Vehicle Component Life Prediction Using Operating Parameter Fit
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting the life expectancy of vehicle components are complex and require extensive real-time data, making them economically inefficient, especially in public transport where limited spare parts and resources are available.
Innovation Solution
A method using a processing unit to analyze status data and operating parameters from similar vehicles to determine a predictive function for the life expectancy of a specific component, allowing for efficient prediction and optimization of spare parts inventory.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If automatic prediction based on machine learning is used, then prediction accuracy is improved, but system complexity and data requirements increase significantly
Solution Approach 1:
The patent uses simple, easily obtainable data (status data and operating parameters that are already collected during regular vehicle operation) instead of complex machine learning models. This approach provides sufficient prediction accuracy without requiring extensive computational resources or complex systems, effectively using 'cheap' data that is already available rather than investing in expensive complex prediction systems
Solution Approach 2:
The patent extracts only the essential elements needed for prediction (status data and operating parameters) from the vehicle operation data, rather than using comprehensive machine learning models that require extensive data processing. This extraction of key parameters simplifies the system while maintaining prediction capability
2Reliability
If extensive real-time data collection is implemented, then prediction reliability is improved, but economic efficiency decreases due to higher costs
Solution Approach 1:
The patent uses data (status data and operating parameters) that the vehicle system already collects and provides during normal operation for its own monitoring purposes. This self-service approach means no additional sensors, data collection infrastructure, or processing resources are needed, maintaining prediction reliability while avoiding additional economic costs
Solution Approach 2:
The patent makes use of existing vehicle data that serves multiple functions - both for regular vehicle operation/monitoring and for life expectancy prediction. This multi-functional use of the same data infrastructure achieves reliable predictions without requiring separate dedicated data collection systems, thereby improving economic efficiency
3Reliability
If more spare parts are stored, then component availability is improved, but storage space and costs increase
Solution Approach 1:
The patent performs life expectancy prediction in advance using status data and operating parameters, allowing the workshop to plan spare parts inventory beforehand. This preliminary prediction enables storing only the specific spare parts that will be needed in the foreseeable future, rather than maintaining large inventories of all possible parts, thus optimizing storage space while ensuring component availability
Solution Approach 2:
The patent uses predicted life expectancy results as feedback to optimize spare parts inventory decisions. The prediction system continuously monitors component status and provides feedback on when parts will need replacement, allowing the workshop to dynamically adjust spare parts storage to match actual needs, reducing unnecessary storage while maintaining availability
Data Source
AI summary
The life expectancy of a component of a vehicle that is being observed is predicted. A processing unit is fed with status data of components of selected vehicles. Moreover, the processing unit is fed with an operating parameter for each of the components of the selected vehicles. The operating parameter influences the status data of the respective component. The processing unit determines a function between the operating parameter and the status data for each of the selected components. One function, which fits best for the component of the observed vehicle, is selected by an algorithm. The processing unit is fed with an operating parameter of the component of the observed vehicle. The processing unit predicts the life expectancy of the component of the observed vehicle using the selected function and the operating parameter of the component of the observed vehicle.