System and method for small channel gas-liquid two-phase flow pattern recognition based on multi-visual information fusion technology
A gas-liquid two-phase flow, flow pattern recognition technology, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of insufficient information acquisition and insufficient accuracy.
Active Publication Date: 2018-12-04
ZHEJIANG UNIV
View PDF1 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Aiming at the problem of insufficient information acquisition and insufficient accuracy of the current identification technology of gas-liquid two-phase flow in small channels based on high-speed photography, the present invention provides a multi-channel gas-liquid two-phase flow based The small channel gas-liquid two-phase flow pattern recognition system and method based on visual information fusion technology proposes to use a multi-vision system to simultaneously acquire images of two mutually perpendicular angles of two-phase flow, and use image processing technology to obtain Hu moment statistical parameters of the image sequence as flow Based on the characteristics of pattern recognition, a single-vision gas-liquid two-phase flow pattern recognition model based on support vector machine (SVM) was established, and the D-S evidence theory was used for information fusion to realize multi-visual flow pattern recognition
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0083] Refer to attached figure 1 , the present invention uses a small channel gas-liquid two-phase flow pattern recognition system based on multi-visual information fusion technology to realize small channel gas-liquid two-phase flow flow pattern recognition. The small-channel gas-liquid two-phase flow pattern recognition system based on multi-visual information fusion technology includes three parts: a small-channel piping system, a multi-vision high-speed image acquisition unit, and an image processing and flow pattern recognition computer.
[0084] Such as figure 2 As shown, the small channel pipeline system 1 is composed of a small pipe 7 immersed in a glycerin tank 6, and the multi-vision high-speed image acquisition unit 2 is composed of a high-speed camera 9, a rectangular prism 8, a first LED light source 4, and a second LED light source 5. , the multi-vision high-speed image acquisition unit is responsible for simultaneously collecting two gas-liquid two-phase flow...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a small channel gas-liquid two-phase flow pattern recognition system and method based on multi-visual information fusion technology. Firstly, two small channel gas-liquid two-phase flow image sequences with mutually perpendicular angles are acquired at the same time; secondly, image correction and preprocessing are performed, and the mean value and standard deviation of the image sequence Hu moments are calculated as the flow pattern identification feature vector; then, the establishment A single-vision small-channel gas-liquid two-phase flow flow pattern recognition model based on support vector machines. Finally, using the D‑S evidence theory, the flow pattern recognition results from two angles are fused to realize bubbly flow, slug flow, and wavy flow. Identification of four typical flow patterns of flow and annular flow. The invention proposes a new small channel gas-liquid two-phase flow pattern recognition system and method. The system has the advantages of non-contact measurement, visualization, and simple structure. It uses multi-visual information fusion method to improve the accuracy of flow pattern recognition of gas-liquid two-phase flow.
Description
technical field [0001] The invention belongs to the field of multiphase flow pattern recognition, and relates to a gas-liquid two-phase flow pattern recognition system based on multi-visual information fusion technology, in particular to a method for gas-liquid two-phase flow pattern recognition using the system. Background technique [0002] Due to the advantages of high efficiency, rapidity, easy control and high integration of small / miniature equipment, it has been widely used in the fields of energy, chemical industry, biology and pharmaceuticals in recent years. research has received increasing attention. [0003] Existing detection methods of micro-channel two-phase flow parameters mainly include electrical method, optical method, thermal method and high-speed camera method. Among them, the high-speed camera method has the advantages of intuition, non-contact and the ability to observe the transient changes between two phases, and has been widely used in the experimen...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/20G06K9/34G06K9/40G06K9/62
CPCG06V20/40G06V10/10G06V10/30G06V10/267G06F18/2411
Inventor 冀海峰郑小虎王保良黄志尧李海青
Owner ZHEJIANG UNIV