Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

View graph of relations

Details

Original languageEnglish
Title of host publicationExploring Service Science - 9th International Conference, IESS 2018, Proceedings
Subtitle of host publication9th International Conference, IESS 2018, Karlsruhe, Germany, September 19–21, 2018, Proceedings
EditorsGerhard Satzger, Niklas Kühl, Peter Hottum, Mohamed Zaki, Lia Patrício
Place of PublicationCham
Pages261-273
Number of pages13
ISBN (electronic)978-3-030-00713-3
Publication statusPublished - 2018

Publication series

NameLecture Notes in Business Information Processing
Volume331
ISSN (Print)1865-1348

Abstract

To ensure availability of industrial machines and reducing breakdown times, a machine monitoring can be an essential help. Unexpected machine downtimes are typically accompanied by high costs. Machine builders as well as component suppliers can use their detailed knowledge about their products to counteract this. One possibility to face the challenge is to offer a product-service system with machine monitoring services to their customers. An implementation approach for such a machine monitoring service is presented in this article. In contrast to previous research, we focus on the integration and interaction of machine learning tools and human domain experts, e.g. for an early anomaly detection and fault classification. First, Long Short-Term Memory Neural Networks are trained and applied to identify unusual behavior in operation time series data of a machine. We describe first results of the implementation of this anomaly detection. Second, domain experts are confronted with related monitoring data, e.g. temperature, vibration, video, audio etc., from different sources to assess and classify anomaly types. With an increasing knowledge base, a classifier module automatically suggests possible causes for an anomaly automatically in advance to support machine operators in the anomaly identification process. Feedback loops ensure continuous learning of the anomaly detector and classifier modules. Hence, we combine the knowledge of machine builders/component suppliers with application specific experience of the customers in the business value stream network.

Keywords

    Hybrid learning, Long Short-Term Memory Neural Networks, Machine monitoring, Product-service systems

ASJC Scopus subject areas

Cite this

Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines. / Olivotti, Daniel; Passlick, Jens; Axjonow, Alexander et al.
Exploring Service Science - 9th International Conference, IESS 2018, Proceedings: 9th International Conference, IESS 2018, Karlsruhe, Germany, September 19–21, 2018, Proceedings. ed. / Gerhard Satzger; Niklas Kühl; Peter Hottum; Mohamed Zaki; Lia Patrício. Cham, 2018. p. 261-273 (Lecture Notes in Business Information Processing; Vol. 331).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Olivotti, D, Passlick, J, Axjonow, A, Eilers, D & Breitner, MH 2018, Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines. in G Satzger, N Kühl, P Hottum, M Zaki & L Patrício (eds), Exploring Service Science - 9th International Conference, IESS 2018, Proceedings: 9th International Conference, IESS 2018, Karlsruhe, Germany, September 19–21, 2018, Proceedings. Lecture Notes in Business Information Processing, vol. 331, Cham, pp. 261-273. https://doi.org/10.1007/978-3-030-00713-3_20
Olivotti, D., Passlick, J., Axjonow, A., Eilers, D., & Breitner, M. H. (2018). Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines. In G. Satzger, N. Kühl, P. Hottum, M. Zaki, & L. Patrício (Eds.), Exploring Service Science - 9th International Conference, IESS 2018, Proceedings: 9th International Conference, IESS 2018, Karlsruhe, Germany, September 19–21, 2018, Proceedings (pp. 261-273). (Lecture Notes in Business Information Processing; Vol. 331).. https://doi.org/10.1007/978-3-030-00713-3_20
Olivotti D, Passlick J, Axjonow A, Eilers D, Breitner MH. Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines. In Satzger G, Kühl N, Hottum P, Zaki M, Patrício L, editors, Exploring Service Science - 9th International Conference, IESS 2018, Proceedings: 9th International Conference, IESS 2018, Karlsruhe, Germany, September 19–21, 2018, Proceedings. Cham. 2018. p. 261-273. (Lecture Notes in Business Information Processing). doi: 10.1007/978-3-030-00713-3_20
Olivotti, Daniel ; Passlick, Jens ; Axjonow, Alexander et al. / Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines. Exploring Service Science - 9th International Conference, IESS 2018, Proceedings: 9th International Conference, IESS 2018, Karlsruhe, Germany, September 19–21, 2018, Proceedings. editor / Gerhard Satzger ; Niklas Kühl ; Peter Hottum ; Mohamed Zaki ; Lia Patrício. Cham, 2018. pp. 261-273 (Lecture Notes in Business Information Processing).
Download
@inproceedings{a41043d54c78470fa6036342b55c6ec6,
title = "Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines.",
abstract = "To ensure availability of industrial machines and reducing breakdown times, a machine monitoring can be an essential help. Unexpected machine downtimes are typically accompanied by high costs. Machine builders as well as component suppliers can use their detailed knowledge about their products to counteract this. One possibility to face the challenge is to offer a product-service system with machine monitoring services to their customers. An implementation approach for such a machine monitoring service is presented in this article. In contrast to previous research, we focus on the integration and interaction of machine learning tools and human domain experts, e.g. for an early anomaly detection and fault classification. First, Long Short-Term Memory Neural Networks are trained and applied to identify unusual behavior in operation time series data of a machine. We describe first results of the implementation of this anomaly detection. Second, domain experts are confronted with related monitoring data, e.g. temperature, vibration, video, audio etc., from different sources to assess and classify anomaly types. With an increasing knowledge base, a classifier module automatically suggests possible causes for an anomaly automatically in advance to support machine operators in the anomaly identification process. Feedback loops ensure continuous learning of the anomaly detector and classifier modules. Hence, we combine the knowledge of machine builders/component suppliers with application specific experience of the customers in the business value stream network.",
keywords = "Hybrid learning, Long Short-Term Memory Neural Networks, Machine monitoring, Product-service systems",
author = "Daniel Olivotti and Jens Passlick and Alexander Axjonow and Dennis Eilers and Breitner, {Michael H.}",
note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions. Publisher Copyright: {\textcopyright} 2018, Springer Nature Switzerland AG. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.",
year = "2018",
doi = "10.1007/978-3-030-00713-3_20",
language = "English",
isbn = "978-3-030-00712-6",
series = "Lecture Notes in Business Information Processing",
pages = "261--273",
editor = "Gerhard Satzger and Niklas K{\"u}hl and Peter Hottum and Mohamed Zaki and Lia Patr{\'i}cio",
booktitle = "Exploring Service Science - 9th International Conference, IESS 2018, Proceedings",

