Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM

Prashant Kumar; Ananda Shankar Hati; Sanjeevikumar Padmanaban; Zbigniew Leonowicz; Prasun Chakrabarti

doi:10.1109/EEEIC/ICPSEurope49358.2020.9160712

Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM

Prashant Kumar
, Ananda Shankar Hati
, Sanjeevikumar Padmanaban
, Zbigniew Leonowicz
, Prasun Chakrabarti

Department of Mechanical, Robotics and Energy Engineering

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

7 Scopus citations

Abstract

The modern industries are driven by the Squirrel cage induction motors (SCIMs), and zero downtime is the need of the hour. Condition-based maintenance is pivotal for achieving zero downtime. The ability of automatic feature extraction of Deep learning has effectively used in fault diagnosis in SCIMs. This paper proposes a novel transfer learning (TL) based deep convolutional neural network (CNN) fault detection model for bearing fault and broken rotor bar detection in SCIM, both individually and jointly. The transfer learning enables the faster learning and accelerates the training of deep CNN based fault detection model. Compared with the deep CNN model trained from scratch, the developed method is meticulous and computationally efficient. This paper has used a current analysis for fault detection in SCIMs. The proposed method owing to its deep structures and inherent ability, automatically learns the features from current signals for fault detection. The proposed fault detection model has achieved a mean accuracy of 99.40%. Also, the proposed method overcomes the disadvantages of deep CNN by applying for the knowledge transfer through transfer learning.

Original language	English
Title of host publication	Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020
Editors	Zhigniew Leonowicz
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728174532
DOIs	https://doi.org/10.1109/EEEIC/ICPSEurope49358.2020.9160712
State	Published - Jun 2020
Event	2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020 - Madrid, Spain Duration: 9 Jun 2020 → 12 Jun 2020

Publication series

Name	Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020

Conference

Conference	2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020
Country/Territory	Spain
City	Madrid
Period	9/06/20 → 12/06/20

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

bearing fault
broken rotor bar
Convolutional neural network
Deep learning
Squirrel cage induction motors
Transfer learning

Access to Document

10.1109/EEEIC/ICPSEurope49358.2020.9160712

Cite this

Kumar, P., Hati, A. S., Padmanaban, S., Leonowicz, Z., & Chakrabarti, P. (2020). Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM. In Z. Leonowicz (Ed.), Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020 Article 9160712 (Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EEEIC/ICPSEurope49358.2020.9160712

Kumar, Prashant ; Hati, Ananda Shankar ; Padmanaban, Sanjeevikumar et al. / Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM. Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020. editor / Zhigniew Leonowicz. Institute of Electrical and Electronics Engineers Inc., 2020. (Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020).

@inproceedings{f2d3e1edd6da4773b3bcec2d4ff746de,

title = "Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM",

abstract = "The modern industries are driven by the Squirrel cage induction motors (SCIMs), and zero downtime is the need of the hour. Condition-based maintenance is pivotal for achieving zero downtime. The ability of automatic feature extraction of Deep learning has effectively used in fault diagnosis in SCIMs. This paper proposes a novel transfer learning (TL) based deep convolutional neural network (CNN) fault detection model for bearing fault and broken rotor bar detection in SCIM, both individually and jointly. The transfer learning enables the faster learning and accelerates the training of deep CNN based fault detection model. Compared with the deep CNN model trained from scratch, the developed method is meticulous and computationally efficient. This paper has used a current analysis for fault detection in SCIMs. The proposed method owing to its deep structures and inherent ability, automatically learns the features from current signals for fault detection. The proposed fault detection model has achieved a mean accuracy of 99.40\%. Also, the proposed method overcomes the disadvantages of deep CNN by applying for the knowledge transfer through transfer learning.",

keywords = "bearing fault, broken rotor bar, Convolutional neural network, Deep learning, Squirrel cage induction motors, Transfer learning",

author = "Prashant Kumar and Hati, \{Ananda Shankar\} and Sanjeevikumar Padmanaban and Zbigniew Leonowicz and Prasun Chakrabarti",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020 ; Conference date: 09-06-2020 Through 12-06-2020",

year = "2020",

month = jun,

doi = "10.1109/EEEIC/ICPSEurope49358.2020.9160712",

language = "English",

series = "Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Zhigniew Leonowicz",

booktitle = "Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020",

address = "United States",

}

Kumar, P, Hati, AS, Padmanaban, S, Leonowicz, Z & Chakrabarti, P 2020, Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM. in Z Leonowicz (ed.), Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020., 9160712, Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020, Institute of Electrical and Electronics Engineers Inc., 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020, Madrid, Spain, 9/06/20. https://doi.org/10.1109/EEEIC/ICPSEurope49358.2020.9160712

Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM. / Kumar, Prashant; Hati, Ananda Shankar; Padmanaban, Sanjeevikumar et al.
Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020. ed. / Zhigniew Leonowicz. Institute of Electrical and Electronics Engineers Inc., 2020. 9160712 (Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020).

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

TY - GEN

T1 - Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM

AU - Kumar, Prashant

AU - Hati, Ananda Shankar

AU - Padmanaban, Sanjeevikumar

AU - Leonowicz, Zbigniew

AU - Chakrabarti, Prasun

PY - 2020/6

Y1 - 2020/6

N2 - The modern industries are driven by the Squirrel cage induction motors (SCIMs), and zero downtime is the need of the hour. Condition-based maintenance is pivotal for achieving zero downtime. The ability of automatic feature extraction of Deep learning has effectively used in fault diagnosis in SCIMs. This paper proposes a novel transfer learning (TL) based deep convolutional neural network (CNN) fault detection model for bearing fault and broken rotor bar detection in SCIM, both individually and jointly. The transfer learning enables the faster learning and accelerates the training of deep CNN based fault detection model. Compared with the deep CNN model trained from scratch, the developed method is meticulous and computationally efficient. This paper has used a current analysis for fault detection in SCIMs. The proposed method owing to its deep structures and inherent ability, automatically learns the features from current signals for fault detection. The proposed fault detection model has achieved a mean accuracy of 99.40%. Also, the proposed method overcomes the disadvantages of deep CNN by applying for the knowledge transfer through transfer learning.

AB - The modern industries are driven by the Squirrel cage induction motors (SCIMs), and zero downtime is the need of the hour. Condition-based maintenance is pivotal for achieving zero downtime. The ability of automatic feature extraction of Deep learning has effectively used in fault diagnosis in SCIMs. This paper proposes a novel transfer learning (TL) based deep convolutional neural network (CNN) fault detection model for bearing fault and broken rotor bar detection in SCIM, both individually and jointly. The transfer learning enables the faster learning and accelerates the training of deep CNN based fault detection model. Compared with the deep CNN model trained from scratch, the developed method is meticulous and computationally efficient. This paper has used a current analysis for fault detection in SCIMs. The proposed method owing to its deep structures and inherent ability, automatically learns the features from current signals for fault detection. The proposed fault detection model has achieved a mean accuracy of 99.40%. Also, the proposed method overcomes the disadvantages of deep CNN by applying for the knowledge transfer through transfer learning.

KW - bearing fault

KW - broken rotor bar

KW - Convolutional neural network

KW - Deep learning

KW - Squirrel cage induction motors

KW - Transfer learning

UR - https://www.scopus.com/pages/publications/85090423369

U2 - 10.1109/EEEIC/ICPSEurope49358.2020.9160712

DO - 10.1109/EEEIC/ICPSEurope49358.2020.9160712

M3 - Conference contribution

AN - SCOPUS:85090423369

T3 - Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020

BT - Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020

A2 - Leonowicz, Zhigniew

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020

Y2 - 9 June 2020 through 12 June 2020

ER -

Kumar P, Hati AS, Padmanaban S, Leonowicz Z, Chakrabarti P. Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM. In Leonowicz Z, editor, Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9160712. (Proceedings - 2020 IEEE International Conference on Environment and Electrical Engineering and 2020 IEEE Industrial and Commercial Power Systems Europe, EEEIC / I and CPS Europe 2020). doi: 10.1109/EEEIC/ICPSEurope49358.2020.9160712

Amalgamation of Transfer Learning and Deep Convolutional Neural Network for Multiple Fault Detection in SCIM

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this