Data Generation with a Physical Model to Support Machine Learning Research for Predictive Maintenance. Klein, P. & Bergmann, R. In Proceedings of the Conference "Lernen, Wissen, Daten, Analysen", LWDA 2018, volume 2191, pages 179–190, 2018. CEUR-WS.org.
Paper abstract bibtex 19 downloads Today, manufacturing machines are continuously equippedwith various sensors, whose data enable to derive a comprehensive picture of the current state of each machine. Predictive maintenance approaches make use of this data in order to predict the occurrence of possible failures before they actually occur, thereby significantly reducing production and service costs. The application of machine learning to sensor data streams is an essential part of data-driven predictive maintenance in order to find the patterns in the data that are indicators of upcoming faults. Thus, research on machine learning for predictive maintenance is a recent and very challenging field. However, there are currently no appropriate data sets available that can be used for thiskind of research. In this paper we therefore propose an approach for the generation of predictive maintenance data by using a physical Fischertechnik model factory equipped with several sensors. Different ways of reproducing real failures using this model are presented as well as a general procedure for data generation.
@inproceedings{klein_data_generation_2018,
publisher = {CEUR-WS.org},
title = {{Data Generation with a Physical Model to Support Machine Learning Research for Predictive Maintenance}},
url = {http://www.wi2.uni-trier.de/publications/2018_KleinBergmann_LWDA.pdf},
booktitle = {Proceedings of the Conference "Lernen, Wissen, Daten, Analysen", {LWDA} 2018},
author = {Klein, Patrick and Bergmann, Ralph},
volume = {2191},
pages = {179--190},
year = {2018},
keywords = {{Data Generation, Machine Learning, Predictive Maintenance, Industry 4.0}},
abstract = {Today, manufacturing machines are continuously equippedwith various sensors, whose data enable to derive a comprehensive picture of the current state of each machine. Predictive maintenance approaches make use of this data in order to predict the occurrence of possible failures before they actually occur, thereby significantly reducing production and service costs. The application of machine learning to sensor data streams is an essential part of data-driven predictive maintenance in order to find the patterns in the data that are indicators of upcoming faults. Thus, research on machine learning for predictive maintenance is a recent and very challenging field. However, there are currently no appropriate data sets available that can be used for thiskind of research. In this paper we therefore propose an approach for the generation of predictive maintenance data by using a physical Fischertechnik model factory equipped with several sensors. Different ways of reproducing real failures using this model are presented as well as a general procedure for data generation.}
}
Downloads: 19
{"_id":"fXSFJH3Bb7ZHqbtCH","bibbaseid":"klein-bergmann-datagenerationwithaphysicalmodeltosupportmachinelearningresearchforpredictivemaintenance-2018","downloads":19,"creationDate":"2018-08-20T13:25:21.538Z","title":"Data Generation with a Physical Model to Support Machine Learning Research for Predictive Maintenance","author_short":["Klein, P.","Bergmann, R."],"year":2018,"bibtype":"inproceedings","biburl":"https://web.wi2.uni-trier.de/publications/WI2Publikationen_IoT.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","publisher":"CEUR-WS.org","title":"Data Generation with a Physical Model to Support Machine Learning Research for Predictive Maintenance","url":"http://www.wi2.uni-trier.de/publications/2018_KleinBergmann_LWDA.pdf","booktitle":"Proceedings of the Conference \"Lernen, Wissen, Daten, Analysen\", LWDA 2018","author":[{"propositions":[],"lastnames":["Klein"],"firstnames":["Patrick"],"suffixes":[]},{"propositions":[],"lastnames":["Bergmann"],"firstnames":["Ralph"],"suffixes":[]}],"volume":"2191","pages":"179–190","year":"2018","keywords":"Data Generation, Machine Learning, Predictive Maintenance, Industry 4.0","abstract":"Today, manufacturing machines are continuously equippedwith various sensors, whose data enable to derive a comprehensive picture of the current state of each machine. Predictive maintenance approaches make use of this data in order to predict the occurrence of possible failures before they actually occur, thereby significantly reducing production and service costs. The application of machine learning to sensor data streams is an essential part of data-driven predictive maintenance in order