Accelerated Failure Time Model for Component Life Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for predicting the remaining useful life of vehicle components rely heavily on sensor data, which can lead to inaccuracies in the absence of functional sensors, and do not effectively incorporate environmental and operational factors, resulting in unplanned maintenance and potential failures.
Innovation Solution
A computer-implemented method using an Accelerated Failure Time model to predict the remaining useful life of components by summarizing environmental and operational conditions experienced over a component's lifetime, allowing for maintenance scheduling without sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data is used to predict component failure, then prediction accuracy is improved, but the system becomes vulnerable to sensor failures and requires hardware installations on vehicles
Solution Approach 1:
The patent introduces environmental data and operational data as intermediary sources that indirectly reflect component stress conditions without requiring direct sensor contact with the component. These intermediary data sources provide alternative pathways to assess component health when traditional sensors fail or are unavailable.
Solution Approach 2:
The patent creates a virtual model of component degradation by copying and analyzing environmental and operational patterns that correlate with component stress. Instead of directly measuring component condition with sensors, the system replicates the degradation process through data correlation and modeling techniques.
2Ease of operation
If traditional reliability engineering methods based on operational hours are used, then maintenance scheduling is simplified, but prediction accuracy decreases due to lack of environmental and operational factor consideration
Solution Approach 1:
The patent transforms the traditional single-parameter (operational hours) approach into a multi-parameter model that incorporates environmental conditions (temperature, humidity, pollution) and operational factors (load, speed, usage patterns). This parameter expansion significantly improves prediction accuracy while maintaining systematic maintenance scheduling through the integrated model.
3Measurement precision
If machine learning methods using onboard sensors are deployed, then real-time prediction capability is improved, but device complexity and hardware requirements increase
Solution Approach 1:
The patent extracts the essential predictive information from complex sensor systems and consolidates it into a centralized modeling approach. By removing the requirement for multiple onboard sensors and concentrating the intelligence in a server-based or cloud-based model, the system reduces hardware complexity while preserving real-time prediction capabilities through alternative data sources.
Data Source
AI summary
Systems and methods are disclosed for predicting a remaining useful life of a component. One method comprises receiving, by a component prediction system, one or more component data sets associated with one or more components of a moving object. Based on the received one or more component data sets, environmental and operational conditions experienced over a lifetime of each failed component may be identified and summarized. Then, the effects of the environmental and operational conditions on a lifetime of a component of interest may be determined by training an accelerated failure time model using the summarized environmental and operational conditions. Using the trained accelerated failure time model, a remaining useful life of the component of interest may be determined.