Minh Cao Ta

This article addresses electric vehicles (EVs) equipped with multiagent systems that integrate multiple motors and energy sources. The objective is to develop a novel energy management strategy (EMS) based on a unified adaptive network-based fuzzy inference system (ANFIS) framework. The unified framework simultaneously optimizes torque distribution regression between two motors and the driving mode classification in the current control between energy sources. By combining the learning of neural networks (NNs) with the interpretability of fuzzy logic, the ANFIS-based EMS effectively balances energy optimization with real-time capability. Experimental hardware-in-the-loop (HIL) validation results demonstrate significant improvements in energy efficiency and a reduction in battery stress. The article contributes to the broader adoption of learning-driven EMS designs in EV applications, particularly for multimotor multisource configurations.

Imagine a freight truck crossing a continent not with one giant hydrogen fuel cell (FC), but with a team of smaller stacks, each quietly playing its part. Some work harder on uphill stretches, others rest when temperatures rise, and a few step in when a teammate begins to weaken. This is the vision behind multistack FC hybrid electric vehicles (MFCHEVs): modular systems in which several low-power FC stacks operate together with a battery to deliver traction power. Such architectures promise higher efficiency, improved durability, and enhanced fault tolerance. However, these benefits can only be realized through artificial intelligent (AI) energy management and effective coordination; otherwise, stacks may degrade unevenly, waste hydrogen, or fail prematurely.

Multi-motor electric vehicles (MMEVs) present complex challenges for control and optimization due to the distribution of control actions and state variables across multiple subsystems and hierarchical levels. Although electric vehicle (EV) modeling has been widely studied, accurately capturing and optimizing the longitudinal energy efficiency and dynamic performance of MMEVs remains a significant challenge. This complexity is further increased by the presence of different motor types, such as induction motors (IMs) and permanent magnet synchronous motors (PMSMs), and various mechanical configurations in all-wheel drive systems. To address these issues, this paper proposes a global-local modeling framework that extends the Energetic Macroscopic Representation (EMR) methodology. The framework integrates detailed models of the electrical drive system with comprehensive mechanical subsystem modeling, including gearbox, differential, half-shafts, wheels, and tires. A global input power model links local control actions and state variables to overall energy flow, supporting a unified approach to longitudinal motion control and energy optimization. In contrast to conventional EMR-based models, the proposed framework explicitly incorporates driveline and tire dynamics, which significantly affect energy consumption due to drivetrain losses and tire slip. The model is evaluated through two scenarios that assess the effects of drivetrain modeling and force distribution strategies. The results show improved control system performance and enhanced energy efficiency, supporting future advancements in longitudinal dynamics modeling for MMEV.

This paper introduces a novel approach in electric vehicle technology by combining dual-motor coupling with a hybrid energy storage system (HESS) using batteries and supercapacitors. This innovation enhances vehicle performance and prolongs battery life. An energy management strategy (EMS) based on Pontryagin's minimum principle (PMP) is used to optimize power distribution within the HESS. To improve PMP performance, the proposal integrates driving pattern recognition (DPR) and co-state variable ( λ ) control. DPR employs an adaptive network-based fuzzy inference system (ANFIS) for real-time pattern recognition. The process involves creating a sample driving cycle, employing subtractive clustering to establish the original fuzzy inference system (FIS), and fine-tuning FIS parameters through neural network training. λ values are updated based on recognition results to adapt control actions for various driving styles. Real-time simulations on Opal-RT reveal significant improvements compared to EMS without DPR. Battery current root mean square and standard deviation decrease by 11.4% and 29.4%, respectively, during the unknown in advance Federal Test Procedure (FTP) cycle. This adaptable DPR method offers versatility for various EMSs and clarifies the impact of disturbances like supercapacitor size, state of charge variations, and off-road conditions on HESS performance, aiding researchers in designing more efficient systems.

