A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests

Dazhong Wu, Connor Jennings, Janis Terpenny, Robert X. Gao, Soundar Kumara

Research output: Contribution to journalArticle

67 Citations (Scopus)

Abstract

Manufacturers have faced an increasing need for the development of predictive models that predict mechanical failures and the remaining useful life (RUL) of manufacturing systems or components. Classical model-based or physics-based prognostics often require an in-depth physical understanding of the system of interest to develop closed-form mathematical models. However, prior knowledge of system behavior is not always available, especially for complex manufacturing systems and processes. To complement model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While previous research has demonstrated the effectiveness of data-driven methods, most of these prognostic methods are based on classical machine learning techniques, such as artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to introduce a random forests (RFs)-based prognostic method for tool wear prediction as well as compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an experimental data collected from 315 milling tests. Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR.

Original languageEnglish (US)
Article number071018
JournalJournal of Manufacturing Science and Engineering, Transactions of the ASME
Volume139
Issue number7
DOIs
StatePublished - Jul 1 2017

Fingerprint

Learning algorithms
Learning systems
Backpropagation
Wear of materials
Neural networks
Artificial intelligence
Machinery
Physics
Mathematical models

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Mechanical Engineering
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

@article{dfb024157b5842d69beb5c0a925495c9,
title = "A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests",
abstract = "Manufacturers have faced an increasing need for the development of predictive models that predict mechanical failures and the remaining useful life (RUL) of manufacturing systems or components. Classical model-based or physics-based prognostics often require an in-depth physical understanding of the system of interest to develop closed-form mathematical models. However, prior knowledge of system behavior is not always available, especially for complex manufacturing systems and processes. To complement model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While previous research has demonstrated the effectiveness of data-driven methods, most of these prognostic methods are based on classical machine learning techniques, such as artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to introduce a random forests (RFs)-based prognostic method for tool wear prediction as well as compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an experimental data collected from 315 milling tests. Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR.",
author = "Dazhong Wu and Connor Jennings and Janis Terpenny and Gao, {Robert X.} and Soundar Kumara",
year = "2017",
month = "7",
day = "1",
doi = "10.1115/1.4036350",
language = "English (US)",
volume = "139",
journal = "Journal of Manufacturing Science and Engineering, Transactions of the ASME",
issn = "1087-1357",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "7",

}

A Comparative Study on Machine Learning Algorithms for Smart Manufacturing : Tool Wear Prediction Using Random Forests. / Wu, Dazhong; Jennings, Connor; Terpenny, Janis; Gao, Robert X.; Kumara, Soundar.

In: Journal of Manufacturing Science and Engineering, Transactions of the ASME, Vol. 139, No. 7, 071018, 01.07.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Comparative Study on Machine Learning Algorithms for Smart Manufacturing

T2 - Tool Wear Prediction Using Random Forests

AU - Wu, Dazhong

AU - Jennings, Connor

AU - Terpenny, Janis

AU - Gao, Robert X.

AU - Kumara, Soundar

PY - 2017/7/1

Y1 - 2017/7/1

N2 - Manufacturers have faced an increasing need for the development of predictive models that predict mechanical failures and the remaining useful life (RUL) of manufacturing systems or components. Classical model-based or physics-based prognostics often require an in-depth physical understanding of the system of interest to develop closed-form mathematical models. However, prior knowledge of system behavior is not always available, especially for complex manufacturing systems and processes. To complement model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While previous research has demonstrated the effectiveness of data-driven methods, most of these prognostic methods are based on classical machine learning techniques, such as artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to introduce a random forests (RFs)-based prognostic method for tool wear prediction as well as compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an experimental data collected from 315 milling tests. Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR.

AB - Manufacturers have faced an increasing need for the development of predictive models that predict mechanical failures and the remaining useful life (RUL) of manufacturing systems or components. Classical model-based or physics-based prognostics often require an in-depth physical understanding of the system of interest to develop closed-form mathematical models. However, prior knowledge of system behavior is not always available, especially for complex manufacturing systems and processes. To complement model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While previous research has demonstrated the effectiveness of data-driven methods, most of these prognostic methods are based on classical machine learning techniques, such as artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to introduce a random forests (RFs)-based prognostic method for tool wear prediction as well as compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an experimental data collected from 315 milling tests. Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR.

UR - http://www.scopus.com/inward/record.url?scp=85018483445&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018483445&partnerID=8YFLogxK

U2 - 10.1115/1.4036350

DO - 10.1115/1.4036350

M3 - Article

AN - SCOPUS:85018483445

VL - 139

JO - Journal of Manufacturing Science and Engineering, Transactions of the ASME

JF - Journal of Manufacturing Science and Engineering, Transactions of the ASME

SN - 1087-1357

IS - 7

M1 - 071018

ER -