A fault detection technique based on deep transfer learning from experimental linear actuator to real-world railway door systems

Simple item page
dc.contributor.authorShimizu, Minoru
dc.contributor.authorPerinpanayagam, Suresh
dc.contributor.authorNamoano, Bernadin
dc.date.accessioned2022-12-14T09:43:46Z
dc.date.available2022-12-14T09:43:46Z
dc.date.issued2022-10-28
dc.description.abstractFault 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 aimed to tackle the issue by employing transfer learning. Firstly, we built a long-short term memory-based deep learning model using linear actuator experimental datasets. Then, we employed a transfer learning technique 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 amount 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.en_UK
dc.identifier.citationShimizu M, Perinpanayagam S, Namoano B. (2022) A Fault Detection Technique based on Deep Transfer Learning from Experimental Linear Actuator to Real-World Railway Door Systems. In: Annual Conference of the Prognostics and Health Management Society, 31 October - 4 November 2022, Nashville, USA, Volume 14, Issue 1en_UK
dc.identifier.urihttps://doi.org/10.36001/phmconf.2022.v14i1.3378
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/18806
dc.language.isoenen_UK
dc.publisherPHM Societyen_UK
dc.rightsAttribution 3.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/*
dc.subjectfault detectionen_UK
dc.subjectPHMen_UK
dc.subjectTransfer Learningen_UK
dc.subjectDeep Learningen_UK
dc.subjectData-driven approachen_UK
dc.subjectLSTMen_UK
dc.subjectLinear Actuatoren_UK
dc.subjectDoor systemsen_UK
dc.titleA fault detection technique based on deep transfer learning from experimental linear actuator to real-world railway door systemsen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
fault_detection_technique-real-world_railway_door_systems-2022.pdf
Size:
987.93 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)