Compute Maritime has revealed the results of its UK Government-funded project, GenDSOM, which utilises generative artificial intelligence and additive manufacturing for ship design.
Working alongside a consortium including Siemens Digital Industries Software, Rapid Fusion, HP, BYD Naval Architects, and the University of Southampton, the company has developed a crew transfer vessel (CTV) design for the offshore wind sector that its performance modelling indicates could save 101,671 litres of fuel and 258.7 tonnes of carbon dioxide every year compared with a conventional baseline.
The 32.5-metre twin-hull CTV, designed by BYD Naval Architects to carry 24 offshore wind technicians and four crew, was developed using Compute Maritime’s NeuralShipper AI platform to optimise its hull form. The design is paired with a diesel-electric hybrid propulsion system developed with Siemens Energy.
“When we launched GenDSOM, we set ourselves a clear and deliberately ambitious goal: to prove that generative AI could deliver real, measurable savings in the water, not just faster drawings on a screen,” said Shahroz Khan, CEO of Compute Maritime.
“This is what the future of shipbuilding looks like to us: intelligence at the core of design, delivering efficiency the industry can measure on its fuel bills and its emissions reports.”
In addition to design enhancements, the project hopes to improve maritime manufacturing methodologies. Compute Maritime and Rapid Fusion developed a complete additive-manufacturing toolset that integrates production constraints, such as build volume, support structures, and material behaviour, directly into the NeuralShipper design loop to allow components to be optimised to be printable from the outset rather than requiring post-design rework.
Using this approach, the consortium produced a functional hydrofoil using Apollo, a robotic large-format additive manufacturing (LFAM) system developed by Rapid Fusion that uses high-deposition pellet printing to build large composite and thermoplastic components.
“Truly efficient ship design now depends on smart tools working on both sides of the problem: a revolutionary generative tool to create and explore high-performing hull forms, and advanced simulation to evaluate them with confidence,” said Dmitry Ponkratov, Marine Director at Siemens Digital Industries Software.
“GenDSOM brings these elements into a single loop, so that design, performance and manufacturability evolve together rather than in sequence. Results like these show what becomes possible when generative AI and high-fidelity simulation are combined.”
