Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Arash Khalatbarisoltani has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An Intelligent Control-Based Charging Strategy for Lithium-Ion Batteries

    by Muhammad Sohail, Muhammad Saeed, Arash Khalatbarisoltani, Hafiz Muhammad Jawaad, Leijiao Ge

    This paper proposes an intelligent framework for the efficient fast charging of Li-ion batteries while strictly following physical constraints and thermal safety. Using an electrothermal coupled model, a MIMO PID observer is first designed to estimate the battery state of charge and core temperature accurately. These insights along with the measurable battery variables are then provided to a deep reinforcement learning (DRL) framework to learn an internal dynamics-aware multi-constrained charging strategy. Besides priority experience replay, a dynamic reward function is formulated to aid efficient learning and convergence. The effectiveness of the proposed DRLguided strategy is demonstrated experimentally using Tesla 21700 battery cells. Results show that the proposed strategy can charge 68 % faster than the recommended 0.3 C CCCV and even surpasses extreme 3C CCCV (which violates critical temperature limits) while perfectly following all physical constraints, highlighting its potential for practical applications.


  • Deep Reinforcement Learning Guided Framework for State Estimation of Li-ion Batteries: A Control-Oriented Approach With High Adaptability

    by Muhammad Saeed, Arash Khalatbarisoltani, Faisal Altaf, Yongjun Pan, Shuai Lu, Xiaosong Hu

    An accurate and robust state estimation of Lithium-ion batteries (LIBs) is crucial for safe and reliable operations. However, due to the modeling uncertainties and complex nonlinear behavior of LIBs in practical scenarios, existing methods fell short of the desired accuracy and adaptability. This article anchors a proportional integral derivative (PID) observer with deep reinforcement learning (DRL) to develop a battery state estimation framework with enhanced performance, stability, and adaptability. First, the PID observer is constructed using a second-order battery equivalent circuit model, and an actor-critic DRL agent is then integrated with the designed observer to learn the optimal policy for observer control. A dynamic reward function with adaptive constraints is formulated to avoid unproductive explorations and aid efficient learning and convergence. In addition, an augmented model bias is also introduced into the battery model to compensate for the model inaccuracies in real time. After successful training, the trained DRL agent, based on the learned optimal policy, auto-adjusts the PID control according to operating conditions, making the proposed method highly adaptive. Finally, a test bench is designed to verify its improved accuracy, enhanced robustness against uncertainties, faster convergence, and comparative usefulness. Moreover, the high adaptability against real electric vehicle data highlights the potential of the proposed framework in improving the safety of LIBs in practical applications.


  • A PID Framework With Intelligent Derivative Control and Model Bias for Robust State Estimation of Large Format Lithium-ion Batteries

    by Muhammad Saeed, Arash Khalatbarisoltani, Zhongwei Deng, Wenxue Liu, Shuai Lu, Congzhi Liu, Xiaosong Hu

    Large format Li-ion batteries (LIBs) are getting huge attention due to higher density, efficient packing, and lower system and design costs. However, due to internal inhomogeneities, they exhibit a strong intermittent behavior against critical operating conditions, making accurate state estimation quite challenging. Therefore, this article presents a novel framework with augmented model bias and intelligent derivative control to ensure the desired accuracy and robustness in state estimation of large format cells. First, an augmented bias is proposed in the LIB equivalent circuit model to compensate for the modeling uncertainties and improve accuracy. Second, observability of the proposed system is investigated rigorously. Third, a proportional integral derivative observer with an intelligent multi-layer error convergence mechanism is proposed to enhance convergence while maintaining stable estimations. The superiority of the proposed framework against critical operations is verified using an experimental setup. Moreover, the comparative results against benchmark algorithms demonstrate improved accuracy, high adaptability, enhanced robustness against measurement uncertainties and disturbances, low computational cost, and five times faster convergence, highlighting the proposed framework's potential to improve the safety of LIBs in practical applications.


