Flame Identification Method for Float Glass Furnace Based on Linear Group and Generalized Feature Optimization

Abstract

The invention relates to a method for flame identification of a float glass melting furnace based on linear group and generalized feature optimization, which belongs to the technical field of advanced manufacturing, automation and image processing, and is characterized in that it is aimed at the harsh production environment of a glass melting furnace (such as dust, oil, Due to the characteristics of large noise, pixel loss and low definition of flame images under high temperature, etc., a method for flame recognition of glass melting furnace based on linear group and generalized feature optimization is proposed. First, the incomplete flame information of the glass melting furnace is transformed into a linear group, and the incomplete flame information after the linear group transformation is restored by using the matrix complete method, so as to obtain a complete flame image; then, the complete flame image information is mapped to To the generalized feature space, the flame state is identified according to the neighbor rule in the generalized feature space. The invention can be effectively applied to identify the flame of the glass melting furnace so as to optimize the combustion state of the glass melting furnace.

Description

technical field [0001] The invention belongs to the technical fields of advanced manufacturing, automation and image processing, and in particular relates to an image recognition method for flame monitoring of a float glass melting furnace in a complex and non-harsh production environment. Background technique [0002] At present, for the problem of image recognition with noise, there are the following types of image processing methods: methods based on partial differential equations, methods based on variation, methods based on pixel blocks; methods based on partial differential equations and methods based on variation are only applicable to a small range However, the range of incomplete flame information in the float glass melting furnace is generally relatively large, so this type of method cannot be adapted to this problem; the method based on pixel blocks needs to iteratively match the similarity between the damaged area of ​​the image and the known area To obtain the b...

AI Technical Summary

Problems solved by technology

[0002] At present, for the problem of image recognition with noise, there are the following types of image processing methods: methods based on partial differential equations, methods based on variation, methods based on pixel blocks; methods based on partial differential equations and methods based on variation are only applicable to a small range However, the range of incomplete flame information in the float glass melting furnace is generally relatively large, so this type of method cannot be adapted to this problem; the method based on pixel blocks needs to iteratively match the similarity between the damaged area of ​​the image and the known area degree to get the best matching block for filling, and each filling needs to traverse the entire image, resulting in high computational complexity, which cannot meet the requirements of float glass enterprises for glass flame identification

Images