Constrained markov decision process modeling for sequential optimization of additive manufacturing build quality

Bing Yao, Hui Yang

Research output: Contribution to journalArticle

1 Scopus citations

Abstract

Additive manufacturing (AM) provides a greater level of flexibility to produce a 3-D part with complex geometries directly from the design. However, the widespread application of AM is currently hampered by technical challenges in process repeatability and quality control. To enhance the in-process information visibility, advanced sensing is increasingly invested for real-time AM process monitoring. The proliferation of in situ sensing data calls for the development of analytical methods for the extraction of features sensitive to layer-wise defects, and the exploitation of pertinent knowledge about defects for in-process quality control of AM builds. As a result, there are increasing interests and rapid development of sensor-based models for the characterization and estimation of layer-wise defects in the past few years. However, very little has been done to go from sensor-based modeling of defects to the suggestion of in situ corrective actions for quality control of AM builds. In this paper, we propose a new sequential decision-making framework for in situ control of AM processes through the constrained Markov decision process (CMDP), which jointly considers the conflicting objectives of both total cost (i.e., energy or time) and build quality. Experimental results show that the CMDP formulation provides an effective policy for executing corrective actions to repair and counteract incipient defects in AM before completion of the build.

Original languageEnglish (US)
Article number8473690
Pages (from-to)54783-54794
Number of pages12
JournalIEEE Access
Volume6
DOIs
StatePublished - Jan 1 2018

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Constrained markov decision process modeling for sequential optimization of additive manufacturing build quality'. Together they form a unique fingerprint.

  • Cite this