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 -