The objective of this research is to develop optimal impulse controllers for nonlinear systems with uncertainties. The approach proposed is based on approximate dynamic programming. Dual neural network architectures will be used to solve the equations resulting from an optimal impulse control formulation.
Intellectual merit of this research lies in realizing unified controller solutions to optimal impulse control problems that are important, yet difficult to solve. Outcome of this research is expected to advance the field of control in the area of impulse control. Furthermore, expected results from the proposed work will advance the state of the art in the field of neural networks since these investigations are based on new approximate dynamic programming formulations with neural network based solution structures.
Broader impact of this research will be in the applications areas. Systems with uncertainties in dynamics where control inputs occur on very short time scales with respect to the systems response time are pervasive and valuable. This class of systems characterizes dynamics of epidemics, insect control, inventory control, exchange rates, interest rates etc. Optimal solutions to such problems could lead to large improvements in cost savings and offer solutions in some health care areas and quality of life improvements. Outreach activities planned in this proposal include using women and minorities and disseminating results through non-engineering collaborators in the medical areas. The project results will be discussed through demonstrations to the area high schools in order to create early career interest in science and engineering.
