Norouzi, Armin (University of Alberta), Shahpouri, Saeid (University of Alberta), Gordon, David (Univ. of Alberta), Winkler, Alexander (RWTH Aachen University), Nuss, Eugen (RWTH Aachen University), Abel, Dirk (RWTH-Aachen University), Andert, Jakob (RWTH Aachen University), Shahbakhti, Mahdi (University of Alberta), Koch, Charles Robert (University of Alberta)

Machine Learning Integrated with Model Predictive Control for Imitative Optimal Control of Compression Ignition Engines

Scheduled for presentation during the Regular Session "Modeling, Estimation, and Control of Internal Combustion Engine - I" (MoAT3), Monday, August 29, 2022, 12:00−12:20, Pfahl Hall 140

10th IFAC International Symposium on Advances in Automotive Control, August 28-31, 2022, Columbus, Ohio, USA

This information is tentative and subject to change. Compiled on April 26, 2024

Abstract

The high thermal efficiency and reliability of the compression-ignition engine makes it the first choice for many applications. For this to continue, a reduction of the pollutant emissions is needed. One solution is the use of Machine Learning (ML) and Model Predictive Control (MPC) to minimize emissions and fuel consumption, without adding substantial computational cost to the engine controller. ML is developed in this paper for both modeling engine performance and emissions and for imitating the behaviour of a Linear Parameter Varying (LPV) MPC. Using a support vector machine-based linear parameter varying model of the engine performance and emissions, a model predictive controller is implemented for a 4.5~L Cummins diesel engine. This online optimized MPC solution offers advantages in minimizing the NOx emissions and fuel consumption compared to the baseline feedforward production controller. To reduce the computational cost of this MPC, a deep learning scheme is designed to mimic the behavior of the developed controller. The performance in reducing NOx emissions at a constant load by the imitative controller is similar to that of the online optimized MPC, however, the imitative controller requires 50 times less computation time when compared to that of the online MPC optimization.