Rotary kiln flame image recognition method based on complex wavelet domain decomposition

Abstract

The invention relates to a rotary kiln flame image recognition method based on complex wavelet domain decomposition. According to the technical scheme, the method includes setting standard flame gray scale images Pym, a normal flame gray scale gallery GI and an abnormal flame gray scale gallery BI; acquiring an image P of the flame to be detected, performing gray scale transform on the image P of the flame to be detected, and acquiring an image x of the flame to be detected; performing average structure similarity coefficient calculation on the image x of the flame to be detected and all the flame gray scale images in a complex wavelet domain, and acquiring 2a average structure similarity coefficients passim (x, Pym); extracting a maximum value passim_MAX of the average structure similarity coefficients, if the standard flame gray scale image Pym corresponding to the maximum value passim_MAX of the average structure similarity coefficients belongs to the normal flame gray scale gallery GI, determining that the image P of the flame to be detected is in a normal state; if not, determining that the image P of the flame to be detected is in an abnormal state. The method has the advantages that the flame state change can be monitored online in real time, the image recognizing process is short, the recognizing accuracy is high, accurate image registration is omitted, and the high robustness is provided for noises.

Description

technical field [0001] The invention belongs to the technical field of recognition methods for flame images of rotary kilns. In particular, it relates to a recognition method of rotary kiln flame image based on complex wavelet domain decomposition. Background technique [0002] Rotary kiln is a thermal equipment used in calcination or roasting and other processing of various industrial raw materials. It is used for mechanical, physical or chemical treatment of input materials. It is widely used in building materials, chemical industry, metallurgy and other industries. Affected by the particularity of the structure of the rotary kiln and the complexity of the process, it is difficult to measure the quality indicators of the clinker obtained online, and it is also difficult to accurately identify the firing state of the clinker. In addition, the multi-variable strong coupling characteristics of the rotary kiln process and uncertain interference, etc. factors, the operation pr...

AI Technical Summary

Problems solved by technology

[0004] "A method for identifying the firing state of a rotary kiln based on the structural similarity of flame images" (CN201310567666.0) is to judge the flame burning state of a rotary kiln from three different angles of image brightness, contrast, and structure. It has the advantages of high precision, but this method requires precise registration of the images, and it is difficult to prevent the small jitter of the CCD camera from causing a small displacement or a large rotation when collecting images of the firing conditions in the kiln. Small angle, so the continuous frame images will not be accurately registered, resulting in certain inaccuracies

Images