Resource-efficient timber construction using single-material wall elements that can be manufactured automatically, based on a fully digital design and manufacturing methodology
Project duration: 03/2024 – 07/2026
This research project focuses on innovative, resource-efficient timber construction in the form of single-material wall elements that can be manufactured automatically. These are tailored to individual requirements and designed using a fully digital planning and manufacturing methodology, with a focus on load-optimised geometric arrangements. The project thus combines innovative timber construction methods with modern machine learning (ML) technologies. The aim of the research project is to replace the previously predominant manual, iterative calculation processes involved in the design of individual timber panels with an ML-supported design tool. The project is being tested using the example of the Interlocking Dowel System (IDS), an innovative, single-material wall construction method, in which load-bearing, flat elements made of wood-based panels are joined using wooden dowels arranged at an angle without the need for additional metal fasteners.
The project aims to develop approaches for using ML to infer suitable partial solutions and assemble these into the desired load-responsive structures. In doing so, the ML-based methods must interact appropriately with CAD software and parametric geometric models. The automatically assembled component geometries to be realised must each meet the requirements of minimising material usage whilst being capable of withstanding the required mechanical loads. The components to be produced as part of the project will be fabricated using robotic manufacturing units at the Timber Construction Research Centre.
Project images
Contact
Prof. Dr.-Ing. Mirco Fuchs
Chair of Computer Vision and Machine Learning
Telephone: +49 (0)341 3076 3104
Email: mirco(dot)fuchs(at)htwk-leipzig.de
Projektteam







