Monday, December 31, 2018
Sunday, November 25, 2018
Journal Article: Model Transfer Across Additive Manufacturing Processes via Mean Effect Equivalence of Lurking Variables
This paper, written by Dr. Arman Sabbaghi and Dr. Qiang Huang, has been recently published by the Annals of Applied Statistics. It presents a strategy based on the engineering effect equivalence principle to address the fundamental challenge in model transfer of handling lurking variables across different environments. The link for the published article follows below.
https://projecteuclid.org/euclid.aoas/1542078050
Comments and discussions are most welcome!
https://projecteuclid.org/euclid.aoas/1542078050
Comments and discussions are most welcome!
Thursday, November 8, 2018
Prescriptive Data-Analytical Modeling of Laser Powder Bed Fusion Processes for Accuracy Improvement -- Available online
http://manufacturingscience.asmedigitalcollection.asme.org/article.aspx?articleid=2707894
Co-authored by He Luan, Marco Grasso, Bianca M. Colosimo and Qiang Huang, this study develops a data-driven prescriptive modeling approach as a promising solution for geometric accuracy improvement in Laser powder bed fusion (LPBF) processes. To address the shape complexity issue, a prescriptive modeling approach is adopted to minimize geometrical deviations of built products through compensating computer aided design models, as opposed to changing process parameters. It allows us to predict and control a wide range of shapes starting from a limited set of measurements on basic benchmark geometries. An error decomposition and compensation scheme is developed to decouple the influence from different error components and to reduce the shape deviations caused by part geometrical deviation, laser beam positioning error, and other location effects simultaneously via an integrated modeling and compensation framework. Experimentation and data collection are conducted to investigate error sources and to validate the developed modeling and accuracy control methods.
Our modeling work is applicable to relatively repeatable LPBF processes where there are no large build-to-build variations. Machine-to-machine variation is not considered in this study. Though the proposed data-analytical black-box modeling framework can be applicable to the production of other geometries, further experimentation and analysis is needed to investigate the LPBF process performance when building larger products with more complicated shapes
Co-authored by He Luan, Marco Grasso, Bianca M. Colosimo and Qiang Huang, this study develops a data-driven prescriptive modeling approach as a promising solution for geometric accuracy improvement in Laser powder bed fusion (LPBF) processes. To address the shape complexity issue, a prescriptive modeling approach is adopted to minimize geometrical deviations of built products through compensating computer aided design models, as opposed to changing process parameters. It allows us to predict and control a wide range of shapes starting from a limited set of measurements on basic benchmark geometries. An error decomposition and compensation scheme is developed to decouple the influence from different error components and to reduce the shape deviations caused by part geometrical deviation, laser beam positioning error, and other location effects simultaneously via an integrated modeling and compensation framework. Experimentation and data collection are conducted to investigate error sources and to validate the developed modeling and accuracy control methods.
Our modeling work is applicable to relatively repeatable LPBF processes where there are no large build-to-build variations. Machine-to-machine variation is not considered in this study. Though the proposed data-analytical black-box modeling framework can be applicable to the production of other geometries, further experimentation and analysis is needed to investigate the LPBF process performance when building larger products with more complicated shapes
Wednesday, October 3, 2018
Yuan Jin passed her dissertation defense on "Statistical Modeling and Process Data Analytics for Smart Manufacturing" on October 2nd, 2018.
Congratulations! Dr. Yuan Jin will join Facebook as a Research Scientist in Machine Learning Track.
Thursday, September 20, 2018
2019 FACAM Workshop will be held at ENS Paris-Saclay on June 17-18 2019.
Please contact Prof. Nabil Anwer and Prof. Q. Huang if you are interested in the workshop.
Saturday, April 28, 2018
He Luan passed her dissertation defense on "Statistical Modeling and Machine Learning for Shape Accuracy Control in Additive Manufacturing" on April 27, 2018
Congratulation! She has started a career at HP Lab.
Tuesday, April 17, 2018
Marie Skłodowska Curie Action (MSCA) training program - Individual Fellowship call 2018 at Politecnico di Milano
The aim of the call is to attract and train young and talented researchers to successfully applying for MSCA European Fellowship with the Politecnico di Milano as host institution. Candidates will be pre-selected based on their expression of interest, CV and motivation. Promising candidates will be invited to the Politecnico di Milano for 3 days (11-13 June 2018) to meet with their supervisors, to visit laboratories and facilities, to attend an in depth training course on the proposal writing and to make use of full support in the application writing process by POLIMI advisors.
The call involves several topics.
One topic at the Department of Mechanical Engineering of Polimi: Metal Additive Manufacturing for Industry 4.0. The focus is on bridging data analytics and statistical methods to additive manufacturing for novel intelligent systems and zero-defect manufacturing.
Details can be found here:
The due date for submission is April 30th, 2018.
Thursday, March 1, 2018
Model Transfer Across Additive Manufacturing Processes via Mean Effect Equivalence of Lurking Variables (accepted by the Annals of Applied Statistics)
Shape deviation models constitute an important component in quality control for additive manufacturing (AM) systems. However, specified models have a limited scope of application across the vast spectrum of processes in a system that are characterized by different settings of process variables, including lurking variables. In this paper, which was recently accepted by the Annals of Applied Statistics, Dr. Arman Sabbaghi and Dr. Qiang Huang present a new effect equivalence framework and Bayesian method that enables deviation model transfer across processes in an AM system with limited experimental runs. Model transfer is performed via inference on the equivalent effects of lurking variables in terms of an observed factor whose effect has been modeled under a previously learned process. Studies on stereolithography illustrate the ability of their framework to broaden both the scope of deviation models and the comprehensive understanding of AM systems. More details about this paper can be found at the following link:
Saturday, February 10, 2018
Friday, January 19, 2018
Subscribe to:
Posts (Atom)