Deep Learning Based Monitoring of Spatter Behavior by the Acoustic Signal in Selective Laser Melting

Abstract

As one of the most promising metal additive manufacturing (AM) technologies, the selective laser melting (SLM) process has high expectations ofr its use in aerospace, medical, and other fields. However, various defects such as spatter, crack, and porosity seriously hinder the applications of the SLM process. In situ monitoring is a vital technique to detect the defects in advance, which is expected to reduce the defects. This work proposed a method that combined acoustic signals with a deep learning algorithm to monitor the spatter behaviors. The acoustic signals were recorded by a microphone and the spatter information was collected by a coaxial high-speed camera simultaneously. The signals were divided into two types according to the number and intensity of spatter during the SLM process with different combinations of processing parameters. Deep learning models, one-dimensional Convolutional Neural Network (1D-CNN), two-dimensional Convolutional Neural Network (2D-CNN), Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit (GRU) were trained to establish the relationships between the acoustic signals and characteristics of spatter. After K-fold verification, the highest classification confidence of models is 85.08%. This work demonstrates that it is feasible to use acoustic signals in monitoring the spatter defect during the SLM process. It is possible to use cheap and simple microphones instead of expensive and complicated high-speed cameras for monitoring spatter behaviors.

A Review of Spatter in Laser Powder Bed Fusion Additive Manufacturing: In Situ Detection, Generation, Effects, and Countermeasures

“…By combining multiple cameras and using image processing arithmetic, 3D information of spatter and its mobility can be gathered. Based on the use of monocular sensors, Luo et al [42] innovatively proposed the use of acoustic signals combined with deep learning for spatter detection, demonstrating the feasibility of the acoustic signal detection of spatter behavior. Due to the dimensional limitation of the 2D image (acquired by the monocular sensor), it is difficult to accurately calculate the behavioral information of the spatter and obtain accurate spatter trajectory, velocity, and other information.…”

Porosity Detection in Powder Bed Fusion Additive Manufacturing with Convolutional Neural Networks

“…As for the area of Additive Manufacturing, specifically powder bed fusion (PBF), Luo et al [19] trained various neural networks with audio spectrograms of the printing process to detect spatter defects. Their best model proved to be a 1D-CNN, achieving a validation accuracy of 85%.…”

An unsupervised online anomaly detection method for metal additive manufacturing processes via a statistical time-frequency domain algorithm

“…Layer-wise detection can also be used preemptively as Scime and Beuth have detected errors in deposited powder beds pre-sinter by inspecting layer-wise recoating images during a L-PBF process. 28 One relatively new method of monitoring the AM process is via acoustics, where either passive 29,30 or active [31][32][33] acoustic signals are used to monitor the sintering response. Eschner et al 34 used structure-borne acoustic transmissions to train a neural network, successfully classifying the porosity of samples.…”