Machine Learning Based Design of Railway Prestressed Concrete Sleepers
The state-of-the-art design methods for railway prestressed concrete sleepers are currently based on the quasi-static stresses resulting from a simplification of dynamic wheel loads, and subsequently the quasi-static responses of concrete sleepers. This method has been widely used in practices to ov...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/20/10311 |
| _version_ | 1797475604045496320 |
|---|---|
| author | Sakdirat Kaewunruen Jessada Sresakoolchai Junhui Huang Yingyu Zhu Chayut Ngamkhanong Alex M. Remennikov |
| author_facet | Sakdirat Kaewunruen Jessada Sresakoolchai Junhui Huang Yingyu Zhu Chayut Ngamkhanong Alex M. Remennikov |
| author_sort | Sakdirat Kaewunruen |
| collection | DOAJ |
| description | The state-of-the-art design methods for railway prestressed concrete sleepers are currently based on the quasi-static stresses resulting from a simplification of dynamic wheel loads, and subsequently the quasi-static responses of concrete sleepers. This method has been widely used in practices to overcome the complexity of dynamic analysis and testing. A single load factor (or called dynamic impact factor) for a partial safety-factored design (or k factors for the test criteria) is commonly used to crudely account for dynamic train–track interactions over different levels of track irregularities. The dynamic impact factors for either design or testing are usually obtained from either (i) railway infrastructure managers (i.e., in EN 13230), or (ii) prescribed standardised factors (i.e., AS 1085.14, AREMA Chapter 30, JSA—JIS E 1201). The existing design concepts for prestressed concrete sleepers using either (i) an allowable stress design or (ii) the limit state design method require many iterations for calculations and optimisations. The design process to achieve optimal products suitable for track, operational, and environmental parameters is, thus, very time-consuming. On this ground, this study investigates the potential capability of machine learning (ML) to learn from large amounts of design data sets and then to facilitate the design and capacity prediction of railway prestressed concrete sleepers. Three ML algorithms are developed, namely deep learning, Bayesian Neural Network, and random forest. Through a combination of hand-calculated design data, industry design data, and experimental investigations in compliance with EN 13230, over 3000 sets of design data have been collected. These data sets are used to assimilate a comprehensive database for machine learning. Four indicators, namely mean squared error (MSE), root-mean-square error (RMSE), mean absolute error (MAE), and R<sup>2</sup> are used to benchmark the accuracy and precision of machine learning models. Our results reveal that the random forest algorithm offers the best performance. The values of MSE, RMSE, MAE, and R<sup>2</sup> are 0.54, 0.74, 0.25, and 0.99, respectively. Note that the Bayesian neural network also performs very well. In contrast, the deep learning algorithm performs worse than the others. The insight demonstrates machine learning’s capability to aid in the design of railway prestressed concrete sleepers, to satisfy both serviceability and ultimate limit states |
| first_indexed | 2024-03-09T20:47:30Z |
| format | Article |
| id | doaj.art-4407adc3adef464daae9cbf89961579e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:47:30Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4407adc3adef464daae9cbf89961579e2023-11-23T22:42:33ZengMDPI AGApplied Sciences2076-34172022-10-0112201031110.3390/app122010311Machine Learning Based Design of Railway Prestressed Concrete SleepersSakdirat Kaewunruen0Jessada Sresakoolchai1Junhui Huang2Yingyu Zhu3Chayut Ngamkhanong4Alex M. Remennikov5Department of Civil Engineering, University of Birmingham, Birmingham B15 2TT, UKDepartment of Civil Engineering, University of Birmingham, Birmingham B15 2TT, UKDepartment of Civil Engineering, University of Birmingham, Birmingham B15 2TT, UKDepartment of Civil Engineering, University of Birmingham, Birmingham B15 2TT, UKDepartment of Civil Engineering, Chulalongkorn University, Phayathai Road, Pathumwan, Bangkok 