Probabilistic predictive control of porosity in laser powder bed fusion

Paromita Nath and Sankaran Mahadevan ()
Additional contact information
Paromita Nath: Vanderbilt University
Sankaran Mahadevan: Vanderbilt University

Journal of Intelligent Manufacturing, 2023, vol. 34, issue 3, No 9, 1085-1103

Abstract: Abstract This work presents a Bayesian methodology for layer-by-layer predictive quality control of an additively manufactured part by integrating physics-based simulation with online monitoring data. The model and the sensor data are first used to infer porosity in the printed layers, prediction of porosity in future layers, and adjustment of process parameters. Since porosity is not directly observable during the printing process, the temperature profile obtained from the monitoring (using an infra-red thermal camera) is used to infer porosity in the finished part. The porosity inference model is constructed by first reducing the dimension of the thermal images by employing singular value decomposition. Next, in process control, the porosity in the final part is predicted, and if this predicted porosity is more than a desired threshold, the process parameters for printing the next layer are adjusted based on optimization. To ensure that the prediction model is both fast and accurate, the expensive finite element model is replaced by a surrogate model, and a discrepancy term calibrated using experimental data is used to correct the surrogate model prediction. The prediction model is also updated at every layer based on the monitoring data, and the updated model is used to predict the porosity in the final part. The effectiveness of the proposed method is demonstrated for controlling porosity in laser powder bed fusion by changing the process parameters such as laser power and laser speed.

Keywords: Additive manufacturing; Laser powder bed fusion; Process optimization; Predictive control; Monitoring; Thermography (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-021-01836-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:34:y:2023:i:3:d:10.1007_s10845-021-01836-6

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-021-01836-6

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().