A utilization method of big sensor data to detect tool anomaly in machining process

Yasuo Kondo, Sho Mizunoya, Satoshi Sakamoto, Kenji Yamaguchi, Tsuyoshi Fujita, Mitsugu Yamaguchi

    Abstract

    The essential features and scale of sensor data was discussed to monitor the tool anomaly in the machining process from the pattern variation of large scale sensor data such as vibration and effective power. The cycle data, the time series sensor data collected with an acceleration or power sensor in one periodical machining of the given groove shape, had been measured periodically. In this study, the graphic pattern formed by overwriting the time series cycle data on a specific coordinate system was treated as the "big sensor data". The big data from the effective power sensor can stably respond to the cutting power changes and showed a strong possibility as a detecting device for tool anomaly such as abrasive wear and chipping. While the big data from the acceleration sensor only responded to a big event like the chattering vibration. The number of cycle data needed to generate the big sensor data also affected on the detection sensitivity for tool anomaly. It had been required a family of time series sensor data enough to represent the cutting power change as a visual graphic pattern.

    Original languageEnglish
    Title of host publicationAdvanced Materials Research and Technologies
    PublisherTrans Tech Publications Ltd
    Pages122-126
    Number of pages5
    Volume719
    ISBN (Print)9783035710052
    DOIs
    StatePublished - 2017
    EventInternational Conference on Advanced Materials Research and Manufacturing Technologies, AMRMT 2016 - Singapore, Singapore

    Publication series

    NameKey Engineering Materials
    Volume719
    ISSN (Print)10139826

    Other

    OtherInternational Conference on Advanced Materials Research and Manufacturing Technologies, AMRMT 2016
    CountrySingapore
    CitySingapore
    Period16/8/1816/8/20

    Fingerprint

    Sensors
    Time series
    Machining
    Big data
    Abrasion

    Keywords

    • Big data
    • Feature extraction
    • Machining process
    • Sensor Data
    • Tool anomaly

    ASJC Scopus subject areas

    • Materials Science(all)
    • Mechanics of Materials
    • Mechanical Engineering

    Cite this

    Kondo, Y., Mizunoya, S., Sakamoto, S., Yamaguchi, K., Fujita, T., & Yamaguchi, M. (2017). A utilization method of big sensor data to detect tool anomaly in machining process. In Advanced Materials Research and Technologies. (Vol. 719, pp. 122-126). (Key Engineering Materials; Vol. 719). Trans Tech Publications Ltd. DOI: 10.4028/www.scientific.net/KEM.719.122

    A utilization method of big sensor data to detect tool anomaly in machining process. / Kondo, Yasuo; Mizunoya, Sho; Sakamoto, Satoshi; Yamaguchi, Kenji; Fujita, Tsuyoshi; Yamaguchi, Mitsugu.

    Advanced Materials Research and Technologies. Vol. 719 Trans Tech Publications Ltd, 2017. p. 122-126 (Key Engineering Materials; Vol. 719).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kondo, Y, Mizunoya, S, Sakamoto, S, Yamaguchi, K, Fujita, T & Yamaguchi, M 2017, A utilization method of big sensor data to detect tool anomaly in machining process. in Advanced Materials Research and Technologies. vol. 719, Key Engineering Materials, vol. 719, Trans Tech Publications Ltd, pp. 122-126, International Conference on Advanced Materials Research and Manufacturing Technologies, AMRMT 2016, Singapore, Singapore, 18-20 August. DOI: 10.4028/www.scientific.net/KEM.719.122
    Kondo Y, Mizunoya S, Sakamoto S, Yamaguchi K, Fujita T, Yamaguchi M. A utilization method of big sensor data to detect tool anomaly in machining process. In Advanced Materials Research and Technologies. Vol. 719. Trans Tech Publications Ltd. 2017. p. 122-126. (Key Engineering Materials). Available from, DOI: 10.4028/www.scientific.net/KEM.719.122

    Kondo, Yasuo; Mizunoya, Sho; Sakamoto, Satoshi; Yamaguchi, Kenji; Fujita, Tsuyoshi; Yamaguchi, Mitsugu / A utilization method of big sensor data to detect tool anomaly in machining process.

    Advanced Materials Research and Technologies. Vol. 719 Trans Tech Publications Ltd, 2017. p. 122-126 (Key Engineering Materials; Vol. 719).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    @inbook{70307027f2984a67abbe2df146e4e06b,
    title = "A utilization method of big sensor data to detect tool anomaly in machining process",
    keywords = "Big data, Feature extraction, Machining process, Sensor Data, Tool anomaly",
    author = "Yasuo Kondo and Sho Mizunoya and Satoshi Sakamoto and Kenji Yamaguchi and Tsuyoshi Fujita and Mitsugu Yamaguchi",
    year = "2017",
    doi = "10.4028/www.scientific.net/KEM.719.122",
    isbn = "9783035710052",
    volume = "719",
    series = "Key Engineering Materials",
    publisher = "Trans Tech Publications Ltd",
    pages = "122--126",
    booktitle = "Advanced Materials Research and Technologies",

    }

    TY - CHAP

    T1 - A utilization method of big sensor data to detect tool anomaly in machining process

    AU - Kondo,Yasuo

    AU - Mizunoya,Sho

    AU - Sakamoto,Satoshi

    AU - Yamaguchi,Kenji

    AU - Fujita,Tsuyoshi

    AU - Yamaguchi,Mitsugu

    PY - 2017

    Y1 - 2017

    N2 - The essential features and scale of sensor data was discussed to monitor the tool anomaly in the machining process from the pattern variation of large scale sensor data such as vibration and effective power. The cycle data, the time series sensor data collected with an acceleration or power sensor in one periodical machining of the given groove shape, had been measured periodically. In this study, the graphic pattern formed by overwriting the time series cycle data on a specific coordinate system was treated as the "big sensor data". The big data from the effective power sensor can stably respond to the cutting power changes and showed a strong possibility as a detecting device for tool anomaly such as abrasive wear and chipping. While the big data from the acceleration sensor only responded to a big event like the chattering vibration. The number of cycle data needed to generate the big sensor data also affected on the detection sensitivity for tool anomaly. It had been required a family of time series sensor data enough to represent the cutting power change as a visual graphic pattern.

    AB - The essential features and scale of sensor data was discussed to monitor the tool anomaly in the machining process from the pattern variation of large scale sensor data such as vibration and effective power. The cycle data, the time series sensor data collected with an acceleration or power sensor in one periodical machining of the given groove shape, had been measured periodically. In this study, the graphic pattern formed by overwriting the time series cycle data on a specific coordinate system was treated as the "big sensor data". The big data from the effective power sensor can stably respond to the cutting power changes and showed a strong possibility as a detecting device for tool anomaly such as abrasive wear and chipping. While the big data from the acceleration sensor only responded to a big event like the chattering vibration. The number of cycle data needed to generate the big sensor data also affected on the detection sensitivity for tool anomaly. It had been required a family of time series sensor data enough to represent the cutting power change as a visual graphic pattern.

    KW - Big data

    KW - Feature extraction

    KW - Machining process

    KW - Sensor Data

    KW - Tool anomaly

    UR - http://www.scopus.com/inward/record.url?scp=85000962031&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85000962031&partnerID=8YFLogxK

    U2 - 10.4028/www.scientific.net/KEM.719.122

    DO - 10.4028/www.scientific.net/KEM.719.122

    M3 - Conference contribution

    SN - 9783035710052

    VL - 719

    T3 - Key Engineering Materials

    SP - 122

    EP - 126

    BT - Advanced Materials Research and Technologies

    PB - Trans Tech Publications Ltd

    ER -