Predicting machine failures from industrial time series data

F.J.M. Jansen; M.J. Holenderski; T. Ozcelebi; Paulien Dam; Bas Tijsma

doi:10.1109/CoDIT.2018.8394915

Predicting machine failures from industrial time series data

F.J.M. Jansen, M.J. Holenderski, T. Ozcelebi, Paulien Dam, Bas Tijsma

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

8 Citations (SciVal)

1 Downloads (Pure)

Abstract

This paper addresses the problem of predicting machine failures in an industrial manufacturing process based on multivariate time series data. A workflow is presented for cleaning and preprocessing the data, and for training and evaluating a predictive model. Its implementation is modular and extensible to support changes in the underlying produc- tion processes and the gathered data. Two predictive models are presented, based on Convolutional Neural Networks and Recurrent Neural Networks, and evaluated on data from an advanced machining process used for cutting complex shapes into metal pieces.

Original language	English
Title of host publication	2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1091-1096
Number of pages	6
ISBN (Electronic)	978-1-5386-5065-3
DOIs	https://doi.org/10.1109/CoDIT.2018.8394915
Publication status	Published - 2018
Event	5th International Conference on Control, Decision and Information Technologies (CoDIT 2018) - Thessaloniki, Greece Duration: 10 Apr 2018 → 13 Apr 2018

Conference

Conference	5th International Conference on Control, Decision and Information Technologies (CoDIT 2018)
Country/Territory	Greece
City	Thessaloniki
Period	10/04/18 → 13/04/18

Access to Document

10.1109/CoDIT.2018.8394915

Cite this

@inproceedings{29eb2e3a4ea64cf19829fc458d8a6f66,

title = "Predicting machine failures from industrial time series data",

abstract = "This paper addresses the problem of predicting machine failures in an industrial manufacturing process based on multivariate time series data. A workflow is presented for cleaning and preprocessing the data, and for training and evaluating a predictive model. Its implementation is modular and extensible to support changes in the underlying produc- tion processes and the gathered data. Two predictive models are presented, based on Convolutional Neural Networks and Recurrent Neural Networks, and evaluated on data from an advanced machining process used for cutting complex shapes into metal pieces.",

author = "F.J.M. Jansen and M.J. Holenderski and T. Ozcelebi and Paulien Dam and Bas Tijsma",

year = "2018",

doi = "10.1109/CoDIT.2018.8394915",

language = "English",

pages = "1091--1096",

booktitle = "2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "5th International Conference on Control, Decision and Information Technologies (CoDIT 2018) ; Conference date: 10-04-2018 Through 13-04-2018",

}

Jansen, FJM, Holenderski, MJ , Ozcelebi, T, Dam, P & Tijsma, B 2018, Predicting machine failures from industrial time series data. in 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT) ., 8394915, Institute of Electrical and Electronics Engineers, Piscataway, pp. 1091-1096, 5th International Conference on Control, Decision and Information Technologies (CoDIT 2018) , Thessaloniki, Greece, 10/04/18. https://doi.org/10.1109/CoDIT.2018.8394915

Predicting machine failures from industrial time series data. / Jansen, F.J.M.; Holenderski, M.J.; Ozcelebi, T. et al.
2018 5th International Conference on Control, Decision and Information Technologies (CoDIT) . Piscataway: Institute of Electrical and Electronics Engineers, 2018. p. 1091-1096 8394915.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Predicting machine failures from industrial time series data

AU - Jansen, F.J.M.

AU - Holenderski, M.J.

AU - Ozcelebi, T.

AU - Dam, Paulien

AU - Tijsma, Bas

PY - 2018

Y1 - 2018

N2 - This paper addresses the problem of predicting machine failures in an industrial manufacturing process based on multivariate time series data. A workflow is presented for cleaning and preprocessing the data, and for training and evaluating a predictive model. Its implementation is modular and extensible to support changes in the underlying produc- tion processes and the gathered data. Two predictive models are presented, based on Convolutional Neural Networks and Recurrent Neural Networks, and evaluated on data from an advanced machining process used for cutting complex shapes into metal pieces.

AB - This paper addresses the problem of predicting machine failures in an industrial manufacturing process based on multivariate time series data. A workflow is presented for cleaning and preprocessing the data, and for training and evaluating a predictive model. Its implementation is modular and extensible to support changes in the underlying produc- tion processes and the gathered data. Two predictive models are presented, based on Convolutional Neural Networks and Recurrent Neural Networks, and evaluated on data from an advanced machining process used for cutting complex shapes into metal pieces.

UR - http://www.scopus.com/inward/record.url?scp=85050220462&partnerID=8YFLogxK

U2 - 10.1109/CoDIT.2018.8394915

DO - 10.1109/CoDIT.2018.8394915

M3 - Conference contribution

SP - 1091

EP - 1096

BT - 2018 5th International Conference on Control, Decision and Information Technologies (CoDIT)

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 5th International Conference on Control, Decision and Information Technologies (CoDIT 2018)

Y2 - 10 April 2018 through 13 April 2018

ER -

Predicting machine failures from industrial time series data

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this