Artificial intelligence-based approach to estimate relative deflection of railroad ties using airborne ultrasonic testing

Ali Zare Hosseinzadeh; Diptojit Datta; Francesco Lanza di Scalea

doi:10.1117/12.2617558

19 April 2022 Artificial intelligence-based approach to estimate relative deflection of railroad ties using airborne ultrasonic testing

Ali Zare Hosseinzadeh, Diptojit Datta, Francesco Lanza di Scalea

Author Affiliations +

Proceedings Volume 12048, Health Monitoring of Structural and Biological Systems XVI; 120480Y (2022) https://doi.org/10.1117/12.2617558
Event: SPIE Smart Structures + Nondestructive Evaluation, 2022, Long Beach, California, United States

Abstract

This paper introduces an enhanced ultrasonic sonar-based ranging technique developed by the Experimental Mechanics, NDE & SHM Laboratory at UC San Diego to estimate the deflections of railroad ties. The deflection profile of the ties can be subsequently inspected to evaluate their performance and prevent unwanted events, like train derailments. The proposed sensing layout is comprised of an array of air-coupled capacitive transducers to perform pulse-echo ultrasonic tests in multiple points along the tie, and a high frame-rate camera to capture images of the objects probed by the array. A machine learning-based image processing technique is developed to classify the tie/ballast images based on the texture signature of the visible objects in the camera’s field of view. Next, the relative deflection profile of the ties is reconstructed by tracking the Time of Flight (ToF) of the received waveforms at the points flagged as a tie. A series of field tests was carried out at the Rail Defect Testing Facility of UC San Diego as well as a BNSF yard in San Diego, CA, by mounting the sensing prototype on a car moving at walking speed. The obtained results confirm the potential of the proposed airborne ranging technique for in-motion measurement of the deflections of railroad ties.

Citation Download Citation

Ali Zare Hosseinzadeh, Diptojit Datta, and Francesco Lanza di Scalea "Artificial intelligence-based approach to estimate relative deflection of railroad ties using airborne ultrasonic testing", Proc. SPIE 12048, Health Monitoring of Structural and Biological Systems XVI, 120480Y (19 April 2022); https://doi.org/10.1117/12.2617558

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available