Railroad Vehicle Abnormality Detection Using Vibration Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormality detection methods for railroad cars are inadequate in distinguishing between car-side and track-side factors causing vibrations, often requiring multiple sensors and leading to erroneous detections and increased maintenance costs.
Innovation Solution
A system that uses a limited number of sensors to analyze vibration and operation data, employing mechanics models to estimate abnormality factors by filtering and comparing data features, thereby identifying car-side and track-side issues efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a dedicated sensor is used for each device where abnormality may occur, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses a single vibration detection device that serves multiple functions: detecting vibrations from both the truck assembly and track, and analyzing both car-side and track-side abnormality factors. This multi-functional approach eliminates the need for separate dedicated sensors for each detection target, reducing device complexity while maintaining comprehensive monitoring capability
Solution Approach 2:
The patent introduces vibration data as an intermediary that indirectly reflects the state of both the truck assembly and track. By detecting vibrations and analyzing their characteristics, the system can infer abnormality factors without direct contact or dedicated sensors for each component, achieving detection with minimal sensing equipment
2Reliability
If vibration data from both truck and wheel axle are filtered and compared, then abnormality detection capability is improved, but the ability to handle combined car-side and track-side abnormalities deteriorates
Solution Approach 1:
The patent segments the vibration analysis into distinct processing paths: one for detecting car-side abnormality factors (related to truck assembly) and another for detecting track-side abnormality factors. By separating the analysis of vibration characteristics into these segments, the system can independently evaluate each type of abnormality and determine their combination, thereby handling complex cases where both car-side and track-side issues coexist
Solution Approach 2:
The patent applies different filtering and processing actions to different vibration data based on their sources and characteristics. By applying partial processing actions tailored to specific vibration types rather than uniform processing, the system maintains sensitivity to various abnormality patterns including combined cases, enhancing both detection reliability and adaptability
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is an abnormality detection device for a railroad car capable of detecting and estimating a factor in not only a case where abnormal vibrations are occurring in the car due to a car-side factor or a track-side factor but also a case where abnormal vibrations are occurring in the car due to both the car-side factor and the track-side factor and further capable of estimating an abnormality factor with a small number of sensors and in a short period of time. A device capable of acquiring vibration data, and operation data such as a traveling position, traveling speed, and occupancy on the railroad car, analyzing the vibration data and operation data thus acquired to derive an abnormality factor element, and estimating or identifying an abnormality factor of vibrations of the railroad car based on the abnormality factor element is included.