<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-07-08T08:44:08Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/B5431985-3865-47C4-8549-638BCF052325" ns1:id="B5431985-3865-47C4-8549-638BCF052325"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/599CB4AE-BA88-4DEC-9F41-3C135C46B316" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/53EC4245-8A30-477B-87FD-F3D3006BE549" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/53EC4245-8A30-477B-87FD-F3D3006BE549" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/C0F8BC21-FCC8-4252-B82C-63DFAE6678A7" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/7EB8D798-FAAB-490A-B4CD-90630D10CC22" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/6907157C-1956-4741-9A6B-0DE2538DC14E" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/2B11B2B9-7613-4C95-BCE4-B924F41AE734" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-03-30T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/C141BF1F-7C36-4B45-BB13-77558FFF53F4" ns1:rel="FUND" ns1:start="2025-08-31T23:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10158631</ns2:identifier></ns2:identifiers><ns2:title>Project AirTwin: AI Control, Weather Routing &amp;amp; Digital Twin Systems for Optimal Wind-Assisted Ship Performance</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Collaborative R&amp;D</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>UK company GT Green Technologies (GT), founded in 2021, are wind-assisted ship propulsion (WASP) technology experts offering turn-key wind propulsion system to the maritime industry to significantly reduce fuel consumption and greenhouse gas (GHG) emissions for retrofit and new-build vessels. In collaboration with The University of Bath (UoB) and end-user Carisbrooke Shipping. This project will advance the self-learning control system from the previous Smart Shipping project 10128007 Self-Learning Wing Trim Optimisation for Airwing Wind Propulsion System; Integrate weather routing software using AirWing polar data, and automate propeller pitch adjustments to maintain safe vessel speed when AirWing is active.

AirWing is a rigid wing sail which utilises patented boundary layer control manipulation to achieve larger thrust output than current state-of-the-art WASP systems, for a smaller stowed deck footprint. The technology enables vessels with limited available deck space to carry wind- powered solutions for the first time. AirWing's superior performance relies on innovative airflow manipulation around the wing, achieved by controlling internal fan power, angle-of-attack, and wing camber. Implementing an adaptive control system to optimise trim for real-time wind conditions could abate ~750k MtCO2 per annum from AirWing installations by 2035 based on our conservative sales assumptions. Further improvements are possible with Reinforcement Learning, which adapts to current conditions and predicts changes. This project builds on a successful CMDC4 demonstration of AirWing's maximised thrust system.

The consortium will explore system modelling and adaptive, reinforced learning control, paving the way for deployment on the first AirWing unit, recently installed on a 130-metre UK-owned cargo vessel operated by Carisbrooke Shipping. A multidisciplinary team---including GT's engineering team (lead), University of Bath experts, and Carisbrooke Shipping---will ensure real-world relevance and end-user engagement. Bureau Veritas UK (BV) and the DfT will also participate to ensure compliance with AI regulations for vessels. By leveraging Reinforcement Learning (RL) trim control, the project aims to drive job creation and economic growth in the UK maritime sector, fostering partnerships with AI experts, vessel owners, operators, and supply chains. This collaboration will advance sustainable shipping technologies, significantly cutting greenhouse gas emissions and improving air quality. A detailed, costed plan will be prepared for deployment on a Carisbrooke vessel in 2025, followed by commercialisation of future AirWing installations. The plan will outline technical approaches, objectives, business case, emissions reductions, economic impact, and target market segments.</ns2:abstractText></ns2:project>