Intelligent Self-calibration of Vehicle Propulsion Systems

Principal Investigators
Michael Kokkolaras, Panos Papalambros (U. of Michigan)

University Researcher
Dennis Assanis (U. of Michigan)

Industry
Terry Wagner (Ford Motor Co.)

Government
Dariusz Mikulski (TARDEC)

Student
Andreas Malikopoulos (U. of Michigan)

We intend to develop the theoretical basis and learning algorithm for making the engine an autonomous system that can learn its optimal calibration for both steady-state and transient operating points in real time while running a vehicle. Through this learning algorithm, the engine will progressively perceive the driver’s conventional driving style and, eventually, learn to operate in a manner that minimizes fuel consumption and emissions for this particular driving style. The longer the engine will run during a particular driving style, the better the fuel consumption and emissions will be. The engine’s ability to learn its optimum calibration will not limited, however, to a particular driving style. The engine can learn to operate optimally for different drivers accordingly, although the drivers should indicate their identities before starting the vehicle. The engine can then adjust its operation to be optimal for a particular driver based on what it has learned in the past regarding his driving style. This will introduce a new technology that can be implemented easily within the electronic control unit (ECU) of an internal combustion engine.

The calibration process, its duration, and its cost grow exponentially with enhanced engine complex technology whereas optimal calibration for the entire feasible engine operating domain cannot be guaranteed with the state of the art in engine calibration. In particular, to pre-specify the huge number of transient engine operation is impractical and, thus, engine calibration cannot be optimized for all cases a priori. This technology will be beneficial to the Army and industry in the sense of providing optimal engine calibration for the both steady-state and transient engine operation.