Aircraft Characterising Codes for Failure Analysis and Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern systems, particularly in aerospace contexts, generate vast amounts of data that is difficult to explore and derive insights from due to its large size, leading to lost insights in investigating failures and enhancing maintenance schedules.
Innovation Solution
A computer-implemented method is introduced to create a database of characterising codes by receiving data, identifying data clusters, assigning parameters to these clusters, generating unique labels, and storing them, allowing for efficient management and comparison of physical systems like aircraft with gas turbine engines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If vast amounts of usage data are collected and stored from sensors and processors in aircraft systems, then the ability to investigate failures and enhance maintenance schedules is improved, but the data becomes prohibitively large and insights are lost due to inability to meaningfully explore the datasets
Solution Approach 1:
The patent segments the vast usage data into discrete parameter sets with specific data types and formats. Each parameter is individually characterized and organized into structured groups, enabling systematic exploration of large datasets without being overwhelmed by their volume. This segmentation allows investigators to focus on specific parameter combinations relevant to failure analysis.
Solution Approach 2:
The patent introduces a standardized data structure as an intermediary layer between the raw sensor data and the analysis tools. This structured format acts as a mediator that organizes the prohibitively large raw data into meaningfully grouped parameters, enabling efficient exploration and insight extraction without requiring direct manipulation of the entire dataset.
2Measurement precision
If all parameter data is stored in detail for every aircraft example, then measurement precision is improved, but the complexity of managing and comparing datasets increases significantly
Solution Approach 1:
The patent divides comprehensive parameter data into discrete, standardized parameter groups with defined data types. This segmentation maintains precise measurement data for each parameter while organizing it into manageable units that can be systematically stored and compared, reducing the overall complexity of data management.
Solution Approach 2:
The patent transforms raw parameter data into standardized formats with specific data types and structures. This parameter transformation maintains the precision of original measurements while changing the organizational form to reduce management complexity, enabling efficient storage and comparison of detailed data.
3Productivity
If comprehensive parameter tracking is implemented for maintenance optimization, then maintenance schedule enhancement is improved, but the computational power required to process and analyze the data increases
Solution Approach 1:
The patent segments comprehensive parameter tracking into focused parameter groups relevant to maintenance decisions. By organizing data into specific parameter sets with defined structures, the system enables maintenance optimization analysis with reduced computational requirements compared to processing all raw data.
Solution Approach 2:
The patent extracts and isolates the specific parameter combinations most relevant to maintenance scheduling from the comprehensive dataset. This extraction focuses computational resources on the critical parameters needed for maintenance optimization, reducing overall computational power consumption while maintaining productivity.
Data Source
AI summary
A computer-implemented method. The method comprising: (a) obtaining a candidate characterising code, the candidate characterising code being indicative of character of an example of a physical system; (b) accessing a database of extant characterising codes, the extant characterising codes being indicative of character of other examples of the physical system; (c) determining a degree of similarity between the candidate characterising code, and at least one of the extant characterising code; and (e) providing, as an output, the results of the comparison.