Fluid pipeline leakage positioning method based on adaptive ICA and improved RLS filter

Abstract

The invention relates to a fluid pipeline leakage positioning method based on an adaptive ICA and an improved RLS filter, and belongs to the field of pipeline leakage detection. The method comprises the following steps of decomposing a collected leakage vibration signal into a limited number of IMF components by adopting an adaptive CEEMDAN algorithm, filtering out the irrelevant IMF components by calculating the Euclidean distance between each component and the corresponding leakage vibration signal, and constructing an observation signal matrix in the ICA by utilizing the screened IMF components; performing strong decorrelation and separation on the real-time leakage vibration signal and the impulse response convolution of a pipeline through the maximum likelihood estimation of the adaptive ICA to obtain a source leakage vibration signal; adaptively determining a filtering order and a forgetting factor of the RLS filter by using a TOPSIS algorithm; and finally, carrying out iterative calculation on the time delay of the source leakage vibration signal by utilizing the optimized RLS filter, thereby realizing positioning of pipeline leakage.

Description

Technical field [0001] The present invention belongs to the field of pipeline leak detection, involving a fluid pipeline leakage positioning method based on adaptive ICA and improved RLS filters. Background technique [0002] With the growth of oil and natural gas pipelines, the pipeline will cause damage due to corrosion or external force, making the health of the pipeline gradually deteriorate, and the transmission safety cannot be guaranteed, causing economic significant losses and even endangering human life. In the actual fluid pipe, the vibration signal acquired by the sensor includes a large number of noise, so that the signal itself is lowered, resulting in a larger correlation time, which affects the pipeline leakage positioning accuracy. Therefore, it is necessary to decorate the collected pipeline leak vibration signal, improve the error ratio of the signal-to-noise ratio and reduce the time delay, thereby increasing the pipeline leakage positioning accuracy. Sun Lizhe...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the object of the present invention is to provide a kind of recursive least square method (Recursive least squares method) improved based on adaptive independent component analysis (Independent component analysis, ICA) and by superiority and inferiority solution distance method (Technique for order preference by similarity to ideal solution, TOPSIS). Leastsquare, RLS) filter fluid pipeline leakage location method, used to solve the real-time leakage vibration signal and pipeline impulse response convolution and leakage caused by human experience to determine the filtering order and forgetting factor in the traditional recursive least squares filter When the positioning accuracy is not high

Images