A Fault Detection Technique based on Deep Transfer Learning from Experimental Linear Actuator to Real-World Railway Door Systems

TY - GEN

T1 - A Fault Detection Technique based on Deep Transfer Learning from Experimental Linear Actuator to Real-World Railway Door Systems

AU - Shimizu, Minoru

AU - Perinpanayagam, Suresh

AU - Namoano, Bernadin

N1 - Publisher Copyright: © 2022 Prognostics and Health Management Society. All rights reserved.

PY - 2022/10/28

Y1 - 2022/10/28

N2 - Fault detection for railway door systems based on data-driven approaches has been investigated in recent years due to the massive amount of available monitoring data. Despite much attention to its application, the major challenge is the lack of available faulty datasets to build a reliable model since railway maintenance is usually conducted regularly to avoid significant defects from economic and safety points of view. We aim to tackle the issue by employing transfer learning. Firstly, a long-short term memory-based deep learning model is built using linear actuator experimental datasets. Then, a transfer learning technique is employed to adjust the deep learning model to be available to real-world railway door systems using a small amount of faulty data. As a result, high fault detection accuracy can be obtained at 0.979 as F1 score. The result reveals that an accurate fault detection model can be built even though a large number of labelled datasets is unavailable. In addition, the proposed method is applicable to other door systems or electro-mechanical actuators since the method is unspecific to physical mechanisms and fault modes, and the only motor current signal is used in this research. The signal is primarily available from the controller or motor drive without additional sensors.

AB - Fault detection for railway door systems based on data-driven approaches has been investigated in recent years due to the massive amount of available monitoring data. Despite much attention to its application, the major challenge is the lack of available faulty datasets to build a reliable model since railway maintenance is usually conducted regularly to avoid significant defects from economic and safety points of view. We aim to tackle the issue by employing transfer learning. Firstly, a long-short term memory-based deep learning model is built using linear actuator experimental datasets. Then, a transfer learning technique is employed to adjust the deep learning model to be available to real-world railway door systems using a small amount of faulty data. As a result, high fault detection accuracy can be obtained at 0.979 as F1 score. The result reveals that an accurate fault detection model can be built even though a large number of labelled datasets is unavailable. In addition, the proposed method is applicable to other door systems or electro-mechanical actuators since the method is unspecific to physical mechanisms and fault modes, and the only motor current signal is used in this research. The signal is primarily available from the controller or motor drive without additional sensors.

UR - http://www.scopus.com/inward/record.url?scp=85150472211&partnerID=8YFLogxK

U2 - 10.36001/phmconf.2022.v14i1.3378

DO - 10.36001/phmconf.2022.v14i1.3378

M3 - Conference contribution

AN - SCOPUS:85150472211

BT - Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM

A2 - Kulkarni, Chetan

A2 - Saxena, Abhinav

PB - Prognostics and Health Management Society

T2 - 2022 Annual Conference of the Prognostics and Health Management Society, PHM 2022

Y2 - 31 October 2022 through 4 November 2022

ER -