Offline-Online pattern recognition for enabling time series anomaly detection on older NC machine tools
 
More details
Hide details
1
Institute of Production Science (wbk), Karlsruhe Institute of Technology (KIT), Germany
 
 
Submission date: 2020-09-30
 
 
Final revision date: 2021-01-07
 
 
Acceptance date: 2021-01-07
 
 
Online publication date: 2021-03-29
 
 
Publication date: 2021-03-29
 
 
Corresponding author
Markus Netzer   

Institute of Production Science (wbk), Karlsruhe Institute of Technology (KIT), Kaiserstraße 12, 76131, Karlsruhe, Germany
 
 
Journal of Machine Engineering 2021;21(1):98-108
 
KEYWORDS
TOPICS
ABSTRACT
Intelligent IoT functions for increased availability, productivity and component quality offer significant added value to the industry. Unfortunately, many old machines and systems are characterized by insufficient, inconsistent IoT connectivity and heterogeneous parameter naming. Furthermore, the data is only available in unstructured form. In the following, a new approach for standardizing information models from existing plants with machine learning methods is described and an offline-online pattern recognition system for enabling anomaly detection under varying machine conditions is introduced. The system can enable the local calculation of signal thresholds that allow more granular anomaly detection than using only single indexing and aims to improve the detection of anomalous machine behaviour especially in finish machining.
 
REFERENCES (11)
1.
ISMAIL A., TRUONG H.L., KASTNER W., 2018, Manufacturing Process Data Analysis Pipelines: a Requirements Analysis and Survey, Journal of Big Data, 6, 1–26.
 
2.
GITTLER T., GONTARZ A., WEISS L., WEGENER K., 2019, A Fundamental Approach for Data Acquisition on Machine Tools as Enabler for Analytical Industrie 4.0 Applications. Procedia CIRP, 79, 586–591, DOI: 10.1016/j.procir.2019.02.088.
 
3.
SOBEL W., 2014, MTConnect Standard, MTConnect Institute, Online available https://github.com/mtconnect /standard.
 
4.
BEN E., BINGYAN Z., HANSEL A., MASAHIKO M., FUJISHIMA M., 2014, Machine Monitoring System Based on MTConnect Technology, Procedia CIRP, 22, 92–97, DOI: 10.1016/j.procir.2014.07.148.
 
5.
LEE J., KAO H.A., YANG S., 2014, Service Innovation and Smart Analytics for Industry 4.0 and Big Data Environment, Procedia CIRP, 16, 3–8, DOI: 10.1016/j.procir.2014.02.001.
 
6.
LIN J., KEOGH E., LONARDI S., PATEL P., 2002, Finding Motifs in Time Series, Proceedings of the Second Workshop on Temporal Data Mining, 53–68.
 
7.
KEOGH E., LIN J., 2005, Clustering of Time-Series Subsequence is Meaningless: Implications for Previous and Future Research, Know. Inf. Syst., 8/2, 154–177, DOI: 10.1007/s10115-004-0172-7.
 
8.
SAKURAI Y., FALOUTSOS Ch., YAMAMURO M., 2007, Stream Monitoring Under the Time Warping Distance, IEEE 23rd International Conference on Data Engineering, Istanbul, 1046–1055.
 
9.
EMEC S., KRÜGER J., SELIGER G., 2016, Online Fault-monitoring in Machine Tools Based on Energy Consumption Analysis and Non-Invasive Data Acquisition for Improved Resource-Efficiency, Procedia CIRP, 40, 236–243, DOI: 10.1016/j.procir.2016.01.111.
 
10.
TANI GmbH Networks for Industry, Copyright 2013–2019, Tani GmbH, Nürnberg, Deutschland, Online available https://www.tanindustrie.de/de....
 
11.
NETZER M., MICHELBERGER J., FLEISCHER J., 2020, Intelligent Anomaly Detection of Machine Tools Based on Mean Shift Clustering, Procedia CIRP, 93, 1448–1453.
 
 
CITATIONS (5):
1.
Production at the Leading Edge of Technology
M. Hansjosten, A. Bott, A. Puchta, P. Gönnheimer, J. Fleischer
 
2.
Machine tool process monitoring by segmented timeseries anomaly detection using subprocess-specific thresholds
Markus Netzer, Yannic Palenga, Jürgen Fleischer
Production Engineering
 
3.
Datenaufnahme und -verarbeitung in der Brownfield-Produktion
Philipp Gönnheimer, Markus Netzer, Carolin Lange, Roman Dörflinger, Judith Armbruster, Jürgen Fleischer
Zeitschrift für wirtschaftlichen Fabrikbetrieb
 
4.
Monitoring of Tool and Component Wear for Self-Adaptive Digital Twins: A Multi-Stage Approach through Anomaly Detection and Wear Cycle Analysis
Robin Ströbel, Alexander Bott, Andreas Wortmann, Jürgen Fleischer
Machines
 
5.
A Domain Knowledge-based Approach for Fault Diagnosis
Markus Netzer, Philipp Alexander, Tobias Schlagenhauf, Juergen Fleischer
Procedia CIRP
 
eISSN:2391-8071
ISSN:1895-7595
Journals System - logo
Scroll to top