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!

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

Thursday, September 20, 2018

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:

Friday, January 19, 2018

Tentative Agenda of FACAM 2018 Workshop

FACAM 2018
Location: GER 206 at University of Southern California
Feb 8
1:30 PMProf. Q. Huang (USC)
Welcome and Introduction
2:00 PMProf. Charyar SOUZANI (ENS Paris-Saclay)
Prediction of geometrical and dimensional deviations of Additive Manufacturing parts
2:45 PM Dr. Jun Zeng (HP), He Luan (HP, USC)
Thoughts on applying machine learning to help to uncover causal effects in
HP’s multi-jet fusion printing process physics
3:30 PMProf. Prahalad Rao (UNL)
The Unusual Effectiveness of Spectral Graph Theory for Quality Assurance in Additive Manufacturing
4:30 PMJie Ren (FSU)
Joint learning of process variation models for process co-monitoring and control using cloud data
5:30 PMWelcome Dinner at USC Faculty Club
Feb 9
9:00 AMRefreshment
9:15 AMProf. Marco Grasso (Politecnico di Milano)
Statistical process monitoring of Powder Bed Fusion processes via in-situ video imaging
10:00 AM
Prof. Arman Sabbaghi (Purdue)
Deviation Modeling Across Different Process Conditions and Shapes in Additive Manufacturing Systems
10:45 AMProf. Matthew Plumlee (Northwestern U)
Calibration with coverage and consistency
11:30 AMYuanxiang Wang (USC)
Statistical Inter-Layer Bonding Effects Modeling and Estimation with Convolution Formulation
12:15 PMBox lunch at GER 206
1:30 PMLinkan Bian (MSU)
Predicting Deformation in Laser-Based Additive Manufacturing Processes
2:15 PMRaquel de Souza Borges Ferreira (Purdue)
Automated Geometric Shape Deviation Modeling
for Additive Manufacturing Systems via Bayesian Neural Networks
3:00 PMProf. Matthew Plumlee (Northwestern U)
3D Printing Product Matching with Approximate Models
4:00 PMAdjourn
4:30 PMLA Live

Wednesday, January 3, 2018

"Revitalizing manufacturing through AI" by Andrew Ng

Source: https://medium.com/@andrewng/revitalizing-manufacturing-through-ai-a9ad32e07814

"AI is already transforming the IT industry." "It is now time to build not just an AI-powered IT industry, but an AI-powered society. One in which our physical needs, health care, transportation, food, and lodging are more accessible through AI, and where every person is freed from repetitive mental drudgery. For the whole world to experience the benefits of AI, it must pervade many industries, not just the IT industry."

The IT industry has primarily shaped our digital environment. Manufacturing touches nearly every part of our society by shaping our physical environment. It is through manufacturing that human creativity goes beyond pixels on a display to become physical objects. By bringing AI to manufacturing, we will deliver a digital transformation to the physical world.

AI technology is well suited to addressing the challenges facing manufacturing, such as variable quality and yield, inflexible production line design, inability to manage capacity, and rising production costs. AI can help address these issues, and improve quality control, shorten design cycles, remove supply-chain bottlenecks, reduce materials and energy waste, and improve production yields."

"Many companies are figuring out how to use AI, but this is not easy. The technology is still complex, and few teams understand AI well enough to implement it effectively. Outside the IT industry, almost no companies have enough access to AI talent.

Further, just as using IT to transform a traditional company requires more than building a website, using AI to transform a company requires much more than training a few machine learning models. The strategy of integrating AI — everything from data acquisition, to organizational structure design, to figuring out how to prioritize AI projects — is as complex as the technology, and good AI strategists are even rarer than good AI technologists."