Tool wear estimation in micro-machining. Part II: neural-network-based periodic inspector for nonmetals

Citation
In. Tansel et al., Tool wear estimation in micro-machining. Part II: neural-network-based periodic inspector for nonmetals, INT J MACH, 40(4), 2000, pp. 609-620
Citations number
18
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Mechanical Engineering
Journal title
INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE
ISSN journal
0890-6955 → ACNP
Volume
40
Issue
4
Year of publication
2000
Pages
609 - 620
Database
ISI
SICI code
0890-6955(200003)40:4<609:TWEIMP>2.0.ZU;2-N
Abstract
Cutting forces are small, and in many cases insignificant, compared with no ise during the micro-machining of many non-metals. The Neural-Network-based Periodic Tool Inspector ((NPTI)-P-2) is introduced to evaluate tool condit ion periodically on a test piece during the machining of non-metal workpiec es. The cutting forces are measured when a slot is being cut on the test pi ece and the neural network estimates the tool life from the variation of th e feed- and thrust-direction cutting forces. The performances of three enco ding methods (force variation, segmental averaging and wavelet transformati ons) and two neural networks [back propagation (BP) and probabilistic neura l network (PNN)] are compared. The advantages of (NPTI)-P-2 are simplicity, low cost, reliability and simple computational requirements. (C) 1999 Else vier Science Ltd. All rights reserved.