to find the patterns in the data that are indicators of upcoming faults. Thus, research on machine learning for predictive maintenance is a recent and very challenging field. However, there are currently no appropriate data sets available that can be used for thiskind of research. In this paper we therefore propose an approach for the generation of predictive maintenance data by using a physical Fischertechnik model factory equipped with several sensors. Different ways of reproducing real failures using this model are presented as well as a general procedure for data generation.","bibtex":"@inproceedings{klein_data_generation_2018,\n\tpublisher = {CEUR-WS.org},\n\ttitle = {{Data Generation with a Physical Model to Support Machine Learning Research for Predictive Maintenance}},\n\turl = {http://www.wi2.uni-trier.de/publications/2018_KleinBergmann_LWDA.pdf},\n\tbooktitle = {Proceedings of the Conference \"Lernen, Wissen, Daten, Analysen\", {LWDA} 2018},\n\tauthor = {Klein, Patrick and Bergmann, Ralph},\n\tvolume = {2191},\n\tpages = {179--190},\n\tyear = {2018},\n\tkeywords = {{Data Generation, Machine Learning, Predictive Maintenance, Industry 4.0}},\n\tabstract = {Today, manufacturing machines are continuously equippedwith various sensors, whose data enable to derive a comprehensive picture of the current state of each machine. Predictive maintenance approaches make use of this data in order to predict the occurrence of possible failures before they actually occur, thereby significantly reducing production and service costs. The application of machine learning to sensor data streams is an essential part of data-driven predictive maintenance in order to find the patterns in the data that are indicators of upcoming faults. Thus, research on machine learning for predictive maintenance is a recent and very challenging field. However, there are currently no appropriate data sets available that can be used for thiskind of research. In this paper we therefore propose an approach for the generation of predictive maintenance data by using a physical Fischertechnik model factory equipped with several sensors. Different ways of reproducing real failures using this model are presented as well as a general procedure for data generation.}\n}\n\n","author_short":["Klein, P.","Bergmann, R."],"key":"klein_data_generation_2018","id":"klein_data_generation_2018","bibbaseid":"klein-bergmann-datagenerationwithaphysicalmodeltosupportmachinelearningresearchforpredictivemaintenance-2018","role":"author","urls":{"Paper":"http://www.wi2.uni-trier.de/publications/2018_KleinBergmann_LWDA.pdf"},"keyword":["Data Generation","Machine Learning","Predictive Maintenance","Industry 4.0"],"metadata":{"authorlinks":{"bergmann, r":"https://bibbase.org/show?bib=https%3A%2F%2Fweb.wi2.uni-trier.de%2Fpublications%2FWI2Publikationen_IoT.bib&group0=year&css=https%3A%2F%2Fweb.wi2.uni-trier.de%2Fpublications%2FWI2.css"}},"downloads":19},"search_terms":["data","generation","physical","model","support","machine","learning","research","predictive","maintenance","klein","bergmann"],"keywords":["data generation","machine learning","predictive maintenance","industry 4.0"],"authorIDs":["2uxKowHMQJJY4bZWi","3FKNrvYDeY7gXnjbC","4EmgB9S9jTddhKg3b","545721042abc8e9f370000b7","5d3a94bba68377da01000052","5dee25490bde9edf0100002c","5df43b0a96bfa7de01000091","5e058ef8d36daddf01000027","5e0cfc6d5631a6de010000cc","5e13925da212e1de01000188","5e1cc5500744c2de01000198","5e22f572df658cdf010000ad","5e32ec7cc1389bde0100005f","5e3384b67a676dee010000d3","5e44c7077759a7df010000ea","5e48445300973ede01000069","5e49e96a885ce9df01000046","5e4a858958ecd9df01000153","5e5085267e0827df01000069","5e5a79dbb6725cde01000028","5e5ee71acc2eefde01000080","5e62fb18377bb9de0100008d","5e674c344d24a6df0100016a","66RAw6NFnEh8zPLoq","7a7qJcTMC6JgZStJy","7fxFYkuRn5LAdiSsp","8Ktdi9Fwhx75Mx5Zz","8MER8fcjZAhongsYb","9Hjm5fp7EXedfiskD","9mW5CPkEsJQwnvDsp","CBKJiA4BdH5CFe23b","CLWW8a47te9FcwqjF","EnRZag5zuqreHtqGf","F9E8QZWcamZ2qYCGw","G76658uDtABmiKaG5","Gfvdv5HcdvX5pjwBk","Hkmw5yKERJ27yCPor","JMNtSurZHcvxyjZ5j","JbNAa4ZtcJhk3xtkp","M4Yqt6uSaKY7N672n","N99hW2FC4kduaAsw8","NQutAbKm37cQ3ATgd","QudrJqag3f6SszAuE","RS8eSCJpc47Eer243","Z45yZHtkDWsBPsZ6m","ahwXAGsnjS6x2Dneo","dBWWi2M2Gx82mZXsA","ewfs58RrvkrCPvgEF","gYDsTGPk5v9xXTn6K","hS4ELye72s8hcw8cZ","j37gfytdec2kjY4J5","kvwGrWNdggwLGrLFb","kwH6B567ZtKJjHrMG","nDLjFvr7imjqbg9RM","nWy8q8hPwZiZrtQXF","pqE6e8cDkxtDHZgae","q2SYg2sb5ZhoMSsay","rkXK3hFnpvN2eKWcd","tfkHuW3HvZ2cf9E34","u5XkZsqkEdkqXfQ5W"],"dataSources":["HPSXnFwLpXtbkmbx7","CnwPa99ZchEF4SZgh","vtdjwAo6eNiqRLfnG","nZxfXH3fRFhwWejKL","MSp3DzP4ToPojqkFy","Td7BJ334QwxWK4vLW"]}