A pattern recognition based method for analyzing corrosion defects in storage tanks using C-scan

Abstract

The application discloses a kind of based on pattern recognition's storage tank corrosion defect C scan analysis method, including the following steps: obtaining storage tank C scan image, decay characteristic time chart, amplitude chart and wall thickness estimation chart;With the preprocessed data set input image boundary passage of cross-modal corrosion boundary perception network;With the preprocessed data set input physical decay passage;Based on the cross-modal fusion module of cross-modal corrosion boundary perception network, cross-modal attention fusion is executed;With the cross-modal fusion feature set input boundary refinement module, generate corrosion region initial segmentation chart and corrosion boundary confidence chart;Based on corrosion boundary confidence chart, corrosion region initial segmentation chart is executed iterative boundary refinement processing;According to target corrosion region segmentation chart and preprocessed data set, establish spatial correspondence.This application cross-modal corrosion boundary perception network realizes the fine identification and quantitative analysis of storage tank corrosion region.

Images