Aircraft Diagnostic Causal Model Updates for Faster Fault Isolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current aircraft maintenance systems require manual interpretation of complex data to diagnose and address system failures, leading to inefficiencies and prolonged downtime, which is costly for vehicle owners.
Innovation Solution
An onboard reasoner and off-board reasoner system using graph-theoretic algorithms and causal models to diagnose aircraft system failures, correlating fault reports with failure modes and generating maintenance actions, with the off-board reasoner updating the onboard model for continuous improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual data interpretation is used for fault diagnosis, then the user can make repair decisions based on their knowledge, but the process is time-consuming and may not identify the most appropriate repair action
Solution Approach 1:
The patent introduces an automated diagnostic system that acts as an intermediary between the complex system data and the user. This system processes performance data, identifies fault modes, and recommends repair actions, thereby reducing the time required for diagnosis while maintaining or improving accuracy through systematic analysis of multiple data points and fault trees.
Solution Approach 2:
The patent replaces the manual mechanical process of data interpretation with an automated computational system. The system uses algorithms to process performance data, evaluate fault trees, and generate diagnostic conclusions, substituting human manual analysis with automated mechanical/computational processes that are faster and more consistent.
2Loss of information
If all performance data is collected and reported to the user, then complete information is available for decision-making, but the user must sort through all data which is time-consuming
Solution Approach 1:
The patent extracts only the relevant information from the complete set of performance data. The automated diagnostic system processes all collected data but selectively identifies and presents only the fault modes and repair actions that are most relevant to the current system state, removing unnecessary data sorting burden from the user.
Solution Approach 2:
The patent creates a simplified representation or copy of the complex data set that is tailored to the specific fault condition. Instead of presenting all raw performance data, the system generates a condensed diagnostic report that mirrors the essential information needed for decision-making, making the data easier to operate with while preserving completeness.
3Reliability
If the vehicle is taken out of service for repair, then the fault can be addressed, but the longer the vehicle is out of service, the more expensive it is to the vehicle owner
Solution Approach 1:
The patent performs preliminary diagnostic analysis to identify the most appropriate repair action before the vehicle is taken out of service. By pre-processing the data and identifying the correct fault mode and recommended repair, the system ensures that when maintenance is performed, it is done efficiently with minimal downtime, reducing the cost to the vehicle owner while maintaining reliability.
Solution Approach 2:
The patent implements a feedback mechanism where the diagnostic system continuously monitors performance data and provides real-time or near-real-time recommendations. This allows for timely intervention and repair scheduling, optimizing the balance between maintaining system reliability and minimizing downtime costs by acting at the optimal moment rather than waiting for complete system failure.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A method is provided for maintaining an onboard reasoner for diagnosing failures on an aircraft that includes aircraft systems configured to report faults to the onboard reasoner. The method includes accessing diagnostic data received from an onboard computer of the aircraft that includes the onboard reasoner. An off-board reasoner builds an off-board diagnostic causal model that describes causal relationships between the failed tests and the diagnosed failure modes. The off-board diagnostic causal model is compared to the diagnostic data. Based thereon, a discrepancy is identified between the graph of the off-board diagnostic causal model, and the other graph of the onboard diagnostic causal model, to determine a new causal relationship relative to the known causal relationships. The onboard diagnostic causal model is updated to further describe the new causal relationship, including producing an updated model, and uploading the updated model to the onboard computer.