Knowledge Distillation-based Information Sharing for Online Process Monitoring in Decentralized Manufacturing System
This work addresses performance variability in process monitoring for decentralized manufacturing units, offering an incremental improvement through knowledge sharing.
The paper tackles the problem of inconsistent monitoring performance in decentralized manufacturing systems by proposing a knowledge distillation-based information sharing framework, which improved poorly performing models with solid data privacy protection in a real-world additive manufacturing case study.
In advanced manufacturing, the incorporation of sensing technology provides an opportunity to achieve efficient in-situ process monitoring using machine learning methods. Meanwhile, the advances of information technologies also enable a connected and decentralized environment for manufacturing systems, making different manufacturing units in the system collaborate more closely. In a decentralized manufacturing system, the involved units may fabricate same or similar products and deploy their own machine learning model for online process monitoring. However, due to the possible inconsistency of task progress during the operation, it is also common that some units have more informative data while some have less informative data. Thus, the monitoring performance of machine learning model for each unit may highly vary. Therefore, it is extremely valuable to achieve efficient and secured knowledge sharing among the units in a decentralized manufacturing system for enhancement of poorly performed models. To realize this goal, this paper proposes a novel knowledge distillation-based information sharing (KD-IS) framework, which could distill informative knowledge from well performed models to improve the monitoring performance of poorly performed models. To validate the effectiveness of this method, a real-world case study is conducted in a connected fused filament fabrication (FFF)-based additive manufacturing (AM) platform. The experimental results show that the developed method is very efficient in improving model monitoring performance at poorly performed models, with solid protection on potential data privacy.