Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.16239 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915628524240896 |
|---|---|
| author | Stern, Michael Hallmann, Michelle Vona, Francesco Franke, Ute Ostertag, Thomas Schlueter, Benjamin Voigt-Antons, Jan-Niklas |
| author_facet | Stern, Michael Hallmann, Michelle Vona, Francesco Franke, Ute Ostertag, Thomas Schlueter, Benjamin Voigt-Antons, Jan-Niklas |
| contents | Rail transportation success depends on efficient maintenance to avoid delays and malfunctions, particularly in rural areas with limited resources. We propose a cost-effective wireless monitoring system that integrates sensors and machine learning to address these challenges. We developed a secure data management system, equipping train cars and rail sections with sensors to collect structural and environmental data. This data supports Predictive Maintenance by identifying potential issues before they lead to failures. Implementing this system requires a robust backend infrastructure for secure data transfer, storage, and analysis. Designed collaboratively with stakeholders, including the railroad company and project partners, our system is tailored to meet specific requirements while ensuring data integrity and security. This article discusses the reasoning behind our design choices, including the selection of sensors, data handling protocols, and Machine Learning models. We propose a system architecture for implementing the solution, covering aspects such as network topology and data processing workflows. Our approach aims to enhance the reliability and efficiency of rail transportation through advanced technological integration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_16239 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Predictive Maintenance: Enhanced AI and Backend Integration Stern, Michael Hallmann, Michelle Vona, Francesco Franke, Ute Ostertag, Thomas Schlueter, Benjamin Voigt-Antons, Jan-Niklas Human-Computer Interaction Rail transportation success depends on efficient maintenance to avoid delays and malfunctions, particularly in rural areas with limited resources. We propose a cost-effective wireless monitoring system that integrates sensors and machine learning to address these challenges. We developed a secure data management system, equipping train cars and rail sections with sensors to collect structural and environmental data. This data supports Predictive Maintenance by identifying potential issues before they lead to failures. Implementing this system requires a robust backend infrastructure for secure data transfer, storage, and analysis. Designed collaboratively with stakeholders, including the railroad company and project partners, our system is tailored to meet specific requirements while ensuring data integrity and security. This article discusses the reasoning behind our design choices, including the selection of sensors, data handling protocols, and Machine Learning models. We propose a system architecture for implementing the solution, covering aspects such as network topology and data processing workflows. Our approach aims to enhance the reliability and efficiency of rail transportation through advanced technological integration. |
| title | Optimizing Predictive Maintenance: Enhanced AI and Backend Integration |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2511.16239 |