Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
AI-Based Ballasted Track GPR Application and Development
https://orcid.org/http://orcid.org/0000-0001-6843-6853
https://orcid.org/http://orcid.org/0009-0005-7758-2330
https://orcid.org/http://orcid.org/0000-0001-9655-2229
The use of ground-penetrating radar (GPR) technology in railway maintenance and inspection has gained significant attention in recent years due to its non-destructive and efficient nature. This paper explores the application and development of artificial intelligence (AI) in conjunction with GPR for the assessment of ballasted tracks. The integration of AI algorithms enhances the interpretation of GPR data, providing a more accurate and automated method for detecting and predicting potential trackbed fouling. This article explores the innovative applications of machine learning and deep learning in GPR data processing for railway track engineering prospection, evaluating their potential, limitations, and future prospects, aiming to contribute to the advancement of railway infrastructure monitoring, with a focus on improving reliability, safety, and maintenance efficiency.
AI-Based Ballasted Track GPR Application and Development
https://orcid.org/http://orcid.org/0000-0001-6843-6853
https://orcid.org/http://orcid.org/0009-0005-7758-2330
https://orcid.org/http://orcid.org/0000-0001-9655-2229
The use of ground-penetrating radar (GPR) technology in railway maintenance and inspection has gained significant attention in recent years due to its non-destructive and efficient nature. This paper explores the application and development of artificial intelligence (AI) in conjunction with GPR for the assessment of ballasted tracks. The integration of AI algorithms enhances the interpretation of GPR data, providing a more accurate and automated method for detecting and predicting potential trackbed fouling. This article explores the innovative applications of machine learning and deep learning in GPR data processing for railway track engineering prospection, evaluating their potential, limitations, and future prospects, aiming to contribute to the advancement of railway infrastructure monitoring, with a focus on improving reliability, safety, and maintenance efficiency.
AI-Based Ballasted Track GPR Application and Development
https://orcid.org/http://orcid.org/0000-0001-6843-6853
https://orcid.org/http://orcid.org/0009-0005-7758-2330
https://orcid.org/http://orcid.org/0000-0001-9655-2229
The use of ground-penetrating radar (GPR) technology in railway maintenance and inspection has gained significant attention in recent years due to its non-destructive and efficient nature. This paper explores the application and development of artificial intelligence (AI) in conjunction with GPR for the assessment of ballasted tracks. The integration of AI algorithms enhances the interpretation of GPR data, providing a more accurate and automated method for detecting and predicting potential trackbed fouling. This article explores the innovative applications of machine learning and deep learning in GPR data processing for railway track engineering prospection, evaluating their potential, limitations, and future prospects, aiming to contribute to the advancement of railway infrastructure monitoring, with a focus on improving reliability, safety, and maintenance efficiency.
AI-Based Ballasted Track GPR Application and Development
Indraratna, Buddhima (Herausgeber:in) / Rujikiatkamjorn, Cholachat (Herausgeber:in) / Qin, Xuanyang (Autor:in) / Peng, Zhan (Autor:in) / Jing, Guoqing (Autor:in)
Recent Advances and Innovative Developments in Transportation Geotechnics ; Kapitel: 4 ; 45-55
27.10.2024
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Understanding ballasted track behaviour
British Library Online Contents | 1996
Development of German non-ballasted track forms
| Online Contents | 2006
Frame sleepers for ballasted track - Status of development
| British Library Online Contents | 2000
Track Modulus: Ballasted and Direct Fixation Track
| TIBKAT | 2019