Data Driven Anomaly Diagnosis for Machining Processes

Yuchen Liang, Sheng Wang, Weidong Li, Xin Lu

Research output: Contribution to journalArticle

4 Downloads (Pure)

Abstract

To achieve zero-defect production during computer numerical control (CNC) machining processes, it is imperative to develop effective diagnosis systems to detect anomalies efficiently. However, due to the dynamic conditions of the machine and tooling during machining processes, the relevant diagnosis systems currently adopted in industries are incompetent. To address this issue, this paper presents a novel data-driven diagnosis system for anomalies. In this system, power data for condition monitoring are continuously collected during dynamic machining processes to support online diagnosis analysis. To facilitate the analysis, preprocessing mechanisms have been designed to de-noise, normalize, and align the monitored data. Important features are extracted from the monitored data and thresholds are defined to identify anomalies. Considering the dynamic conditions of the machine and tooling during machining processes, the thresholds used to identify anomalies can vary. Based on historical data, the values of thresholds are optimized using a fruit fly optimization (FFO) algorithm to achieve more accurate detection. Practical case studies were used to validate the system, thereby demonstrating the potential and effectiveness of the system for industrial applications.

Original languageEnglish
Pages (from-to)646-652
Number of pages7
JournalEngineering
Volume5
Issue number4
Early online date19 Jun 2019
DOIs
Publication statusPublished - Aug 2019

Fingerprint

Machining
Condition monitoring
Fruits
Industrial applications
Defects
Industry

Bibliographical note

Published by Elsevier LTD on behalf of Chinese Academy of Engineering and Higher Education Press Limited Company. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Keywords

  • Anomaly detection
  • Computer numerical control machining
  • Data-driven method
  • Fruit fly optimization algorithm

ASJC Scopus subject areas

  • Computer Science(all)
  • Environmental Engineering
  • Chemical Engineering(all)
  • Materials Science (miscellaneous)
  • Energy Engineering and Power Technology
  • Engineering(all)

Cite this

Data Driven Anomaly Diagnosis for Machining Processes. / Liang, Yuchen; Wang, Sheng; Li, Weidong; Lu, Xin.

In: Engineering, Vol. 5, No. 4, 08.2019, p. 646-652.

Research output: Contribution to journalArticle

@article{bfe874d126274dcc9826d904e524de47,
title = "Data Driven Anomaly Diagnosis for Machining Processes",
abstract = "To achieve zero-defect production during computer numerical control (CNC) machining processes, it is imperative to develop effective diagnosis systems to detect anomalies efficiently. However, due to the dynamic conditions of the machine and tooling during machining processes, the relevant diagnosis systems currently adopted in industries are incompetent. To address this issue, this paper presents a novel data-driven diagnosis system for anomalies. In this system, power data for condition monitoring are continuously collected during dynamic machining processes to support online diagnosis analysis. To facilitate the analysis, preprocessing mechanisms have been designed to de-noise, normalize, and align the monitored data. Important features are extracted from the monitored data and thresholds are defined to identify anomalies. Considering the dynamic conditions of the machine and tooling during machining processes, the thresholds used to identify anomalies can vary. Based on historical data, the values of thresholds are optimized using a fruit fly optimization (FFO) algorithm to achieve more accurate detection. Practical case studies were used to validate the system, thereby demonstrating the potential and effectiveness of the system for industrial applications.",
keywords = "Anomaly detection, Computer numerical control machining, Data-driven method, Fruit fly optimization algorithm",
author = "Yuchen Liang and Sheng Wang and Weidong Li and Xin Lu",
note = "Published by Elsevier LTD on behalf of Chinese Academy of Engineering and Higher Education Press Limited Company. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).",
year = "2019",
month = "8",
doi = "10.1016/j.eng.2019.03.012",
language = "English",
volume = "5",
pages = "646--652",
journal = "Engineering",
number = "4",

}

TY - JOUR

T1 - Data Driven Anomaly Diagnosis for Machining Processes

AU - Liang, Yuchen

AU - Wang, Sheng

AU - Li, Weidong

AU - Lu, Xin

N1 - Published by Elsevier LTD on behalf of Chinese Academy of Engineering and Higher Education Press Limited Company. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

PY - 2019/8

Y1 - 2019/8

N2 - To achieve zero-defect production during computer numerical control (CNC) machining processes, it is imperative to develop effective diagnosis systems to detect anomalies efficiently. However, due to the dynamic conditions of the machine and tooling during machining processes, the relevant diagnosis systems currently adopted in industries are incompetent. To address this issue, this paper presents a novel data-driven diagnosis system for anomalies. In this system, power data for condition monitoring are continuously collected during dynamic machining processes to support online diagnosis analysis. To facilitate the analysis, preprocessing mechanisms have been designed to de-noise, normalize, and align the monitored data. Important features are extracted from the monitored data and thresholds are defined to identify anomalies. Considering the dynamic conditions of the machine and tooling during machining processes, the thresholds used to identify anomalies can vary. Based on historical data, the values of thresholds are optimized using a fruit fly optimization (FFO) algorithm to achieve more accurate detection. Practical case studies were used to validate the system, thereby demonstrating the potential and effectiveness of the system for industrial applications.

AB - To achieve zero-defect production during computer numerical control (CNC) machining processes, it is imperative to develop effective diagnosis systems to detect anomalies efficiently. However, due to the dynamic conditions of the machine and tooling during machining processes, the relevant diagnosis systems currently adopted in industries are incompetent. To address this issue, this paper presents a novel data-driven diagnosis system for anomalies. In this system, power data for condition monitoring are continuously collected during dynamic machining processes to support online diagnosis analysis. To facilitate the analysis, preprocessing mechanisms have been designed to de-noise, normalize, and align the monitored data. Important features are extracted from the monitored data and thresholds are defined to identify anomalies. Considering the dynamic conditions of the machine and tooling during machining processes, the thresholds used to identify anomalies can vary. Based on historical data, the values of thresholds are optimized using a fruit fly optimization (FFO) algorithm to achieve more accurate detection. Practical case studies were used to validate the system, thereby demonstrating the potential and effectiveness of the system for industrial applications.

KW - Anomaly detection

KW - Computer numerical control machining

KW - Data-driven method

KW - Fruit fly optimization algorithm

UR - http://www.scopus.com/inward/record.url?scp=85069657977&partnerID=8YFLogxK

U2 - 10.1016/j.eng.2019.03.012

DO - 10.1016/j.eng.2019.03.012

M3 - Article

VL - 5

SP - 646

EP - 652

JO - Engineering

JF - Engineering

IS - 4

ER -