}

Download

TY - GEN

T1 - Combining Machine Learning and Domain Experience - A Hybrid-Learning Monitor Approach for Industrial Machines.

AU - Olivotti, Daniel

AU - Passlick, Jens

AU - Axjonow, Alexander

AU - Eilers, Dennis

AU - Breitner, Michael H.

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions. Publisher Copyright: © 2018, Springer Nature Switzerland AG. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2018

Y1 - 2018

N2 - To ensure availability of industrial machines and reducing breakdown times, a machine monitoring can be an essential help. Unexpected machine downtimes are typically accompanied by high costs. Machine builders as well as component suppliers can use their detailed knowledge about their products to counteract this. One possibility to face the challenge is to offer a product-service system with machine monitoring services to their customers. An implementation approach for such a machine monitoring service is presented in this article. In contrast to previous research, we focus on the integration and interaction of machine learning tools and human domain experts, e.g. for an early anomaly detection and fault classification. First, Long Short-Term Memory Neural Networks are trained and applied to identify unusual behavior in operation time series data of a machine. We describe first results of the implementation of this anomaly detection. Second, domain experts are confronted with related monitoring data, e.g. temperature, vibration, video, audio etc., from different sources to assess and classify anomaly types. With an increasing knowledge base, a classifier module automatically suggests possible causes for an anomaly automatically in advance to support machine operators in the anomaly identification process. Feedback loops ensure continuous learning of the anomaly detector and classifier modules. Hence, we combine the knowledge of machine builders/component suppliers with application specific experience of the customers in the business value stream network.

AB - To ensure availability of industrial machines and reducing breakdown times, a machine monitoring can be an essential help. Unexpected machine downtimes are typically accompanied by high costs. Machine builders as well as component suppliers can use their detailed knowledge about their products to counteract this. One possibility to face the challenge is to offer a product-service system with machine monitoring services to their customers. An implementation approach for such a machine monitoring service is presented in this article. In contrast to previous research, we focus on the integration and interaction of machine learning tools and human domain experts, e.g. for an early anomaly detection and fault classification. First, Long Short-Term Memory Neural Networks are trained and applied to identify unusual behavior in operation time series data of a machine. We describe first results of the implementation of this anomaly detection. Second, domain experts are confronted with related monitoring data, e.g. temperature, vibration, video, audio etc., from different sources to assess and classify anomaly types. With an increasing knowledge base, a classifier module automatically suggests possible causes for an anomaly automatically in advance to support machine operators in the anomaly identification process. Feedback loops ensure continuous learning of the anomaly detector and classifier modules. Hence, we combine the knowledge of machine builders/component suppliers with application specific experience of the customers in the business value stream network.

KW - Hybrid learning

KW - Long Short-Term Memory Neural Networks

KW - Machine monitoring

KW - Product-service systems

UR - http://www.scopus.com/inward/record.url?scp=85053871566&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-00713-3_20

DO - 10.1007/978-3-030-00713-3_20

M3 - Conference contribution

SN - 978-3-030-00712-6

T3 - Lecture Notes in Business Information Processing

SP - 261

EP - 273

BT - Exploring Service Science - 9th International Conference, IESS 2018, Proceedings

A2 - Satzger, Gerhard

A2 - Kühl, Niklas

A2 - Hottum, Peter

A2 - Zaki, Mohamed

A2 - Patrício, Lia

CY - Cham

ER -

By the same author(s)