Aircraft Engine Defect Detection With Event-Driven Neuromorphic Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional sensors used in aircraft engine monitoring generate large volumes of data, posing challenges in efficient analysis and storage, especially in aircraft with limited data processing and storage capabilities.
Innovation Solution
The implementation of a data acquisition system that incorporates a visual neuromorphic sensor to asynchronously report changes in visual data characteristics, coupled with synchronous data collection sensors, to identify events and detect defects in aircraft engines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional synchronous sensors are used for continuous monitoring, then complete data coverage is achieved, but data volume becomes excessively large
Solution Approach 1:
The patent extracts only the meaningful changes from the continuous data stream by using neuromorphic sensors that detect and report only when visual characteristics change. This separates the essential defect detection information from the redundant continuous data, achieving complete coverage of defect events while minimizing data volume.
Solution Approach 2:
Instead of continuous synchronous sampling, the system uses event-driven periodic action where data acquisition is triggered only when a visual change is detected. This transforms continuous monitoring into discrete event-based monitoring, maintaining reliability for defect detection while dramatically reducing overall data volume.
2Reliability
If continuous data acquisition is performed, then no defects are missed, but processing and storage resources are overwhelmed
Solution Approach 1:
The system extracts only the critical defect-related events from the continuous monitoring stream. By using neuromorphic sensors that inherently filter out redundant information and report only changes, the system maintains complete defect detection while presenting a manageable subset of data to processing and storage systems.
Solution Approach 2:
The neuromorphic sensor performs preliminary filtering and event detection before data reaches the processing system. This preliminary action of identifying and reporting only meaningful changes reduces the burden on subsequent processing and storage operations, improving overall system productivity.
3Measurement precision
If synchronous sensors sample at high frequency, then transient defects are captured, but data storage requirements increase significantly
Solution Approach 1:
The system extracts only the transient defect events from the high-frequency sampling stream. Neuromorphic sensors naturally capture transient changes by reporting only when visual characteristics change, discarding the redundant high-frequency data that does not contain defect information, thus reducing storage requirements while maintaining detection precision.
Solution Approach 2:
Instead of uniform high-frequency sampling, the system uses event-triggered periodic action where data is captured only when a transient change occurs. This maintains the ability to detect transient defects while avoiding the storage burden of continuous high-frequency data acquisition.
Data Source
AI summary
Embodiments of the present disclosure generally relate to aircraft engines and, more particularly, to detecting defects in aircraft engines using visual neuromorphic sensors. In some embodiments, an event associated with a portion of an aircraft engine may be identified based on a change on a visual data characteristic from a visual neuromorphic sensor. In response to identifying the event associated with the portion of the aircraft engine, synchronous data from a synchronous data collection sensor coupled to the aircraft engine may be retrieved for a predetermined period of time, and a defect associated with the aircraft engine detected based on the identified event and the synchronous data. Other embodiments may be disclosed or claimed.