Drone Engine Inspection With Obstruction-Aware Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Gas turbine engine inspections are often invasive, time-consuming, and expensive due to the need for manual access and the challenges of navigating obstructions within the engine.
Innovation Solution
A system utilizing drones equipped with imaging devices and light sources, operated by processors that include neural networks, to autonomously navigate and inspect gas turbine engine components by identifying and overcoming obstructions to obtain unobstructed images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual inspection methods are used to inspect gas turbine engine components, then inspection accuracy can be maintained, but inspection time increases and engine downtime increases
Solution Approach 1:
The patent replaces manual mechanical inspection methods with an automated drone-based inspection system. The drone navigates autonomously within the engine, captures images of components, and uses neural networks for automated analysis, eliminating the need for manual intervention while maintaining inspection accuracy and significantly reducing inspection time.
Solution Approach 2:
The inspection system performs self-service through autonomous drone navigation and automated defect detection using neural networks. The system independently identifies components, captures images, detects obstructions, and analyzes defects without requiring continuous manual operation, thereby reducing both inspection time and engine downtime.
2Productivity
If drones are used to automate inspection of gas turbine engines, then inspection speed increases and downtime decreases, but the system must handle obstructions that block views of target surfaces
Solution Approach 1:
The system uses neural networks to analyze captured images and provide feedback about obstruction detection. When an obstruction is detected blocking the view of a target surface, the system automatically adjusts the drone's position or imaging device orientation to obtain an unobstructed view, creating a closed-loop feedback system that handles obstructions efficiently.
Solution Approach 2:
The drone system dynamically adapts to obstructions by automatically adjusting its position, orientation, or imaging device angles based on real-time obstruction detection. This dynamic response allows the system to maintain high inspection speed while effectively handling unexpected obstructions that block views of target surfaces.
3Area of stationary object
If multiple drones are deployed to inspect different areas simultaneously, then inspection coverage increases, but system complexity increases
Solution Approach 1:
The patent employs multiple drones that can be deployed simultaneously to inspect different areas of the engine. Each drone is equipped with universal capabilities including autonomous navigation, imaging, and neural network-based defect detection, allowing them to independently perform complete inspection functions while collectively increasing overall inspection coverage and efficiency.
Data Source
Figure 1~3
Figure 4~5
AI summary
A system (20) includes at least one drone (26) that is equipped with an imaging device (40) and a light source (42). At least one processor (34) is configured to: operate the at least one drone (26) to fly into a gas turbine engine (22) to a first position (P1) with respect to a component (48) in the gas turbine engine (22), operate the imaging device (40) and the light source (42) to take an image (50, 51a, 51b) of a target surface (48a) of the component (48) from the first position (P1), identify whether the image (50, 51a, 51b) includes an obstruction (52) blocking a portion of the target surface (48a) from view of the imaging device (40), in response to identifying the obstruction (52), operate the at least one drone (26) to fly to a second position (P2) from which there is a line-of-sight to the target surface (48a) without the obstruction (52), and operate the imaging device (40) and the light source (42) to obtain an unobstructed image (50a) of the target surface (48a) from the second position (P2).