Rail Track Defect Detection Using Derivative Wavelet Transform

2012 ◽  
Author(s):  
Shahyar Taheri ◽  
Saied Taheri
Keyword(s):  
Wavelet Transform ◽  
Defect Detection ◽  
Vertical Acceleration ◽  
High Frequencies ◽  
Acceleration Signal ◽  
Detection Systems ◽  
Limit Value ◽  
Accelerometer Signal ◽  
Acceleration Data ◽  
Track Monitoring

Railroad track monitoring systems are used for finding rail defects that may lead to a derailment of the train. The classical limit-value based defect detection systems are simple but are limited in their capability to detect small defects. As a cutting-edge supervision method, signal derivative filters can help to reveal information in the acceleration signal collected while the train is moving on the rail. The derivative filters are designed based on the required performance of the application. However, their design should be done with caution because they can greatly amplify the noise in the data, especially in high frequencies. Derivative filters can be implemented in the sample domain of space or time. The derivative filters in time domain are not always sufficient to study all the features of a signal. To explore the signal content, wavelet transformation was chosen, because it gives accurate description of the frequency contents according to their position in time. It should be noted that the wavelet transform that gives the derivative of a signal, has the properties of smoothing and differentiation. The proposed algorithm processes the data using continuous and discrete derivative wavelets filters, and is able to locate defects and provide information that may help to distinguish between various types of rail and wheel defects, including rail cracks, squats, corrugation, and wheel out-of-rounds. The wavelet-based algorithm developed was applied to a sample accelerometer signal and the results show the potential of this algorithm to locate and diagnose defects from limited bogie vertical acceleration data.

Broken Rail Prediction and Detection Using Wavelets and Artificial Neural Networks

2011 ◽  
Author(s):  
Brad M. Hopkins ◽  
Saied Taheri
Keyword(s):  
Neural Networks ◽  
Defect Detection ◽  
Classification Algorithm ◽  
Vertical Acceleration ◽  
Acceleration Signal ◽  
Acceleration Data ◽  
Frequency Domains ◽  
Artificial Neural ◽  
The Fourier Transform ◽  
Signal Processing Methods

Current track health monitoring requires time consuming use of railway monitoring vehicles. This paper presents a rail defect detection and classification algorithm that could potentially be used with bogie side frame vertical acceleration data from a data acquisition system located onboard a train car during daily operation. The algorithm uses wavelets to process the vertical acceleration data and detect irregularities in the signal. Wavelets have proven themselves to be useful in event detection and other applications where localization is needed in both the time and frequency domains. Traditional signal processing methods may use the Fourier transform which is limited to localization only in the frequency domain. Wavelets provide a solution for recognizing rail defects and determining their location. The wavelet-processed data is fed into an artificial neural network for defect classification. Neural networks can be a powerful tool in pattern recognition and classification because of their ability to be taught. The network in this algorithm has been trained to recognize impending breaks and breaks in a rail from the original vertical acceleration signal and the first four scales of the wavelet transformed signal. This paper presents an offline analysis of a set of collected data using the proposed defect detection and classification algorithm.

Prediction of Railroad Track Foundation Defects Using Wavelets

2013 ◽  
Author(s):  
Kuya Takami ◽  
Saied Taheri ◽  
Mehdi Taheri ◽  
Tomonari Furukawa
Keyword(s):  
Dynamic Simulation ◽  
Defect Detection ◽  
Detection Algorithm ◽  
Monitoring Systems ◽  
Railroad Track ◽  
Novel Technique ◽  
Accelerometer Signal ◽  
Further Development ◽  
Track Monitoring

This paper presents a novel technique that utilizes wavelet analysis to identify and predict the defects in railroad foundations and rails to prevent derailment or other damages. The proposed defect detection algorithm eliminates the use of wheel and/or track monitoring systems, which are expensive and time inefficient. The algorithm has been validated for the rail crack prediction using only vertical accelerometer signal which accurately detects impending rail breakage while distinguishing the signal generated by special track components such as rail joins and switches. Since the algorithm is flexible, further development can be tailored to detect significantly different rail defects such as track shift and other rail foundation defects. The algorithm is further improved by incorporating SIMPACK dynamic simulation to assist classification of the acceleration signatures. The actual data was then compared to simulation in order to validate the effectiveness of the algorithm.

