Scholarlink

<p>A hybrid Model Predictive Control (MPC)–Offline Reinforcement Learning (RL) framework for lifetime-optimized State-of-Charge (SoC) regulation in electric vehicle (EV) batteries is presented in this paper. It is forecast- and State-of-Health (SoH)-aware. Achieving lifetime-aware State-of-Charge (SoC) regulation with enhanced tracking precision, decreased degradation, and computational viability under representative drive cycles is the main goal of this work. Hardware-in-the-loop (HIL)-validated physics-based electrothermal model for real-time state forecasting, an offline-trained RL policy for adaptive decision-making, and a constrained MPC safety layer are all integrated into the suggested architecture. With peak temperature deviations under 2.5&#xa0;°C, experimental validation under Worldwide Harmonized Light Vehicle Test Procedure (WLTP), New European Driving Cycle (NEDC), and Urban Dynamometer Driving Schedule (UDDS) cycles shows strong SoC tracking and thermal safety. In comparison to baseline MPC, the hybrid controller improves forecast accuracy by 12.8% while achieving a 25.6% lower SoC tracking RMSE, a 19.3% decrease in degradation rate, and an 18% increase in computational efficiency. Under all circumstances, the correlation between the hardware and simulation results was within ± 3%. Additionally, Pareto-based optimization made sure that the trade-offs between computational cost, accuracy, and degradation were balanced. Thus, the framework advances real-time monitoring, fault diagnosis, and AI-driven optimization in intelligent energy storage systems by offering a scalable, interpretable, and safety-compliant starting point for HIL-validated model-based framework-assisted battery control.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Experimental and Simulation-Based Validation of a HIL-Validated Model-Based Framework–Driven Hybrid Control Framework for EV Battery Optimization

  • 期刊论文

  • 发表日期：

    2026年4月10日

查看全文
  • Gandi Ramarao,
  • Dasyam Chandra Mouli,
  • Rebba Sasidhar,
  • Sivasankara Raju Rallabandi,
  • Prasad Chongala,
  • Kiran Kumar Kalyana,
  • Vasupalli Manoj

摘要

A hybrid Model Predictive Control (MPC)–Offline Reinforcement Learning (RL) framework for lifetime-optimized State-of-Charge (SoC) regulation in electric vehicle (EV) batteries is presented in this paper. It is forecast- and State-of-Health (SoH)-aware. Achieving lifetime-aware State-of-Charge (SoC) regulation with enhanced tracking precision, decreased degradation, and computational viability under representative drive cycles is the main goal of this work. Hardware-in-the-loop (HIL)-validated physics-based electrothermal model for real-time state forecasting, an offline-trained RL policy for adaptive decision-making, and a constrained MPC safety layer are all integrated into the suggested architecture. With peak temperature deviations under 2.5 °C, experimental validation under Worldwide Harmonized Light Vehicle Test Procedure (WLTP), New European Driving Cycle (NEDC), and Urban Dynamometer Driving Schedule (UDDS) cycles shows strong SoC tracking and thermal safety. In comparison to baseline MPC, the hybrid controller improves forecast accuracy by 12.8% while achieving a 25.6% lower SoC tracking RMSE, a 19.3% decrease in degradation rate, and an 18% increase in computational efficiency. Under all circumstances, the correlation between the hardware and simulation results was within ± 3%. Additionally, Pareto-based optimization made sure that the trade-offs between computational cost, accuracy, and degradation were balanced. Thus, the framework advances real-time monitoring, fault diagnosis, and AI-driven optimization in intelligent energy storage systems by offering a scalable, interpretable, and safety-compliant starting point for HIL-validated model-based framework-assisted battery control.