Please use this identifier to cite or link to this item:
Title: Feature-based tool condition monitoring for milling
Keywords: milling, TCM, BSVM, ARD, TWE, TWR
Issue Date: 28-Dec-2004
Citation: DONG JIANFEI (2004-12-28). Feature-based tool condition monitoring for milling. ScholarBank@NUS Repository.
Abstract: This study is to investigate the effectiveness of various features for tool condition monitoring (TCM) during milling processes. The study concentrates on the approaches based on force signatures. 16 different feature extraction methodologies are considered. These include time-series analysis, statistical analysis, and signal processing approaches. Two innovative methodologies for neural networks are adopted in TCM, which are Bayesian interpretations for support vector machines (BSVM) and automatic relevance determination. Based on these approaches, two relevant feature sets have been identified from the 16 features for two main tasks in TCM: tool wear estimation (TWE) and tool wear recognition (TWR). The generalization capabilities of the entire, selected, and rejected feature sets have been tested and compared. Good generalization results have been achieved for both TWE and TWR using the selected features, which are superior to those using either the entire or the rejected feature set. The results prove that the selected features are relatively more relevant to tool wear processes, and draw attention to using the BSVM methodologies in TCM.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
MEngThesisDongJianfei.pdf4.05 MBAdobe PDF



Page view(s)

checked on Nov 17, 2018


checked on Nov 17, 2018

Google ScholarTM


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