Classification of Acceleration Waveforms during Walking by Wavelet Transform

1997 ◽  
Vol 36 (04/05) ◽  
pp. 356-359 ◽  
Author(s):  
M. Sekine ◽  
M. Ogawa ◽  
T. Togawa ◽  
Y. Fukui ◽  
T. Tamura
Keyword(s):  
Wavelet Transform ◽  
Wavelet Analysis ◽  
Center Of Gravity ◽  
Dynamic Responses ◽  
Sequential Data ◽  
Acceleration Signal ◽  
Continuous Dynamic

Abstract:In this study we have attempted to classify the acceleration signal, while walking both at horizontal level, and upstairs and downstairs, using wavelet analysis. The acceleration signal close to the body’s center of gravity was measured while the subjects walked in a corridor and up and down a stairway. The data for four steps were analyzed and the Daubecies 3 wavelet transform was applied to the sequential data. The variables to be discriminated were the waveforms related to levels -4 and -5. The sum of the square values at each step was compared at levels -4 and -5. Downstairs walking could be discriminated from other types of walking, showing the largest value for level -5. Walking at horizontal level was compared with upstairs walking for level -4. It was possible to discriminate the continuous dynamic responses to walking by the wavelet transform.

scholarly journals Defect Detection in Fabric using Wavelet Transform and Genetic Algorithm

2015 ◽  
Vol 3 (6) ◽  
Author(s):  
Depavath Harinath ◽  
K. Ramesh Babu ◽  
P. Satyanarayana ◽  
M.V. Ramana Murthy
Keyword(s):  
Genetic Algorithm ◽  
Wavelet Transform ◽  
Defect Detection

APPLICATION OF WAVELET TRANSFORM TO DEFECT DETECTION OF BUILDING’S STRUCTURE

Mechanika ◽  
2013 ◽  
Vol 18 (6) ◽  
Author(s):  
V. Volkovas ◽  
M. Eidukevičiūte ◽  
H. S. Nogay ◽  
T. C. Akinci
Keyword(s):  
Wavelet Transform ◽  
Defect Detection

scholarly journals A Determination Method for Gait Event Based on Acceleration Sensors

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5499 ◽  
Author(s):  
Chang Mei ◽  
Farong Gao ◽  
Ying Li
Keyword(s):  
Motion Capture ◽  
Inertial Sensors ◽  
Gait Recognition ◽  
Three Dimensional ◽  
High Standard ◽  
Vertical Displacement ◽  
Human Gait ◽  
Vertical Acceleration ◽  
Acceleration Signal ◽  
Acceleration Sensors

A gait event is a crucial step towards the effective assessment and rehabilitation of motor dysfunctions. However, for the data acquisition of a three-dimensional motion capture (3D Mo-Cap) system, the high cost of setups, such as the high standard laboratory environment, limits widespread clinical application. Inertial sensors are increasingly being used to recognize and classify physical activities in a variety of applications. Inertial sensors are now sufficiently small in size and light in weight to be part of a body sensor network for the collection of human gait data. The acceleration signal has found important applications in human gait recognition. In this paper, using the experimental data from the heel and toe, first the wavelet method was used to remove noise from the acceleration signal, then, based on the threshold of comprehensive change rate of the acceleration signal, the signal was primarily segmented. Subsequently, the vertical acceleration signals, from heel and toe, were integrated twice, to compute their respective vertical displacement. Four gait events were determined in the segmented signal, based on the characteristics of the vertical displacement of heel and toe. The results indicated that the gait events were consistent with the synchronous record of the motion capture system. The method has achieved gait event subdivision, while it has also ensured the accuracy of the defined gait events. The work acts as a valuable reference, to further study gait recognition.

scholarly journals Deep Active Learning for Surface Defect Detection

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1650 ◽  
Author(s):  
Xiaoming Lv ◽  
Fajie Duan ◽  
Jia-Jia Jiang ◽  
Xiao Fu ◽  
Lin Gan
Keyword(s):  
Active Learning ◽  
Object Detection ◽  
Defect Detection ◽  
Surface Defect ◽  
Candidate List ◽  
Detection Model ◽  
Detection Systems ◽  
Learning Framework ◽  
Surface Defect Detection ◽  
Sampling Scale

Most of the current object detection approaches deliver competitive results with an assumption that a large number of labeled data are generally available and can be fed into a deep network at once. However, due to expensive labeling efforts, it is difficult to deploy the object detection systems into more complex and challenging real-world environments, especially for defect detection in real industries. In order to reduce the labeling efforts, this study proposes an active learning framework for defect detection. First, an Uncertainty Sampling is proposed to produce the candidate list for annotation. Uncertain images can provide more informative knowledge for the learning process. Then, an Average Margin method is designed to set the sampling scale for each defect category. In addition, an iterative pattern of training and selection is adopted to train an effective detection model. Extensive experiments demonstrate that the proposed method can render the required performance with fewer labeled data.

Sign in / Sign up

Export Citation Format

Share Document