Self adaptive diagnosis of tool wear with a microcontroller

Erkki Jantunen (Corresponding Author), E. Vaajoensuu

Research output: Contribution to journalArticleScientificpeer-review

5 Citations (Scopus)

Abstract

Tool wear monitoring is very important for economical reasons. In this paper a new and very economical solution is presented. The idea is to use easily available microcontroller based hardware, which is very cheap due to mass production. The cheap hardware is combined together with sophisticated software. The use of regression analysis techniques together with fuzzy logic makes the system self adaptive, i.e., the system can monitor new tools automatically after a short learning period. The automatic learning period typically only lasts in the order of 5% of the total tool life time of an individual tool and thus makes the introduction of the method really simple and effective. The article focuses on the introduction and use of microcontroller based hardware but also covers and summarizes the principles behind the new approach which makes it possible to use hardware with limited capability. A more detailed description of the physical and mathematical background can be found in the given references. The proposed approach is tested with data from drilling tests.
Original languageEnglish
Pages (from-to)223-230
Number of pages8
JournalJournal of Intelligent Manufacturing
Volume21
Issue number2
DOIs
Publication statusPublished - 2010
MoE publication typeA1 Journal article-refereed

Fingerprint

Microcontrollers
Wear of materials
Hardware
Regression analysis
Fuzzy logic
Drilling
Monitoring

Keywords

  • Condition monitoring
  • Diagnosis
  • Drill wear
  • Fuzzy classification
  • Microcontroller
  • Polynomial regression analysis

Cite this

Jantunen, Erkki ; Vaajoensuu, E. / Self adaptive diagnosis of tool wear with a microcontroller. In: Journal of Intelligent Manufacturing. 2010 ; Vol. 21, No. 2. pp. 223-230.
@article{d01e155441774a0992a64d04f05216c1,
title = "Self adaptive diagnosis of tool wear with a microcontroller",
abstract = "Tool wear monitoring is very important for economical reasons. In this paper a new and very economical solution is presented. The idea is to use easily available microcontroller based hardware, which is very cheap due to mass production. The cheap hardware is combined together with sophisticated software. The use of regression analysis techniques together with fuzzy logic makes the system self adaptive, i.e., the system can monitor new tools automatically after a short learning period. The automatic learning period typically only lasts in the order of 5{\%} of the total tool life time of an individual tool and thus makes the introduction of the method really simple and effective. The article focuses on the introduction and use of microcontroller based hardware but also covers and summarizes the principles behind the new approach which makes it possible to use hardware with limited capability. A more detailed description of the physical and mathematical background can be found in the given references. The proposed approach is tested with data from drilling tests.",
keywords = "Condition monitoring, Diagnosis, Drill wear, Fuzzy classification, Microcontroller, Polynomial regression analysis",
author = "Erkki Jantunen and E. Vaajoensuu",
year = "2010",
doi = "10.1007/s10845-008-0195-0",
language = "English",
volume = "21",
pages = "223--230",
journal = "Journal of Intelligent Manufacturing",
issn = "0956-5515",
publisher = "Springer",
number = "2",

}

Self adaptive diagnosis of tool wear with a microcontroller. / Jantunen, Erkki (Corresponding Author); Vaajoensuu, E.

In: Journal of Intelligent Manufacturing, Vol. 21, No. 2, 2010, p. 223-230.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Self adaptive diagnosis of tool wear with a microcontroller

AU - Jantunen, Erkki

AU - Vaajoensuu, E.

PY - 2010

Y1 - 2010

N2 - Tool wear monitoring is very important for economical reasons. In this paper a new and very economical solution is presented. The idea is to use easily available microcontroller based hardware, which is very cheap due to mass production. The cheap hardware is combined together with sophisticated software. The use of regression analysis techniques together with fuzzy logic makes the system self adaptive, i.e., the system can monitor new tools automatically after a short learning period. The automatic learning period typically only lasts in the order of 5% of the total tool life time of an individual tool and thus makes the introduction of the method really simple and effective. The article focuses on the introduction and use of microcontroller based hardware but also covers and summarizes the principles behind the new approach which makes it possible to use hardware with limited capability. A more detailed description of the physical and mathematical background can be found in the given references. The proposed approach is tested with data from drilling tests.

AB - Tool wear monitoring is very important for economical reasons. In this paper a new and very economical solution is presented. The idea is to use easily available microcontroller based hardware, which is very cheap due to mass production. The cheap hardware is combined together with sophisticated software. The use of regression analysis techniques together with fuzzy logic makes the system self adaptive, i.e., the system can monitor new tools automatically after a short learning period. The automatic learning period typically only lasts in the order of 5% of the total tool life time of an individual tool and thus makes the introduction of the method really simple and effective. The article focuses on the introduction and use of microcontroller based hardware but also covers and summarizes the principles behind the new approach which makes it possible to use hardware with limited capability. A more detailed description of the physical and mathematical background can be found in the given references. The proposed approach is tested with data from drilling tests.

KW - Condition monitoring

KW - Diagnosis

KW - Drill wear

KW - Fuzzy classification

KW - Microcontroller

KW - Polynomial regression analysis

U2 - 10.1007/s10845-008-0195-0

DO - 10.1007/s10845-008-0195-0

M3 - Article

VL - 21

SP - 223

EP - 230

JO - Journal of Intelligent Manufacturing

JF - Journal of Intelligent Manufacturing

SN - 0956-5515

IS - 2

ER -