Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
ANOMALY DETECTION DEVICE, MACHINE TOOL, ANOMALY DETECTION METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2020/121429
Kind Code:
A1
Abstract:
Provided is an anomaly detection device for a machine tool comprising a blade tool for drilling, a first driving unit for axially rotating said blade tool, and a second driving unit for moving said blade tool in the Z-axis direction, which is the axial direction of the blade tool. The anomaly detection device comprises: a time series data-acquiring unit for acquiring object time series data, which is time series data on the movement load of the blade tool in the Z-axis direction during drilling; an evaluation value-deriving unit for deriving an evaluation value, which represents the degree of resemblance between at least a portion of the acquired object time series data and at least a portion of reference time series data that can be considered to be normal movement load time series data, using singular spectrum transformation; and an anomaly-determining unit for determining the presence or absence of an anomaly of the machine tool on the basis of the derived evaluation value.

Inventors:
UCHIDA GO (JP)
ESAKI HIROTAKE (JP)
OIKE HIROSHI (JP)
NALLATHAMBI ANUSUYA (JP)
Application Number:
PCT/JP2018/045640
Publication Date:
June 18, 2020
Filing Date:
December 12, 2018
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
FUJI CORP (JP)
International Classes:
B23Q17/09; B23B49/00
Foreign References:
JP2004130407A2004-04-30
JP2001079734A2001-03-27
JPH06201398A1994-07-19
Other References:
IDE, TSUYOSHI: "INTRODUCTION TO ANOMALY DETECTION USING MACHINE LEARNING", 2015, CORONA PUBLISHING CO., LTD, Tokyo, ISBN: 978-4-339-02491-3, pages: 194 - 205
Attorney, Agent or Firm:
ITEC INTERNATIONAL PATENT FIRM (JP)
Download PDF: