A novel image feature descriptor for SLM spattering pattern classification using a consumable camera

Abstract

In selective laser melting (SLM), spattering is an important phenomenon that is highly related to the quality of the manufactured parts. Characterisation and monitoring of spattering behaviours are highly valuable in understanding the manufacturing process and improving the manufacturing quality of SLM. This paper introduces a method of automatic visual classification to distinguish spattering characteristics of SLM processes in different manufacturing conditions. A compact feature descriptor is proposed to represent spattering patterns and its effectiveness is evaluated using real images captured in different conditions. The feature descriptor of this work combines information of spatter trajectory morphology, spatial distributions, and temporal information. The classification is performed using support vector machine (SVM) and random forests for testing and shows highly promising classification accuracy of about 97%. The advantages of this work include compactness for representation and semantic interpretability with the feature description. In addition, the qualities of manufacturing parts are mapped with spattering characteristics under different laser energy densities. Such a map table can be then used to define the desired spatter features, providing a non-contact monitoring solution for online anomaly detection. This work will lead to a further integration of real-time vision monitoring system for an online closed-loop prognostic system for SLM systems, in order to improve the performance in terms of manufacturing quality, power consumption, and fault detection.

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

“…While we are currently working on a real-time version of this monitoring system, the camera’s high sampling rate has already led us to make design decisions that reduce the amount of computations required. These design decisions include the avoidance of deep learning, placing limits on the number of video features (e.g., the spatter direction features were limited to six even through Ji and Han used 80 spatter direction features in a similar approach [ 38 ]) and the preference for smaller neural networks for pore density prediction.…”

“…Recently, Ji and Han [ 38 ] argued that the direction in which spatters travel may be a useful feature for identifying pore creation. To characterise spatter direction with a consistent number of features, we followed their approach and made use of a combination of the polar [ 39 ] and Radon transforms [ 40 ].…”

“…The sums from each zone were then used as features that roughly captured the directions of spatter. As we employed a faster camera than the one used by Ji and Han (20,000 fps vs. 50 fps), we were able to capture spatters using a single ring of angular zones as opposed to the 5 used by Ji and Han [ 38 ].…”

In situ monitoring methods for selective laser melting additive manufacturing process based on images — A review

“…Therefore, the hyperparameters of the algorithm need to be tuned in advance. Ji et al [61] adopted the in situ monitoring system to collect the images of spatters during the forming process. The description operator in polar coordinates for the spatters in the image was designed to extract features of spatters, which can be used to distinguish different energy densities.…”

Predicting laser powder bed fusion defects through in-process monitoring data and machine learning

“…Different sensors, e.g., acoustic sensors [8,9], high resolution optical camera [10][11][12], high speed camera [13], infrared thermography [14][15][16], infrared (IR) camera [17], optical tomography [18][19][20][21], synchrotron X-ray [22,23], etc., can be applied for the monitoring of the L-PBF process. These sensors reveal diverse phenomena of the powder bed and melt pool: e.g., powder bed surface topography (before and after exposure), spattering, balling, pore formation, cracking, and deformation.…”