Machine Learning approach for Predictive Maintenance in Industry 4.0. Paolanti, M., Romeo, L., Felicetti, A., Mancini, A., Frontoni, E., & Loncarski, J. In 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), pages 1–6, July, 2018. doi abstract bibtex Condition monitoring together with predictive maintenance of electric motors and other equipment used by the industry avoids severe economic losses resulting from unexpected motor failures and greatly improves the system reliability. This paper describes a Machine Learning architecture for Predictive Maintenance, based on Random Forest approach. The system was tested on a real industry example, by developing the data collection and data system analysis, applying the Machine Learning approach and comparing it to the simulation tool analysis. Data has been collected by various sensors, machine PLCs and communication protocols and made available to Data Analysis Tool on the Azure Cloud architecture. Preliminary results show a proper behavior of the approach on predicting different machine states with high accuracy.
@inproceedings{paolanti_machine_2018,
title = {Machine {Learning} approach for {Predictive} {Maintenance} in {Industry} 4.0},
doi = {10.1109/MESA.2018.8449150},
abstract = {Condition monitoring together with predictive maintenance of electric motors and other equipment used by the industry avoids severe economic losses resulting from unexpected motor failures and greatly improves the system reliability. This paper describes a Machine Learning architecture for Predictive Maintenance, based on Random Forest approach. The system was tested on a real industry example, by developing the data collection and data system analysis, applying the Machine Learning approach and comparing it to the simulation tool analysis. Data has been collected by various sensors, machine PLCs and communication protocols and made available to Data Analysis Tool on the Azure Cloud architecture. Preliminary results show a proper behavior of the approach on predicting different machine states with high accuracy.},
booktitle = {2018 14th {IEEE}/{ASME} {International} {Conference} on {Mechatronic} and {Embedded} {Systems} and {Applications} ({MESA})},
author = {Paolanti, M. and Romeo, L. and Felicetti, A. and Mancini, A. and Frontoni, E. and Loncarski, J.},
month = jul,
year = {2018},
keywords = {Azure cloud architecture, Current measurement, Forecasting, Industries, Industry 4.0, Machine learning, Predictive maintenance, Time measurement, cloud computing, communication protocols, condition monitoring, data analysis, data collection, data system analysis, economic loss, electric motors, failure analysis, learning (artificial intelligence), machine PLCs, machine learning approach, maintenance engineering, motor failures, predictive maintenance, production engineering computing, programmable controllers, protocols, random forest approach, reliability, sensors, simulation tool analysis, system reliability},
pages = {1--6},
}
Downloads: 0
{"_id":"sifCYNxts75xnuaDd","bibbaseid":"paolanti-romeo-felicetti-mancini-frontoni-loncarski-machinelearningapproachforpredictivemaintenanceinindustry40-2018","author_short":["Paolanti, M.","Romeo, L.","Felicetti, A.","Mancini, A.","Frontoni, E.","Loncarski, J."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Machine Learning approach for Predictive Maintenance in Industry 4.0","doi":"10.1109/MESA.2018.8449150","abstract":"Condition monitoring together with predictive maintenance of electric motors and other equipment used by the industry avoids severe economic losses resulting from unexpected motor failures and greatly improves the system reliability. This paper describes a Machine Learning architecture for Predictive Maintenance, based on Random Forest approach. The system was tested on a real industry example, by developing the data collection and data system analysis, applying the Machine Learning approach and comparing it to the simulation tool analysis. Data has been collected by various sensors, machine PLCs and communication protocols and made available to Data Analysis Tool on the Azure Cloud architecture. Preliminary results show a proper behavior of the approach on predicting different machine states with high accuracy.","booktitle":"2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA)","author":[{"propositions":[],"lastnames":["Paolanti"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Romeo"],"firstnames":["L."],"suffixes":[]},{"propositions":[],"lastnames":["Felicetti"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Mancini"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Frontoni"],"firstnames":["E."],"suffixes":[]},{"propositions":[],"lastnames":["Loncarski"],"firstnames":["J."],"suffixes":[]}],"month":"July","year":"2018","keywords":"Azure