Log-based predictive maintenance in discrete parts manufacturing

Clemens Gutschi, Nikolaus Furian, Dietmar Neubacher

Research output: Contribution to conferenceAbstractResearchpeer-review

Abstract

The performance of discrete parts manufacturing systems is heavily influenced by unplanned machine breakdowns. Predictive maintenance allows for the conversation of unplanned machine breakdowns to scheduled corrective maintenance actions. We present a data-driven log-based approach for estimating the probability of machine breakdowns during specified time intervals in the future. Machine learning algorithms are utilized for a specific use-case which is based on real-world data-sets including machine log messages, event logs and operational information. We will present an overview on predictive maintenance strategies as well as applied data-preparation, feature-engineering and machine learning methods for estimating the remaining useful lifetime. The comparison of two different methods for RUL-estimation is indicating that machine failures can be predicted up to 168 hours in advance with promising precision and hit-rate.
Translated title of the contributionLog-based predictive maintenance in discrete parts manufacturing
LanguageEnglish
StatusPublished - Jun 2019
Event30th European Conference on Operational Research - University College Dublin, Dublin, Ireland
Duration: 23 Jun 201926 Jun 2019
https://www.euro2019dublin.com/

Conference

Conference30th European Conference on Operational Research
Abbreviated titleEURO 2019
CountryIreland
CityDublin
Period23/06/1926/06/19
Internet address

Fingerprint

Learning systems
Learning algorithms
Machine breakdown
Manufacturing
Machine learning
Learning methods
Corrective maintenance
Learning algorithm
Maintenance strategy
Preparation
Manufacturing systems

Keywords

  • predictive analytics
  • Predictive maintenance
  • random forest
  • ensemble prediction
  • Machine learning
  • Probability of failure estimation
  • maintenance
  • Maintenance Management
  • data mining
  • feature engineering
  • feature selection
  • Remaining useful life
  • Ensemble prediction
  • Random forrest
  • condition monitoring

ASJC Scopus subject areas

  • Artificial Intelligence
  • Industrial and Manufacturing Engineering
  • Management Science and Operations Research
  • Control and Systems Engineering

Fields of Expertise

  • Mobility & Production

Cite this

Gutschi, C., Furian, N., & Neubacher, D. (2019). Log-based predictive maintenance in discrete parts manufacturing. Abstract from 30th European Conference on Operational Research, Dublin, Ireland.

Log-based predictive maintenance in discrete parts manufacturing. / Gutschi, Clemens; Furian, Nikolaus; Neubacher, Dietmar.

2019. Abstract from 30th European Conference on Operational Research, Dublin, Ireland.

Research output: Contribution to conferenceAbstractResearchpeer-review

Gutschi, C, Furian, N & Neubacher, D 2019, 'Log-based predictive maintenance in discrete parts manufacturing' 30th European Conference on Operational Research, Dublin, Ireland, 23/06/19 - 26/06/19, .
Gutschi C, Furian N, Neubacher D. Log-based predictive maintenance in discrete parts manufacturing. 2019. Abstract from 30th European Conference on Operational Research, Dublin, Ireland.
Gutschi, Clemens ; Furian, Nikolaus ; Neubacher, Dietmar. / Log-based predictive maintenance in discrete parts manufacturing. Abstract from 30th European Conference on Operational Research, Dublin, Ireland.
@conference{5fe7bf6dfcf644eda1f47b4ed6f1adbe,
title = "Log-based predictive maintenance in discrete parts manufacturing",
abstract = "The performance of discrete parts manufacturing systems is heavily influenced by unplanned machine breakdowns. Predictive maintenance allows for the conversation of unplanned machine breakdowns to scheduled corrective maintenance actions. We present a data-driven log-based approach for estimating the probability of machine breakdowns during specified time intervals in the future. Machine learning algorithms are utilized for a specific use-case which is based on real-world data-sets including machine log messages, event logs and operational information. We will present an overview on predictive maintenance strategies as well as applied data-preparation, feature-engineering and machine learning methods for estimating the remaining useful lifetime. The comparison of two different methods for RUL-estimation is indicating that machine failures can be predicted up to 168 hours in advance with promising precision and hit-rate.",
keywords = "predictive analytics, Predictive maintenance, random forest, ensemble prediction, Machine learning, Probability of failure estimation, maintenance, Maintenance Management, data mining, feature engineering, feature selection, Remaining useful life, Ensemble prediction, Random forrest, condition monitoring",
author = "Clemens Gutschi and Nikolaus Furian and Dietmar Neubacher",
year = "2019",
month = "6",
language = "English",
note = "30th European Conference on Operational Research, EURO 2019 ; Conference date: 23-06-2019 Through 26-06-2019",
url = "https://www.euro2019dublin.com/",

}

TY - CONF

T1 - Log-based predictive maintenance in discrete parts manufacturing

AU - Gutschi, Clemens

AU - Furian, Nikolaus

AU - Neubacher, Dietmar

PY - 2019/6

Y1 - 2019/6

N2 - The performance of discrete parts manufacturing systems is heavily influenced by unplanned machine breakdowns. Predictive maintenance allows for the conversation of unplanned machine breakdowns to scheduled corrective maintenance actions. We present a data-driven log-based approach for estimating the probability of machine breakdowns during specified time intervals in the future. Machine learning algorithms are utilized for a specific use-case which is based on real-world data-sets including machine log messages, event logs and operational information. We will present an overview on predictive maintenance strategies as well as applied data-preparation, feature-engineering and machine learning methods for estimating the remaining useful lifetime. The comparison of two different methods for RUL-estimation is indicating that machine failures can be predicted up to 168 hours in advance with promising precision and hit-rate.

AB - The performance of discrete parts manufacturing systems is heavily influenced by unplanned machine breakdowns. Predictive maintenance allows for the conversation of unplanned machine breakdowns to scheduled corrective maintenance actions. We present a data-driven log-based approach for estimating the probability of machine breakdowns during specified time intervals in the future. Machine learning algorithms are utilized for a specific use-case which is based on real-world data-sets including machine log messages, event logs and operational information. We will present an overview on predictive maintenance strategies as well as applied data-preparation, feature-engineering and machine learning methods for estimating the remaining useful lifetime. The comparison of two different methods for RUL-estimation is indicating that machine failures can be predicted up to 168 hours in advance with promising precision and hit-rate.

KW - predictive analytics

KW - Predictive maintenance

KW - random forest

KW - ensemble prediction

KW - Machine learning

KW - Probability of failure estimation

KW - maintenance

KW - Maintenance Management

KW - data mining

KW - feature engineering

KW - feature selection

KW - Remaining useful life

KW - Ensemble prediction

KW - Random forrest

KW - condition monitoring

M3 - Abstract

ER -