CN103578111B - Rotary kiln based on flame image structural similarity burns till state identification method - Google Patents

Abstract

The invention relates to a method for identifying the firing state of a rotary kiln based on the structural similarity of flame images. The technical solution is to set a standard flame gray image y, a normal flame gray image library FN and an abnormal flame gray image library FA. Obtain the flame image P to be tested, perform filtering and grayscale transformation on the flame image P to be tested, and obtain the grayscale image x of the flame to be tested; calculate the average structural similarity coefficient between the grayscale image x of the flame to be tested and all standard flame grayscale images y Calculate and obtain a+b average structural similarity coefficients MSSIM(x, y); take the maximum value of the average structural similarity coefficient MAXmssim, if the standard flame gray image y corresponding to the maximum average structural similarity coefficient MAXmssim belongs to a normal flame The grayscale library FN and the flame image P to be tested belong to the normal state; otherwise, it belongs to the abnormal state. The invention has the characteristics of high precision, low calculation complexity, short processing process and can realize online real-time monitoring of flame state changes.

Description

Rotary Kiln Firing State Recognition Method Based on Flame Image Structural Similarity

technical field

The invention belongs to the technical field of rotary kiln firing state recognition. In particular, it relates to a method for identifying the firing state of a rotary kiln based on the structural similarity of flame images.

Background technique

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 process of the rotary kiln is still in the open-loop operation stage of "manually watching the fire", and it is difficult to realize the automatic control of the rotary kiln control system. Long-term operation is likely to cause unstable clinker quality indicators, low production capacity, high energy consumption and manual labor. issues of strength.

The flame image is an effective response to the combustion process, the brightness information reflects the radiant heat and combustion effect during the combustion process, and the flame shape reflects the shape of the area where the combustion reaction occurs. Therefore, it is of great significance to use reasonable technology to judge the firing state of the flame image, so as to determine the operating state and combustion stability of the rotary kiln.

In recent years, one of the research hotspots of rotary kiln firing state recognition technology is digital image processing technology. After image preprocessing and image segmentation, feature extraction and selection are performed on the image, and the extracted and selected image features are sent to the pattern classifier for pattern recognition of the target, so as to determine the burning state of the flame. So far, many scholars have done a lot of in-depth research on each module of digital image processing. Although the recognition method of using digital image processing technology to judge the burning state of flame images has the advantages of high recognition accuracy, diverse and mature algorithms, but This kind of method inevitably has the defects of high computational complexity, long processing time, and the inability to monitor in real time online. It has not fundamentally changed the mode of "manual fire inspection", and affects the safety and reliability of the rotary kiln control system. It causes a series of problems such as unstable clinker quality index, low production capacity and high cost.

Contents of the invention

The present invention aims to overcome the defects of the prior art, and aims to provide a rotary kiln firing state identification method based on flame image structure similarity that has high precision, low computational complexity, short processing process and can realize online real-time monitoring.

For accomplishing above-mentioned task, the concrete steps of the technical solution that the present invention adopts are:

The first step, the standard flame image Q is calibrated by the rotary kiln operation experts; the standard flame image Q constitutes the standard flame library L, the standard flame library L is divided into the normal flame library LN and the abnormal flame library LA, the normal flame library LN consists of a normal state The abnormal flame image library LA is composed of b pieces of standard flame images Q in an abnormal state; the standard flame image Q is filtered and grayscale transformed to obtain the standard flame grayscale image y; all standard flame grayscale images y constitutes the standard flame gray scale gallery F, and the standard flame gray scale gallery F is divided into the normal flame gray scale gallery FN and the abnormal flame grayscale gallery FA.

The second step is to obtain a flame image P to be tested from the collected flame video of the firing zone of the rotary kiln; filter and transform the flame image P to obtain a grayscale image x of the flame to be measured.

The third step is to use the calculation method of the average structural similarity coefficient to calculate the average structural similarity coefficient MSSIM(x, y) between a flame gray image x to be tested and each standard flame gray image y, and obtain a+b average structural similarity coefficients MSSIM(x,y).

The fourth step is to compare the a+b average structural similarity coefficients MSSIM(x, y) obtained in the third step, and select the maximum value of the average structural similarity coefficient MAXmssim; if the maximum value of the average structural similarity coefficient MAXmssim corresponds to If the standard flame grayscale image y belongs to the normal flame grayscale library FN, it is determined that the firing state of the flame image P to be tested is a normal state; if the standard flame grayscale image y corresponding to the maximum value of the average structural similarity coefficient MAXmssim belongs to the abnormal flame The grayscale library FA determines that the firing state of the flame image P to be tested is an abnormal state.

