Remanufacturing and Refurbishment of Large Industrial Equipment

With the rapid development of the industrial Internet of Things (IoT), the real-world industry has gradually become a data-rich environment, which makes the data-driven intelligent maintenance and lifetime extension techniques acquire an unpreceded development and application. The success of these advanced methods depends on the abundant data. However, it is extremely difficult to collect enough data in certain practical situations, e.g., when a sudden catastrophic failure happens, only a few samples can be acquired before the system shuts down. We propose a new approach, called Feature Space Metric-based Meta-learning Model (FSM3), to overcome the challenge of the few-shot problem for large industrial equipment under multiple limited data conditions.