Battery and ultra-capacitor (UCp) combination forms the multiple energy storage model (MESM), which provides the optimum benefit to hybrid electric vehicles/electric vehicles (EVs) for its successful operation. The inherent high power density characteristic of UCp is used during starting and momentary periods of EV. On the other hand, the battery provides the average power to the EV, during the steady-state periods. The development of the supervisory energy management strategy, corresponding to the EV dynamics is one of the key issues. In this paper, a new control technique is proposed to attain a smooth and automatic transition between energy sources in MESM according to the EV requirement. A speed condition-based (SCB) controller is designed with four individual math functions, corresponding to the speed of the electric motor (EM). A combination of the SCB controller and the artificial neural network (ANN) formed a SCBANN hybrid controller (SCBANNHC). To identify the proper power split between energy sources, the proposed SCBANNHC is applied to the main circuit in four different case studies corresponding to the load on the EM. Four different case study circuit models are realized in the MATLAB/Simulink environment along with a prototype hardware model for validation of the proposed control technique.

中文翻译：

---

用一种新的控制技术在电动汽车应用中实现原型硬件模型

电池和超级电容器 (UCp) 的组合形成了多储能模型 (MESM)，它为混合动力电动汽车/电动汽车 (EV) 的成功运行提供了最佳效益。UCp 固有的高功率密度特性用于 EV 的启动和瞬时期间。另一方面，在稳态期间，电池为 EV 提供平均功率。与电动汽车动态相对应的监管能源管理策略的发展是关键问题之一。在本文中，提出了一种新的控制技术，以根据 EV 要求在 MESM 中实现能源之间的平滑和自动转换。基于速度条件 (SCB) 的控制器设计有四个独立的数学函数，对应于电动机 (EM) 的速度。SCB 控制器和人工神经网络 (ANN) 的组合形成了 SCBANN 混合控制器 (SCBANNHC)。为了确定能源之间的适当功率分配，建议的 SCBANNHC 在四个不同的案例研究中应用于主电路，对应于 EM 上的负载。在 MATLAB/Simulink 环境中实现了四种不同的案例研究电路模型以及用于验证所提出的控制技术的原型硬件模型。