A Learning Algorithm for Optimal Internal Combustion Engine Calibration in Real Time

Abstract

Advanced internal combustion engine technologies have increased the number of accessible variables of an engine and our ability to control them. The optimal values of these variables are designated during engine calibration by means of a static correlation between the controllable variables and the corresponding steady-state engine operating points. While the engine is running, these correlations are being interpolated to provide values of the controllable variables for each operating point. These values are controlled by the electronic control unit to achieve desirable engine performance, for example in fuel economy, pollutant emissions, and engine acceleration. The state-of-the-art engine calibration cannot guarantee continuously optimal engine operation for the entire operating domain, especially in transient cases encountered in driving styles of different drivers. This paper presents the theoretical basis and algorithmic implementation for allowing the engine to learn the optimal set values of accessible variables in real time while running a vehicle. Through this new approach, the engine progressively perceives the driver’s driving style and eventually learns to operate in a manner that optimizes specified performance indices. The effectiveness of the approach is demonstrated through simulation of a spark ignition engine, which learns to optimize fuel economy with respect to spark ignition timing, while it is running a vehicle.