An efficient transient temperature monitoring of fused filament fabrication process with physics-based compressive sensing

Sensors play an important role in manufacturing processes. Different types of sensors have been used in process monitoring to ensure the quality of products. As a result, the cost of quality control is rising. Processing a large amount of sensor data for real-time process monitoring is also challenging. Recently, a Physics-Based Compressive Sensing (PBCS) approach was proposed to reduce the number of sensors and the amount of data collection associated with manufacturing process monitoring. PBCS significantly improves the compression ratio from traditional compressed sensing by incorporating the knowledge of physical phenomena in specific applications. In this article the PBCS approach is demonstrated with the dynamic process of fused filament fabrication where the constantly changing temperature field needs to be continuously monitored. A transient thermal model for PBCS is formulated. Based on the model, three-dimensional thermal distributions in manufacturing processes can be efficiently monitored by reconstructing distributions from sparse samplings in both spatial and temporal domains. The systematic error from reconstruction can also be predicted and compensated based on a Gaussian process uncertainty quantification approach.