Georgia Southern University
Railroad Condition Monitoring Using Distributed Acoustic Sensing and Deep Learning Techniques
Abstract
dc:description.abstractProper condition monitoring has been a major issue among railroad administrations since it might cause catastrophic dilemmas that lead to fatalities or damage to the infrastructure. Although various aspects of train safety have been conducted by scholars, in-motion monitoring detection of defect occurrence, cause, and severity is still a big concern. Hence extensive studies are still required to enhance the accuracy of inspection methods for railroad condition monitoring (CM). Distributed acoustic sensing (DAS) has been recognized as a promising method because of its sensing capabilities over long distances and for massive structures. As DAS produces large datasets, algorithms for precise real-time, and reliable analysis are essential. Deep learning (DL) based data-driven algorithms could be a valuable solution to identify patterns and behaviors that might not appear by manual inspections of rail infrastructures. On the other hand, due to the wide variety of challenges from weather interference, the on-site testing of the DAS-Fiber Optic-Railroad set-up has proven to be highly expensive. This research work proposes a novel DL algorithm using multiple datasets acquired from the High Tonnage Loop (HTL), facilities of MxV Rail in Pueblo, CO. In the end, a finite element analysis (FEA) is conducted to determine the effectiveness of fiber optic acoustic detection in various circumstances and to reduce the cost of on-site testing.
Degree
thesis:*- Name thesis:degree_name
- Master of Science in Applied Engineering (M.S.A.E.)
- Level thesis:degree_level
- Thesis (open access)
- Discipline thesis:degree_discipline
- Department of Manufacturing Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Rahman, Md Arifur
- Contributors dc:contributor
-
- Jongyeop Kim
- Meenalosini Vimal Cruz
Subjects
dc:subject × 21- Distributed Acoustic Sensing (DAS)
- Condition Monitoring (CM)
- High Tonnage Loop (HTL)
- Deep Learning (DL)
- Finite element analysis (FEA)
- Railroad
- Anomaly Detection
- Railroad Safety
- Acoustics, Dynamics, and Controls
- Aviation Safety and Security
- Computer-Aided Engineering and Design
- Databases and Information Systems
- Digital Communications and Networking
- Electro-Mechanical Systems
- Maintenance Technology
- Management and Operations
- Numerical Analysis and Scientific Computing
- Operations Research, Systems Engineering and Industrial Engineering
- Programming Languages and Compilers
- Structural Engineering
- Transportation Engineering
Rights
- Licence dc:rights.license
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.georgiasouthern.edu/etd/2755