Analysis of High Frequency Data of a Machine Tool via Edge Computing

Stefan Trabesinger; Andre Butzerin; Daniel Schall; Rudolf Pichler

doi:https://doi.org/10.1016/j.promfg.2020.04.028

Analysis of High Frequency Data of a Machine Tool via Edge Computing

Stefan Trabesinger^*, Andre Butzerin, Daniel Schall, Rudolf Pichler

^*Corresponding author for this work

Institute of Production Engineering (3010)

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

New technological capabilities of digitalization are enablers of processing a broad range of machine data. While so-called Low-Frequency Data (LFD) is captured at a sampling rate of several hundred milliseconds, High-Frequency Data (HFD) is based on a sampling rate in the single-digit millisecond range. In this paper, HFD is used to implement an edge-based analytics application for prediction purposes in a machine tool. This edge application leverages Siemens SINUMERIK Edge to capture HFD from a machine tool to recognize anomalies of any kind. The edge application is implemented as a show case in the Learning Factory of Graz University of Technology, the smartfactory@tugraz.

Translated title of the contribution	Analyse von hochfrequenten Daten einer Werkzeugmaschine mittels Edge Computing
Original language	English
Title of host publication	Learning Factories across the value chain – from innovation to service – The 10th Conference on Learning Factories 2020
Pages	343-348
Number of pages	6
Volume	45
Edition	2351-9789
DOIs	https://doi.org/10.1016/j.promfg.2020.04.028
Publication status	Published - 15 Apr 2020
Event	10th Conference on Learning Factories: CLF 2020 - TU Graz, Virtuell, Austria Duration: 15 Apr 2020 → 17 Apr 2020 https://www.tugraz.at/events/clf2020/home/

Publication series

Name	Procedia Manufacturing
Publisher	Elsevier B.V.

Conference

Conference	10th Conference on Learning Factories
Abbreviated title	CLF 2020
Country/Territory	Austria
City	Virtuell
Period	15/04/20 → 17/04/20
Internet address	https://www.tugraz.at/events/clf2020/home/

Keywords

Anomaly Detection
Edge Computing
High-Frequency Data
Machine Learning
Prediction of Tool Breakage

ASJC Scopus subject areas

Artificial Intelligence
Industrial and Manufacturing Engineering

Fields of Expertise

Mobility & Production

Access to Document

https://doi.org/10.1016/j.promfg.2020.04.028Licence: CC BY-NC-ND 4.0

Cite this

Trabesinger, S., Butzerin, A., Schall, D., & Pichler, R. (2020). Analysis of High Frequency Data of a Machine Tool via Edge Computing. In Learning Factories across the value chain – from innovation to service – The 10th Conference on Learning Factories 2020 (2351-9789 ed., Vol. 45, pp. 343-348). (Procedia Manufacturing). https://doi.org/10.1016/j.promfg.2020.04.028

Analysis of High Frequency Data of a Machine Tool via Edge Computing. / Trabesinger, Stefan; Butzerin, Andre; Schall, Daniel et al.
Learning Factories across the value chain – from innovation to service – The 10th Conference on Learning Factories 2020. Vol. 45 2351-9789. ed. 2020. p. 343-348 (Procedia Manufacturing).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Trabesinger, S, Butzerin, A, Schall, D & Pichler, R 2020, Analysis of High Frequency Data of a Machine Tool via Edge Computing. in Learning Factories across the value chain – from innovation to service – The 10th Conference on Learning Factories 2020. 2351-9789 edn, vol. 45, Procedia Manufacturing, pp. 343-348, 10th Conference on Learning Factories, Virtuell, Austria, 15/04/20. https://doi.org/10.1016/j.promfg.2020.04.028

