Optimized User Experience for Labeling Systems for Predictive Maintenance Applications (Extended)

TL;DR

The paper addresses the challenge of building reliable predictive maintenance for rail systems by prioritizing high‑quality labeled data and user‑centered labeling interfaces. It introduces DigiOnTrack, a cost‑effective, structure‑borne noise–driven predictive maintenance system with a Dockerized backend and a secure data flow via distributed ledger technology, plus two role‑specific labeling dashboards. Usability evaluations show excellent usability for locomotive drivers and good usability for workshop foremen, highlighting the importance of workflow integration while identifying perspicuity as an area for data‑intensive scenarios. The work demonstrates a practical, integrable approach to Industry 4.0 labeling in rail, with implications for scalable data management, secure sharing, and future guidelines for labeling interfaces in critical infrastructure.

Abstract

The maintenance of rail vehicles and infrastructure plays a critical role in reducing delays, preventing malfunctions, and ensuring the economic efficiency of rail transportation companies. Predictive maintenance systems powered by supervised machine learning offer a promising approach by detecting failures before they occur, reducing unscheduled downtime, and improving operational efficiency. However, the success of such systems depends on high quality labeled data, necessitating user centered labeling interfaces tailored to annotators needs for Usability and User Experience. This study introduces a cost effective predictive maintenance system developed in the federally funded project DigiOnTrack, which combines structure borne noise measurement with supervised learning to provide monitoring and maintenance recommendations for rail vehicles and infrastructure in rural Germany. The system integrates wireless sensor networks, distributed ledger technology for secure data transfer, and a dockerized container infrastructure hosting the labeling interface and dashboard. Train drivers and workshop foremen labeled faults on infrastructure and vehicles to ensure accurate recommendations. The Usability and User Experience evaluation showed that the locomotive drivers interface achieved Excellent Usability, while the workshop foremans interface was rated as Good. These results highlight the systems potential for integration into daily workflows, particularly in labeling efficiency. However, areas such as Perspicuity require further optimization for more data intensive scenarios. The findings offer insights into the design of predictive maintenance systems and labeling interfaces, providing a foundation for future guidelines in Industry 4.0 applications, particularly in rail transportation.

Figures (8)

• Figure 1: Dashboard for Train Car Faults Labeling of the Workshop Foreman: Back, Help, and Logout Buttons in the Header; Number of Unlabeled Workshop Visits on the Left; Entry, Exit, and Train Car Identification Selection Input Fields at the Top; Lists with Labels for Labeling of Faults and Repairs in the Center and Bottom, Button for the Creation of a New Label Below the Labels
• Figure 2: Dashboard for Train Car Faults Labeling of the Workshop Foreman - Continuation: Both Label Category Lists are Visible, Submit Button at the Bottom
• Figure 3: Overlay for Creating a New Label: In the Center are the List with Already Available Labels and an Input Field for the New Label, at the Bottom of the Overlay are the Buttons to Go Back and to Confirm the Input, it is Possible to Close the Overlay with the Close Button in the Upper Right Corner
• Figure 4: Data Verification Before Submitting Labels: User is Asked if the Following Data Should Be Submitted, Train Car Data with Selected Labels is Listed, at the Bottom of the Overlay are the Buttons to Go Back and to Confirm the Input, it is Possible to Close the Overlay with the Close Button in the Upper Right Corner
• Figure 5: Dashboard for Rail Faults Labeling of the Train Car Drivers: List of Events on the Left, Date, Time, Train Identification and Event Location are shown at the Top, Label List at the Bottom