EGR Intelligent Control of Diesel Engine Based on Deep Reinforcement Learning

DOI

10.2991/978-94-6463-022-0_14How to use a DOI?

Keywords

Deep Reinforcement Learning (DRL); Exhaust Gas Recycling (EGR); Mean Value Model

Abstract

Intelligent Connected Vehicle (ICV), as a revolutionary technology for automobiles, is rapidly developing and changing the way people travel. However, the current smart cars lack the intelligent control of the powertrain, and even if the network connection is completed, the power, economy and emissions cannot be greatly improved. State-of-the-art deep reinforcement learning algorithms, whose agents continuously interact with the model, employ an end-to-end control strategy. The deep learning neural network is used to fit the mapping relationship between the state and the action, and the action of the agent is evaluated by the reinforcement learning reward function, and iteratively learns the control strategy that meets the goal. This paper adopts a new EGR control method based on deep reinforcement learning, and compares it with the traditional PID control method to verify whether the method is feasible and provide a reference for the intelligent control of the engine.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - ChenGuang Lai
AU  - ChaoBing Wu
AU  - SiZheng Wang
AU  - JiaXi Li
AU  - Bo Hu
PY  - 2022
DA  - 2022/12/07
TI  - EGR Intelligent Control of Diesel Engine Based on Deep Reinforcement Learning
BT  - Proceedings of the International Conference of Fluid Power and Mechatronic Control Engineering (ICFPMCE 2022)
PB  - Atlantis Press
SP  - 151
EP  - 161
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6463-022-0_14
DO  - 10.2991/978-94-6463-022-0_14
ID  - Lai2022
ER  -