Deep learning-based data fusion method for in-situ porosity detection in laser-based additive manufacturing

Qi Tian, Shenghan Guo, Weihong Guo, Linkan Bian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Laser-Based Additive Manufacturing (LBAM) provides unprecedented possibilities to produce complicated parts with multiple functions for lots of engineering applications. Melt pool is one of the most important signatures in LBAM and is indicative of process anomalies and part defects. High-speed temperature images of the melt pool captured during LBAM make it possible for in-situ melt pool monitoring and porosity prediction. This paper aims to broaden current knowledge of the underlying relationship between process and porosity in LBAM and provide new possibilities for efficient and accurate porosity prediction. We present a deep learning-based data fusion method to predict porosity in LBAM parts by leveraging the measured melt pool thermal history and deep learning. A PyroNet, based on Convolutional Neural Networks, is developed to correlate in-process pyrometer images with layer-wise porosity; an IRNet, based on Long-term Recurrent Convolutional Networks, is developed to correlate sequential thermal images from infrared camera with layer-wise porosity. Predictions from PyroNet and IRNet are fused at the decision level to obtain a more accurate prediction of layer-wise porosity. The model fidelity is validated with LBAM Ti-6Al-4V thin-wall structure. Our method can achieve 100% accuracy with high efficiency, allowing the method to be applicable for in-situ porosity detection in LBAM.

Original languageEnglish (US)
Title of host publicationManufacturing Processes; Manufacturing Systems; Nano/Micro/Meso Manufacturing; Quality and Reliability
PublisherAmerican Society of Mechanical Engineers
ISBN (Electronic)9780791884263
DOIs
StatePublished - 2020
Externally publishedYes
EventASME 2020 15th International Manufacturing Science and Engineering Conference, MSEC 2020 - Virtual, Online
Duration: Sep 3 2020 → …

Publication series

NameASME 2020 15th International Manufacturing Science and Engineering Conference, MSEC 2020
Volume2

Conference

ConferenceASME 2020 15th International Manufacturing Science and Engineering Conference, MSEC 2020
CityVirtual, Online
Period9/3/20 → …

Keywords

  • Data fusion
  • Deep learning
  • In-situ porosity detection
  • Laser-based additive manufacturing

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Materials Science (miscellaneous)
  • Control and Optimization
  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Fingerprint

Dive into the research topics of 'Deep learning-based data fusion method for in-situ porosity detection in laser-based additive manufacturing'. Together they form a unique fingerprint.

Cite this