A Generative Physics-Informed Reinforcement Learning-Based Approach for Construction of Representative Drive Cycle

TL;DR

This paper introduces a physics-informed reinforcement learning method, PIESMC, that efficiently constructs representative driving cycles capturing dynamic features, outperforming traditional methods in accuracy and computational speed.

Contribution

The paper presents a novel physics-informed reinforcement learning approach, PIESMC, for generating accurate and efficient vehicle driving cycles, improving upon existing methods in fidelity and speed.

Findings

PIESMC reduces cumulative kinematic fragment errors by up to 57.3%.

It is nearly ten times faster than conventional cycle construction techniques.

PIESMC accurately reproduces key vehicle kinematic and energy metrics.

Abstract

Accurate driving cycle construction is crucial for vehicle design, fuel economy analysis, and environmental impact assessments. A generative Physics-Informed Expected SARSA-Monte Carlo (PIESMC) approach that constructs representative driving cycles by capturing transient dynamics, acceleration, deceleration, idling, and road grade transitions while ensuring model fidelity is introduced. Leveraging a physics-informed reinforcement learning framework with Monte Carlo sampling, PIESMC delivers efficient cycle construction with reduced computational cost. Experimental evaluations on two real-world datasets demonstrate that PIESMC replicates key kinematic and energy metrics, achieving up to a 57.3% reduction in cumulative kinematic fragment errors compared to the Micro-trip-based (MTB) method and a 10.5% reduction relative to the Markov-chain-based (MCB) method. Moreover, it is nearly an order of magnitude faster than conventional techniques. Analyses of vehicle-specific power distributions and wavelet-transformed frequency content further confirm its ability to reproduce experimental central tendencies and variability.