Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process

Xing，Wei1,2,4; Chu，Xin2; Lyu，Tianyi2; Lee，Chi Guhn3; Zou，Yu2; Rong，Yiming4

2022-02-01

10.1016/j.jmapro.2021.12.030

Journal of Manufacturing Processes   影响因子和分区

1526-6125

2212-4616

In a selective laser melting (SLM) process, the fluctuation of as-produced part quality remains a problem that hinders its broader industrial applications. In situ monitoring that identifies the variations of melt pool characteristics is promising to improve part quality and control the SLM process. So far, such monitoring approaches have been impeded by the limitation of image processing methods that cannot classify large volumes of melt pool images during a short time. Here we demonstrate that convolutional neural networks (CNN) could be an effective, efficient, and reliable solution to improve the SLM process. In this study, we employ the images captured at five input laser energy levels to train and test CNN models. Compared with a statistical method, the use of CNN has improved the classification of melt pools to the highest achieved accuracy of 96.6%, which is resulted from the ability of utilizing complex image features from the melt pool region. Thus, the CNN is a reliable method with the potential to monitor the influence of other process parameters on melt pool characteristics, potentially leading to the improvement of production in SLM.

Convolutional neural networks (CNN) In situ monitoring Melt pool Selective laser melting (SLM)

SCI ; EI

英语

其他

Engineering

Engineering, Manufacturing

WOS:000740941200005

ELSEVIER SCI LTD

20220111430678

Convolutional neural networks ; Image enhancement ; Lakes ; Melting ; Pulsed lasers ; Selective laser melting

Information Theory and Signal Processing:716.1 ; Lasers, General:744.1 ; Reproduction, Copying:745.2 ; Chemical Operations:802.3

2-s2.0-85122193732

Scopus

1.School of Mechatronics Engineering,Harbin Institute of Technology,Harbin,150001,China
2.Department of Materials Science and Engineering,University of Toronto,M5S 3E4,Canada
3.Department of Mechanical and Industrial Engineering,University of Toronto,M5S 3E4,Canada
4.Department of Mechanical and Energy Engineering,Southern University of Science and Technology,518055,China

Xing，Wei,Chu，Xin,Lyu，Tianyi,et al. Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process[J]. Journal of Manufacturing Processes,2022,74:486-499.

Xing，Wei,Chu，Xin,Lyu，Tianyi,Lee，Chi Guhn,Zou，Yu,&Rong，Yiming.(2022).Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process.Journal of Manufacturing Processes,74,486-499.

Xing，Wei,et al."Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process".Journal of Manufacturing Processes 74(2022):486-499.