Bridge modal identification using acceleration measurements within moving vehicles

Eshkevari, Soheil Sadeghi; Matarazzo, Thomas J.; Pakzad, Shamim N.

doi:10.1016/j.ymssp.2020.106733

Cited by 65 publications

(26 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the rail track vibration signal data collected by the mobile sensor networks is spatio-temporal, and is subjected to vehicle interference noise. Recent researches [42,43] proposed some methods where sparse vibration data based on mobile sensor networks were used to successfully achieve feature identification of bridge structures. Therefore, future work can be focused on investigating a more robust extraction method of the high-dimensional feature information of wheel-rail dynamic system around the method of VBoW model and sparse representation using vehicle mobile sensor networks.…”

Section: Discussionmentioning

confidence: 99%

Vibration-based and computer vision-aided nondestructive health condition evaluation of rail track structures

Wang

Zheng

Tang

et al. 2022

J Civil Struct Health Monit

View full text Add to dashboard Cite

In railway engineering, monitoring the health condition of rail track structures is crucial to prevent abnormal vibration issues of the wheel–rail system. To address the problem of low efficiency of traditional nondestructive testing methods, this work investigates the feasibility of the computer vision-aided health condition monitoring approach for track structures based on vibration signals. The proposed method eliminates the tedious and complicated data pre-processing including signal mapping and noise reduction, which can achieve robust signal description using numerous redundant features. First, the method converts the raw wheel–rail vibration signals directly into two-dimensional grayscale images, followed by image feature extraction using the FAST-Unoriented-SIFT algorithm. Subsequently, Visual Bag-of-Words (VBoW) model is established based on the image features, where the optimal parameter selection analysis is implemented based on fourfold cross-validation by considering both recognition accuracy and stability. Finally, the Euclidean distance between word frequency vectors of testing set and the codebook vectors of training set is compared to recognize the health condition of track structures. For the three health conditions of track structures analyzed in this paper, the overall recognition rate could reach 96.7%. The results demonstrate that the proposed method performs higher recognition accuracy and lower bias with strong time-varying and random vibration signals, which has promising application prospect in early-stage structural defect detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Vibration-based and computer vision-aided nondestructive health condition evaluation of rail track structures

Wang

Zheng

Tang

et al. 2022

J Civil Struct Health Monit

View full text Add to dashboard Cite

show abstract

“…The idea of using indirect methods, known as such because the vibrations on the bridge are never measured directly, was first proposed in [ 13 ] and several studies have been published on this topic since. The focus of the early studies was the identification of highway bridge frequencies using the accelerations obtained from the quarter- or half-car models in numerical simulations [ 14 , 15 , 16 , 17 , 18 , 19 ]. Several other studies then aimed to determine the mode shapes of bridges [ 20 , 21 , 22 , 23 , 24 , 25 , 26 ], to identify and remove the adverse effects of surface roughness [ 27 , 28 , 29 , 30 , 31 ], or to identify the presence of damage [ 32 , 33 , 34 , 35 , 36 ].…”

Section: Introductionmentioning

confidence: 99%

Identification of Vibration Frequencies of Railway Bridges from Train-Mounted Sensors Using Wavelet Transformation

Erduran

Pettersen

Gönen

et al. 2023

Sensors

View full text Add to dashboard Cite

This article presents a novel methodology to extract the bridge frequencies from the vibrations recorded on train-mounted sensors. Continuous wavelet transform is used to distinguish the bridge frequencies from the other peaks that are visible in the Fourier amplitude spectrum of the accelerations recorded on train bogies. The efficacy of the proposed method is demonstrated through numerical case studies. For this, a detailed three-dimensional finite element model that can capture the vibration characteristics of the bridge, track, and train is created, and each component of the model is separately validated. The train model used is a three-dimensional multi-degree-of-freedom system that can simulate the pitching and rolling behavior. The train was then virtually driven over the bridge at different speeds and under varying track irregularities to evaluate the robustness of the proposed method in extracting bridge frequencies from train-mounted sensors under different conditions. The proposed methodology is shown to be capable of identifying bridge modal frequencies even for aggressive track irregularity profiles and relatively high speeds of trains.

show abstract

“…A prevailing issue in extracting high level information from mobile sensors in a realistic scenario is the noise from collecting the response inside a moving vehicle; the road conditions, vehicle suspension system, and vehicle speed play critical roles in the signal quality [9]. Recent studies have shown that by solving an inverse problem -deconvolving the measured cabin accelerations to recover the tire-level input -the detrimental suspension effects could be mitigated [10,11]. To incorporate error in modeling and measurements, [12] proposed a Gaussian process latent force model that successfully estimated the road input for a linear, damped, two degrees of freedom (DOF) quarter car suspension model.…”

Section: Introductionmentioning

confidence: 99%

“…However, all these models require complete knowledge about the system which is less practical for real-world applications. To address this, [10] also proposed a data-driven method based on blind source separation (BSS) techniques. While avoiding the modeling complications, this method has alternate limitations from the BSS assumptions pertaining to the system linearity and signal's frequency distribution.…”

Section: Introductionmentioning

confidence: 99%

Transfer Learning for Input Estimation of Vehicle Systems

Cronin

Eshkevari

Sen

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

This study proposes a learning-based method with domain adaptability for input estimation of vehicle suspension systems. In a crowdsensing setting for bridge health monitoring, vehicles carry sensors to collect samples of the bridge's dynamic response. The primary challenge is in preprocessing; signals are highly contaminated from road profile roughness and vehicle suspension dynamics. Additionally, signals are collected from a diverse set of vehicles vitiating model-based approaches. In our data-driven approach, two autoencoders for the cabin signal and the tire-level signal are constrained to force the separation of the tire-level input from the suspension system in the latent state representation. From the extracted features, we estimate the tire-level signal and determine the vehicle class with high accuracy (98% classification accuracy). Compared to existing solutions for the vehicle suspension deconvolution problem, we show that the proposed methodology is robust to vehicle dynamic variations and suspension system nonlinearity.

show abstract

Bridge modal identification using acceleration measurements within moving vehicles

Cited by 65 publications

References 55 publications

Vibration-based and computer vision-aided nondestructive health condition evaluation of rail track structures

Vibration-based and computer vision-aided nondestructive health condition evaluation of rail track structures

Identification of Vibration Frequencies of Railway Bridges from Train-Mounted Sensors Using Wavelet Transformation

Transfer Learning for Input Estimation of Vehicle Systems

Contact Info

Product

Resources

About