Sustainability Tracking and Optimisation Tool In Commodity Components

STOTIC's vision is to create sustainable and efficient production networks that use advanced technologies such as machine learning and deep learning to minimise environmental impact and optimise the use of resources.

Electric microswitches have a wide range of applications. For example, they ensure that ventilators in hospitals function reliably and that wind turbines are protected in the event of overload. A single microswitch can consist of up to 27 components, which are manufactured worldwide in several steps within complex production networks. These production networks are generally focussed on monetary terms and take less account of the resulting emissions and the resource and energy efficiency in the supply chain.

In this context, the STOTIC project aims to develop a digital sustainability tracking and optimisation tool to make location-based production decisions and supply decisions for components based on sustainability information. Machine learning and deep learning will be used to make predictions about the sustainability of production supply chains. In addition, the AI-supported tool will enable the customisation and configuration of supply chains.

As part of STOTIC, the TMDT is responsible for the design, development and evaluation of the learning methods for assessing the sustainability of configurable supply chains. In particular, the TMDT makes a major contribution to modelling, taking into account modern neural network architectures and their applicability for processing sustainability information.

Further information can be found here(stotic.uni-wuppertal.de) on the official STOTIC website.