Integrating AI into Computer Aided Design (CAx)
Artificial intelligence has the potential to fundamentally change the way we work and operate. CLAAS GmbH & Co. KGaA, an international manufacturer of agricultural machinery, has recognized this potential and is testing a special use case in the AI marketplace for the integration of AI into Computer Aided Design (CAx).
Against the backdrop of constantly increasing product complexity and number of variants, the reuse of components offers an important opportunity to save manufacturing, development and storage costs. However, the search for identical and similar parts is a great challenge, as these parts have often been developed in a project-specific context and have therefore not been considered for reuse as standard parts. Furthermore, non-variable parts often cannot be found because the master data is not correctly maintained. If “too many” similar parts have been found, human intelligence is needed today, i.e. also a lot of time to reduce the search results to the usable level.
For this reason, the “AI Marketplace” project is designing and prototyping an intelligent common parts management system. Starting from a feature extraction, CAD models are first classified according to their geometry, later also with regard to function, and missing master data or further meta data is added. The resulting knowledge database enables the use of AI procedures such as Case Based Reasoning (CBR) and the identification of common parts based on geometry and with regard to their functionality and design context. In accordance with the CBR cycle, the starting problem must first be described, which points to similar problems. These can be reused, but also adapted or rejected. The knowledge about reuse, adaptation or rejection is used to improve the performance of the tool.
The aim is to improve the search for similar parts in order to reduce the number of parts in the inventory database in the medium term and to keep it under control. For this purpose, potential common parts or evolutionary steps could, for example, be suggested to the developer already during the design phase, which also reduces the effort of the design.