Use of Machine Learning for Real-Time Non-Linear Model Predictive Engine Control

Non-linear model predictive engine control (nMPC) systems have the ability to reduce calibration effort while improving transient engine response. The main drawback of nMPC for engine control is the computational power required to realize real-time operation. Most of this computational power is spent linearizing the non-linear plant model at each time step. Additionally, the effectiveness of the nMPC system relies heavily on the accuracy of the model(s) used to predict the future system behavior, which can be difficult to model physically. This paper introduces a hybrid modeling approach for internal combustion engines that combines physics-based and machine learning techniques to generate accurate models that can be linearized with low computational power. This approach preserves the generalization and robustness of physics-based models, while maintaining high accuracy of data-driven models. Advantages of applying the proposed model with nMPC are discussed. The combination of nMPC and the machine learning enhanced models is validated in using both simulation and real-time dynamometer tests. The neural network based-approach is more accurate and three times faster compared to the other regression methods tested. The proposed control system successfully controls the investigated engine with tractable computational load, suggesting that this approach could be feasible for future Engine Control Units (ECUs).