Rail Support Deformation Signals for Rolling Stock Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting anomalies in rolling stock on railway rails are complex, difficult to model, and not robust, especially for trains with irregular load distributions, leading to false alarms and inefficient detection of abnormalities.
Innovation Solution
A computer-implemented method using discrete wavelet transform to decompose deformation sensor signals into approximation and detail signals, forming a residual signal to detect outliers, classify anomalies, and separate noise from transient phenomena, employing a Symlet 5 wavelet for optimal separation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If discrete wavelet transform with masking is used for square wheel detection, then detection capability is improved, but device complexity increases
Solution Approach 1:
The patent extracts and removes the masking step from the wavelet transform process. By taking out this complex component, the method simplifies the detection algorithm while maintaining reliability through the core wavelet decomposition and outlier detection in residual signals.
Solution Approach 2:
The patent segments the detection process into distinct phases: wavelet transform decomposition, residual signal formation, and outlier detection. This segmentation allows each component to be optimized independently, reducing overall complexity while maintaining detection effectiveness.
2Reliability
If acceleration measurement linked to rail-wheel contact force is used, then anomaly detection is enabled, but measurement precision deteriorates due to difficulty in modeling
Solution Approach 1:
The patent substitutes the complex mechanical contact force measurement model with a direct deformation measurement approach using fiber optic Bragg grating sensors. This replacement eliminates the need for complex rail-wheel contact force modeling while providing precise measurement of rail support deformation caused by rolling stock anomalies.
3Ease of operation
If statistical approach is used to search for outliers, then detection simplicity is improved, but reliability deteriorates for trains with irregular load distributions
Solution Approach 1:
The patent changes the detection parameters from simple statistical outliers to wavelet-based residual signal analysis. This parameter transformation enables the method to handle irregular load distributions effectively by capturing transient deformation characteristics that statistical methods miss, while maintaining computational simplicity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the robustness and accuracy of anomaly detection, distinguishing between different types of anomalies and reducing noise interference, thereby improving the reliability of rail support monitoring.
Implementation Method 1
Rail supports can also be instrumented, for example by integrating fiber optic Bragg grating sensors as described in patent FR 2 983 812 B1, to measure micro-deformations
Implementation Method 2
The invention uses a discrete wavelet transform to decompose the deformation signal into an approximation signal and a residual signal
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
The invention relates to a computer-implemented method for detecting anomalies in rolling stock on railway tracks resting on a rail support. This method comprises a decomposition (DECOMP) by discrete wavelet transform of a measurement signal (S) delivered by a rail support deformation sensor into an approximation signal (AJ) and a residual signal (RJ), and a search (RECH-PA) for outliers (PA) in the residual signal (RJ) to detect rolling stock anomalies.