AI-powered, Smart, and Sustainable EV/e-bike Charging

With the increasing popularity of electric vehicles/bikes (EV/e-bikes), the demand for their efficient and sustainable charging stations is more critical than ever. This PhD project aims to develop an integrated system that not only monitors and manages the operation of EV/e-bike charging stations with energy supply from solar energy, but also ensures their safety and sustainability. The project brings together cutting-edge technologies such as remote monitoring, generative AI, machine learning, and eco-accounting to enhance the efficiency and sustainability of e-bike charging stations. To achieve this goal, the candidate is expected to conduct the following, or some of the following subject to the candidate’s background:

(1) Intelligent remote energy monitoring. Develop a system to monitor and manage the working condition of EV/e-bike charging stations distributed across multiple locations. This involves real-time tracking the electrical energy generated by solar panels, the energy stored in battery power storage systems, and the energy utilised to charge EV, e-bikes or e-scooters.

(2) AI-powered fault detection and diagnostics. Utilise advanced Large Language Models (LLMs) to analyse and diagnose working status of the charging stations and identify potential issues before they are exposed. This research will focus on battery’s state of health, electric energy flow patterns, and fault records, while establishing reliable communication channels between IoT devices, AI processing modules, and data repository.

(3) Predictive maintenance through machine learning. Build machine learning models that analyse past and current data to predict when batteries degrade or fail. These predictions will enable operators to schedule maintenance, reduce downtime, and extend the lifespan of batteries.

(4) Environmental impact assessment. Conduct the comprehensive evaluation of the environmental impact of EV/e-bike charging stations. The life cycle analysis (LCA) method ‘Product Environment Footprint (PEF)’ will be utilised to assess the sustainability of the charging station and related components/products such as the batteries used to store the electricity obtained from the solar panels.

This PhD research is part of a project supported by the European Commission’s Horizon Europe programme.

Supervisors

Dr Wenjie Peng - wenjie.peng@ntu.ac.uk

Professor Daizhong Su - daizhong.su@ntu.ac.uk