PhD in Thermal Route Optimization of Predictive Controls to Improve BEV Efficiency Using AI & ML

Funding Source: Industrial CASE (iCASE)

Sponsor Company: JLR

Start Date: October 2024

Course: MPhil/PhD

Project Page – Centre

Project Overview

Route information has significantly improved the optimization of hybrid vehicle propulsion by determining the most efficient power source for different parts of a journey. It's commonly used for eco-coaching by influencing driving behaviour for better fuel efficiency. However, the potential for leveraging route data to optimize energy consumption in Battery Electric Vehicles (BEVs) has been less explored. This project introduces an innovative approach to enhance BEV Thermal Management using route-specific data, incorporating factors like vehicle speed, V2X, traffic, and weather details.

This project aims to address the following challenges:

• Utilizing Route Information & e-Horizon Integration: Exploring methods to optimize thermal management system (improving range, efficiency, and passenger comfort).
• Applying Artificial Intelligence & Machine Learning: Investigating the use of AI and ML techniques to learn and adapt optimal settings for thermal management control systems based on varying route conditions.
• Implementing Hierarchical Control: Developing and implementing hierarchical control strategies for multi-level thermal management systems to effectively regulate temperature and energy usage.

Essential and Desirable Student background Criteria

• Background: engineering
• Essential knowledge - skills – experience: analytical skills, ability to demonstrate good knowledge in system modelling – simulation, control theories and applications with evidence
• Desirable knowledge - skills – experience: electrification technology,  knowledge and experience in automotive/transport sectors, energy storages (battery), advanced control techniques (optimisation / adaptive / robust / intelligent control)

Funding and Eligibility

Industrial CASE (iCASE) funding is primarily for Home UK candidates but international candidates are also welcome.

Key Information

Funding Duration: 4 Years

Supervisors: Truong Dinh, Kaibo Li and Andrew McGordon

Eligibility: Home UK candidates but international candidates are also welcome

Industrial Supervisor: Rhys Comissiong

Research Group: Energy Applications Group

Subject Areas

• Artificial Intelligence
• Machine Learning
• Automotive Engineering
• Control Systems
• Electrical Engineering
• Energy Technologies
• System Engineering
• Engineering Mathematics
• Mathematical Modelling

Route information has significantly improved the optimization of hybrid vehicle propulsion by determining the most efficient power source for different parts of a journey. It's commonly used for eco-coaching by influencing driving behaviour for better fuel efficiency. However, the potential for leveraging route data to optimize energy consumption in Battery Electric Vehicles (BEVs) has been less explored. This project introduces an innovative approach to enhance BEV Thermal Management using route-specific data, incorporating factors like vehicle speed, V2X, traffic, and weather details.

This project aims to address the following challenges:

• Utilizing Route Information & e-Horizon Integration: Exploring methods to optimize thermal management system (improving range, efficiency, and passenger comfort).
• Applying Artificial Intelligence & Machine Learning: Investigating the use of AI and ML techniques to learn and adapt optimal settings for thermal management control systems based on varying route conditions.
• Implementing Hierarchical Control: Developing and implementing hierarchical control strategies for multi-level thermal management systems to effectively regulate temperature and energy usage.