Apparatus and method for measuring thickness of pipe based on image analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for measuring pipe thickness using computed radiography are subjective and inconsistent, requiring experienced inspectors and lacking standardized historical tracking due to variability in image capture locations.
Innovation Solution
An apparatus and method utilizing neural networks to analyze radiographic images, distinguishing pipes from non-pipe objects, and measuring thickness through pixel distances and contour analysis, providing standardized and automated thickness measurement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual inspection by experienced inspectors is used to measure pipe thickness, then measurement accuracy can be achieved, but subjectivity and inconsistency increase, making it difficult to establish standardized criteria
Solution Approach 1:
The patent replaces the manual mechanical inspection process with an automated image analysis system using neural networks. The system automatically detects pipe contours, identifies inner and outer circumferential surfaces, and calculates thickness measurements from radiographic images, eliminating human subjectivity and establishing standardized measurement criteria through algorithmic processing.
Solution Approach 2:
The system performs self-service by automatically analyzing radiographic images to identify pipe structures, detect surfaces, and measure thickness without requiring experienced inspectors. The neural network model autonomously processes images, extracts features, and generates measurements, making the inspection process independent of human expertise while maintaining consistency.
2Measurement precision
If visual inspection after converting image plate data is used, then pipe thickness can be assessed, but the process requires experienced inspectors and cannot be accurately generalized
Solution Approach 1:
The patent replaces the complex manual visual inspection process with an automated neural network-based image analysis system. The system automatically processes converted image plate data, identifies pipe structures, and measures thickness, simplifying the inspection process while improving generalizability through consistent algorithmic application across all measurements.
3Reliability
If manual image file inspection is used for historical tracking, then some tracking capability exists, but consistent location capture is difficult, reducing tracking accuracy
Solution Approach 1:
The system performs self-service by automatically analyzing radiographic images to identify pipe structures, detect surfaces, and measure thickness without requiring experienced inspectors. The neural network model autonomously processes images, extracts features, and generates measurements, making the inspection process independent of human expertise while maintaining consistency.
Data Source
AI summary
Proposed is a method for measuring a thickness. The method includes training neural networks generating a pipe image that distinguishes a pipe from non-pipe object in a radiographic image, generating, by a recognition part, the pipe image using the neural networks; and measuring a pipe thickness as a distance between a first pixel of one outer circumferential surface of the pipe and a second pixel of an inner circumferential surface closest to the first pixel, and a total pipe thickness as a distance between the first pixel and a third pixel of a second outer circumferential surface of the pipe closest to the first pixel, by analyzing the pipe image.