Target of this research project is the development of an expert system capable of controlling a CAD-Software for medical prosthesis manufacturing. The usage of an expert system on one hand increases the availability of the knowledge needed to build such a medical prosthesis and on the other hand increases the reproducibility and consistency of the resulting prosthesis by reducing the human interaction.

The project is divided in three subprojects:

1. Acquisition of the available knowledge and implementation of the initial knowledge base.

2. Evaluation and correction of the initial knowledge base.

3. Applying machine learning techniques to further improve and update the expert system.

Subprojects 1 and 2 are complete. In subproject 3 currently supervised learning techniques like genetic programming as well as unsupervised learning techniques like data clustering are researched and evaluated.