Knowledge Distillation-based Information Sharing for Online Process Monitoring in Decentralized Manufacturing System

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 are data-rich while some are data-poor. Thus, the learning progress of the machine learning-based process monitoring model for each unit may vary. Therefore, it is highly valuable to achieve efficient and secured knowledge sharing among the units in a decentralized manufacturing system. To realize this goal, this paper proposes a knowledge distillation-based information sharing (KD-IS) framework, which could distill informative knowledge from data-rich unit to improve the monitoring performance of data-poor unit. 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 efficient in improving model monitoring performance at data-poor unit, with solid protection on potential data privacy.