Train Wheel Maintenance Prediction Using Dynamic Condition Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current maintenance planning for train wheels relies on either time-based or mileage-based methods, which can lead to inefficient inspections and maintenance, as they do not accurately account for the condition of the wheels, potentially resulting in over- or under-maintenance.
Innovation Solution
A computer-implemented method that predicts a maintenance point for train wheels by analyzing measurement data, including roundness error, surface roughness, vibration, and vertical load data, using dynamic coefficients and forecasting models to determine the optimal time or distance for maintenance, while adhering to external regulations and schedules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If time-based or mileage-based maintenance methods are used, then maintenance scheduling is simplified, but maintenance efficiency decreases due to over- or under-maintenance
Solution Approach 1:
The patent transitions from fixed time/mileage parameters to dynamic parameters based on actual wheel condition measurements. The system uses measured parameters (roundness error, surface roughness, vibration, vertical load) to dynamically determine maintenance timing, changing the maintenance criterion from static schedules to condition-based thresholds.
Solution Approach 2:
The maintenance system enables the train wheel to essentially monitor its own condition through sensors that detect wear and damage. The wheel's actual state drives the maintenance decision, rather than external schedules, allowing the system to self-determine when maintenance is truly needed based on measured degradation.
2Reliability
If condition-based monitoring with large safety margins is used, then safety is improved, but maintenance frequency increases leading to unnecessary inspections
Solution Approach 1:
The system performs preliminary measurements and predictions to forecast when maintenance will be needed. By predicting the maintenance point in advance based on current degradation trends, the system can plan maintenance at the optimal time rather than using conservative fixed intervals, preventing both premature and delayed maintenance.
Solution Approach 2:
The system continuously measures wheel condition parameters and uses this feedback to update predictions of when maintenance will be required. This closed-loop feedback allows dynamic adjustment of maintenance timing based on actual wear rates, optimizing the balance between safety and maintenance frequency.
3Productivity
If condition-based monitoring with large time intervals is used, then inspection costs are reduced, but maintenance may be delayed beyond necessity
Solution Approach 1:
The system performs preliminary measurements and predictions to forecast when maintenance will be needed. By predicting the maintenance point in advance based on current degradation trends, the system can plan maintenance at the optimal time rather than using conservative fixed intervals, preventing both premature and delayed maintenance.
Solution Approach 2:
The patent replaces traditional mechanical inspection methods with sensor-based measurement systems that continuously monitor wheel conditions. This substitution enables more precise and frequent condition assessment without the costs and disruptions of full mechanical inspections, improving both timing accuracy and cost efficiency.
4Reliability
If frequent maintenance is performed, then safety is ensured, but operational efficiency decreases due to unnecessary maintenance
Solution Approach 1:
The system performs preliminary measurements and predictions to forecast when maintenance will be needed. By predicting the maintenance point in advance based on current degradation trends, the system can plan maintenance at the optimal time rather than using conservative fixed intervals, preventing both premature and delayed maintenance.
Solution Approach 2:
The maintenance schedule transitions from static (fixed intervals) to dynamic (condition-based). The system continuously adapts the maintenance timing based on actual wheel condition measurements and predicted degradation rates, allowing the maintenance frequency to dynamically match the actual need rather than following rigid schedules.
Data Source
Figure 1A~1F
Figure 2A~3
Figure 4A~4H
AI summary
A computer-implemented method for maintenance planning for a train wheel, the method comprising: receiving (S1) measurement data of the train wheel; determining (S2), using the measurement data, whether the train wheel will need to undergo maintenance in the future; and predicting (S3), if the train wheel will need to undergo maintenance in the future, a maintenance point (M1), in particular a critical time point (T1) and/or a critical travel distance (D1) until maintenance.