AI Adoption Case Study: AVEVA's work with Drax and SUEZ on AI driven predictive maintenance
techUK’s AI adoption collection of case studies showcases examples of how organisations are Putting AI into Action, either through the adoption of AI models within their orgnaisations, or by developing AI tools that can be leveraged by others.
By shining a light on these use cases, techUK hopes to demonstrate examples of best practice from across sectors and from organisations of all sizes.
1. Challenge:
Time series data historians such as AVEVA’s Pi system constantly store the data coming from equipment sensors, organise and contextualise the data and performing checks to ensure data quality. Predictive Analytics, a key AI enabling technology harnesses that data using an easily explainable machine learning anomaly detection model to encode the good operational behaviour of a piece of equipment from the historical sensor data. Once that model is deployed on the live data it is silently watching, twenty four hours a day and seven days a week, for the first hints of when an equipment departing from the good historical envelope. This gives warning, long in advance, and allows Drax and SUEZ to plan, assemble spare parts and schedule maintenance interventions when they will be least impactful to electricity production or waste processing. The solution is configured for Engineers and equipment experts to generate valuable outcomes; not only does it detect anomalies in the data, but it recognises signatures of typical faults, for example a damaged bearing, giving prescriptive advice for Engineers to be able to follow up with the appropriate corrective actions. When an anomaly is caught the system is gives precise citations to show the user which sensors are contributing such that the results of the system are highly accountable and not obscured in an AI ‘black-box’. The system is highly scalable capable of monitoring hundreds or thousands of pieces of critical industrial equipment, but is computationally highly efficient requiring little more than a desktop computer to run.
2. Solution:
Time series data historians such as AVEVA’s Pi system constantly store the data coming from equipment sensors, organise and contextualise the data and performing checks to ensure data quality. Predictive Analytics, a key AI enabling technology harnesses that data using an easily explainable machine learning anomaly detection model to encode the good operational behaviour of a piece of equipment from the historical sensor data. Once that model is deployed on the live data it is silently watching, twenty four hours a day and seven days a week, for the first hints of when an equipment departing from the good historical envelope. This gives warning, long in advance, and allows Drax and SUEZ to plan, assemble spare parts and schedule maintenance interventions when they will be least impactful to electricity production or waste processing. The solution is configured for Engineers and equipment experts to generate valuable outcomes; not only does it detect anomalies in the data, but it recognises signatures of typical faults, for example a damaged bearing, giving prescriptive advice for Engineers to be able to follow up with the appropriate corrective actions. When an anomaly is caught the system is gives precise citations to show the user which sensors are contributing such that the results of the system are highly accountable and not obscured in an AI ‘black-box’. The system is highly scalable capable of monitoring hundreds or thousands of pieces of critical industrial equipment, but is computationally highly efficient requiring little more than a desktop computer to run.
3. Impact:
From the first implementation of the software both Drax and SUEZ started to detect issues with their equipment.
Drax found a generator transformer gas in oil measurement increasing indicative of a serious fault. A similar transformer had previously failed causing an unplanned stop of the unit for more than four weeks. With the early detection provided by Predictive Analytics Drax were able to operate the transformer differently, perform a short remedial repair and continue operation until the next major planned stop.
One of SUEZ steam turbines showed signs of a large axial movement of the rotor; a tell-tale sign of a balance-piston seal failure. When the machine was later opened, the inspection verified that the seal was indeed severely damaged. Although this case didn’t pose an immediate risk to operation, the early detection allowed better preparation for the next planned overhaul for the risk that more work would be required to remediate.
Usman Ikhlaq
Usman joined techUK in January 2024 as Programme Manager for Artificial Intelligence.
techUK - Putting AI into Action
Our Putting AI into Action campaign serves as a one stop shop for showcasing the opportunities and benefits of AI adoption across four strategic sectors - Health and Social Care, Cyber, Central Government and Transport.
techUK is coordinating a calendar of events, reports, and insights to demonstrate some of the most significant opportunities for AI adoption in 2024, as well as working with key stakeholders to identify and address current barriers to adoption.
Visit our AI Adoption Hub to learn more, or find our latest activity below.
Upcoming AI Adoption events
Latest news and insights
Get our tech and innovation insights straight to your inbox
Sign-up to get the latest updates and opportunities from our Technology and Innovation and AI programmes.
Contact the team
Usman Ikhlaq
Usman Ikhlaq
Usman joined techUK in January 2024 as Programme Manager for Artificial Intelligence.
His role is to help techUK members of all sizes and across all sectors to adopt AI at scale. This includes identifying the barriers to adoption, considering solutions and how best to maximise AI's potential.
Prior to joining techUK, Usman worked as a policy, government affairs and public affairs professional in the advertising sector. He has also worked in sales and marketing and FinTech.
Usman is a graduate of the London School of Economics and Political Science (MSc), BPP Law School (GDL and LLB) and Queen Mary University of London (BA).
When he isn’t working, Usman enjoys spending time with his family and friends. He also has a keen interest in running, reading and travelling.
Learn more about our AI Adoption campaign:
