Deep Reinforcement Learning for Dynamic Control of Fuel Injection Timing in Multi-Pulse Compression Ignition Engines

Research output: Contribution to journalArticlepeer-review

8 Scopus Citations

Abstract

Conventional compression-ignition (CI) engines have long offered high thermal efficiencies and torque across a wide range of loads, but often require extensive exhaust gas treatment that decreases efficiency to meet ever-increasing emissions regulations. One strategy to decrease emissions is to split the fuel injection into a series of smaller injections. In this paper, we explore a new way of discovering optimal control strategies for the next generation of CI engines using deep reinforcement learning (DRL). We outline a DRL procedure to maximize the weighted reward of engine work while minimizing end-of-cycle NOx emissions. Through the procedure outlined in this paper, we show that the DRL agent is able to reduce NOx emissions threefold while only decreasing network by 2%. We demonstrate the use of transfer learning (TL) across hierarchies of physical models to accelerate the learning process, making this approach feasible for a range of control problems within this space. This paper presents a framework and demonstration for using DRL to design control systems in technology areas such as multi-pulse engine control where a hierarchy of models combined with multi-objective rewards are used for optimal operation.

Original languageAmerican English
Pages (from-to)1503-1521
Number of pages19
JournalInternational Journal of Engine Research
Volume23
Issue number9
DOIs
StatePublished - Sep 2022

Bibliographical note

Publisher Copyright:
© IMechE 2021.

NREL Publication Number

  • NREL/JA-2C00-77550

Keywords

  • control
  • Deep reinforcement learning
  • multi-pulse compression ignition
  • transfer learning

Fingerprint

Dive into the research topics of 'Deep Reinforcement Learning for Dynamic Control of Fuel Injection Timing in Multi-Pulse Compression Ignition Engines'. Together they form a unique fingerprint.

Cite this