Sensor-Based Build Condition Monitoring in Laser Powder Bed Fusion Additive Manufacturing Process Using a Spectral Graph Theoretic Approach

Abstract

The goal of this work is to monitor the laser powder bed fusion (LPBF) process using an array of sensors so that a record may be made of those temporal and spatial build locations where there is a high probability of defect formation. In pursuit of this goal, a commercial LPBF machine at the National Institute of Standards and Technology (NIST) was integrated with three types of sensors, namely, a photodetector, high-speed visible camera, and short wave infrared (SWIR) thermal camera with the following objectives: (1) to develop and apply a spectral graph theoretic approach to monitor the LPBF build condition from the data acquired by the three sensors; (2) to compare results from the three different sensors in terms of their statistical fidelity in distinguishing between different build conditions. The first objective will lead to early identification of incipient defects from in-process sensor data. The second objective will ascertain the monitoring fidelity tradeoff involved in replacing an expensive sensor, such as a thermal camera, with a relatively inexpensive, low resolution sensor, e.g., a photodetector. As a first-step toward detection of defects and process irregularities that occur in practical LPBF scenarios, this work focuses on capturing and differentiating the distinctive thermal signatures that manifest in parts with overhang features. Overhang features can significantly decrease the ability of laser heat to diffuse from the heat source. This constrained heat flux may lead to issues such as poor surface finish, distortion, and microstructure inhomogeneity. In this work, experimental sensor data are acquired during LPBF of a simple test part having an overhang angle of 40.5 deg. Extracting and detecting the difference in sensor signatures for such a simple case is the first-step toward in situ defect detection in additive manufacturing (AM). The proposed approach uses the Eigen spectrum of the spectral graph Laplacian matrix as a derived signature from the three different sensors to discriminate the thermal history of overhang features from that of the bulk areas of the part. The statistical accuracy for isolating the thermal patterns belonging to bulk and overhang features in terms of the F-score is as follows: (a) F-score of 95% from the SWIR thermal camera signatures; (b) 83% with the high-speed visible camera; (c) 79% with the photodetector. In comparison, conventional signal analysis techniques—e.g., neural networks, support vector machines, linear discriminant analysis were evaluated with F-score in the range of 40–60%.

In-Process Monitoring of Material Cross-Contamination Defects in Laser Powder Bed Fusion

“…The previous works are mainly restricted for offline characterization and use spectral graph eigenvalues which are not amenable for real-time adaptive monitoring of a fast-changing processes such as PBF. The underlying mathematics described herewith bears close resemblance to our previous works in spectral graph theory but is nonetheless repeated here for the sake of cohesiveness and continuity [66][67][68][69][70][71].…”

“…A similar form as the approach proposed in this work has been used previously by the authors in the context of surface finish characterization in chemical mechanical planarization semiconductor manufacturing process; monitoring chatter in ultraprecision diamond turning; and recently for assessment of postprocess geometric integrity in polymer additive manufacturing [66][67][68][69][70][71]. The main difference of this work from these previous forays lies in the application of spectral graph eigenvectors for real-time classification of material crosscontamination in PBF.…”

“…To realize this aim, the key idea is to transform the raw data into a domain that makes it tractable to extract signatures in real-time. In this work, the signal transformation procedure adopted is from the area of spectral graph theory and has been discussed in depth in our previous research [66][67][68][69][70][71].…”

Development of a Cone CVT by SDPD and Topology Optimization

“…Scholars have tried to avoid/diminish these defects by controlling the controllable process parameters such as laser specifications or control the fabrication signatures such as melting pool specifications during the fabrication process [20,29]. A number of scholars also attempted to derive the optimized process parameters even before printing a part by studying the effects of different parameters on the fabrication process through multi-physics simulation of the printing process [30,31].…”

WEC fault modelling and condition monitoring: A graph‐theoretic approach

“…In this category, graph-theoretic approaches for time series signal processing are a nascent domain [22,23]. Utilising 'big data' collected from SCADA, graph-theoretic approaches embed high-dimensional data as an undirected graph and subsequently project data into the eigenvector space of the graph Laplacian for feature extraction and has attracted increasing attention within the condition monitoring community [24,25].…”