@inproceedings{b5042addc3e641fc8302bf623174305b,

title = "Analysis of High Frequency Data of a Machine Tool via Edge Computing",

abstract = "New technological capabilities of digitalization are enablers of processing a broad range of machine data. While so-called Low-Frequency Data (LFD) is captured at a sampling rate of several hundred milliseconds, High-Frequency Data (HFD) is based on a sampling rate in the single-digit millisecond range. In this paper, HFD is used to implement an edge-based analytics application for prediction purposes in a machine tool. This edge application leverages Siemens SINUMERIK Edge to capture HFD from a machine tool to recognize anomalies of any kind. The edge application is implemented as a show case in the Learning Factory of Graz University of Technology, the smartfactory@tugraz.",

keywords = "Anomaly Detection, Edge Computing, High-Frequency Data, Machine Learning, Prediction of Tool Breakage",

author = "Stefan Trabesinger and Andre Butzerin and Daniel Schall and Rudolf Pichler",

year = "2020",

month = apr,

day = "15",

doi = "https://doi.org/10.1016/j.promfg.2020.04.028",

language = "English",

volume = "45",

series = "Procedia Manufacturing",

publisher = "Elsevier B.V.",

pages = "343--348",

booktitle = "Learning Factories across the value chain – from innovation to service – The 10th Conference on Learning Factories 2020",

edition = "2351-9789",

note = "10th Conference on Learning Factories : CLF 2020, CLF 2020 ; Conference date: 15-04-2020 Through 17-04-2020",

url = "https://www.tugraz.at/events/clf2020/home/",

}

TY - GEN

T1 - Analysis of High Frequency Data of a Machine Tool via Edge Computing

AU - Trabesinger, Stefan

AU - Butzerin, Andre

AU - Schall, Daniel

AU - Pichler, Rudolf

PY - 2020/4/15

Y1 - 2020/4/15

N2 - New technological capabilities of digitalization are enablers of processing a broad range of machine data. While so-called Low-Frequency Data (LFD) is captured at a sampling rate of several hundred milliseconds, High-Frequency Data (HFD) is based on a sampling rate in the single-digit millisecond range. In this paper, HFD is used to implement an edge-based analytics application for prediction purposes in a machine tool. This edge application leverages Siemens SINUMERIK Edge to capture HFD from a machine tool to recognize anomalies of any kind. The edge application is implemented as a show case in the Learning Factory of Graz University of Technology, the smartfactory@tugraz.

AB - New technological capabilities of digitalization are enablers of processing a broad range of machine data. While so-called Low-Frequency Data (LFD) is captured at a sampling rate of several hundred milliseconds, High-Frequency Data (HFD) is based on a sampling rate in the single-digit millisecond range. In this paper, HFD is used to implement an edge-based analytics application for prediction purposes in a machine tool. This edge application leverages Siemens SINUMERIK Edge to capture HFD from a machine tool to recognize anomalies of any kind. The edge application is implemented as a show case in the Learning Factory of Graz University of Technology, the smartfactory@tugraz.

KW - Anomaly Detection

KW - Edge Computing

KW - High-Frequency Data

KW - Machine Learning

KW - Prediction of Tool Breakage

UR - https://www.semanticscholar.org/paper/Analysis-of-High-Frequency-Data-of-a-Machine-Tool-Trabesinger-Butzerin/6714e58e2378aa5e274c87c05b33ba686c49a469

UR - https://www.researchgate.net/publication/341037317_Analysis_of_High_Frequency_Data_of_a_Machine_Tool_via_Edge_Computing

UR - http://www.scopus.com/inward/record.url?scp=85085485865&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.promfg.2020.04.028

DO - https://doi.org/10.1016/j.promfg.2020.04.028

M3 - Conference paper

VL - 45

T3 - Procedia Manufacturing

SP - 343

EP - 348

BT - Learning Factories across the value chain – from innovation to service – The 10th Conference on Learning Factories 2020

T2 - 10th Conference on Learning Factories

Y2 - 15 April 2020 through 17 April 2020

ER -

Analysis of High Frequency Data of a Machine Tool via Edge Computing

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Fields of Expertise

Access to Document

Other files and links

Fingerprint

SFTUG - smartfactory@tugraz - interdisciplinary research on digital manufacturing