Tech Soft 3D HOOPS AI has launched, the first framework purpose-built to unlock AI and machine learning for CAD data, following a successful beta program involving more than 30 companies.
Software vendors and engineers working in PLM, MES, CAM, manufacturing and any other team with complex 3D datasets looking to integrate 3D engineering data into modern machine learning pipelines, can now leverage HOOPS AI to support data preparation and model experimentation – allowing teams to run hundreds or thousands of models simultaneously.
This rapid iteration allows for a smaller team to cut software development cycles from months to weeks. The resultant capabilities teams can create include automated part classification and metadata enrichment, manufacturing feature detection, similarity search and duplicate detection, design reuse and optimisation and more.
New since its limited release, it now includes official support for both Windows and Linux, the latter being particularly important for AI and data-processing pipelines, enabling developers to integrate HOOPS AI more easily into modern ML infrastructure.
Tech Soft 3D says its data translators have processed more CAD data than any other toolkit, with decades of providing CAD data access, performance and accuracy to hundreds of partners, including Ansys, Siemens, Hexagon, Nvidia Omniverse, Unreal Engine and Unity 3D.
Future planned developments include Python Access to expose more CAD data, specifically targeting product manufacturing information (PMI). Tech Soft 3D say that the long-term vision of the product aims to capture the expert engineering knowledge in CAD models and unlock it across teams.
While current examples of HOOPS AI in action are trained on public datasets, the goal is for organisations to train using their own private data, tailoring the machine learning program more closely to their needs.
“The official launch of HOOPS AI marks an important step in Tech Soft 3D leading the effort to bring AI to engineering data. For the first time, developers have a framework designed specifically to make CAD data usable in modern machine learning workflows,” said Tech Soft 3D CTO Gavin Bridgeman.
