Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing

Yong Ren, Qian Wang, Pan Michaleris

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

Abstract

This paper presents a machine-learning based predictive modeling approach on how process input parameters affect melt-pool volumes for a Laser Powder Bed Fusion (LPBF) additive manufacturing (AM) process. A physics-informed approach is adopted to define input features for the machine-learning models, and a two-level architecture is defined for the model training and validation. Specifically, a so-called initial (pre-deposition) temperature at the deposition point is identified as one key variable in characterizing thermal history for predicting melt-pool sizes. At the lower-level of the two-level modeling architecture, a hybrid model consisting of an analytical computation and a Gaussian process is developed to predict the pre-deposition temperature using process input parameters. Then at the higher-level of the modeling architecture, eight machine learning algorithms (including machine-learning based regression models and a two-layer neural network) are evaluated in predicting melt-pool volumes using the pre-deposition temperature and process parameters. For this proof-of-concept study, simulation data generated from the Autodesk Netfabb Local Simulation are used for model training and validation. The study shows that the proposed two-level machine learning model achieves high prediction performance and its prediction accuracy improves significantly compared to the one-level machine learning without using pre-deposition temperature as an input feature.

Original languageEnglish (US)
Title of host publicationAdvanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791859148
DOIs
StatePublished - Jan 1 2019
EventASME 2019 Dynamic Systems and Control Conference, DSCC 2019 - Park City, United States
Duration: Oct 8 2019Oct 11 2019

Publication series

NameASME 2019 Dynamic Systems and Control Conference, DSCC 2019
Volume1

Conference

ConferenceASME 2019 Dynamic Systems and Control Conference, DSCC 2019
CountryUnited States
CityPark City
Period10/8/1910/11/19

Fingerprint

3D printers
Learning systems
Fusion reactions
Powders
Lasers
Temperature
Learning algorithms
Hot Temperature
Physics
Neural networks

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Mechanical Engineering
  • Industrial and Manufacturing Engineering

Cite this

Ren, Y., Wang, Q., & Michaleris, P. (2019). Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing. In Advanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing [v001t10a001] (ASME 2019 Dynamic Systems and Control Conference, DSCC 2019; Vol. 1). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/DSCC2019-8995
Ren, Yong ; Wang, Qian ; Michaleris, Pan. / Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing. Advanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing. American Society of Mechanical Engineers (ASME), 2019. (ASME 2019 Dynamic Systems and Control Conference, DSCC 2019).
@inproceedings{808d032cd07c49cd8e8655a0bf0721d4,
title = "Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing",
abstract = "This paper presents a machine-learning based predictive modeling approach on how process input parameters affect melt-pool volumes for a Laser Powder Bed Fusion (LPBF) additive manufacturing (AM) process. A physics-informed approach is adopted to define input features for the machine-learning models, and a two-level architecture is defined for the model training and validation. Specifically, a so-called initial (pre-deposition) temperature at the deposition point is identified as one key variable in characterizing thermal history for predicting melt-pool sizes. At the lower-level of the two-level modeling architecture, a hybrid model consisting of an analytical computation and a Gaussian process is developed to predict the pre-deposition temperature using process input parameters. Then at the higher-level of the modeling architecture, eight machine learning algorithms (including machine-learning based regression models and a two-layer neural network) are evaluated in predicting melt-pool volumes using the pre-deposition temperature and process parameters. For this proof-of-concept study, simulation data generated from the Autodesk Netfabb Local Simulation are used for model training and validation. The study shows that the proposed two-level machine learning model achieves high prediction performance and its prediction accuracy improves significantly compared to the one-level machine learning without using pre-deposition temperature as an input feature.",
author = "Yong Ren and Qian Wang and Pan Michaleris",
year = "2019",
month = "1",
day = "1",
doi = "10.1115/DSCC2019-8995",
language = "English (US)",
series = "ASME 2019 Dynamic Systems and Control Conference, DSCC 2019",
publisher = "American Society of Mechanical Engineers (ASME)",
booktitle = "Advanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing",

}

Ren, Y, Wang, Q & Michaleris, P 2019, Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing. in Advanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing., v001t10a001, ASME 2019 Dynamic Systems and Control Conference, DSCC 2019, vol. 1, American Society of Mechanical Engineers (ASME), ASME 2019 Dynamic Systems and Control Conference, DSCC 2019, Park City, United States, 10/8/19. https://doi.org/10.1115/DSCC2019-8995

Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing. / Ren, Yong; Wang, Qian; Michaleris, Pan.

Advanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing. American Society of Mechanical Engineers (ASME), 2019. v001t10a001 (ASME 2019 Dynamic Systems and Control Conference, DSCC 2019; Vol. 1).

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

TY - GEN

T1 - Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing

AU - Ren, Yong

AU - Wang, Qian

AU - Michaleris, Pan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - This paper presents a machine-learning based predictive modeling approach on how process input parameters affect melt-pool volumes for a Laser Powder Bed Fusion (LPBF) additive manufacturing (AM) process. A physics-informed approach is adopted to define input features for the machine-learning models, and a two-level architecture is defined for the model training and validation. Specifically, a so-called initial (pre-deposition) temperature at the deposition point is identified as one key variable in characterizing thermal history for predicting melt-pool sizes. At the lower-level of the two-level modeling architecture, a hybrid model consisting of an analytical computation and a Gaussian process is developed to predict the pre-deposition temperature using process input parameters. Then at the higher-level of the modeling architecture, eight machine learning algorithms (including machine-learning based regression models and a two-layer neural network) are evaluated in predicting melt-pool volumes using the pre-deposition temperature and process parameters. For this proof-of-concept study, simulation data generated from the Autodesk Netfabb Local Simulation are used for model training and validation. The study shows that the proposed two-level machine learning model achieves high prediction performance and its prediction accuracy improves significantly compared to the one-level machine learning without using pre-deposition temperature as an input feature.

AB - This paper presents a machine-learning based predictive modeling approach on how process input parameters affect melt-pool volumes for a Laser Powder Bed Fusion (LPBF) additive manufacturing (AM) process. A physics-informed approach is adopted to define input features for the machine-learning models, and a two-level architecture is defined for the model training and validation. Specifically, a so-called initial (pre-deposition) temperature at the deposition point is identified as one key variable in characterizing thermal history for predicting melt-pool sizes. At the lower-level of the two-level modeling architecture, a hybrid model consisting of an analytical computation and a Gaussian process is developed to predict the pre-deposition temperature using process input parameters. Then at the higher-level of the modeling architecture, eight machine learning algorithms (including machine-learning based regression models and a two-layer neural network) are evaluated in predicting melt-pool volumes using the pre-deposition temperature and process parameters. For this proof-of-concept study, simulation data generated from the Autodesk Netfabb Local Simulation are used for model training and validation. The study shows that the proposed two-level machine learning model achieves high prediction performance and its prediction accuracy improves significantly compared to the one-level machine learning without using pre-deposition temperature as an input feature.

UR - http://www.scopus.com/inward/record.url?scp=85076437465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076437465&partnerID=8YFLogxK

U2 - 10.1115/DSCC2019-8995

DO - 10.1115/DSCC2019-8995

M3 - Conference contribution

AN - SCOPUS:85076437465

T3 - ASME 2019 Dynamic Systems and Control Conference, DSCC 2019

BT - Advanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing

PB - American Society of Mechanical Engineers (ASME)

ER -

Ren Y, Wang Q, Michaleris P. Machine-learning based thermal-geometric predictive modeling of laser powder bed fusion additive manufacturing. In Advanced Driver Assistance and Autonomous Technologies; Advances in Control Design Methods; Advances in Robotics; Automotive Systems; Design, Modeling, Analysis, and Control of Assistive and Rehabilitation Devices; Diagnostics and Detection; Dynamics and Control of Human-Robot Systems; Energy Optimization for Intelligent Vehicle Systems; Estimation and Identification; Manufacturing. American Society of Mechanical Engineers (ASME). 2019. v001t10a001. (ASME 2019 Dynamic Systems and Control Conference, DSCC 2019). https://doi.org/10.1115/DSCC2019-8995