Neuromorphic FOD Detection for Automated Aircraft Engine Inspection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting foreign object debris (FOD) in aircraft engines are inefficient and require manual inspection, which is time-consuming and prone to missing potential engine-damaging debris, leading to substantial consequences like engine damage or failure.
Innovation Solution
A neuromorphic FOD detection system using neuromorphic sensors and artificial intelligence machine learning (AIML) models, such as deep convolutional neural networks (DCNN) or deep convolutional auto encoders (CAE), to automatically detect and alert technicians to the presence of FOD by analyzing pixel data from a field of view containing the engine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual inspection methods are used to detect FOD, then the system is simple and easy to implement, but the detection efficiency is low and time-consuming
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated optical detection system using neuromorphic sensors and AI processing. The neuromorphic sensor captures visual data of the engine area, and the AIML model automatically processes this data to detect FOD, substituting human visual inspection with an automated electronic system that achieves both high efficiency and acceptable complexity.
2Loss of information
If traditional pixel cameras are used to capture full images for FOD detection, then complete visual information is obtained, but the data processing load and memory requirements are high
Solution Approach 1:
The patent extracts only the relevant visual information needed for FOD detection rather than processing complete images. The neuromorphic sensor outputs pixel data selectively, and the system processes only the necessary visual features to detect foreign objects, eliminating redundant data while maintaining detection effectiveness.
Solution Approach 2:
The system focuses processing resources on detecting specific local features indicative of FOD rather than analyzing every pixel uniformly. The AIML model is trained to identify localized foreign objects against the background of the engine, applying different processing priorities to different regions of the visual field based on their relevance to FOD detection.
3Measurement precision
If automated detection systems are implemented, then detection accuracy and speed improve, but the system complexity and processing requirements increase
Solution Approach 1:
The patent replaces complex manual inspection procedures with an automated neuromorphic sensing system coupled with AI processing. This substitution achieves high detection accuracy through the specialized neuromorphic sensor and trained AIML model while managing system complexity through efficient data processing that leverages the event-driven nature of neuromorphic sensors.
Data Source
AI summary
A neuromorphic foreign object debris (FOD) detection system includes a FOD processing system and a neuromorphic sensor. The FOD processing system includes a FOD controller including a trained artificial intelligence machine learning (AIML) model representing an area of interest. The neuromorphic sensor has a field of view (FOV) containing the area of interest and is configured to output pixel data in response to FOD appearing in the FOV. The FOD controller detects the FOD is present in the area of interest in response to receiving the pixel data, and generates an alert signal indicating the presence of the FOD.