Enhanced particle filter for tool wear prediction

Jinjiang Wang; Peng Wang; Robert X. Gao

doi:10.1016/j.jmsy.2015.03.005

Enhanced particle filter for tool wear prediction

Jinjiang Wang
, Peng Wang
, Robert X. Gao

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

152 Scopus citations

Abstract

Timely assessment and prediction of tool wear is essential to ensuring part quality, minimizing material waste, and contributing to sustainable manufacturing. This paper presents a probabilistic method based on particle filtering to account for uncertainties in the tool wear process. Tool wear state is predicted by recursively updating a physics-based tool wear rate model with online measurement, following a Bayesian inference scheme. For long term prediction where online measurement is not available, regression analysis methods such as autoregressive model and support vector regression are investigated by incorporating predicted measurement into particle filter. The effectiveness of the developed method is demonstrated using experiments performed on a CNC milling machine.

Original language	English
Pages (from-to)	35-45
Number of pages	11
Journal	Journal of Manufacturing Systems
Volume	36
DOIs	https://doi.org/10.1016/j.jmsy.2015.03.005
State	Published - May 22 2015

Bibliographical note

Publisher Copyright:
© 2015 The Society of Manufacturing Engineers. Published by Elsevier Ltd. All rights reserved.

Funding

This research was partially supported by National Science Foundation under grants CNS-1239030 and CMMI-1300999 , and Science Foundation of China University of Petroleum, Beijing (no. 2462014YJRC039 ). Valuable comments from the anonymous reviewers are sincerely appreciated.

Funders	Funder number
National Science Foundation Arctic Social Science Program	CMMI-1300999, CNS-1239030
Science Foundation of China University of Petroleum, Beijing	2462014YJRC039

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

ASJC Scopus subject areas

Software
Control and Systems Engineering
Hardware and Architecture
Industrial and Manufacturing Engineering

Access to Document

10.1016/j.jmsy.2015.03.005

Cite this

@article{dcdf180a60aa406e81f470ba9c4bf00f,

title = "Enhanced particle filter for tool wear prediction",

abstract = "Timely assessment and prediction of tool wear is essential to ensuring part quality, minimizing material waste, and contributing to sustainable manufacturing. This paper presents a probabilistic method based on particle filtering to account for uncertainties in the tool wear process. Tool wear state is predicted by recursively updating a physics-based tool wear rate model with online measurement, following a Bayesian inference scheme. For long term prediction where online measurement is not available, regression analysis methods such as autoregressive model and support vector regression are investigated by incorporating predicted measurement into particle filter. The effectiveness of the developed method is demonstrated using experiments performed on a CNC milling machine.",

author = "Jinjiang Wang and Peng Wang and Gao, \{Robert X.\}",

year = "2015",

month = may,

day = "22",

doi = "10.1016/j.jmsy.2015.03.005",

language = "English",

volume = "36",

pages = "35--45",

}

TY - JOUR

T1 - Enhanced particle filter for tool wear prediction

AU - Wang, Jinjiang

AU - Wang, Peng

AU - Gao, Robert X.

PY - 2015/5/22

Y1 - 2015/5/22

N2 - Timely assessment and prediction of tool wear is essential to ensuring part quality, minimizing material waste, and contributing to sustainable manufacturing. This paper presents a probabilistic method based on particle filtering to account for uncertainties in the tool wear process. Tool wear state is predicted by recursively updating a physics-based tool wear rate model with online measurement, following a Bayesian inference scheme. For long term prediction where online measurement is not available, regression analysis methods such as autoregressive model and support vector regression are investigated by incorporating predicted measurement into particle filter. The effectiveness of the developed method is demonstrated using experiments performed on a CNC milling machine.

AB - Timely assessment and prediction of tool wear is essential to ensuring part quality, minimizing material waste, and contributing to sustainable manufacturing. This paper presents a probabilistic method based on particle filtering to account for uncertainties in the tool wear process. Tool wear state is predicted by recursively updating a physics-based tool wear rate model with online measurement, following a Bayesian inference scheme. For long term prediction where online measurement is not available, regression analysis methods such as autoregressive model and support vector regression are investigated by incorporating predicted measurement into particle filter. The effectiveness of the developed method is demonstrated using experiments performed on a CNC milling machine.

UR - https://www.scopus.com/pages/publications/84930009562

UR - https://www.scopus.com/pages/publications/84930009562#tab=citedBy

U2 - 10.1016/j.jmsy.2015.03.005

DO - 10.1016/j.jmsy.2015.03.005

M3 - Article

AN - SCOPUS:84930009562

SN - 0278-6125

VL - 36

SP - 35

EP - 45

JO - Journal of Manufacturing Systems

JF - Journal of Manufacturing Systems

ER -

Enhanced particle filter for tool wear prediction

Abstract

Bibliographical note

Funding

UN SDGs

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this