Railway Device Failure Prediction Using Temporal Behavior Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current diagnostic systems for railway systems lack the ability to predict malfunctions in safety-related devices effectively, leading to inefficient maintenance and potential downtime.
Innovation Solution
A computer-implemented method that records and stores the technical statuses of railway system devices at intervals, using similar devices' temporal behaviors to estimate when a malfunction will occur, allowing for predictive maintenance and reducing downtime by defining a reference behavior based on identical or similar devices' historical data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If diagnostic systems only detect faults after they occur, then the system complexity remains low, but the reliability and productivity of the railway system deteriorate due to unexpected failures and downtime
Solution Approach 1:
The system performs preliminary actions by recording technical statuses at time intervals and storing them as temporal behaviors before malfunctions occur. By analyzing trends in historical data from similar devices, the system predicts future failures and enables preventive maintenance, thereby improving reliability without requiring complex real-time intervention mechanisms.
Solution Approach 2:
The system uses temporal behavior data from similar or identical devices as reference models to predict malfunctions in the target device. By copying and comparing behavioral patterns across multiple devices, the system achieves accurate predictions while keeping individual device diagnostics relatively simple, resolving the contradiction between reliability improvement and system complexity.
2Productivity
If preventive maintenance is implemented based on malfunction prediction, then productivity improves by reducing downtime, but the measurement precision requirements increase to accurately predict failure times
Solution Approach 1:
The system merges data from multiple similar devices to create reference temporal behaviors. By combining historical data from several devices performing similar functions, the system achieves more robust and accurate predictions for individual devices, meeting the precision requirements for effective preventive maintenance while improving overall productivity through reduced downtime.
3Measurement precision
If detailed temporal behavior data is collected and stored for all devices, then the prediction accuracy improves, but the loss of information storage and processing increases
Solution Approach 1:
The system extracts only the essential temporal behavior characteristics from detailed device data, storing recorded technical statuses at time intervals rather than continuous data. This extraction approach maintains sufficient prediction accuracy while significantly reducing data storage and processing requirements, resolving the contradiction between precision and information loss.
Data Source
Figure 1~2
Figure 3
AI summary
The invention relates to a computer-implemented method for checking the technical function of an electrical and/or mechanical first device of a railway system, in particular a first device of a train or track infrastructure, wherein a technical state of the first device is recorded at time intervals, wherein the recorded technical states of the first device are stored as the first temporal behavior, wherein a technical state of a second device of the railway system is recorded at time intervals, wherein the recorded technical states of the second device are stored as the second temporal behavior, wherein the second device is similar or identical to the first device according to at least one technical parameter, wherein, in the event of a first malfunction of the first device, the first temporal behavior is determined as the temporal reference behavior.and wherein, based on the reference behavior and the second temporal behavior, a time point is estimated at which a malfunction will occur in the second device.