Reinforcement learning based feedback controller for complex nonlinear discrete-time systems with application to spark engine EGR operation
Reinforcement learning based output feedback controller for nonlinear discrete time system with application to spark ignition engines operating lean and EGR
Reinforcement learning based output-feedback controller for nonlinear discrete-time systems with application to spark engines
Keywords and Phrases
Exhaust gas recirculation (EGR)
"A spark ignition (SI) engine can be described by non-strict feedback nonlinear discrete-time system with the output dependent upon on the states in a nonlinear manner. The controller developed in this thesis utilizes the inherent universal approximation property of neural networks (NN) to simplify the design process and solve the non-causality problem inherent with traditional designs. It also exploits a long-term performance index called the strategic utility function to minimize and assist in updating of the NN weights; therefore, an optimal controller can be realized. Finally, through Lyapunov equations, the controller guarantees stability"--Abstract, page iv.
Sarangapani, Jagannathan, 1965-
Smith, Scott C.
Drallmeier, J. A.
Electrical and Computer Engineering
M.S. in Computer Engineering
University of Missouri--Rolla
xi, 93 pages
© 2007 Peter Shih, All rights reserved.
Thesis - Open Access
Automobiles -- Motors -- Computer control systems
Automobiles -- Motors -- Exhaust gas
Neural networks (Computer science)
Reinforcement learning (Machine learning)
Print OCLC #
Electronic OCLC #
Link to Catalog Record
Shih, Peter, "Reinforcement-learning based output-feedback controller for nonlinear discrete-time system with application to spark ignition engines operating lean and EGR" (2007). Masters Theses. 4550.