  • Open Access

    Safety-and Physics-Informed Platooning: Eco-Driving and Energy Management

    by Arash Khalatbarisoltani, Jie Han, Saeed Muhammad, Wenxue Liu, Cong-Zhi Liu, Xiaosong Hu

    Due to the inherent complexity arising from powertrain, aerodynamic, and unseen driving scenarios, efficient coordination of connected hybrid electric vehicles (C-HEVs) platooning encounters complex challenges. Existing studies primarily do not consider thermal load impacts. However, this overlooks the interconnection between the C-HEVs related to powertrain power and thermal loads, which can hinder effective optimization and collaboration across C-HEV platoon members. To fully address this gap, a multi-agent deep reinforcement learning (DRL)-based joint cooperative adaptive cruise control (CACC) with an integrated thermal and energy management (ITEM) framework is proposed. Additionally, to decrease the sample complexity and accelerate policy learning, the vehicle-level (string stability and time headway) and powertrain-level (energy consumption and health indicator) information are integrated into the reward function to design a safety-and physics-informed DRL framework. To meticulously assess the mutual impact of thermal load and management on the platooning optimization problem, air drag and airflow reductions related to inter-vehicle distance (IVD) are accounted for with a high-fidelity model provided by Autonomie. Numerical and hardware-in-the-loop (HIL) experiments demonstrate that the proposed CACC+ITEM algorithm outperforms the classic DRL version in stability, energy-saving, driving comfort, and battery longevity.


  • Comparative Analysis of Control Observer-Based Methods for State Estimation of Lithium-Ion Batteries in Practical Scenarios

    by Muhammad Saeed, Arash Khalatbarisoltani, Zhongwei Deng, Wenxue Liu, Faisal Altaf, Shuai Lu, Xiaosong Hu

    The reliability, lower computational complexity, and ease of implementation of control observers make them one of the most promising methods for the state estimation of Li-ion batteries (LIBs) in commercial applications. To pave their way, this study performs a comprehensive and systematic evaluation of four main categories of control observer-based methods in different practical scenarios considering estimation accuracy, computational time convergence speed, stability, and robustness against measurement uncertainties. Observers are designed using a second-order equivalent circuit model whose observability against different scenarios is rigorously investigated to verify the feasibility of the proposed analysis. Established techniques then are validated against driving datasets and their comparative usefulness is evaluated using an experimental setup. The analysis also evaluates the adaptability of different techniques to electric vehicle (field data. The results indicate better accuracy, stability, robustness, and faster convergence for the PI and PID, while the estimations of the Luenberger observers find it hard to converge against highly dynamic loadfiles. Moreover, this study also discusses the sensitivity of observer-based techniques to battery ohmic polarization and voltage-related measurement uncertainties. The most remarkable contribution of the proposed study lies in providing guidance for researchers when choosing the control observers for online state estimation of LIBs.


  • Enhanced Electrothermal State Estimation and Experimental Validations for Electric Flying Car Batteries

    by Wenxue Liu, Yusheng Zheng, Arash Khalatbarisoltani, Le Xu, Yongjun Pan, Xiaosong Hu

    Urban air mobility (UAM) has become an emerging urban travel paradigm due to its viability of alleviating traffic congestion and reducing commute time. Accurate and robust knowledge of key battery states, such as state of charge (SOC), state of temperature (SOT), and state of power (SOP), is a prerequisite for the safe, efficient, and reliable operation of electric flying cars. In this article, we propose an enhanced multistate joint estimation framework for collaboratively capturing the battery SOC, SOT, and SOP under typical UAM cycling profiles, where the underlying couplings among these states are investigated explicitly. The battery SOC is estimated by combining an adaptive extended Kalman filter with a simple electrical model calibrated in real-time. The SOT estimation is achieved through an adaptive Kalman filter and a control-oriented two-dimensional spatially resolved thermal model, and then the estimation accuracy is further enhanced by a gated recurrent unit network. Based on key electrothermal state estimations, the instantaneous and continuous dynamic power capability assessments are fulfilled considering multiple operational constraints. A temperature-constrained peak power assessment method, with the electrical parameters updated online, enables more accurate and reliable SOP estimation. The influence of battery SOT on peak power assessments is thoroughly investigated. The proposed estimation framework is validated against the experiments under various typical UAM profiles and ambient temperatures, demonstrating satisfactory accuracy and resilience.


