Multiple classification of the force and acceleration signals extracted during multiple machine processes: part 1 intelligent classification from an anomaly perspective

James Griffin, Alejandro J Doberti, Valbort Hernández, Nicolás A. Miranda, Maximiliano A. Vélez

Research output: Contribution to journalArticle

3 Citations (Scopus)
11 Downloads (Pure)

Abstract

This paper is the first in a two-part work, where the investigation into the characteristics of multiple machine pro-cesses is made in order to accurately control them via the frequently used machine centre platform. The two machining processes under investigation are grinding and hole making: for grinding anomalies, grinding burn and chatter and for hole making, drilling, increased tool wear and onset of drill tool malfunction, which is also significant to severe scoring and material dragging. Most researchers usually report on one ma-chining process as opposed to multiple which is less consistent with automated flexible systems where more than one ma-chining process must be catered for. For efficient monitoring of automated multiple manufacturing processes, any unwant-ed anomalies should be identified and dealt with in a prompt and seamless manner. This first part provides two experimen-tal set-ups (same set-up with tool interchange) to obtain signal signatures for both grinding and drilling phenomena (using the same material). Here, an approach based on neural net-works and CARTs is used to reliably detect anomalies for both processes using a single acquisition path, opening the door for control implementation.
Original languageEnglish
Pages (from-to)811-823
Number of pages13
JournalThe International Journal of Advanced Manufacturing Technology
Volume93
Issue number1-4
Early online date29 Mar 2017
DOIs
Publication statusPublished - Oct 2017

Fingerprint

Drilling
Interchanges
Machining
Wear of materials
Neural networks
Monitoring

Keywords

  • Burn
  • Chatter
  • Force
  • Accelerations
  • Drilling
  • Tool malfunction
  • Grinding
  • CART
  • Neural network
  • STFT

Cite this

Multiple classification of the force and acceleration signals extracted during multiple machine processes: part 1 intelligent classification from an anomaly perspective. / Griffin, James; Doberti, Alejandro J; Hernández, Valbort ; Miranda, Nicolás A. ; Vélez, Maximiliano A. .

In: The International Journal of Advanced Manufacturing Technology, Vol. 93, No. 1-4, 10.2017, p. 811-823.

Research output: Contribution to journalArticle

@article{f5783cb1d8854431b7327853ddd9173e,
title = "Multiple classification of the force and acceleration signals extracted during multiple machine processes: part 1 intelligent classification from an anomaly perspective",
abstract = "This paper is the first in a two-part work, where the investigation into the characteristics of multiple machine pro-cesses is made in order to accurately control them via the frequently used machine centre platform. The two machining processes under investigation are grinding and hole making: for grinding anomalies, grinding burn and chatter and for hole making, drilling, increased tool wear and onset of drill tool malfunction, which is also significant to severe scoring and material dragging. Most researchers usually report on one ma-chining process as opposed to multiple which is less consistent with automated flexible systems where more than one ma-chining process must be catered for. For efficient monitoring of automated multiple manufacturing processes, any unwant-ed anomalies should be identified and dealt with in a prompt and seamless manner. This first part provides two experimen-tal set-ups (same set-up with tool interchange) to obtain signal signatures for both grinding and drilling phenomena (using the same material). Here, an approach based on neural net-works and CARTs is used to reliably detect anomalies for both processes using a single acquisition path, opening the door for control implementation.",
keywords = "Burn, Chatter , Force, Accelerations , Drilling , Tool malfunction, Grinding , CART , Neural network, STFT",
author = "James Griffin and Doberti, {Alejandro J} and Valbort Hern{\'a}ndez and Miranda, {Nicol{\'a}s A.} and V{\'e}lez, {Maximiliano A.}",
year = "2017",
month = "10",
doi = "10.1007/s00170-017-0320-3",
language = "English",
volume = "93",
pages = "811--823",
journal = "The International Journal of Advanced Manufacturing Technology",
issn = "0268-3768",
publisher = "Springer Verlag",
number = "1-4",

}

TY - JOUR

T1 - Multiple classification of the force and acceleration signals extracted during multiple machine processes: part 1 intelligent classification from an anomaly perspective

AU - Griffin, James

AU - Doberti, Alejandro J

AU - Hernández, Valbort

AU - Miranda, Nicolás A.

AU - Vélez, Maximiliano A.

PY - 2017/10

Y1 - 2017/10

N2 - This paper is the first in a two-part work, where the investigation into the characteristics of multiple machine pro-cesses is made in order to accurately control them via the frequently used machine centre platform. The two machining processes under investigation are grinding and hole making: for grinding anomalies, grinding burn and chatter and for hole making, drilling, increased tool wear and onset of drill tool malfunction, which is also significant to severe scoring and material dragging. Most researchers usually report on one ma-chining process as opposed to multiple which is less consistent with automated flexible systems where more than one ma-chining process must be catered for. For efficient monitoring of automated multiple manufacturing processes, any unwant-ed anomalies should be identified and dealt with in a prompt and seamless manner. This first part provides two experimen-tal set-ups (same set-up with tool interchange) to obtain signal signatures for both grinding and drilling phenomena (using the same material). Here, an approach based on neural net-works and CARTs is used to reliably detect anomalies for both processes using a single acquisition path, opening the door for control implementation.

AB - This paper is the first in a two-part work, where the investigation into the characteristics of multiple machine pro-cesses is made in order to accurately control them via the frequently used machine centre platform. The two machining processes under investigation are grinding and hole making: for grinding anomalies, grinding burn and chatter and for hole making, drilling, increased tool wear and onset of drill tool malfunction, which is also significant to severe scoring and material dragging. Most researchers usually report on one ma-chining process as opposed to multiple which is less consistent with automated flexible systems where more than one ma-chining process must be catered for. For efficient monitoring of automated multiple manufacturing processes, any unwant-ed anomalies should be identified and dealt with in a prompt and seamless manner. This first part provides two experimen-tal set-ups (same set-up with tool interchange) to obtain signal signatures for both grinding and drilling phenomena (using the same material). Here, an approach based on neural net-works and CARTs is used to reliably detect anomalies for both processes using a single acquisition path, opening the door for control implementation.

KW - Burn

KW - Chatter

KW - Force

KW - Accelerations

KW - Drilling

KW - Tool malfunction

KW - Grinding

KW - CART

KW - Neural network

KW - STFT

U2 - 10.1007/s00170-017-0320-3

DO - 10.1007/s00170-017-0320-3

M3 - Article

VL - 93

SP - 811

EP - 823

JO - The International Journal of Advanced Manufacturing Technology

JF - The International Journal of Advanced Manufacturing Technology

SN - 0268-3768

IS - 1-4

ER -