Aircraft Component Rotability Classification Using Harmonized ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Aircraft hardware components' rotability classification is hindered by opaque and inconsistent data, lacking training examples that map signals to determinations of rotability, impeding the development of supervised classifiers.
Innovation Solution
A system and method for training and deploying multiple rotability classifiers using historical signals, harmonizing their outputs to determine whether a component is rotable, and integrating these determinations into a searchable database for improved aircraft component searches.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple rotability classifiers are trained and deployed using historical signals, then prediction robustness is improved, but device complexity increases
Solution Approach 1:
The system divides the rotability classification task into multiple specialized classifiers, each trained on different historical signals or feature subsets. This segmentation allows each classifier to focus on specific patterns, improving overall prediction robustness while maintaining manageable complexity through modular architecture
Solution Approach 2:
Multiple classifier outputs are merged through harmonization to produce a final rotability determination. This combining approach leverages the strengths of individual classifiers trained on different signals, achieving robust predictions that overcome the limitations of any single classifier
2Measurement precision
If rotability determinations are integrated into searchable database with rotability indications, then data resolution is improved, but loss of information is reduced
Solution Approach 1:
Rotability determinations are pre-calculated and stored in the database alongside component information. This preliminary action ensures that rotability data is readily available and consistently formatted, improving data resolution and eliminating information opacity during search operations without requiring real-time analysis
Data Source
AI summary
An application extracts a plurality of features of a hardware component of an aircraft. The application inputs a first subset of features of the plurality of features into a first machine learning model, and receives as output a first determination of whether the hardware component is rotable. The application inputs a second subset of features of the plurality of features into a second machine learning model, and receives as output a second determination of whether the hardware component is rotable. The applications determines, based on the first determination and the second determination, a final determination of whether the hardware component is rotable, and adds a data structure for the hardware component with the final determination in a searchable database. The application receives a query from a user that is associated with the hardware component, runs a search, outputs whether the hardware component is rotable.