Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/14608
Title: Approaches for efficient tool condition monitoring based on support vector machine
Authors: SUN JIE
Keywords: tool condition monitoring, support vector machine, feature selection, acoustic emission, cutting force
Issue Date: 23-Apr-2005
Source: SUN JIE (2005-04-23). Approaches for efficient tool condition monitoring based on support vector machine. ScholarBank@NUS Repository.
Abstract: The objective of this study is to propose a framework of tool condition monitoring (TCM), which generalizes sensing signal selection, feature analysis, performance evaluation and decision making. Acoustic emission and cutting force are used as sensor signals in this monitoring task.Firstly, basic requirements to sensor signals are proposed, and feature analysis is utilized to select the most effective set as the inputs of tool condition identification. Automatic relevance determination and support vector machine (SVM) are coupled together to explore this feature set from the commonly used features. Secondly, a new performance evaluation function with the potential manufacturing loss consideration is suggested to evaluate the performance of TCM. Two kinds of manufacturing loss due to misclassifying tool conditions are analyzed, and a modified SVM approach with two regularization parameters is employed to optimize this evaluation function. Finally this method is extended to multilevel classification of tool conditions. The experimental results confirm that the developed framework can reliably and efficiently identify tool conditions over a range of cutting processes. The contribution of this research is to improve the efficiency and reliability of TCM for future industrial applications.
URI: http://scholarbank.nus.edu.sg/handle/10635/14608
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
SunJ_Cover.pdf7.65 kBAdobe PDF

OPEN

NoneView/Download
SunJ_chapter0.pdf123.18 kBAdobe PDF

OPEN

NoneView/Download
SUNJ_CHAPTERS.pdf1.15 MBAdobe PDF

OPEN

NoneView/Download
SUNJ_appendix.pdf641.84 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

293
checked on Dec 11, 2017

Download(s)

727
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.