Machine learning-based image processing for on-line defect recognition in additive manufacturing

被引：303

作者：

Caggiano, Alessandra ^{[1
,2
]}

Zhang, Jianjing ^{[3
]}

Alfieri, Vittorio ^{[4
]}

Caiazzo, Fabrizia ^{[4
]}

Gao, Robert ^{[3
]}

Teti, Roberto ^{[2
,5
]}

机构：

[1] Univ Naples Federico II, Dept Ind Engn, Naples, Italy

[2] Fh J LEAPT UniNaples, Fraunhofer Joint Lab Excellence Adv Prod Technol, Naples, Italy

[3] Case Western Reserve Univ, Dept Mech & Aerosp Engn, Cleveland, OH 44106 USA

[4] Univ Salerno, Dept Ind Engn, Fisciano, SA, Italy

[5] Univ Naples Federico II, Dept Chem Mat & Ind Prod Engn, Naples, Italy

来源：

CIRP ANNALS-MANUFACTURING TECHNOLOGY | 2019年 / 68卷 / 01期

关键词：

Machine learning; Additive manufacturing; Fault recognition; LASER;

D O I：

10.1016/j.cirp.2019.03.021

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

A machine learning approach for on-line fault recognition via automatic image processing is developed to timely identify material defects due to process non-conformities in Selective Laser Melting (SLM) of metal powders. In-process images acquired during the layer-by-layer SLM processing are analyzed via a bi-stream Deep Convolutional Neural Network-based model, and the recognition of SLM defective condition-related pattern is achieved by automated image feature learning and feature fusion. Experimental evaluations confirmed the effectiveness of the machine learning method for on-line detection of defects due to process non-conformities, providing the basis for adaptive SLM process control and part quality assurance. (C) 2019 Published by Elsevier Ltd on behalf of CIRP.

引用

页码：451 / 454

页数：4

共 17 条

[1] Spatter formation in selective laser melting process using multi-laser technology [J].