Application of a CMAC neural network to the control of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle

Optimizing and controlling the energy use of a hybrid-electric propulsion system is difficult due to the interaction of nonlinear mechanical, thermodynamic, and electromechanical devices. An optimization routine for the energy use of a parallel hybrid-electric propulsion system for a small unmanned aerial vehicle (UAV), the application of a cerebellar model arithmetic computer (CMAC) neural network to approximate the optimization results and control the hybrid-electric system, and simulation results are presented. The small hybrid-electric UAV is intended for military and homeland security missions involving intelligence, surveillance, or reconnaissance (ISR). The flexible optimization routine allows relative importance to be assigned between the use of gasoline, electricity, and recharging. The CMAC controller saves on the required memory compared to a look-up table by two orders of magnitude. The hybrid-electric UAV with the CMAC controller uses 37.8% less energy than a two-stroke gasoline-powered UAV during a three-hour ISR mission.