Aircraft Fault Graph Analysis for Prioritized Maintenance Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aircraft maintenance diagnostics face challenges due to innate ambiguity in fault models, leading to higher costs and longer downtime, as multiple maintenance tasks are required to identify and address potential root causes, often resulting in unnecessary checks and inconsistent performance.
Innovation Solution
A method using structural-temporal analysis of fault propagation graphs to diagnose failures on aircraft, which includes performing a failure mode effect analysis, constructing a fault propagation model, building a fault pattern library, and applying a greedy selection algorithm to identify the most likely root cause, while also considering contextual rules for refining maintenance actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple maintenance tasks are performed to test, isolate and remove failed components, then the reliability of fault identification is improved, but the loss of time and productivity deteriorate due to longer aircraft-on-ground downtime
Solution Approach 1:
The system performs preliminary analysis by constructing a fault propagation model and building a fault pattern library before actual maintenance is needed. When faults occur, the greedy selection algorithm quickly identifies the most likely root cause by matching observed fault patterns against the pre-built library, eliminating the need for multiple sequential maintenance tasks and reducing aircraft downtime while maintaining high identification accuracy
Solution Approach 2:
The patent replaces the traditional mechanical trial-and-error maintenance approach with an information-processing system that uses structural-temporal analysis and greedy selection algorithms to automatically diagnose faults. This substitution of mechanical testing with computational analysis dramatically reduces the time required for fault identification while maintaining or improving accuracy
2Reliability
If multiple potential root causes are identified, then the completeness of fault analysis is improved, but the device complexity and ease of operation worsen due to lack of specified examination order
Solution Approach 1:
The system dynamically generates a prioritized examination order based on the fault propagation model and observed fault patterns. The greedy selection algorithm adaptively determines the sequence in which potential root causes should be examined, considering factors such as probability of occurrence and temporal relationships. This dynamic ordering maintains complete fault analysis while significantly simplifying the maintenance procedure by providing clear guidance to technicians
Solution Approach 2:
The fault pattern library acts as an intermediary between the complex fault propagation model and the maintenance personnel. It pre-processes and organizes potential root causes into actionable patterns with recommended examination sequences, serving as a bridge that translates complex analytical results into simple, followable maintenance procedures
3Ease of manufacture
If traditional fault diagnosis methods are used, then the ease of manufacture is improved, but the loss of information deteriorates due to tribal knowledge being kept in the maintainer's head
Solution Approach 1:
The system captures and utilizes maintenance operational context automatically during the diagnostic process. As the greedy selection algorithm analyzes fault patterns and determines examination sequences, it inherently records and processes contextual information that would otherwise be lost. This self-service approach to context capture eliminates the need for manual documentation while preserving valuable maintenance knowledge
Solution Approach 2:
The fault propagation model and fault pattern library serve as digital copies of the tacit knowledge traditionally held in maintainers' heads. By encoding expert knowledge into structured models and patterns, the system creates persistent, searchable representations of maintenance context that can be consistently applied across different situations and personnel, preventing information loss while remaining relatively easy to implement
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method is provided for diagnosing a failure on an aircraft that includes aircraft systems and monitors configured to report effects of failure modes of the aircraft systems. The method includes receiving a fault report that indicates one or more of the monitors that reported the effects of a failure mode in an aircraft system of the aircraft systems, and accessing a fault pattern library that describes relationships between possible failure modes and patterns of those of the monitors configured to report the effects of the possible failure modes. The method also includes diagnosing the failure mode of the aircraft system from the one or more of the monitors that reported, and using the fault pattern library and a greedy selection algorithm, determining a maintenance action for the failure mode; and generating a maintenance message including at least the maintenance action.