Anomaly detection on industrial time series for retaining energy efficiency

Philipp Theumer; Reinhard Zeiser; Ludwig Trauner; Gunther Reinhart

doi:10.1016/j.procir.2021.03.006

Anomaly detection on industrial time series for retaining energy efficiency

Philipp Theumer
, Reinhard Zeiser
, Ludwig Trauner
, Gunther Reinhart

Chair of Sustainable Production

Fraunhofer Institute for Casting, Composite and Processing Technology IGCV

Research output: Contribution to journal › Conference article › peer-review

11 Scopus citations

Abstract

Improving upon or even just retaining energy efficiency at industrial plants presents a rising challenge. Energy efficiency is gradually lowered due to equipment wear and operating errors. Energy consumption increases as a result, whereas output remains nearly constant or even decreases. Maintaining energy efficiency can be achieved by continuously monitoring power consumption and taking measures accordingly. However, due to the amount of collected data in factories, employees require support in the detection of anomalies. Therefore, this paper proposes a method which is able to detect inefficiencies on univariate time series based on historical data. This enables suitable measures to be taken in order to maintain energy efficiency without the need of additional expert knowledge.

Original language	English
Pages (from-to)	33-38
Number of pages	6
Journal	Procedia CIRP
Volume	99
DOIs	https://doi.org/10.1016/j.procir.2021.03.006
State	Published - 2021
Event	14th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2020 - Naples, Italy Duration: 15 Jul 2020 → 17 Jul 2020

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Anomaly detection
Energy efficiency
Machine learning

Access to Document

10.1016/j.procir.2021.03.006

Cite this

@article{70b356de8e3048caa2378ea14770bd87,

title = "Anomaly detection on industrial time series for retaining energy efficiency",

abstract = "Improving upon or even just retaining energy efficiency at industrial plants presents a rising challenge. Energy efficiency is gradually lowered due to equipment wear and operating errors. Energy consumption increases as a result, whereas output remains nearly constant or even decreases. Maintaining energy efficiency can be achieved by continuously monitoring power consumption and taking measures accordingly. However, due to the amount of collected data in factories, employees require support in the detection of anomalies. Therefore, this paper proposes a method which is able to detect inefficiencies on univariate time series based on historical data. This enables suitable measures to be taken in order to maintain energy efficiency without the need of additional expert knowledge.",

keywords = "Anomaly detection, Energy efficiency, Machine learning",

author = "Philipp Theumer and Reinhard Zeiser and Ludwig Trauner and Gunther Reinhart",

note = "Publisher Copyright: {\textcopyright} 2021 The Authors. Published by Elsevier B.V.; 14th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2020 ; Conference date: 15-07-2020 Through 17-07-2020",

year = "2021",

doi = "10.1016/j.procir.2021.03.006",

language = "English",

volume = "99",

pages = "33--38",

journal = "Procedia CIRP",

issn = "2212-8271",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Anomaly detection on industrial time series for retaining energy efficiency

AU - Theumer, Philipp

AU - Zeiser, Reinhard

AU - Trauner, Ludwig

AU - Reinhart, Gunther

PY - 2021

Y1 - 2021

N2 - Improving upon or even just retaining energy efficiency at industrial plants presents a rising challenge. Energy efficiency is gradually lowered due to equipment wear and operating errors. Energy consumption increases as a result, whereas output remains nearly constant or even decreases. Maintaining energy efficiency can be achieved by continuously monitoring power consumption and taking measures accordingly. However, due to the amount of collected data in factories, employees require support in the detection of anomalies. Therefore, this paper proposes a method which is able to detect inefficiencies on univariate time series based on historical data. This enables suitable measures to be taken in order to maintain energy efficiency without the need of additional expert knowledge.

AB - Improving upon or even just retaining energy efficiency at industrial plants presents a rising challenge. Energy efficiency is gradually lowered due to equipment wear and operating errors. Energy consumption increases as a result, whereas output remains nearly constant or even decreases. Maintaining energy efficiency can be achieved by continuously monitoring power consumption and taking measures accordingly. However, due to the amount of collected data in factories, employees require support in the detection of anomalies. Therefore, this paper proposes a method which is able to detect inefficiencies on univariate time series based on historical data. This enables suitable measures to be taken in order to maintain energy efficiency without the need of additional expert knowledge.

KW - Anomaly detection

KW - Energy efficiency

KW - Machine learning

UR - https://www.scopus.com/pages/publications/85106442686

U2 - 10.1016/j.procir.2021.03.006

DO - 10.1016/j.procir.2021.03.006

M3 - Conference article

AN - SCOPUS:85106442686

SN - 2212-8271

VL - 99

SP - 33

EP - 38

JO - Procedia CIRP

JF - Procedia CIRP

T2 - 14th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2020

Y2 - 15 July 2020 through 17 July 2020

ER -

Anomaly detection on industrial time series for retaining energy efficiency

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this