelope of initial state profiles). We compare our technique and results with another approach to synthesizing optimal DPS neurocontrollers introduced.
Keywords :
backpropagation; control system synthesis; distributed parameter systems; neurocontrollers; optimal control; partial differential equations; DPS; backpropagation; controllers synthesis; distributed parameter systems; infinite horizon regulator; initial state profiles; lumped parameter systems; optimal control; optimal neurocontrollers; partial differential equations; Backpropagation; Computer networks; Distributed parameter systems; Neural networks; Neurocontrollers; Neurofeedback; Partial differential equations; Regulators; State feedback; State-space methods;
Conference_Titel :
American Control Conference, 2003. Proceedings of the 2003
Print_ISBN :
0-7803-7896-2
DOI :
10.1109/ACC.2003.1239074
