Rail Switch Health Detection via Discrete Wavelet Transform
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack effective, automated solutions for around-the-clock monitoring and early detection of rail switch degradations and failures, which are critical for maintaining a healthy and efficient railroad network.
Innovation Solution
A method involving the collection and analysis of rail switch measurement data using Discrete Wavelet Transform and k Nearest Neighbor algorithms to classify switch health, enabling the detection of degradations and failures, and triggering maintenance actions as necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated monitoring methods are implemented for rail switch detection, then detection reliability and early failure detection improve, but system complexity and implementation cost increase
Solution Approach 1:
The patent replaces manual inspection methods with automated electronic monitoring systems that use sensors, data acquisition devices, and computational algorithms to detect switch degradations and failures, thereby improving reliability while managing system complexity through automation
Solution Approach 2:
The patent introduces intermediate processing components including data acquisition units, feature extraction modules, and classification algorithms that mediate between raw sensor data and final detection decisions, enabling reliable detection while structuring system complexity into manageable functional layers
2Reliability
If continuous around-the-clock monitoring is implemented, then detection capability improves, but energy consumption and computational resources increase
Solution Approach 1:
The patent implements periodic monitoring cycles where measurement data is collected during switch moves and processed at intervals rather than continuously, enabling reliable detection capability while reducing energy consumption and computational resource requirements through time-based sampling strategies
Solution Approach 2:
The patent performs preliminary processing of measurement data during switch moves when data is naturally generated, preparing feature vectors and health assessments in advance before they are needed for classification, thereby reducing real-time computational demands and energy consumption
3Measurement precision
If detailed measurement data collection is performed, then measurement precision improves, but data processing time and computational load increase
Solution Approach 1:
The patent extracts only the most relevant features from collected measurement data using feature extraction techniques that identify key indicators of switch health, thereby maintaining measurement precision while significantly reducing data processing time and computational load by eliminating redundant information
Solution Approach 2:
The patent segments the data processing task into distinct stages including data collection, feature extraction, and health classification, allowing detailed measurement data to be processed systematically with each stage handling specific aspects, thereby improving measurement precision while managing processing time through structured computation
Data Source
AI summary
Method for detecting rail switches degradation and failures, the method having the steps of applying a Discrete Wavelet Transform to stored measurement data relative to a switch move to be analysed and obtaining a feature vector associated with said switch move and including Discrete Wavelet Transform coefficients delivered by the applied Discrete Wavelet Transform; comparing the obtained feature vector with feature vectors associated with rail switch moves previously obtained and associating each to a respective health class among several given health classes; and determining a health class for the said switch move to be analyzed by selecting one of the health classes associated with the previously obtained feature vectors based upon the comparison step.