Jet Engine Blade Image Processing for Defect Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for inspecting blades in a jet engine, such as using endoscopes, are inefficient in capturing and processing images of rotating blades, leading to difficulties in defect detection and requiring extensive storage for video files, which increases storage capacity needs.
Innovation Solution
An image processing apparatus and method that captures and processes images of rotating blades by correlating frame images with a template image, allowing for efficient inspection and storage by saving only highly correlated frame images as still images, reducing storage requirements and improving inspection precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sequential images of rotating blades are captured and stored as video files for inspection, then defect detection capability is maintained, but storage capacity requirements increase significantly
Solution Approach 1:
The patent extracts only the essential information from sequential video frames by comparing each frame with a reference blade image. Only frames containing actual defects are saved as still images rather than storing complete video sequences, thereby extracting and retaining only the necessary defect information while discarding redundant data.
Solution Approach 2:
The system discards redundant video data by comparing sequential frames with a reference image and only recovering/saving those frames that contain actual defects. This selective retention approach discards normal, defect-free blade images while preserving only the defective frames for inspection.
2Reliability
If all sequential blade images are processed and stored for inspection, then comprehensive defect detection is achieved, but processing time and computational resources increase
Solution Approach 1:
The patent extracts only the essential information from sequential video frames by comparing each frame with a reference blade image. Only frames containing actual defects are saved as still images rather than storing complete video sequences, thereby extracting and retaining only the necessary defect information while discarding redundant data.
Solution Approach 2:
Instead of processing and storing all sequential frames, the system performs partial processing by comparing frames with a reference image and only processing/saving those that show differences indicating defects. This partial action approach reduces overall processing time while maintaining comprehensive defect detection capability.
3Measurement precision
If high-resolution video files are stored for blade inspection, then inspection precision is maintained, but storage requirements and data transmission needs increase
Solution Approach 1:
The patent extracts only the essential information from sequential video frames by comparing each frame with a reference blade image. Only frames containing actual defects are saved as still images rather than storing complete video sequences, thereby extracting and retaining only the necessary defect information while discarding redundant data.
Data Source
AI summary
An image processing apparatus includes a display section that displays a first image, which forms a streaming video obtained by capturing blades periodically arrayed in a jet engine, and also displays information indicating the position of a blade corresponding to the first image.