Aircraft Maintenance Interval Planning with Multi-Model Failure Risk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aircraft maintenance schedules often require frequent maintenance intervals, leading to increased downtime and operational inefficiencies, as they typically address failure modes individually without considering the combined risk of multiple failure modes.
Innovation Solution
A computing system implements a multi-model approach using predictive models such as minor-evident, condition-based, and risk-equivalent models to determine maintenance intervals by analyzing sensor data from a population of aircraft, combining these models to accurately assess failure modes and optimize maintenance tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional maintenance schedules are used to address failure modes individually, then reliability is maintained, but productivity decreases due to frequent maintenance intervals and increased downtime
Solution Approach 1:
The patent combines multiple predictive models (minor-evident model, condition-based model, and risk-equivalent model) into an integrated system that simultaneously evaluates multiple failure modes. This merging allows the system to determine maintenance intervals based on the combined risk assessment of all failure modes rather than addressing them individually, thereby extending maintenance intervals while maintaining reliability coverage.
2Measurement precision
If multiple predictive models are implemented to accurately characterize failure modes, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent segments the complex prediction task by dividing it into three specialized predictive models, each focusing on a specific aspect: minor-evident model for early failure detection, condition-based model for real-time monitoring, and risk-equivalent model for overall risk assessment. This segmentation allows each model to be optimized for its specific function while the integrated system achieves comprehensive failure mode characterization, balancing precision with manageable complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An example method (300) performed by a computing system (100) for determining a maintenance interval (102) for a subject aircraft configuration (104) comprises obtaining sensor data (150) reported by an electronic system (144) of a population (140) of the subject aircraft configuration (104). The method (300) further comprises obtaining a failure mode definition (172) that identifies a set of failure modes (210) involving a component (221) of the subject aircraft configuration (104). The method (300) further comprises implementing a first predictive model (120, 122, 124) to determine a first lifetime-probability distribution (261) of a failure mode (211, 212, 213) involving the component (221) based on the sensor data (150). The method (300) further comprises implementing a second predictive model (120, 122, 124) that differs from the first predictive model (120, 122, 124) to determine a second lifetime-probability distribution (262) of a failure mode (211, 212, 213) involving the component (221) based on the sensor data (150). The method (300) further comprises determining a maintenance interval (102) for the component (221) based on the first lifetime-probability distribution (261) and the second lifetime-probability distribution (262).