Deep reinforcement learning for dynamic control of fuel injection timing in multi-pulse compression ignition engines
| Autor: | Marc Henry de Frahan, Ray Grout, Nicholas T Wimer, Shashank Yellapantula |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
020209 energy
Mechanical Engineering Aerospace Engineering Exhaust gas Ocean Engineering 02 engineering and technology Fuel injection 01 natural sciences Automotive engineering 010305 fluids & plasmas law.invention Ignition system law Pulse compression Range (aeronautics) 0103 physical sciences Automotive Engineering Thermal 0202 electrical engineering electronic engineering information engineering Environmental science Reinforcement learning Torque |
| Zdroj: | International Journal of Engine Research. 23:1503-1521 |
| ISSN: | 2041-3149 1468-0874 |
| DOI: | 10.1177/14680874211019345 |
| Popis: | 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 NO x emissions. Through the procedure outlined in this paper, we show that the DRL agent is able to reduce NO x 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|