Learning Based Model Predictive Control of Combustion Timing in Multi-Cylinder Partially Premixed Combustion Engine Lund University

Format:

Book

Conference/Event

Author/Creator:

Li, Xiufei, author.

Contributor:

Johansson, Rolf

Tunestal, Per

Yin, Lianhao

Conference Name:

14th International Conference on Engines & Vehicles (2019-09-15 : Capri, Italy)

Language:

English

Physical Description:

1 online resource cm

Place of Publication:

Warrendale, PA SAE International 2019

Summary:

Partially Premixed Combustion (PPC) has shown to be a promising advanced combustion mode for future engines in terms of efficiency and emission levels. The combustion timing should be suitably phased to realize high efficiency. However, a simple constant model based predictive controller is not sufficient for controlling the combustion during transient operation. This article proposed one learning based model predictive control (LBMPC) approach to achieve controllability and feasibility. A learning model was developed to capture combustion variation. Since PPC engines could have unacceptably high pressure-rise rates at different operation points, triple injection is applied as a solvent, with the use of two pilot fuel injections. The LBMPC controller utilizes the main injection timing to manage the combustion timing. The cylinder pressure is used as the combustion feedback. The method is validated in a multi-cylinder heavy-duty PPC engine for transient control

Notes:

Vendor supplied data

Publisher Number:

2019-24-0016

Access Restriction:

Restricted for use by site license