This book presents a step-by-step guide to the engine control system design, providing case studies and a thorough analysis of the modeling process using machine learning, and model predictive control (MPC). Covering advanced processes alongside the theoretical foundation, MPC enables engineers to improve performance in both hybrid and non-hybrid vehicles.
Control system improvement is one of the major priorities for engineers seeking to enhance an engine. Often possible on a low budget, substantial improvements can be made by applying cutting-edge methods, such as artificial intelligence when modeling engine control system designs and using MPC. This book presents approaches to control system improvement at mid, low, and high levels of control. Beginning with the model-in-the-loop hierarchical control design of ported fuel injection SI engines, this book focuses on optimal control of both transient and steady state and also discusses hardware-in-the-loop. The chapter on low-level control discusses adaptive MPC and adaptive variable functioning, as well as designing a fuel injection feed-forward controller. At mid-level control, engine calibration maps are discussed, with consideration of constraints such as limits on pollutant emissions. Finally, the high-level control methodology is discussed in detail in relation to transient torque control of SI engines.
This comprehensive yet clear guide to control system improvement is an essential read for any engineer working in automotive engineering and engine control system design.