  • Open Access

    Review of: "Neuro-Fuzzy-Based Adaptive Control for Autonomous Drone Flight"

    by Arash Khalatabrisoltani

    This research suggests the creation, advancement, and utilization of a smart adaptive hybrid controller for the purpose of managing and maintaining stability of the drone. The LQR produces the training data for ANFIS in the presence of white-noise...

  • Energy Management in Plug-In Hybrid Electric Vehicles: Preheating the Battery Packs in Low-Temperature Driving Scenarios

    by Jie Han, Arash Khalatbarisoltani, Yalian Yang, Xiaosong Hu

    Plug-in hybrid electric vehicles (PHEVs) with large battery packs have significant advantages in improving fuel efficiency and lowering harmful emissions. However, battery charging and discharging performance degrades dramatically at low temperatures, resulting in increasing vehicle operating expenses, which hinders the deployment of PHEVs in severe cold regions. To address this challenge, this paper proposes an energy management strategy (EMS) that combines a battery preheating strategy to preheat the battery to a battery-friendly temperature before vehicle operation. This study provides three specific contributions. First, a high-precision electro-thermal-aging coupled model for a wide temperature range is developed, considering the effect of temperature on the battery’s available capacity. Second, the grid-and battery-powered preheating strategies are established using a flexible polyimide heating film to preheat the batteries. Finally, the particle swarm optimization (PSO) algorithm is utilized to determine the preheating time, while Pontryagin’s minimum principle (PMP) is employed to solve the multi-objective energy management problem. The efficacy of the proposed method in low-temperature driving scenarios is validated, and the link between preheating needs, cost savings, driving mileage, and changes in the price of energy carriers is also explored. Simulation results indicate that at a $-$ 20 $^{\circ}$ C ambient temperature, grid-and battery-powered preheating solutions could cut energy usage by 48.30% and 44.89%, respectively, compared to the non-preheating option.


  • Top Cited Papers

    Energy Management Strategies for Fuel Cell Vehicles: A Comprehensive Review of the Latest Progress in Modeling, Strategies, and Future Prospects

    by Arash Khalatbarisoltani, Haitao Zhou, Xiaolin Tang, Mohsen Kandidayeni, Loïc Boulon, Xiaosong Hu

    Fuel cell vehicles (FCVs) are considered a promising solution for reducing emissions caused by the transportation sector. An energy management strategy (EMS) is undeniably essential in increasing hydrogen economy, component lifetime, and driving range. While the existing EMSs provide a range of performance levels, they suffer from significant shortcomings in robustness, durability, and adaptability, which prohibit the FCV from reaching its full potential in the vehicle industry. After introducing the fundamental EMS problem, this review article provides a detailed description of the FCV powertrain system modeling, including typical modeling, degradation modeling, and thermal modeling, for designing an EMS. Subsequently, an in-depth analysis of various EMS evolutions, including rule-based and optimization-based, is carried out, along with a thorough review of the recent advances. Unlike similar studies, this paper mainly highlights the significance of the latest contributions, such as advanced control theories, optimization algorithms, artificial intelligence (AI), and multi-stack fuel cell systems (MFCSs). Afterward, the verification methods of EMSs are classified and summarized. Ultimately, this work illuminates future research directions and prospects from multi-disciplinary standpoints for the first time. The overarching goal of this work is to stimulate more innovative thoughts and solutions for improving the operational performance, efficiency, and safety of FCV powertrains.