Smart multioutput fast charger for electric vehicles using deep learning controllers

1. Smart Multi-output DC Fast Charger (DCFC) Development: • Introduced a smart multi-output DC fast charger (DCFC) designed to significantly improve the charging efficiency of electric vehicle (EV) batteries. 2. Leveraging Deep Learning Techniques: • Implemented advanced deep learning (DL) techniques to optimize the charging process, enhancing the capabilities of the fast charger. • Employed two types of deep learning controllers (DLCs): a custom neural (CN) network and a neural net fitting (NNF). 3. Comprehensive System Architecture: • Integrated a front-end converter (FEC) to convert grid AC voltage and current into DC, managed by three deep learning controllers (DLCs). • Utilized a high-frequency inverter (HFI), a high-frequency isolation transformer (HFIT), and a diode bridge rectifier (DBR) for efficient AC-DC conversion. • Employed HFI and HFIT to achieve efficient energy conversion and isolation. • The use of a DBR further improved the reliability and performance of the charging system. 4. Enhanced Charger Output Performance: • The inverter's gate drives, regulated by DLCs, ensured optimal output performance of the charger. • The system achieved a ripple-free, smooth DC bus voltage, current, and battery charging current, crucial for efficient and safe charging. • The CN network-based DCFC demonstrated superior performance compared to the NNF-based controller. • Key improvements included minimized settling time, reduced overshoot, and lower harmonic distortion. 5. Efficiency in Reducing Charging Time: • Addressed the critical issue of long charging times for EV batteries, aiming to significantly reduce the overall time required for battery charging. • Enhanced charging efficiency contributed to extending the driving range of EVs by optimizing battery capacity utilization. • Thoroughly evaluated the performance of the DLC-based DCFC using MATLAB & Simulink software. The increasing adoption of electric vehicles has intensified the demand for efficient, high-performance charging solutions to address long charging times and range limitations. This paper presents the development of a smart multioutput Direct-current fast charger leveraging deep learning techniques to enhance electric vehicle battery charging capabilities. The proposed Direct-current fast charger integrates a front-end converter to transform grid AC voltage and current into DC, managed by three deep learning controllers. The charger incorporates a high-frequency inverter, a high-frequency isolation transformer, and a diode bridge rectifier for AC-DC conversion. The inverter gate drive system is optimized by using a deep learning controller to regulate output performance. Two types of deep learning controllers such as custom neural network and neural net fitting are implemented to minimize settling time, overshoot, and harmonics, ensuring ripple-free, smooth DC bus voltage, current, and battery charging current. Comparative analysis reveals that the custom neural network-based Direct-current fast charger is superior to the neural net fitting in terms of settling time, overshoot, complexity, accuracy, and efficiency. MATLAB & Simulink simulations validate the effectiveness of the proposed system, demonstrating its potential for improving electric vehicle charging performance. Fig. Graphical Abstract of Deep Learning Controller-based DC Fast Charger