Deep learning characterization of surface defects in the selective laser melting process

Ruoxin Wang, Chi Fai Cheung (Corresponding Author), Chunjin Wang, Mei Na Cheng

Research output: Journal article publicationJournal articleAcademic researchpeer-review

9 Citations (Scopus)


Surface defects in the selective laser melting (SLM) process adversely affect the surface quality of additive manufacturing workpieces. Although some studies have been conducted to classify or detect defects, the investigation of the distribution of defects has received relatively little attention. Currently, there are many studies which focus on the counting of objects and they typically adopt a backbone convolutional neural network to obtain an initial feature map, which contains more semantic information but loses some geometric details. In this paper, the distribution of surface defects and defect count estimation of additive manufactured components are first studied as well as presentation of a developed deep learning characterization method (DLCM) based on a detail-aware dilated convolutional neural network (DDCNN) incorporated with a fine details feature map extractor designed to obtain final fine semantic features. It features two dilated convolutional layer combination blocks (DCBs), which are proposed to fuse low-level features with semantic features. Data are acquired from the surface of a workpiece fabricated by SLM. A series of experiments have been conducted to validate the performance of the DLCM. Compared with the other main state-of-the-art methods, the proposed DLCM yields better results.
Original languageEnglish
Article number103662
JournalComputers in Industry
Issue number4
Publication statusPublished - Sept 2022


  • Additive manufacturing
  • Surface characterization
  • Selective laser melting
  • Convolutional neural network (CNN)
  • Surface defects
  • Machine learning


Dive into the research topics of 'Deep learning characterization of surface defects in the selective laser melting process'. Together they form a unique fingerprint.

Cite this