A method for quickly positioning and evaluating air leakage of a subway ventilation construction pipeline

Abstract

The present application belongs to the technical field of pipeline detection, and particularly relates to a method for quickly positioning and evaluating air leakage of a subway ventilation construction pipeline. The method adopts acoustic and pressure multi-source information fusion and a Bayesian inference algorithm. The acoustic method is sensitive to slight air leakage, the pressure method has obvious response to large air leakage, and the two methods are complementary, so that the air leakage point can be accurately positioned and a confidence interval can be output. The present application enhances the air leakage signal characteristics through dynamic pressure scanning working conditions, quickly determines the position through the fusion positioning algorithm, and does not need to block and check each section. The present application realizes five-level division of severity and automatic sorting of repair priority through comprehensive air leakage, pressure drop rate and position sensitivity indexes. The present application sets a positive and negative pressure bidirectional detection and acoustic pressure double-source cross verification mechanism to reduce the missed detection rate and false positive rate, and the prior probability distribution is adapted to complex topological structures.

Images