Safe Reinforcement Learning-based Control for Hydrogen Diesel Dual-Fuel Engines

TL;DR

This paper introduces a safe, data-efficient reinforcement learning control method for hydrogen-diesel dual-fuel engines, validated on real hardware, reducing computation time compared to traditional control methods.

Contribution

It presents a novel offline RL approach with state augmentation for safe, constraint-compliant control of hydrogen-diesel engines, enabling real-time implementation.

Findings

Controllers are constraint compliant and sample-efficient.

The offline RL controller reduces computation time by six times.

Experimental validation on a real engine demonstrates practical feasibility.

Abstract

The urgent energy transition requirements towards a sustainable future stretch across various industries and are a significant challenge facing humanity. Hydrogen promises a clean, carbon-free future, with the opportunity to integrate with existing solutions in the transportation sector. However, adding hydrogen to existing technologies such as diesel engines requires additional modeling effort. Reinforcement Learning (RL) enables interactive data-driven learning that eliminates the need for mathematical modeling. The algorithms, however, may not be real-time capable and need large amounts of data to work in practice. This paper presents a novel approach which uses offline model learning with RL to demonstrate safe control of a 4.5 L Hydrogen Diesel Dual-Fuel (H2DF) engine. The controllers are demonstrated to be constraint compliant and can leverage a novel state-augmentation approach for sample-efficient learning. The offline policy is subsequently experimentally validated on the real engine where the control algorithm is executed on a Raspberry Pi controller and requires 6 times less computation time compared to online Model Predictive Control (MPC) optimization.