Method for identifying flow type of soft grain two-phase turbulence based on artificial intelligence

Abstract

The invention relates to a method for identifying the flow type of soft grain two-phase turbulence based on artificial intelligence, comprising the following steps: 1), collecting the pressure signals of the soft grain two-phase turbulence; 2), extracting and analyzing the pressure signal characteristics: carrying out multi-level division on a frequency band by using a small wave packet method, further decomposing a high-frequency part without dispersed multiple resolution ratios, adaptively selecting corresponding frequency bands according to the characteristics of the analyzed signals so asto match the corresponding frequency bands with signal frequency spectrums; and 3), training and identifying flow type samples composed of defined characteristic parameters by using a probabilistic neural network, wherein learning samples are characteristic vectors of information entropy of a small wave packet after normalization according to a relationship between a probabilistic neural network structure and the learning samples, determining the structure of the probabilistic neural network for flow type identification as well as carrying out relative set on the network and learning training, and identifying the samples with different flow types by using the probabilistic neural network. The method has high veracity, good applicability and high reliability, and can effectively meet on-line identification requirements.

Description

technical field [0001] The invention relates to a two-phase flow flow pattern recognition method, more specifically, an artificial intelligence-based soft abrasive particle two-phase turbulent flow pattern recognition method. Background technique [0002] The flow pattern (characterizing the flow form of the fluid) can be divided into laminar flow, turbulent flow and transition flow in between. It represents the trajectory and velocity distribution of fluid particle motion. The laminar flow pattern in the circular tube is a parabolic velocity distribution; the velocity distribution of the turbulent flow pattern obeys the Karman-Prand 1 / 7 exponential law. The two-phase flow pattern also characterizes the phase interface distribution of the two-phase flow medium. At present, two-phase flow conditions are involved in many production equipment in power, chemical, nuclear energy, refrigeration, petroleum and metallurgy industries, and even have applications in the precision mac...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing soft abrasive particle two-phase turbulent flow pattern identification method, which have low accuracy, poor applicability, low reliability, and inability to meet the requirements of online identification, the present invention provides a method with high accuracy and applicability. An artificial intelligence-based identification method for two-phase turbulent flow patterns of soft abrasive particles with good performance and high reliability, which can effectively meet the requirements of online identification

Images