Aircraft Operational Testing Using Cross-System Sensor Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current operational testing of aircraft systems is costly and time-consuming, and changes to one system can lead to undetected effects on other systems due to the need for separate testing of each system.
Innovation Solution
A method and system that utilize sensors and analytic models to monitor aircraft conditions, allowing for the evaluation of multiple operational tests simultaneously by processing sensor data from one test to predict and detect effects on other systems, thereby covering test matrices without separate testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If separate operational tests are performed for each aircraft system, then testing coverage for individual systems is ensured, but the number of tests increases leading to higher costs and time consumption
Solution Approach 1:
The patent combines multiple separate operational tests into a single integrated test execution. By using analytic models to evaluate multiple aircraft systems simultaneously during one test, the system merges the functionality of separate tests while maintaining comprehensive coverage through model-based evaluation of sensor data across different systems.
Solution Approach 2:
The analytic models serve multiple functions: they evaluate the primary aircraft system under test, detect unexpected effects on other systems, and provide comprehensive testing coverage. This multi-functionality allows a single test to replace multiple separate tests, reducing time and cost while maintaining reliability.
2Reliability
If separate operational tests are performed for each aircraft system, then individual system testing is thorough, but the overall testing process becomes costly
Solution Approach 1:
The patent merges multiple costly separate tests into a single integrated test execution. By using analytic models to evaluate multiple systems simultaneously, the approach reduces the overall testing cost while maintaining thorough evaluation of each system through model-based analysis of sensor data.
Solution Approach 2:
The analytic models automatically evaluate multiple aircraft systems using sensor data collected during test execution. This self-service capability eliminates the need for separate manual testing processes for each system, reducing costs while maintaining testing accuracy through automated model-based evaluation.
3Measurement precision
If operational tests are performed for a specific system after a change, then effects on that system are detected, but unexpected effects on other systems can go undetected
Solution Approach 1:
The analytic models are designed to evaluate multiple aircraft systems simultaneously, not just the primary system under test. This multi-functionality enables the detection of both expected effects on the targeted system and unexpected effects on other systems, preventing information loss about cross-system interactions.
Solution Approach 2:
The system continuously monitors sensor data and uses analytic models to provide feedback about the state of multiple aircraft systems. This feedback mechanism detects unexpected effects on systems not directly under test, ensuring comprehensive information about change impacts across the entire aircraft system architecture.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method (300) includes obtaining a first test matrix for a first aircraft system and a second test matrix for a second aircraft system (302). The method also includes, during a first operational test of the first test matrix, obtaining sensor data that includes second sensor data that is not specified by the first test matrix (304). The method includes evaluating a second operational test of the second test matrix by processing the second sensor data using a second analytic model of the second aircraft system (310). The method also includes generating second predicted sensor data based on the evaluation of the second operational test (312). The method includes generating a second error measure by comparing a second subset of the sensor data to the second predicted sensor data (316). The method includes determining, based at least in part on a range of the second sensor data, a test coverage metric of the second test matrix (318).