The objectives of this project were (1) to improve the defect detection reliability and (2) to improve the inspection speed of conventional rail defect detection methods. The prototype developed in this work uses noncontact transducers, ultrasonic guided waves, and real-time statistical pattern recognition to improve system reliability. The prototype was field tested seven times with the support of the Federal Railroad Administration (FRA) R-4 hy-railer vehicle. The latest tests at Herzog, Inc., in June 2010 showed excellent results. Two blind tests resulted in a defect detection reliability exceeding industry average and American Railway Engineering and Maintenance-of-Way Association recommendations. These tests also proved the potential for distinguishing good welds from defective welds, an excellent detestability of the vertical split head defect, and the potential for characterizing different rail surface conditions for grinding management purposes. Within this project, a 250-foot-long rail defect farm was also constructed at the University of California--San Diego, with in-kind donations from BNSF Railway, for the development of this and other rail inspection technologies of interest to FRA and to the railroad industry.

The Federal Railroad Administration (FRA) Office of Research and Development's Track and Structures Program sponsored a study for developing and testing a rail defect detection system based on ultrasonic guided waves and non-contact probing. Current rail defect detection systems based on ultrasonic testing have limitations in terms of reliability of defect detection, inspection speed, and other drawbacks associated with the requirement for contact between the ultrasonic probes and the rail surface. More importantly, conventional ultrasonic testing of rails has serious difficulties detecting internal defects in the presence of surface shelling. The rail defect detection technique that is being funded is based on fundamentally new concepts in that 1) uses ultrasonic waves traveling along, rather than across the rail running direction, 2) uses non-contact means of generating and detecting the ultrasonic waves in the rail, and 3) uses advanced signal processing algorithms to de-noise the measurements and extract robust defect-sensitive information. A prototype is being assembled based on this technology and plans are in place to install and test the prototype in the FRA Research Car.

The Federal Railroad Administration (FRA) Office of Research and Development's Track and Structures Program sponsored a study for developing and testing a rail defect detection system based on ultrasonic guided waves and non-contact probing. Current rail defect detection systems based on ultrasonic testing have limitations in terms of reliability of defect detection, inspection speed, and other drawbacks associated with the requirement for contact between the ultrasonic probes and the rail surface. More importantly, conventional ultrasonic testing of rails has serious difficulties detecting internal defects in the presence of surface shelling. The rail defect detection technique that is being funded is based on fundamentally new concepts in that 1) uses ultrasonic waves traveling along, rather than across the rail running direction, 2) uses non-contact means of generating and detecting the ultrasonic waves in the rail, and 3) uses advanced signal processing algorithms to de-noise the measurements and extract robust defect-sensitive information. A prototype is being assembled based on this technology and plans are in place to install and test the prototype in the FRA Research Car.

This book focuses on the deep learning technologies and their applications in the catenary detection of high-speed railways. As the only source of power for high-speed trains, the catenary's service performance directly affects the safe operation of high-speed railways. This book systematically shows the latest research results of catenary detection in high-speed railways, especially the detection of catenary support component defect and fault. Some methods or algorithms have been adopted in practical engineering. These methods or algorithms provide important references and help the researcher, scholar, and engineer on pantograph and catenary technology in high-speed railways. Unlike traditional detection methods of catenary support component based on image processing, some advanced methods in the deep learning field, including convolutional neural network, reinforcement learning, generative adversarial network, etc., are adopted and improved in this book. The main contents include the overview of catenary detection of electrified railways, the introduction of some advance of deep learning theories, catenary support components and their characteristics in high-speed railways, the image reprocessing of catenary support components, the positioning of catenary support components, the detection of defect and fault, the detection based on 3D point cloud, etc.

The rapid expansion of transportation industries worldwide, including railways, and the never-ending desire to reduce travel time have highlighted the need to resort to advanced transit systems. Conventional railway systems have been modified to make them travel at much higher speeds. High-Speed Rail includes the main topics and basic principles of high-speed railways (HSRs). The book reflects new engineering and track developments, the most current design methods, as well as the latest industry standards and policies. It provides a comprehensive overview of the significant characteristics for HSRs; highlights recent advancements, requirements, and improvements; and details the latest techniques in the global market. High-Speed Rail contains a collection of the latest research developments on HSRs. This book comprehensively covers basic theory and practice in sufficient depth to provide a solid grounding for railway engineers. It also helps readers maximize effectiveness in all facets of HSRs. This professional book as a credible source and a valuable reference can be very applicable and useful for professors, researchers, engineers, practicing professionals, trainee practitioners, students, and others interested in HSRs.

Dynamics of Coupled Systems in High-Speed Railways: Theory and Practice presents the relationship between various coupled systems that can affect train operation, including interaction between track and train, the pantograph-catenary system and train, power supply system and train, and airflow and train, with respect to the structure and characteristics of high-speed railway. The overall simulation optimization and control are achieved based on an analysis of the dynamics generated by coupled systems in high-speed trains, with a theoretical framework for the dynamics presented in the book. Presents the first book available on the dynamics of coupled systems in high-speed trains Provides a systematic view of high-speed vehicle dynamics, covering the issues that are especially concerned for high speed operations, such as high-speed pantograph and catenary, aerodynamic characteristics and running stability of high-speed trains Covers the optimization of dynamic performance, the design of parameters, the simulation of high-speed train service processes, and the identification of high-speed train state and condition assessment