Rail Vehicle Speed Determination Using Wheel Vibration and Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the speed of rail-based vehicles, such as Doppler RADAR, GPS, and optical systems, face challenges like slip effects, high costs, interference issues, and limitations in underground environments, making them inefficient for precise speed measurement.
Innovation Solution
A device using wireless sensors to collect vibration data from wheels, which is then processed by a machine learning method, specifically a convolutional neural network, to determine ground speed, enabling accurate speed measurement even in tunnels and underground areas by leveraging known route features and GPS positions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Doppler RADAR is used to measure speed, then speed measurement capability is improved, but device complexity and cost increase due to technically challenging transmission and receiving mechanics combined with real-time capable microprocessor technology
Solution Approach 1:
The patent replaces complex mechanical radar transmission and receiving systems with a simplified accelerometer-based measurement system. Instead of using Doppler RADAR with technically challenging transmission and receiving mechanics, the invention uses accelerometers to measure wheel acceleration, combined with wheel rotation data, to calculate speed through integration and mathematical processing.
2Measurement precision
If GPS satellite navigation is used to determine position and speed, then measurement precision is improved, but reliability deteriorates in underground environments where satellite signals cannot be received
Solution Approach 1:
The patent implements a dynamic measurement system that adapts to different operating environments. The system uses accelerometers and wheel rotation sensors that function reliably both above ground and underground, providing continuous speed measurement capability regardless of GPS signal availability. The system dynamically processes acceleration data and wheel rotation data to maintain accurate speed determination in all environments.
3Measurement precision
If optical systems are used to detect surface changes for speed determination, then speed measurement capability is improved, but maintenance requirements increase due to device soiling and illumination requirements
Solution Approach 1:
The patent replaces optical systems that require illumination and are susceptible to soiling with accelerometer-based mechanical sensing. The accelerometer system measures wheel acceleration through mechanical means, eliminating the need for optical components, illumination sources, and associated maintenance requirements while maintaining speed measurement capability.
4Ease of manufacture
If wheel rotation evaluation is used to measure speed, then cost is reduced compared to radar systems, but measurement precision deteriorates due to slip effects
Solution Approach 1:
The patent combines wheel rotation evaluation with accelerometer-based acceleration measurement to compensate for the limitations of each individual method. By merging these two measurement approaches and processing them together through integration and mathematical calculations, the system achieves accurate speed determination that overcomes the slip effects inherent in pure wheel rotation evaluation while maintaining cost-effectiveness.
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
This solution provides a precise and cost-effective method for determining ground speed and wheel/rail position, capable of functioning without GPS signals, and continuously adapts to changes due to wear, ensuring accurate speed measurement and rail monitoring across various environments.
Implementation Method 1
an interface for collecting one-dimensional or multi-dimensional vibration data as acceleration of the rail-based vehicle, the vibrations being detectable using at least one wireless sensor, which is arranged in the region of the at least one wheel
Data Source
AI summary
A device (9) for determining a speed of a rail-based vehicle with wheels on a predetermined network of routes includes an interface (8) for collecting one-dimensional or multi-dimensional vibration data (5) corresponding to vibrations of at least one wheel acting on the rail-based vehicle as an acceleration of the rail-based vehicle. The vibrations are detectable using at least one wireless sensor (2a, 2b, 2c, 2d) arranged proximate the at least one wheel. A learning module is configured to apply a trained machine-learned model to the vibration data to determine a ground speed. The trained machine-learned model is trained based on a distance traveled and a ground truth speed (17) and a corresponding portion of the vibration data (5).