Autonomous anomaly detection and self-healing in a smart test environment

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 already conflicts with a transition to renewable generation. 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.

To address this challenge this project will undertake three broad methodological approaches. First, an exploratory analysis of what constitutes an anomaly in different contexts; this will include qualitative studies regarding what data quality is and whether it is consistent across applications. Second, a methodological exploration using historic or synthetic data; this will explore different anomaly detection approaches, be it statistical or machine learning (including but not limited to classification, clustering and fuzzy logic), and test these on existing or artificially altered data. Finally, a specific anomaly detection approach will be refined and tested iteratively on real testbed data.

In practise, the outputs of this project will facilitate more effective testing of automotive technology on a testbed by reducing redundant tests and subsequently improving the quality of data being used for virtual models and simulations. More effective testing will have two key impacts, first, allowing new, low-carbon technologies to be developed and deployed to the consumer faster, thus aiding the transition to a net zero society. Second, it will reduce the energy intensity of the testing and development phase of mobility options due to minimal wasted tests and more effective virtual models, which will also support decarbonisation targets through reduced energy demand.

Impact Summary

This proposal has been developed from the ground up to guarantee the highest level of impact. The two principal routes towards impact are via the graduates that we train and by the embedding of the research that is undertaken into commercial activity. The impact will have a significant commercial value through addressing skills requirements and providing technical solutions for the automotive industry - a key sector for the UK economy.

The graduates that emerge from our CDT (at least 84 people) will be transformative in two distinct ways. The first is a technical route and the second is cultural.

In a technical role, their deep subject matter expertise across all of the key topics needed as the industry transitions to a more sustainable future. This expertise is made much more accessible and applicable by their broad understanding of the engineering and commercial context in which they work. They will have all of the right competencies to ensure that they can achieve a very significant contribution to technologies and processes within the sector from the start of their careers, an impact that will grow over time. Importantly, this CDT is producing graduates in a highly skilled sector of the economy, leading to jobs that are £50,000 more productive per employee than average (i.e. more GVA). These graduates are in demand, as there are a lack of highly skilled engineers to undertake specialist automotive propulsion research and fill the estimated 5,000 job vacancies in the UK due to these skills shortages. Ultimately, the CDT will create a highly specialised and productive talent pipeline for the UK economy.

The route to impact through cultural change is perhaps of even more significance in the long term. Our cohort will be highly diverse, an outcome driven by our wide catchment in terms of academic background, giving them a 'diversity edge'. The cultural change that is enabled by this powerful cohort will have a profound impact, facilitating a move away from 'business as usual'.

The research outputs of the CDT will have impact in two important fields - the products produced and processes used within the indsutry. The academic team leading and operating this CDT have a long track record of generating impact through the application of their research outputs to industrially relevant problems. This understanding is embodied in the design of our CDT and has already begun in the definition of the training programmes and research themes that will meet the future needs of our industry and international partners. Exchange of people is the surest way to achieve lasting and deep exchange of expertise and ideas. The students will undertake placements at the collaborating companies and will lead to employment of the graduates in partner companies.

The CDT is an integral part of the IAAPS initiative. The IAAPS Business Case highlights the need to develop and train suitably skilled and qualified engineers in order to achieve, over the first five years of IAAPS' operations, an additional £70 million research and innovation expenditure, creating an additional turnover of £800 million for the automotive sector, £221 million in GVA and 1,900 new highly productive jobs.

The CDT is designed to deliver transformational impact for our industrial partners and the automotive sector in general. The impact is wider than this, since the products and services that our partners produce have a fundamental part to play in the way we organise our lives in a modern society. The impact on the developing world is even more profound. The rush to mobility across the developing world, the increasing spending power of a growing global middle class, the move to more urban living and the increasingly urgent threat of climate change combine to make the impact of the work we do directly relevant to more people than ever before. This CDT can help change the world by effecting the change that needs to happen in our industry.