The fifth step, if it is judged that the firing state of the flame image P to be tested is normal, the recognition of the firing state of the next flame image is performed directly;

If it is determined that the firing state of the flame image P to be measured is abnormal, the system will alarm, and after the flame firing state of the rotary kiln is improved, the firing state of the next flame image will be recognized.

The sixth step, repeat the second to fifth steps until the end.

The a is a natural number from 1 to 1000; the b is a natural number from 1 to 1000.

The calculation method of the average structure similarity coefficient is as follows: the flame gray image x to be tested and the standard flame gray image y are moved pixel by pixel from the upper left corner to the lower right corner in a window of the same size to obtain M to be tested The flame gray image block x _j and M standard flame gray image blocks y _j , calculate the structural similarity coefficient SSIM between each flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j (x _j ,y _j ), get M structural similarity coefficients SSIM(x _j ,y _j ), and then accumulate and average the M structural similarity coefficients SSIM(x _j ,y _j ), to obtain the flame gray scale to be measured The average structural similarity coefficient MSSIM(x,y) of image x and standard flame grayscale image y:

$\mathrm{<span\; class="notranslate">\; MS\; SIM</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

In formula (1): SSIM(x _j , y _j ) is the structural similarity coefficient between the flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j :

$\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{<span\; class="notranslate">\; (</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; \&Center\; Dot;</span>\frac{{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; )</span>$

In formula (2): C ₁ =6.5025, C ₂ =58.5225;

u _{x, j} is the mean value of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 3</span>}<span\; class="notranslate">\; )</span>$

u _{y, j} is the mean value of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; )</span>$

σ _x,j is the standard deviation of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 5</span>}<span\; class="notranslate">\; )</span>$

σ _y,j is the standard deviation of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 6</span>}<span\; class="notranslate">\; )</span>$

σ _xy,j is the covariance between the standard flame gray image block y _j and the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 7</span>}<span\; class="notranslate">\; )</span>$

In formulas (3) to (7): N is the number of pixels of the flame gray image block x _j to be tested and the standard flame gray image block y _j ;

x _{j, i} is the value of the i-th pixel of the flame gray image block x _j to be tested;

y _j,i is the value of the i-th pixel of the standard flame gray image block y _j .

Owing to adopting above-mentioned technical scheme, the present invention has following advantage compared with prior art:

In the technical field of rotary kiln flame image recognition, the present invention adopts the structural similarity index for the first time, and judges the firing state of the rotary kiln from three different angles of brightness, contrast and structure, and the discrimination accuracy is high; in addition, the method belongs to a more An image quality evaluation method that conforms to the basic principles of the human visual system, and the judgment results are more in line with subjective evaluation.

The discriminant method used in the present invention does not require special training and learning of the flame image, which greatly reduces the computational complexity and shortens the processing time.

The present invention can independently judge the firing state of a single flame image, meets the conditions for online real-time monitoring of flame changes in the rotary kiln, can detect changes in the firing state of the flame in the rotary kiln in a very short time, and make corresponding adjustments in time, thereby Increase the safety and reliability of the rotary kiln control system, make the quality of the clinker produced more stable, greatly reduce the cost of industrial production, and lay the foundation for the realization of closed-loop control for real-time monitoring of the entire rotary kiln system, and for the real realization of " "Machine watching the fire" instead of "manual watching the fire" provides a basic guarantee.

Therefore, the present invention has the characteristics of high precision, low computational complexity, short processing process and the ability to realize online real-time monitoring of flame state changes.

Description of drawings

Below in conjunction with accompanying drawing and embodiment the present invention is described in further detail:

Fig. 1 is a kind of flowchart of the present invention;

Fig. 2 is the flame image P to be measured in embodiment 1;

Fig. 3 is the flame grayscale image x to be measured in embodiment 1;

Fig. 4 is the flame image P to be measured in embodiment 2;

Fig. 5 is the flame grayscale image x to be measured in embodiment 2;

Fig. 6 is the flame image P to be measured in embodiment 3;

Fig. 7 is the flame grayscale image x to be measured in embodiment 3;

Fig. 8 is the flame image P to be measured in embodiment 4;

FIG. 9 is the grayscale image x of the flame to be tested in Example 4.