cloud architecture, Current measurement, Forecasting, Industries, Industry 4.0, Machine learning, Predictive maintenance, Time measurement, cloud computing, communication protocols, condition monitoring, data analysis, data collection, data system analysis, economic loss, electric motors, failure analysis, learning (artificial intelligence), machine PLCs, machine learning approach, maintenance engineering, motor failures, predictive maintenance, production engineering computing, programmable controllers, protocols, random forest approach, reliability, sensors, simulation tool analysis, system reliability","pages":"1–6","bibtex":"@inproceedings{paolanti_machine_2018,\n\ttitle = {Machine {Learning} approach for {Predictive} {Maintenance} in {Industry} 4.0},\n\tdoi = {10.1109/MESA.2018.8449150},\n\tabstract = {Condition monitoring together with predictive maintenance of electric motors and other equipment used by the industry avoids severe economic losses resulting from unexpected motor failures and greatly improves the system reliability. This paper describes a Machine Learning architecture for Predictive Maintenance, based on Random Forest approach. The system was tested on a real industry example, by developing the data collection and data system analysis, applying the Machine Learning approach and comparing it to the simulation tool analysis. Data has been collected by various sensors, machine PLCs and communication protocols and made available to Data Analysis Tool on the Azure Cloud architecture. Preliminary results show a proper behavior of the approach on predicting different machine states with high accuracy.},\n\tbooktitle = {2018 14th {IEEE}/{ASME} {International} {Conference} on {Mechatronic} and {Embedded} {Systems} and {Applications} ({MESA})},\n\tauthor = {Paolanti, M. and Romeo, L. and Felicetti, A. and Mancini, A. and Frontoni, E. and Loncarski, J.},\n\tmonth = jul,\n\tyear = {2018},\n\tkeywords = {Azure cloud architecture, Current measurement, Forecasting, Industries, Industry 4.0, Machine learning, Predictive maintenance, Time measurement, cloud computing, communication protocols, condition monitoring, data analysis, data collection, data system analysis, economic loss, electric motors, failure analysis, learning (artificial intelligence), machine PLCs, machine learning approach, maintenance engineering, motor failures, predictive maintenance, production engineering computing, programmable controllers, protocols, random forest approach, reliability, sensors, simulation tool analysis, system reliability},\n\tpages = {1--6},\n}\n\n","author_short":["Paolanti, M.","Romeo, L.","Felicetti, A.","Mancini, A.","Frontoni, E.","Loncarski, J."],"key":"paolanti_machine_2018","id":"paolanti_machine_2018","bibbaseid":"paolanti-romeo-felicetti-mancini-frontoni-loncarski-machinelearningapproachforpredictivemaintenanceinindustry40-2018","role":"author","urls":{},"keyword":["Azure cloud architecture","Current measurement","Forecasting","Industries","Industry 4.0","Machine learning","Predictive maintenance","Time measurement","cloud computing","communication protocols","condition monitoring","data analysis","data collection","data system analysis","economic loss","electric motors","failure analysis","learning (artificial intelligence)","machine PLCs","machine learning approach","maintenance engineering","motor failures","predictive maintenance","production engineering computing","programmable controllers","protocols","random forest approach","reliability","sensors","simulation tool analysis","system reliability"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["azure cloud architecture","current measurement","forecasting","industries","industry 4.0","machine learning","predictive maintenance","time measurement","cloud computing","communication protocols","condition monitoring","data analysis","data collection","data system analysis","economic loss","electric motors","failure analysis","learning (artificial intelligence)","machine plcs","machine learning approach","maintenance engineering","motor failures","predictive maintenance","production engineering computing","programmable controllers","protocols","random forest approach","reliability","sensors","simulation tool analysis","system reliability"],"search_terms":["machine","learning","approach","predictive","maintenance","industry","paolanti","romeo","felicetti","mancini","frontoni","loncarski"],"title":"Machine Learning approach for Predictive Maintenance in Industry 4.0","year":2018}