Abnormal data analysis in process industries using deep-learning method

Wen Song, Wei Weng, Shigeru Fujimura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This research is mainly about the abnormal data analysis in factories of process industries. In the processing factory, there are many sensors which transmit the values to each other. Workers in process factory need to be alerted when the values of some sensors are abnormal values. In our research, the main target is to detect the potential abnormal value from different sensors of process industries. Since the value is filled with noise and delays, we first use the cross-correlation and wavelet transformation to remove them. Then, use deep-learning method to train the model with processed data and use the model to detect potential abnormal value. Finally, we evaluate the model we trained by the data extracted from a real process factory. The result shows that our model performs well.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017
PublisherIEEE Computer Society
Pages2356-2360
Number of pages5
Volume2017-December
ISBN (Electronic)9781538609484
DOIs
Publication statusPublished - 2018 Feb 9
Event2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017 - Singapore, Singapore
Duration: 2017 Dec 102017 Dec 13

Other

Other2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017
CountrySingapore
CitySingapore
Period17/12/1017/12/13

Fingerprint

Industrial plants
Industry
Sensors
Deep learning
Process industry
Learning methods
Processing
Factory
Sensor

Keywords

  • Data analysis
  • deep-learning
  • wavelet-denoising

ASJC Scopus subject areas

  • Business, Management and Accounting (miscellaneous)
  • Industrial and Manufacturing Engineering
  • Safety, Risk, Reliability and Quality

Cite this

Song, W., Weng, W., & Fujimura, S. (2018). Abnormal data analysis in process industries using deep-learning method. In 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017 (Vol. 2017-December, pp. 2356-2360). IEEE Computer Society. https://doi.org/10.1109/IEEM.2017.8290313

Abnormal data analysis in process industries using deep-learning method. / Song, Wen; Weng, Wei; Fujimura, Shigeru.

2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017. Vol. 2017-December IEEE Computer Society, 2018. p. 2356-2360.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Song, W, Weng, W & Fujimura, S 2018, Abnormal data analysis in process industries using deep-learning method. in 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017. vol. 2017-December, IEEE Computer Society, pp. 2356-2360, 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017, Singapore, Singapore, 17/12/10. https://doi.org/10.1109/IEEM.2017.8290313
Song W, Weng W, Fujimura S. Abnormal data analysis in process industries using deep-learning method. In 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017. Vol. 2017-December. IEEE Computer Society. 2018. p. 2356-2360 https://doi.org/10.1109/IEEM.2017.8290313
Song, Wen ; Weng, Wei ; Fujimura, Shigeru. / Abnormal data analysis in process industries using deep-learning method. 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017. Vol. 2017-December IEEE Computer Society, 2018. pp. 2356-2360
@inproceedings{0a7ac7e5440a44e29b5b58d679fea4a4,
title = "Abnormal data analysis in process industries using deep-learning method",
abstract = "This research is mainly about the abnormal data analysis in factories of process industries. In the processing factory, there are many sensors which transmit the values to each other. Workers in process factory need to be alerted when the values of some sensors are abnormal values. In our research, the main target is to detect the potential abnormal value from different sensors of process industries. Since the value is filled with noise and delays, we first use the cross-correlation and wavelet transformation to remove them. Then, use deep-learning method to train the model with processed data and use the model to detect potential abnormal value. Finally, we evaluate the model we trained by the data extracted from a real process factory. The result shows that our model performs well.",
keywords = "Data analysis, deep-learning, wavelet-denoising",
author = "Wen Song and Wei Weng and Shigeru Fujimura",
year = "2018",
month = "2",
day = "9",
doi = "10.1109/IEEM.2017.8290313",
language = "English",
volume = "2017-December",
pages = "2356--2360",
booktitle = "2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Abnormal data analysis in process industries using deep-learning method

AU - Song, Wen

AU - Weng, Wei

AU - Fujimura, Shigeru

PY - 2018/2/9

Y1 - 2018/2/9

N2 - This research is mainly about the abnormal data analysis in factories of process industries. In the processing factory, there are many sensors which transmit the values to each other. Workers in process factory need to be alerted when the values of some sensors are abnormal values. In our research, the main target is to detect the potential abnormal value from different sensors of process industries. Since the value is filled with noise and delays, we first use the cross-correlation and wavelet transformation to remove them. Then, use deep-learning method to train the model with processed data and use the model to detect potential abnormal value. Finally, we evaluate the model we trained by the data extracted from a real process factory. The result shows that our model performs well.

AB - This research is mainly about the abnormal data analysis in factories of process industries. In the processing factory, there are many sensors which transmit the values to each other. Workers in process factory need to be alerted when the values of some sensors are abnormal values. In our research, the main target is to detect the potential abnormal value from different sensors of process industries. Since the value is filled with noise and delays, we first use the cross-correlation and wavelet transformation to remove them. Then, use deep-learning method to train the model with processed data and use the model to detect potential abnormal value. Finally, we evaluate the model we trained by the data extracted from a real process factory. The result shows that our model performs well.

KW - Data analysis

KW - deep-learning

KW - wavelet-denoising

UR - http://www.scopus.com/inward/record.url?scp=85045243036&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045243036&partnerID=8YFLogxK

U2 - 10.1109/IEEM.2017.8290313

DO - 10.1109/IEEM.2017.8290313

M3 - Conference contribution

VL - 2017-December

SP - 2356

EP - 2360

BT - 2017 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2017

PB - IEEE Computer Society

ER -