A novel generalized approach for real-time tool condition monitoring

Download
  1. Get@NRC: A novel generalized approach for real-time tool condition monitoring (Opens in a new window)
DOIResolve DOI: http://doi.org/10.1115/1.4037553
AuthorSearch for: ; Search for: ; Search for: ; Search for:
TypeArticle
Journal titleJournal of Manufacturing Science and Engineering
ISSN1087-1357
1528-8935
Subjectcondition monitoring; cutting; signals; statistical analysis; failure; wear; machinery; engines; product quality; motors
AbstractIn high speed cutting processes, late replacement of defective tools may lead to machine breakdowns and badly affect the product quality, which subsequently lead to scrap parts and high process costs. Accurate tool condition detection is essential to achieve high level of competitiveness via increasing process productivity and standardizing the quality of the produced parts. Therefore, tool condition monitoring (TCM) systems have been widely emphasized as an important principle to achieve these industrial demands. Several studies for tool condition monitoring were carried out to capture tool failure using complex conventional and artificial intelligence techniques. However, these studies suffer from the absence of standardization and generalization. Hence, this paper presents a robust and reliable processing technique for the cutting process signals to extract generalized features in time and frequency domains. The proposed technique masks the effects of the cutting conditions on the extracted features and accentuates the tool condition effect. Characterization and statistical analysis of the processed features were performed to examine their sensitivity to the tool condition. The results revealed the processing technique capability to separate the features extracted from the spindle motor current signals into two mutually exclusive clusters according to their tool condition. The statistical analysis results were employed to optimize the tool condition detection approach using linear discrimination analysis LDA model. The results indicate the capability of the processing technique to minimize the system learning effort and to detect tool wear above the threshold level with accuracy above 90%.
Publication date
PublisherAmerican Society of Mechanical Engineers
LanguageEnglish
AffiliationNational Research Council Canada; Aerospace
Peer reviewedYes
NPARC number23002394
Export citationExport as RIS
Report a correctionReport a correction
Record identifierb2fa53a0-07fd-4ded-ad21-870e16aaf261
Record created2017-10-26
Record modified2017-10-26
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)