Predicting Track Geometry Using Machine-Learning Methods

Ahmed, Mohammed; Palese, Joseph W; Zarembski, Allan M.

i

Predicting Track Geometry Using Machine-Learning Methods

2023-10-06
By Ahmed, Mohammed ; Palese, Joseph W ; Zarembski, Allan M.

File Language:

English

Details

Creators:

Ahmed, Mohammed ; Palese, Joseph W ; Zarembski, Allan M.
Corporate Creators:

University of Delaware. Department of Civil and Environmental Engineering
Corporate Contributors:

United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology ; University Transportation Center on Improving Rail Transportation Infrastructure Sustainability and Durability. USDOT Tier 1
Subject/TRT Terms:
Publication/ Report Number:

RailTEAM UD-3
Resource Type:

Tech Report
Geographical Coverage:

United States
Corporate Publisher:

University of Nevada. University Transportation Center on Improving Rail Transportation Infrastructure Sustainability and Durability
Abstract:

This study centers on predictive maintenance, an approach that foresees maintenance requirements based on anticipated defect occurrences. The research aims to create a model that accurately forecasts track geometry irregularities, empowering engineers to proactively address maintenance needs. Traditionally, maintenance decisions relied on experience, manual inspections, and cyclical upkeep, leading to potential safety concerns and cost escalations. This research takes a novel approach by integrating mechanical and data-driven models, utilizing functional networks, Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) networks. RNNs capture sequences effectively, while LSTM networks excel in tracing long-term dependencies, making them apt for predicting track degradation patterns.
Format:

PDF
Funding:

69A3551747132
Download URL:

https://rosap.ntl.bts.gov/view/dot/80897/dot_80897_DS1.pdf
File Type:

[PDF - 3.37 MB]
Collection(s):

University Transportation Centers
Main Document Checksum:

urn:sha-512:635f9b904d6cbe3973d508a3b981bd14da703d4a3776213c3fe7715b00c42ca8e790377d874c7070fcd56f5ee917b5a184ea5e82cfbda50153c6366c7b3012f4

File Language:

English

ON THIS PAGE

Details

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.