Abstract
A new automotive fuel-injection controller using the cerebellar model articulation controller (CMAC) neural network is developed and implemented to maintain the engine air-to-fuel ratio at its stoichiometric value. In contrast to conventional fuel-injection controllers, which rely heavily on laborious calibration and tuning processes the CMAC controller requires minimal knowledge of the dynamic system and possesses the ability so achieve a desired performance through rapid on-line learning. This real-time CMAC controller is experimentally evaluated on a research vehicle in a configuration fully compatible with production controllers. The results show the highly promising potential of the new controller.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
