Automatic Failure Message Analysis System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current expert systems for analyzing failure and state messages in complex systems like aircraft are inefficient due to human errors, incomplete databases, and inability to distinguish between messages requiring analysis and those that do not, leading to slowed diagnostics and increased maintenance costs.
Innovation Solution
A method that integrates messages into a database and determines an index of overall interest for each message based on frequency of occurrence and correlation with predefined indexes, allowing for automatic filtering and prioritization of messages for analysis, including steps for determining local interest, associating messages with documentation, and assigning stability labels to system configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If expert systems are used to analyze failure messages, then analysis capability is provided, but the systems are complex and require complete databases which are costly and time-consuming to establish
Solution Approach 1:
The patent segments the analysis process into two distinct phases: offline message collection and database construction, and online automatic analysis. This segmentation allows the complex database creation to occur separately from the analysis operation, reducing the operational complexity while maintaining automatic analysis capability.
Solution Approach 2:
The patent performs preliminary actions by collecting messages and constructing the database offline before actual analysis is needed. This preliminary database construction phase prepares all necessary data structures and relationships in advance, so that the online analysis phase can operate efficiently without dealing with the complexity of database creation.
2Measurement precision
If all failure messages are analyzed, then complete diagnostics are achieved, but the large number of messages slows down the diagnostic process
Solution Approach 1:
The patent extracts and removes redundant information from the message set through the offline database construction phase. By pre-processing messages and storing only essential diagnostic information in the database, the system eliminates unnecessary data that would otherwise slow down the analysis process while maintaining diagnostic completeness.
Solution Approach 2:
The patent creates a simplified copy of the failure message information in the offline database. Instead of analyzing all raw messages during online operation, the system uses pre-processed database entries that contain only the critical diagnostic information needed for quick analysis.
3Measurement precision
If manual analysis of all messages is performed, then accurate diagnostics are achieved, but human errors and inhomogeneities reduce reliability
Solution Approach 1:
The patent implements self-service by enabling the system to automatically perform the analysis function that previously required human operators. The automatic analysis system eliminates human errors and inhomogeneities by using consistent, rule-based processing of failure messages, while the offline database construction ensures accurate and reliable diagnostic data is available.
Data Source
AI summary
This method for automatic analysis of failure or state messages generated by at least one complex system is characterized in that it comprises the steps for integrating said messages to a database of failure or state messages, and for determining with a computer, for each of said messages, an index of overall interest characterizing a degree of relevance of said message, on the basis of at least one parameter representative of a frequency of occurrence of similar messages in said database, and a correlation between said or each representative parameter and a predefined number of indexes of overall interest. A corresponding analysis system is also provided.