In recent decades, the demands placed on engineering and the creative development of designs have changed significantly: Instead of constantly reinventing the wheel, it is now necessary to use the knowledge already gained from existing mechanical designs and to transfer known solutions from one application to another in a meaningful way. This is particularly important in view of the increasing number of individual designs in which existing designs are precisely tailored to the individual needs of the customer.
An absolute prerequisite for this is complete knowledge of the set of parts used in the company. It is not only a question of knowing the existence of a component, but also of the designation, with which the part can be found in the part database, as well as its appearance and the correct use or configuration. However, the enormous volume of available purchased parts or company-specific parts makes it impossible for engineers to keep a complete overview. Young engineers, in particular, lack years of professional experience and the opportunity to innovatively combine acquired knowledge.
The aim of the KOGNIA project is therefore to automatically prepare the knowledge of experienced mechanical designers from past drafts for future designs and make it available. The originally personal expertise acquired over many years is bundled in a system, processed and made available to all employees of the company. Machine learning allows to identify patterns and laws, such as commonly used or combined parts, in existing and newly created designs. Based on this knowledge, engineers can automatically be presented with useful suggestions for the next required purchased and own parts during the design phase, thus making generic and company-specific engineering knowledge more easily accessible. Not only junior engineers, whose learning phase is shortened, should benefit from this system, but also experienced designers due to the acquisition or transfer of knowledge from other experienced colleagues.
AI-based Recommender System for CAD
Prof. Dr. Alexander Schiendorfer, former head of project
Institute for Software & Systems Engineering
The Institute for Software & Systems Engineering (ISSE), directed by Prof. Dr. Wolfgang Reif, is a scientific institution within the Faculty of Applied Computer Science of the University of Augsburg. In research, the institute supports both fundamental and application-oriented research in all areas of software and systems engineering. In teaching, the institute facilitates the further development of the faculty's and university's relevant course offerings.