Deep Learning Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes. / Ruan, Hang; Dorneanu, Bogdan ; Mohamed, Abdelrahim ; Arellano-Garcia, Harvey ; Xiao, Pei ; Zhang, Li.

In: IEEE Access, 20.01.2022.

Research output: Contribution to journalArticlepeer-review

Published

Standard

Deep Learning Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes. / Ruan, Hang; Dorneanu, Bogdan ; Mohamed, Abdelrahim ; Arellano-Garcia, Harvey ; Xiao, Pei ; Zhang, Li.

In: IEEE Access, 20.01.2022.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

Ruan, Hang ; Dorneanu, Bogdan ; Mohamed, Abdelrahim ; Arellano-Garcia, Harvey ; Xiao, Pei ; Zhang, Li. / Deep Learning Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes. In: IEEE Access. 2022.

BibTeX

@article{74dc6d3d8784498394c20b649713fad6,
title = "Deep Learning Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes",
abstract = "This paper investigates the challenging fault prediction problem in process industries that adopt autonomous and intelligent cyber-physical systems (CPS), which is in line with the emerging developments of industrial internet of things (IIoT) and Industry 4.0. Particularly, we developed an end-to-end deep learning approach based on a large volume of real-time sensory data collected from a chemical plant equipped with wireless sensors. Firstly, a novel recursive architecture with multi-lookback inputs is proposed to perform autoregression on imbalanced time-series data as a preliminary prediction. In this process, a novel learning algorithm named recursive gradient descent (RGD) is developed for the proposed architecture to reduce cumulative prediction uncertainties. Subsequently, a classification model based on temporal convolutions over multiple channels with decay effect is proposed to perform multi-class classification for fault root cause identification and localization. The overall network is named the cumulative uncertainty reduction network (CURNet), for its superior capacity in reducing prediction uncertainties accumulated over multiple prediction steps. Performance evaluations show that CURNet is able to achieve superior performance especially in terms of fault prediction recall and fault type classification accuracy, compared to the existing techniques.",
author = "Hang Ruan and Bogdan Dorneanu and Abdelrahim Mohamed and Harvey Arellano-Garcia and Pei Xiao and Li Zhang",
year = "2022",
month = jan,
day = "20",
doi = "10.1109/ACCESS.2022.3144333",
language = "English",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Deep Learning Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes

AU - Ruan, Hang

AU - Dorneanu, Bogdan

AU - Mohamed, Abdelrahim

AU - Arellano-Garcia, Harvey

AU - Xiao, Pei

AU - Zhang, Li

PY - 2022/1/20

Y1 - 2022/1/20

N2 - This paper investigates the challenging fault prediction problem in process industries that adopt autonomous and intelligent cyber-physical systems (CPS), which is in line with the emerging developments of industrial internet of things (IIoT) and Industry 4.0. Particularly, we developed an end-to-end deep learning approach based on a large volume of real-time sensory data collected from a chemical plant equipped with wireless sensors. Firstly, a novel recursive architecture with multi-lookback inputs is proposed to perform autoregression on imbalanced time-series data as a preliminary prediction. In this process, a novel learning algorithm named recursive gradient descent (RGD) is developed for the proposed architecture to reduce cumulative prediction uncertainties. Subsequently, a classification model based on temporal convolutions over multiple channels with decay effect is proposed to perform multi-class classification for fault root cause identification and localization. The overall network is named the cumulative uncertainty reduction network (CURNet), for its superior capacity in reducing prediction uncertainties accumulated over multiple prediction steps. Performance evaluations show that CURNet is able to achieve superior performance especially in terms of fault prediction recall and fault type classification accuracy, compared to the existing techniques.

AB - This paper investigates the challenging fault prediction problem in process industries that adopt autonomous and intelligent cyber-physical systems (CPS), which is in line with the emerging developments of industrial internet of things (IIoT) and Industry 4.0. Particularly, we developed an end-to-end deep learning approach based on a large volume of real-time sensory data collected from a chemical plant equipped with wireless sensors. Firstly, a novel recursive architecture with multi-lookback inputs is proposed to perform autoregression on imbalanced time-series data as a preliminary prediction. In this process, a novel learning algorithm named recursive gradient descent (RGD) is developed for the proposed architecture to reduce cumulative prediction uncertainties. Subsequently, a classification model based on temporal convolutions over multiple channels with decay effect is proposed to perform multi-class classification for fault root cause identification and localization. The overall network is named the cumulative uncertainty reduction network (CURNet), for its superior capacity in reducing prediction uncertainties accumulated over multiple prediction steps. Performance evaluations show that CURNet is able to achieve superior performance especially in terms of fault prediction recall and fault type classification accuracy, compared to the existing techniques.

U2 - 10.1109/ACCESS.2022.3144333

DO - 10.1109/ACCESS.2022.3144333

M3 - Article

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -