A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction

Ryo Fujita, Takashi Yoshimi

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

Abstract

This research aims to develop an anomaly prediction method only based on sensor data acquired from machine tools. In order to realize this aim, first of all, it is necessary to extract the feature to classify whether the machine tool is in an anomalous state or normal state. This paper shows the result of examining the feature extraction method of machine tool applying distribution and chaos theory to acquired sensor data. In the distribution method, an anomalous state and a normal state are compared by creating a frequency distribution diagram using the heat map. In chaos theory, the anomalous state and the normal state are compared by reconstructing attractors using Takens' embedding theorem. In addition, quantitative evaluation using topological geometry to the anomaly prediction of machine tools is considered and its result is shown. Both methods, the distribution and chaos theory, were confirmed their features for classifying the normal state and the anomalous state. And, we also confirmed the effectiveness of the quantitative analysis of the reconstructed attractors by using the method of topological geometry.

Original languageEnglish
Title of host publication2017 Asian Control Conference, ASCC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1505-1508
Number of pages4
Volume2018-January
ISBN (Electronic)9781509015733
DOIs
Publication statusPublished - 2018 Feb 7
Event2017 11th Asian Control Conference, ASCC 2017 - Gold Coast, Australia
Duration: 2017 Dec 172017 Dec 20

Other

Other2017 11th Asian Control Conference, ASCC 2017
CountryAustralia
CityGold Coast
Period17/12/1717/12/20

ASJC Scopus subject areas

  • Control and Optimization

Cite this

Fujita, R., & Yoshimi, T. (2018). A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction. In 2017 Asian Control Conference, ASCC 2017 (Vol. 2018-January, pp. 1505-1508). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASCC.2017.8287396

A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction. / Fujita, Ryo; Yoshimi, Takashi.

2017 Asian Control Conference, ASCC 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1505-1508.

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

Fujita, R & Yoshimi, T 2018, A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction. in 2017 Asian Control Conference, ASCC 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1505-1508, 2017 11th Asian Control Conference, ASCC 2017, Gold Coast, Australia, 17/12/17. https://doi.org/10.1109/ASCC.2017.8287396
Fujita R, Yoshimi T. A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction. In 2017 Asian Control Conference, ASCC 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1505-1508 https://doi.org/10.1109/ASCC.2017.8287396
Fujita, Ryo ; Yoshimi, Takashi. / A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction. 2017 Asian Control Conference, ASCC 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1505-1508
@inproceedings{8150df4c553a40aa87a3c7b4afc9492a,
title = "A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction",
abstract = "This research aims to develop an anomaly prediction method only based on sensor data acquired from machine tools. In order to realize this aim, first of all, it is necessary to extract the feature to classify whether the machine tool is in an anomalous state or normal state. This paper shows the result of examining the feature extraction method of machine tool applying distribution and chaos theory to acquired sensor data. In the distribution method, an anomalous state and a normal state are compared by creating a frequency distribution diagram using the heat map. In chaos theory, the anomalous state and the normal state are compared by reconstructing attractors using Takens' embedding theorem. In addition, quantitative evaluation using topological geometry to the anomaly prediction of machine tools is considered and its result is shown. Both methods, the distribution and chaos theory, were confirmed their features for classifying the normal state and the anomalous state. And, we also confirmed the effectiveness of the quantitative analysis of the reconstructed attractors by using the method of topological geometry.",
author = "Ryo Fujita and Takashi Yoshimi",
year = "2018",
month = "2",
day = "7",
doi = "10.1109/ASCC.2017.8287396",
language = "English",
volume = "2018-January",
pages = "1505--1508",
booktitle = "2017 Asian Control Conference, ASCC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A study on anomaly prediction method of machine tools - Feature extraction for anomaly prediction

AU - Fujita, Ryo

AU - Yoshimi, Takashi

PY - 2018/2/7

Y1 - 2018/2/7

N2 - This research aims to develop an anomaly prediction method only based on sensor data acquired from machine tools. In order to realize this aim, first of all, it is necessary to extract the feature to classify whether the machine tool is in an anomalous state or normal state. This paper shows the result of examining the feature extraction method of machine tool applying distribution and chaos theory to acquired sensor data. In the distribution method, an anomalous state and a normal state are compared by creating a frequency distribution diagram using the heat map. In chaos theory, the anomalous state and the normal state are compared by reconstructing attractors using Takens' embedding theorem. In addition, quantitative evaluation using topological geometry to the anomaly prediction of machine tools is considered and its result is shown. Both methods, the distribution and chaos theory, were confirmed their features for classifying the normal state and the anomalous state. And, we also confirmed the effectiveness of the quantitative analysis of the reconstructed attractors by using the method of topological geometry.

AB - This research aims to develop an anomaly prediction method only based on sensor data acquired from machine tools. In order to realize this aim, first of all, it is necessary to extract the feature to classify whether the machine tool is in an anomalous state or normal state. This paper shows the result of examining the feature extraction method of machine tool applying distribution and chaos theory to acquired sensor data. In the distribution method, an anomalous state and a normal state are compared by creating a frequency distribution diagram using the heat map. In chaos theory, the anomalous state and the normal state are compared by reconstructing attractors using Takens' embedding theorem. In addition, quantitative evaluation using topological geometry to the anomaly prediction of machine tools is considered and its result is shown. Both methods, the distribution and chaos theory, were confirmed their features for classifying the normal state and the anomalous state. And, we also confirmed the effectiveness of the quantitative analysis of the reconstructed attractors by using the method of topological geometry.

UR - http://www.scopus.com/inward/record.url?scp=85047497174&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047497174&partnerID=8YFLogxK

U2 - 10.1109/ASCC.2017.8287396

DO - 10.1109/ASCC.2017.8287396

M3 - Conference contribution

AN - SCOPUS:85047497174

VL - 2018-January

SP - 1505

EP - 1508

BT - 2017 Asian Control Conference, ASCC 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -