Model-based iterative learning control strategies for precise trajectory tracking in gasoline engines

Hedinger, Raffael; Zsiga, Norbert; Salazar, Mauro; Onder, Christopher H.

doi:10.1016/j.conengprac.2019.03.002

Cited by 7 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different types of ILC have been implemented for internal combustion engine control. ILC has been used in SI engine load control, 50,51 a dual-fuel control of homogeneous charge compression ignition (HCCI) engine, 52 SI engine speed and air-to-fuel ratio, 53 parameter optimization in a turbocharged SI engine, 54 variable injection rate control for compression ignition (CI) engines, 55 diesel N O x control, 56,57 and exhaust gas recalculation (EGR) control in a CI engine. 58 Although ILC has been used in literature as a model-free learning-based controller, it requires a repetitive environment to learn from the repetition.…”

Section: Introductionmentioning

confidence: 99%

Safe deep reinforcement learning in diesel engine emission control

Norouzi

Shahpouri

Gordon

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

A deep reinforcement learning application is investigated to control the emissions of a compression ignition diesel engine. The main purpose of this study is to reduce the engine-out nitrogen oxide [Formula: see text] emissions and to minimize fuel consumption while tracking a reference engine load. First, a physics-based engine simulation model is developed in GT-Power and calibrated using experimental data. Using this model and a GT-Power/Simulink co-simulation, a deep deterministic policy gradient is developed. To reduce the risk of an unwanted output, a safety filter is added to the deep reinforcement learning. Based on the simulation results, this filter has no effect on the final trained deep reinforcement learning; however, during the training process, it is crucial to enforce constraints on the controller output. The developed safe reinforcement learning is then compared with an iterative learning controller and a deep neural network–based nonlinear model predictive controller. This comparison shows that the safe reinforcement learning is capable of accurately tracking an arbitrary reference input while the iterative learning controller is limited to a repetitive reference. The comparison between the nonlinear model predictive control and reinforcement learning indicates that for this case reinforcement learning is able to learn the optimal control output directly from the experiment without the need for a model. However, to enforce output constraint for safe learning reinforcement learning, a simple model of system is required. In this work, reinforcement learning was able to reduce [Formula: see text] emissions more than the nonlinear model predictive control; however, it suffered from slightly higher error in load tracking and a higher fuel consumption.

show abstract

Section: Introductionmentioning

confidence: 99%

Safe deep reinforcement learning in diesel engine emission control

Norouzi

Shahpouri

Gordon

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

show abstract

“…This control scheme has a great practical significance in dealing with systems having nonlinear coupling, high complexity, difficulty in modeling, and highprecision tracking. [19][20][21][22][23][24] Based on the iterative learning control scheme, Riel et al 20 investigated the tracking accuracy of an optical telescope system used for satellite tracking and laser ranging applications. Bu et al 22 proposed a distributed model-free adaptive iterative learning control method for the multiagent systems with fixed or iteration-varying topologies to perform consensus tracking.…”

Section: Introductionmentioning

confidence: 99%

“…The iterative learning control was first proposed by Uchiyama in 1978 and introduced by Arimoto et al 18 in 1984. This control scheme has a great practical significance in dealing with systems having nonlinear coupling, high complexity, difficulty in modeling, and high‐precision tracking 19–24 . Based on the iterative learning control scheme, Riel et al 20 investigated the tracking accuracy of an optical telescope system used for satellite tracking and laser ranging applications.…”

Section: Introductionmentioning

confidence: 99%

Iterative learning heterogeneous trajectory tracking for partially interdependent networks

Guo

Chai

et al. 2021

Asian Journal of Control

View full text Add to dashboard Cite

Trajectory tracking is a hot topic in the field of complex systems. In this paper, based on the Lyapunov stability theory, combined with the adaptive iterative learning control method, the heterogeneous trajectory tracking of partially interdependent networks is investigated in a given finite time interval. The considered network consists of two subnets, where only the first m nodes are intercoupled. Firstly, some suitable iterative learning controllers, as well as the adaptive laws and the coupling strength learning laws, are designed for each node. Secondly, the boundedness and the convergence of the signals are proved using the proposed control strategy. Finally, some simulations are presented to illustrate the effectiveness and feasibility of the theoretical results presented in this paper. Generally, the accuracy trajectory tracking is found almost proportional to the number of iterations. When the number of iterations is fixed, with the increasing number of nodes having interdependence, the time required to track target accurately is reduced.

show abstract

Experimental investigation on automated assembly of space structure from cooperative modular components

Huang

Zhang

et al. 2020

Acta Astronautica

View full text Add to dashboard Cite

Model-based iterative learning control strategies for precise trajectory tracking in gasoline engines

Cited by 7 publications

References 17 publications

Safe deep reinforcement learning in diesel engine emission control

Safe deep reinforcement learning in diesel engine emission control

Iterative learning heterogeneous trajectory tracking for partially interdependent networks

Experimental investigation on automated assembly of space structure from cooperative modular components

Contact Info

Product

Resources

About