10330, ThailandSchool of Civil, Mining, and Environmental Engineering, University of Wollongong, Wollongong, NSW 2522, AustraliaThe state-of-the-art design methods for railway prestressed concrete sleepers are currently based on the quasi-static stresses resulting from a simplification of dynamic wheel loads, and subsequently the quasi-static responses of concrete sleepers. This method has been widely used in practices to overcome the complexity of dynamic analysis and testing. A single load factor (or called dynamic impact factor) for a partial safety-factored design (or k factors for the test criteria) is commonly used to crudely account for dynamic train–track interactions over different levels of track irregularities. The dynamic impact factors for either design or testing are usually obtained from either (i) railway infrastructure managers (i.e., in EN 13230), or (ii) prescribed standardised factors (i.e., AS 1085.14, AREMA Chapter 30, JSA—JIS E 1201). The existing design concepts for prestressed concrete sleepers using either (i) an allowable stress design or (ii) the limit state design method require many iterations for calculations and optimisations. The design process to achieve optimal products suitable for track, operational, and environmental parameters is, thus, very time-consuming. On this ground, this study investigates the potential capability of machine learning (ML) to learn from large amounts of design data sets and then to facilitate the design and capacity prediction of railway prestressed concrete sleepers. Three ML algorithms are developed, namely deep learning, Bayesian Neural Network, and random forest. Through a combination of hand-calculated design data, industry design data, and experimental investigations in compliance with EN 13230, over 3000 sets of design data have been collected. These data sets are used to assimilate a comprehensive database for machine learning. Four indicators, namely mean squared error (MSE), root-mean-square error (RMSE), mean absolute error (MAE), and R<sup>2</sup> are used to benchmark the accuracy and precision of machine learning models. Our results reveal that the random forest algorithm offers the best performance. The values of MSE, RMSE, MAE, and R<sup>2</sup> are 0.54, 0.74, 0.25, and 0.99, respectively. Note that the Bayesian neural network also performs very well. In contrast, the deep learning algorithm performs worse than the others. The insight demonstrates machine learning’s capability to aid in the design of railway prestressed concrete sleepers, to satisfy both serviceability and ultimate limit stateshttps://www.mdpi.com/2076-3417/12/20/10311machine learningrailway constructiondesignprestressed concrete sleepers |
| spellingShingle | Sakdirat Kaewunruen Jessada Sresakoolchai Junhui Huang Yingyu Zhu Chayut Ngamkhanong Alex M. Remennikov Machine Learning Based Design of Railway Prestressed Concrete Sleepers Applied Sciences machine learning railway construction design prestressed concrete sleepers |
| title | Machine Learning Based Design of Railway Prestressed Concrete Sleepers |
| title_full | Machine Learning Based Design of Railway Prestressed Concrete Sleepers |
| title_fullStr | Machine Learning Based Design of Railway Prestressed Concrete Sleepers |
| title_full_unstemmed | Machine Learning Based Design of Railway Prestressed Concrete Sleepers |
| title_short | Machine Learning Based Design of Railway Prestressed Concrete Sleepers |
| title_sort | machine learning based design of railway prestressed concrete sleepers |
| topic | machine learning railway construction design prestressed concrete sleepers |
| url | https://www.mdpi.com/2076-3417/12/20/10311 |
| work_keys_str_mv | AT sakdiratkaewunruen machinelearningbaseddesignofrailwayprestressedconcretesleepers AT jessadasresakoolchai machinelearningbaseddesignofrailwayprestressedconcretesleepers AT junhuihuang machinelearningbaseddesignofrailwayprestressedconcretesleepers AT yingyuzhu machinelearningbaseddesignofrailwayprestressedconcretesleepers AT chayutngamkhanong machinelearningbaseddesignofrailwayprestressedconcretesleepers AT alexmremennikov machinelearningbaseddesignofrailwayprestressedconcretesleepers |