Signal Filter Cut-Off Frequency Determination to Enhance the Accuracy of Rail Track Irregularity Detection and Localization

The records of maintenance activities are required for modeling the track irregularity deterioration process. However, it is hard to guarantee the completeness and accuracy of the maintenance records. To tackle this problem, an adaptive piecewise modeling framework for the rail track deterioration process driven by historical measurement data from the comprehensive inspection train (referred to as CIT) is proposed. The identification of when maintenance activities occurred is reformulated as a model selection optimization problem based on Bayesian Information Criterion. An efficient solution algorithm utilizing adaptive thresholding and dynamic programming is proposed for solving this optimization problem. This framework’s validity and practicability are illustrated by the measurement data from the CIT inspection of the mileage section of K21 + 184 to K220 + 308 on the Nanchang-Fuzhou railway track from 2014 to 2019. The results indicate that this framework can overcome the disturbance of contaminated measurement data and accurately estimate when maintenance activities were undertaken without any historical maintenance records. What is more, the adaptive piecewise fitting model provided by this framework can describe the irregular deterioration process of corresponding rail track sections.

Download Full-text

Rail Track Irregularity Detection Method Based on Computer Vision and Gesture Analysis

International Journal of Online Engineering (iJOE) ◽

10.3991/ijoe.v12i12.6444 ◽

2016 ◽

Vol 12 (12) ◽

pp. 55

Author(s):

Jian Rong ◽

Shiyang Song ◽

Zhen Dang ◽

Hongliang Shi ◽

Yong Cao

Keyword(s):

Computer Vision ◽

Kalman Filter ◽

Unscented Kalman Filter ◽

Detection System ◽

Vibration Signal ◽

Calculation Error ◽

Rail Track ◽

Sensor Device ◽

Gesture Analysis ◽

Track Irregularity

In this paper, rail track irregularity detection system based on computer vision and SVD analysis is proposed and located in the train's operator cabin near the front. Images are captured by FLEA3 camera of Point-Grey, and vibration signals are collected by sensor device MPU6050 integrating 3-axis accelerometer and 3-axis gyroscope. Root mean square of gray-scale threshold Pulse Coupled Neural Network (RMS-PCNN) is used for segmentation of the rail track's image in a single loop, and the improved coupled map lattice(CML) is used for filtering the image and signifying the rail track. After perspective, the track radius can be fetched by analysis of regression. Vibration signal filtered by SVD-unscented Kalman filter(UKF) can reflect the wagon movements. In unscented Kalman filter, Cholesky is replaced by SDV in UT(unscented transform), which can solve negative definite matrix caused by covariance matrix on account of calculation error and round-off error. Also numerical stability is improved under the guarantee of filtering accuracy and the same complexity level of algorithm based on SVD-UKF. Looking up the radius record table, the corresponding threshold in gyroscope signal can be selected, and Compared to the super elevation, the invisible irregularity defects of rail bed will be found out.

Download Full-text