Aura Centre for Doctoral Training

Background: I graduated with an MEng in Chemical Engineering with Environmental Engineering from the University of Nottingham in 2014. During my degree, I undertook a year-long placement at BP Chemicals followed by a summer placement at Vivergo Fuels. After graduating, I worked as a process engineer for Vivergo Fuels, who make bioethanol and animal feed from wheat. Three years later, I moved into the plastics industry working for a company called Nippon Gohsei who make a copolymer. I have gained a breadth of industrial experience (as well as Chartered status!) and am now looking to gain a depth of knowledge in the Offshore Wind sector.

Research Interests: Industry 4.0. The Internet of Things. Big Data. Machine Learning. Artificial Intelligence. Currently, these are all buzz words used in industry but are yet to have any meaningful contribution (in the majority of cases). There is a potential that utilising data to improve diagnostics will revolutionise manufacturing operation to improve maintenance and operation, but it is essential that the technology is developed with the end goal in mind. I am interested in researching how we can implement these powerful tools within the Offshore Wind Industry so that we can fully comprehend the benefits.

Why you applied for the Aura CDT: At the beginning of my career I wanted to work in a green industry. Starting off in the biofuel industry, I was shocked by some of the inefficiencies so I moved to an established plastic industry. There were a lot of unexpected parallels between the industries but I had to ask myself the question: Is it better to make something sustainable less efficiently or something unsustainable efficiently? In order to provide a more sustainable and efficient future for green energy I decided that research is key. Our energy consumption is ever increasing and therefore is of paramount importance that we get this sector right.

PhD Research:

My project seeks to advance how the collected data from wind turbines is processed using machine learning algorithms. The health state of individual turbines and the wind farm as a whole could then be assessed in near real-time with improved accuracy. This improvement to structural health monitoring could maximise the performance of current turbines and be used in the design of future turbines.

Find out more about this research

Contact: sarah.bee-2020@hull.ac.uk LinkedIn: https://www.linkedin.com/in/scbee/ Personal website: sarahbee.dev