Predictive modelling of surface roughness in fused deposition modelling using data fusion

Dazhong Wu, Yupeng Wei, Janis Terpenny

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

To realise high quality, additively manufactured parts, real-time process monitoring and advanced predictive modelling tools are crucial for accelerating quality assurance in additive manufacturing. While previous research has demonstrated the effectiveness of physics- and model-based diagnosis and prognosis for additive manufacturing, very little research has been reported on real-time monitoring and predictive modelling of the surface roughness of additively manufactured parts. This paper presents a data fusion approach to predicting surface roughness in fused deposition modelling (FDM) processes. The predictive models are trained using random forests (RFs), support vector regression (SVR), ridge regression (RR), and least absolute shrinkage and selection operator (LASSO). A real-time monitoring system is developed to monitor the health condition of a FDM machine in real-time using multiple sensors. RFs, SVR, RR, and LASSO are demonstrated on the condition monitoring data collected from these sensors. To integrate the data sources, a feature-level data fusion method is introduced. Experimental results have shown that the predictive models trained by the machine learning algorithms are capable of predicting the surface roughness of additively manufacturing parts with very high accuracy. The prediction accuracy can be further improved using the data fusion method.

Original languageEnglish (US)
Pages (from-to)3992-4006
Number of pages15
JournalInternational Journal of Production Research
Volume57
Issue number12
DOIs
StatePublished - Jun 18 2019

Fingerprint

Data fusion
3D printers
Surface roughness
Monitoring
Process monitoring
Sensors
Condition monitoring
Quality assurance
Learning algorithms
Learning systems
Physics
Health
Modeling
Predictive modeling
Manufacturing
Support vector regression
Operator
Ridge regression
Shrinkage
Sensor

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Wu, Dazhong ; Wei, Yupeng ; Terpenny, Janis. / Predictive modelling of surface roughness in fused deposition modelling using data fusion. In: International Journal of Production Research. 2019 ; Vol. 57, No. 12. pp. 3992-4006.
@article{e793befe063546e081ee6f067754d4aa,
title = "Predictive modelling of surface roughness in fused deposition modelling using data fusion",
abstract = "To realise high quality, additively manufactured parts, real-time process monitoring and advanced predictive modelling tools are crucial for accelerating quality assurance in additive manufacturing. While previous research has demonstrated the effectiveness of physics- and model-based diagnosis and prognosis for additive manufacturing, very little research has been reported on real-time monitoring and predictive modelling of the surface roughness of additively manufactured parts. This paper presents a data fusion approach to predicting surface roughness in fused deposition modelling (FDM) processes. The predictive models are trained using random forests (RFs), support vector regression (SVR), ridge regression (RR), and least absolute shrinkage and selection operator (LASSO). A real-time monitoring system is developed to monitor the health condition of a FDM machine in real-time using multiple sensors. RFs, SVR, RR, and LASSO are demonstrated on the condition monitoring data collected from these sensors. To integrate the data sources, a feature-level data fusion method is introduced. Experimental results have shown that the predictive models trained by the machine learning algorithms are capable of predicting the surface roughness of additively manufacturing parts with very high accuracy. The prediction accuracy can be further improved using the data fusion method.",
author = "Dazhong Wu and Yupeng Wei and Janis Terpenny",
year = "2019",
month = "6",
day = "18",
doi = "10.1080/00207543.2018.1505058",
language = "English (US)",
volume = "57",
pages = "3992--4006",
journal = "International Journal of Production Research",
issn = "0020-7543",
publisher = "Taylor and Francis Ltd.",
number = "12",

}

Predictive modelling of surface roughness in fused deposition modelling using data fusion. / Wu, Dazhong; Wei, Yupeng; Terpenny, Janis.

In: International Journal of Production Research, Vol. 57, No. 12, 18.06.2019, p. 3992-4006.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predictive modelling of surface roughness in fused deposition modelling using data fusion

AU - Wu, Dazhong

AU - Wei, Yupeng

AU - Terpenny, Janis

PY - 2019/6/18

Y1 - 2019/6/18

N2 - To realise high quality, additively manufactured parts, real-time process monitoring and advanced predictive modelling tools are crucial for accelerating quality assurance in additive manufacturing. While previous research has demonstrated the effectiveness of physics- and model-based diagnosis and prognosis for additive manufacturing, very little research has been reported on real-time monitoring and predictive modelling of the surface roughness of additively manufactured parts. This paper presents a data fusion approach to predicting surface roughness in fused deposition modelling (FDM) processes. The predictive models are trained using random forests (RFs), support vector regression (SVR), ridge regression (RR), and least absolute shrinkage and selection operator (LASSO). A real-time monitoring system is developed to monitor the health condition of a FDM machine in real-time using multiple sensors. RFs, SVR, RR, and LASSO are demonstrated on the condition monitoring data collected from these sensors. To integrate the data sources, a feature-level data fusion method is introduced. Experimental results have shown that the predictive models trained by the machine learning algorithms are capable of predicting the surface roughness of additively manufacturing parts with very high accuracy. The prediction accuracy can be further improved using the data fusion method.

AB - To realise high quality, additively manufactured parts, real-time process monitoring and advanced predictive modelling tools are crucial for accelerating quality assurance in additive manufacturing. While previous research has demonstrated the effectiveness of physics- and model-based diagnosis and prognosis for additive manufacturing, very little research has been reported on real-time monitoring and predictive modelling of the surface roughness of additively manufactured parts. This paper presents a data fusion approach to predicting surface roughness in fused deposition modelling (FDM) processes. The predictive models are trained using random forests (RFs), support vector regression (SVR), ridge regression (RR), and least absolute shrinkage and selection operator (LASSO). A real-time monitoring system is developed to monitor the health condition of a FDM machine in real-time using multiple sensors. RFs, SVR, RR, and LASSO are demonstrated on the condition monitoring data collected from these sensors. To integrate the data sources, a feature-level data fusion method is introduced. Experimental results have shown that the predictive models trained by the machine learning algorithms are capable of predicting the surface roughness of additively manufacturing parts with very high accuracy. The prediction accuracy can be further improved using the data fusion method.

UR - http://www.scopus.com/inward/record.url?scp=85052073830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052073830&partnerID=8YFLogxK

U2 - 10.1080/00207543.2018.1505058

DO - 10.1080/00207543.2018.1505058

M3 - Article

AN - SCOPUS:85052073830

VL - 57

SP - 3992

EP - 4006

JO - International Journal of Production Research

JF - International Journal of Production Research

SN - 0020-7543

IS - 12

ER -