Bridging the gap: A conceptual framework for developing and operating hybrid modeled digital twins under limited model input conditions

Hybrid modeled digital twins, using a combination of physics-based and data-driven models, offer great potential for manufacturing process improvement at different levels of the manufacturing system. Commonly digital twin approaches in academic research have a high level of model input availability. However, in industry this availability level is often not met. This leads to significant gaps for the model development and operation, that hinder the transfer of the benefits to actual manufacturing processes. To overcome these hurdles, this paper presents a conceptual framework for identifying, analyzing, and overcoming model input gaps. To exemplify the proposed approach, we present a polishing process use case based on the data of a hybrid model from previous work.