• Ellie Smallwood

  • Theme:Digital Systems, Optimisation and Integration
  • Project:Anomaly detection, self-healing, and process evaluation for improved efficiency and data quality in automotive testing environments
  • Supervisor: Richard Burke ,Andrew Barnes
  • Industry Partner: AVL
  • The Gorgon's Head - Bath University Logo


Ellie completed a BSc in Environmental Sciences from the University of Leeds in 2020, gaining an understanding and appreciation for the complexity of environmental, social, and technological systems. From this, an overarching goal of climate change mitigation led her to complete an MSc in Energy Systems and Data Analytics at UCL, within which the connectivity of transport, built environment, and social and political sectors were explored using machine learning techniques on big data, to identify plausible solutions for decarbonisation. Projects completed included investigating the driving factors of micromobility demand, and carrying out an uncertainty analysis on global net zero pathways using clustering for her thesis. Outside of her university work Ellie was also involved in additional research roles, including looking into public responses to carbon taxes, and how demographics can impact this, and also the applicability of digital platforms to inform and engage the public in local policy changes.

It is due to the dynamism of the transportation sector, and the challenge that it poses to reaching net zero targets by 2050, that Ellie chose to pursue this area of study. Her specific research interests revolve around sustainability and efficiency; by utilising machine learning techniques she hopes to identify novel approaches that unlock the potential of technological innovation, policy measures, and behavioural change for large scale decarbonisation.


  • Prior to focussing on the automotive sector, I travelled to South Africa and Mexico to conduct ecological research.
  • I have competed at national level in the equestrian sport Eventing.
  • I have an HGV licence.
  • I can play five instruments, to varying levels.

Anomaly detection, self-healing, and process evaluation for improved efficiency and data quality in automotive testing environments

To achieve net zero by 2050, the IEA have stated that 50% of the technology required is yet to be developed, thus, rapid testing and development in all sectors is required. Increased intensity of testing could however have a significant impact on energy demand, which conflicts with a transition to a renewable energy system. The automotive industry continues to support, and in many instances grow, an already carbon intensive transport sector; despite lulls during the COVID-19 pandemic and increased electric vehicle sales, road transport still equates to around 28% of global carbon emissions. Therefore one area of focus to support the required decarbonisation of the automotive sector, whilst allowing new low-carbon technology to be developed, is associated with increasing the efficiency and efficacy of the testing phase of vehicle technology development.

Physical testing is time consuming due to real-time constraints and complex and technologically delicate systems, and is thus, highly energy intensive. Additionally, human-errors in set up, faulty or mis-calibrated sensors, or unforeseen mechanical failures are often only identified post-test and result in these tests being redundant and needing to be repeated. Virtual testing environments play a role in minimising these tests, allowing simulations to be run earlier in the development process and for more use-cases to be considered. However, if not provided with robust physical data, these models will not be able to accurately simulate hardware responses - they therefore still rely on physical testing for the test data used to adapt and optimise the virtual models. Some physical testing will also still be required for technology to be suitable for market release to account for product variance, unknown effects and simulation inaccuracies.


As the general change of the powertrain development process makes it harder to compensate poor measurement quality by engineering experience, anomaly detection – a method of finding unexpected patterns in data - presents a possible solution to minimise physical testbed time whilst increasing the reliability of real data to feed into virtual simulation models. If applied to a range of powertrain units, be it internal combustion engine, pure electrical drive, fuel cell or hybrid setup, it has the potential to reduce the energy intensity of vehicle testing and development, whilst simultaneously increasing the speed at which low-carbon technologies can be released into the public domain to aid large scale decarbonisation of the transport sector.

© Copyright 2024 AAPS CDT, Centre for Doctoral Training in Advanced Automotive Propulsion Systems at the University of Bath