Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine Learning
Railway noise, stemming from various sources such as wheel/rail interactions, locomotives, and track machinery, affects both human health and the environment. This study explores the application of machine learning (ML) models to quantify tram noise at sharp curves, considering variables such as wea...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10778546/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536169354985472 |
|---|---|
| author | Junhui Huang Hao Liu Wenyan Xi Sakdirat Kaewunruen |
| author_facet | Junhui Huang Hao Liu Wenyan Xi Sakdirat Kaewunruen |
| author_sort | Junhui Huang |
| collection | DOAJ |
| description | Railway noise, stemming from various sources such as wheel/rail interactions, locomotives, and track machinery, affects both human health and the environment. This study explores the application of machine learning (ML) models to quantify tram noise at sharp curves, considering variables such as weather conditions, train speed, crowd levels, and running directions. Data collection is carried out on a tram line in Birmingham, using an iPhone 11 to record acoustic data at a sample rate of 48 kHz. The noise is categorized into impact noise, rolling noise, flanging noise, and squeal noise based on frequency and power spectrum characteristics. Random Forests (RF) and Extreme Gradient Boosting (XGBoost) are employed to predict the root mean square (R.M.S) values of each type of noise. Results indicate that XGBoost outperformed RF with an R2 up to 0.96 during k-fold cross-validation. This model provides a robust tool for railway operators to optimize noise control measures and contributes to improved compliance with environmental regulations and a better quality of life for communities near rail tracks. |
| format | Article |
| id | doaj-art-456e62eaebe3401898b75aa28159c087 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-456e62eaebe3401898b75aa28159c0872025-01-15T00:02:04ZengIEEEIEEE Access2169-35362024-01-011218355518356310.1109/ACCESS.2024.351249510778546Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine LearningJunhui Huang0Hao Liu1Wenyan Xi2Sakdirat Kaewunruen3https://orcid.org/0000-0003-2153-3538Department of Civil Engineering, School of Engineering, University of Birmingham, Birmingham, U.K.Department of Civil Engineering, School of Engineering, University of Birmingham, Birmingham, U.K.Department of Civil Engineering, School of Engineering, University of Birmingham, Birmingham, U.K.Department of Civil Engineering, School of Engineering, University of Birmingham, Birmingham, U.K.Railway noise, stemming from various sources such as wheel/rail interactions, locomotives, and track machinery, affects both human health and the environment. This study explores the application of machine learning (ML) models to quantify tram noise at sharp curves, considering variables such as weather conditions, train speed, crowd levels, and running directions. Data collection is carried out on a tram line in Birmingham, using an iPhone 11 to record acoustic data at a sample rate of 48 kHz. The noise is categorized into impact noise, rolling noise, flanging noise, and squeal noise based on frequency and power spectrum characteristics. Random Forests (RF) and Extreme Gradient Boosting (XGBoost) are employed to predict the root mean square (R.M.S) values of each type of noise. Results indicate that XGBoost outperformed RF with an R2 up to 0.96 during k-fold cross-validation. This model provides a robust tool for railway operators to optimize noise control measures and contributes to improved compliance with environmental regulations and a better quality of life for communities near rail tracks.https://ieeexplore.ieee.org/document/10778546/Railway noisemachine learningnoise quantificationenvironmental factorsrandom forestsXGBoost |
| spellingShingle | Junhui Huang Hao Liu Wenyan Xi Sakdirat Kaewunruen Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine Learning IEEE Access Railway noise machine learning noise quantification environmental factors random forests XGBoost |
| title | Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine Learning |
| title_full | Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine Learning |
| title_fullStr | Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine Learning |
| title_full_unstemmed | Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine Learning |
| title_short | Automated Prognostics and Diagnostics of Railway Tram Noises Using Machine Learning |
| title_sort | automated prognostics and diagnostics of railway tram noises using machine learning |
| topic | Railway noise machine learning noise quantification environmental factors random forests XGBoost |
| url | https://ieeexplore.ieee.org/document/10778546/ |
| work_keys_str_mv | AT junhuihuang automatedprognosticsanddiagnosticsofrailwaytramnoisesusingmachinelearning AT haoliu automatedprognosticsanddiagnosticsofrailwaytramnoisesusingmachinelearning AT wenyanxi automatedprognosticsanddiagnosticsofrailwaytramnoisesusingmachinelearning AT sakdiratkaewunruen automatedprognosticsanddiagnosticsofrailwaytramnoisesusingmachinelearning |