Recipient organisationSustainable Pipeline Systems Limited
Funding£30K
PeriodJun 2025 — Dec 2025
In plain English
AI plain-English summary
A hydrogen pipeline in Aberdeen will use machine learning to spot and classify its own structural defects in real time, before they become leaks or ruptures. Traditional pipeline inspections require shutdowns, manual checks, and costly repairs. The Mobile Automated Spiral Intelligent Pipeline (MASiP) already cuts construction carbon emissions by 70% and embeds fibre optic sensors that continuously monitor pressure, strain, and temperature. What it lacks is the ability to interpret those signals automatically—to distinguish a harmless vibration from a growing crack, and to rank defects by severity. This project, run by Sustainable Pipeline Systems Ltd with Swansea University’s ASTUTE Centre, will train machine learning models on the sensor data. The tools will classify threats, quantify their seriousness, and recommend when to intervene. That shifts pipeline maintenance from reactive, schedule-based repairs to predictive, condition-based action. If successful, the system could keep hydrogen flowing through critical energy infrastructure with less downtime and lower cost. It supports the UK’s hydrogen strategy and helps decarbonise heavy industry and transport—sectors that are hard to electrify. The technology is not about discovery; it is about making a clean-energy pipeline network safer and more reliable at scale.
View original technical description
Sustainable Pipeline Systems Ltd (SPS), based in Aberdeen, specialises in cutting-edge pipeline solutions designed to support the transition to clean energy. This project focuses on advancing SPS's flagship product, the Mobile Automated Spiral Intelligent Pipeline (MASiP), a next-generation pipeline technology engineered for hydrogen transport. MASiP features an innovative composite structure combined with helically wound fibre optic sensors, enabling real-time digital monitoring of pressure, strain, and temperature. Its unique design reduces construction-related carbon emissions by 70% compared to traditional pipelines, supporting global efforts to achieve Net Zero by 2050\. In collaboration with the ASTUTE Centre of Excellence at Swansea University, this project builds on a successful feasibility study. ASTUTE will provide expertise in advanced machine learning (ML) techniques to enhance MASiP's operational capabilities. Together, the partners aim to develop ML-tools that classify threats, assess defect severity, and provide real-time decision-making support, ensuring pipeline safety and reliability. The project aligns with the UK's hydrogen strategy and Net Zero goals, supporting the development of critical infrastructure for clean hydrogen transport. By improving efficiency, reducing downtime, and enabling cost-effective monitoring, MASiP offers a scalable, sustainable solution to decarbonise energy-intensive sectors such as heavy industry and transport. This collaboration positions MASiP as a key enabler in the global transition to a low-carbon future. The project seeks to develop a key enabling tool for energy pipeline networks by providing and interpreting in real time optical fibre signal patters and quantifying them in terms of severity so that network safety can be improved and maintenance and repair actions can be more efficient and more preventative.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know