In hybrid energy storage systems (HESS) powered by battery (BAT) and lithium-capacitor (Li-CAP), sizing problems are crucial in optimizing system operation and reducing device costs. This study provides a novel hierarchical sizing technique based on mixed integer nonlinear programming and Pontryagin's minimum principle. With a multi-objective optimal problem, the algorithm allows for determining a series of feasible solutions satisfying given constraints. These constraints include nominal voltage of a source package, nominal current of a cell, and the maximum volume. The proposed algorithm's effectiveness is numerically validated.

The Energetic Macroscopic Representation formalism is more and more used for the modelling and control organization of energy conversion systems. Many applications for electrified vehicles have been developed using this formalism. If different simulation packages have included EMR libraries, there is still no drawing software dedicated to this formalism. To address this limitation, an open-source EMR drawing software is proposed in this paper. This software aims to provide a comprehensive solution for visualizing and organizing EMR models. By offering a user-friendly interface and compatibility with different word processing software, this tool contributes to the advancement and wider adoption of EMR in energy conversion system design and control.

This paper explores the transition from full-scale simulation to reduced-scale hardware-in-the-loop testing using Energetic Macroscopic Representation (EMR) for dual-source off-road electric vehicles. A comprehensive EMR model is developed, incorporating two energy sources (batteries and super capacitors). Full-scale simulation is established for further vehicle performance optimization. Reduced-scale hardware-in-the-loop testing creates a physical prototype, integrated with the EMR simulation platform for real-time interaction. This approach offers cost-effective validation of EMR-based strategies development, evaluating performance and energy management indicators. It enables iterative design improvements and rapid prototyping. Integration of the reduced-scale prototype with EMR simulation software facilitates seamless data exchange and control signal interaction. Simulations on the prototype verify the accuracy and effectiveness of EMR-based strategies. Results are compared with full-scale simulation, establishing the reliability of the EMS model. This transition enables the development and validation of strategies for our off-road electric vehicle, ensuring accurate performance evaluation and optimization. The research demonstrates the potential of EMR as a valuable tool for advanced electric vehicle system design and development.

Electric vehicles (EVs) have been regarded as one of the promising alternatives to zero-emission transportation. New EV registrations have increased as a result of government policies and consumers’ awareness of climate change. Moreover, EV technology is being improved through ongoing research and development efforts. Among these, a powertrain with a combination of two electric motors has been proposed for high driving and efficiency performance. The study presents a comprehensive state-of-the-art review of architectures and energy distribution for a dual-motor equipped with dual-source EV system. In detail, various dual-motor configurations, and energy management strategies (EMSs) used in the literature are investigated and categorized. A comparison of the benefits and drawbacks of existing topologies and the EMSs of hybrid energy storage systems (HESSs) is also discussed. Following that, research gaps have been considered. This study can be used as a reference for researchers who are interested in the design and optimal control of the dual-motor dual-source EVs.

The development of electric vehicles (EVs) has been considered one of the most efficient ways to reduce the carbon footprint of the transportation system. Among battery EV designs, a dual-motor configuration is introduced as a promising solution to improve dynamic performance and energy efficiency. In this study, a novel energy management strategy framework based on an Adaptive Network-based Fuzzy Inference System (ANFIS) is proposed for torque distribution optimization between two different motors. At first, Dynamic Programming (DP) is employed to find global optimization of the torque distribution. After training with the DP-obtained data set, the ANFIS model can execute a torque distribution online. By minimizing the battery energy consumption, the motor torque-speed solution pair is found under representative driving cycles (only three cycles). In addition, the best ANFIS model has been selected using a clustering technique, goodness-of-fit metrics, and sensitivity analysis. This distinguishes the optimization problem in this study from previously published literatures. The simulation results show that over an unknown Urban Dynamometer Driving Schedule (UDDS) cycle, the torque prediction using this ANFIS model achieves 98.3% of the benchmark DP result. As a result, the overall efficiency of the proposed strategy is increased to 73.3%, which is 3.4% higher than that of the rule-based method. Furthermore, the signal hardware-in-the-loop (S-HIL) experiments validate the real-time prediction of the ANFIS-based approach.