Automatic Quality Assessments of Laser Powder Bed Fusion Builds from Photodiode Sensor Measurements

Abstract

This study evaluates whether a combination of photodiode sensor measurements, taken during laser powder bed fusion (L-PBF) builds, can be used to predict the resulting build quality via a purely data-based approach. We analyse the relationship between build density and features that are extracted from sensor data collected from three different photodiodes. The study uses a Singular Value Decomposition to extract lower-dimensional features from photodiode measurements, which are then fed into machine learning algorithms. Several unsupervised learning methods are then employed to classify low density (< 99% part density) and high density (≥ 99% part density) specimens. Subsequently, a supervised learning method (Gaussian Process regression) is used to directly predict build density. Using the unsupervised clustering approaches, applied to features extracted from both photodiode sensor data as well as observations relating to the energy transferred to the material, build density was predicted with up to 93.54% accuracy. With regard to the supervised regression approach, a Gaussian Process algorithm was capable of predicting the build density with a RMS error of 3.65%. The study shows, therefore, that there is potential for machine learning algorithms to predict indicators of L-PBF build quality from photodiode build-measurements. Moreover, the work herein describes approaches that are predominantly probabilistic, thus facilitating uncertainty quantification in machine-learnt predictions of L-PBF build quality.

Deep semi-supervised learning of dynamics for anomaly detection in laser powder bed fusion

“…In comparison, this work indicates the potential to locate material degradation at lower FPR even while maintaining 0.999 TPR, though more data is required to quantify this to localisation. Jayasinghe et al (2020) were capable of differentiating porosity below 99% with an AUC of 0.946 using three photodiodes. This is equivalent to − 8 mm unstable parameter in the present work, where a mean AUC of 0.999 was achieved with a single laser pulse.…”

In-situ measurement and monitoring methods for metal powder bed fusion: an updated review

“…Among the most important factors affecting the quality of the measured data, the measurement wavelength range and the sensor field of view play a central role. In all the studies reported in Table 7, the wavelength range was slightly above or below 1000 nm, whereas some researchers used dual-wavelength measurements in the ranges 700 nm to 1050 nm and 1100 nm to 1700 nm (Jayasinghe et al 2020, Okaro et al 2019, Alberts et al 2017. Measuring melt pool radiation above 1000 nm was prevented, in some cases, by the optical chain (Clijster et al 2014), but this limit was overcome in other studies (e.g., Forien et al 2019 andYang et al 2019).…”

Encoding Stability into Laser Powder Bed Fusion Monitoring Using Temporal Features and Pore Density Modelling

“…During an LPBF build process, various defects can occur, which impact the strength and structural integrity of the produced part [ 3 , 4 ]. These defects can be the result of printing instabilities brought on by, for example, variations in the material properties of the metal powder, heat accumulating in the printed part, and disturbances in the build environment (e.g., changes in humidity and air flow) [ 5 , 6 ]. One such defect type is porosity : the introduction of pores (or voids) in the printed parts due to unstable printing conditions.…”

“…In order to reduce the scrap rates in LPBF, we require the ability to reduce porosity by creating and maintaining a stable printing process, even in a constantly changing environment. In order to adjust build parameters on-the-fly, the state of the LPBF process needs to be actively monitored, and any instabilities need to be communicated to the 3D printer in real-time [ 4 , 6 ].…”