A generative physics-informed reinforcement learning-based approach for construction of representative drive cycle
提出一种物理信息强化学习与蒙特卡洛采样结合的PIESMC方法，用于构建代表性行驶工况，在保持高保真度的同时大幅降低计算成本，实验显示误差减少最高83.9%，速度提升30倍以上。
Accurate driving cycle construction is crucial for vehicle design, fuel economy analysis, and environmental impact assessments. A generative Physics Informed Expected (State Action Reward State Action) 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 an 83.9 % reduction in cumulative kinematic fragment errors compared to the Micro-trip-based (MTB) method and a 61.9 % reduction relative to the Markov-chain-based (MCB) method. Moreover, it is over an order of magnitude faster than conventional techniques, delivering more than a 30 × decrease in computational time. Analyses of vehicle-specific power distributions and wavelet-transformed frequency content further confirm its ability to reproduce experimental central tendencies and variability.