detailed description

Below in conjunction with accompanying drawing and specific embodiment, the present invention will be further described, not limitation to its protection scope:

Example 1

A method for identifying the firing state of an alumina rotary kiln based on the structural similarity of flame images. The specific steps of the rotary kiln firing state identification method are shown in Figure 1:

The first step, the standard flame image Q is calibrated by alumina rotary kiln operation experts, and the size of the standard flame image Q is 512×384×3. The standard flame image Q constitutes the standard flame image library L, and the standard flame image library L is divided into the normal flame image library LN and the abnormal flame image image library LA. The standard flame image Q is composed of the standard flame image Q; the standard flame image Q is filtered and grayscale transformed to obtain the standard flame grayscale image y; all the standard flame grayscale images y form the standard flame grayscale library F, and the standard flame grayscale library F is divided into It is the normal flame gray scale gallery FN and the abnormal flame gray scale gallery FA.

The filtering extracts the low-pass part for wavelet decomposition.

The y size of the standard flame grayscale image is 256×192.

The second step is to obtain a color image P of the flame to be tested as shown in Figure 2 from the collected flame video of the alumina rotary kiln. The image P is subjected to wavelet decomposition to extract the low-pass part and grayscale transformation to obtain the grayscale image x of the flame to be tested with a size of 256×192 as shown in Figure 3 .

The third step is to use the calculation method of the average structural similarity coefficient to calculate the average structural similarity coefficient MSSIM(x, y) between a flame gray image x to be tested and each standard flame gray image y, and obtain The 20 average structural similarity coefficients MSSIM(x, y) between the flame gray image x to be tested and the 20 standard flame gray images y in the normal flame gray library FN, and the flame gray image to be tested are obtained at the same time 20 average structural similarity coefficients MSSIM(x,y) between the high-degree image x and the 20 standard flame gray-scale images y in the abnormal flame gray-scale library FA.

The 40 average structural similarity coefficients MSSIM(x,y) are shown in Table 1.

Table 1

The fourth step, according to Table 1, compares the 40 average structural similarity coefficients MSSIM(x, y) obtained in the third step, and selects the maximum value of the average structural similarity coefficient MAXmssim as 0.6238. Since the standard flame grayscale image y corresponding to the maximum value of the average structural similarity coefficient MAXmssim belongs to the normal flame grayscale library FN, it is determined that the firing state of the flame image P to be tested is a normal state.

The fifth step, if it is judged that the firing state of the flame image P to be tested is normal, the recognition of the firing state of the next flame image is performed directly;

If it is determined that the firing state of the flame image P to be measured is abnormal, the system will alarm, and after the flame firing state of the rotary kiln is improved, the firing state of the next flame image will be recognized.

Since the firing state of the flame image P to be measured is determined to be a normal state, the recognition of the firing state of the next flame image is performed directly.

The sixth step, repeat the second to fifth steps until the end.

The calculation method of the average structural similarity coefficient described in this embodiment is as follows: the flame gray image x to be tested and the standard flame gray image y are respectively moved pixel by pixel from the upper left corner to the lower right corner in a 4×4 window to obtain 193929 flame gray image blocks x _j to be tested and 193929 standard flame gray image blocks y _j , calculate the structure between each flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j Similarity coefficient SSIM(x _j ,y _j ), to get 193929 structural similarity coefficients SSIM(x _j ,y _j ), and then accumulate and average the 193929 structural similarity coefficients SSIM(x _j ,y _j ), to obtain The average structural similarity coefficient MSSIM(x,y) of the measured flame grayscale image x and the standard flame grayscale image y:

$\mathrm{<span\; class="notranslate">\; MS\; SIM</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

In formula (1): M=193929;

SSIM(x _j ,y _j ) is the structural similarity coefficient of the flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j :

$\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{<span\; class="notranslate">\; (</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; \&Center\; Dot;</span>\frac{{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; )</span>$

In formula (2): C ₁ =6.5025, C ₂ =58.5225;

u _x,j is the mean value of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 3</span>}<span\; class="notranslate">\; )</span>$

u _{y, j} is the mean value of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; )</span>$

σ _x,j is the standard deviation of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 5</span>}<span\; class="notranslate">\; )</span>$

σ _y,j is the standard deviation of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 6</span>}<span\; class="notranslate">\; )</span>$

σ _xy,j is the covariance between the standard flame gray image block y _j and the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 7</span>}<span\; class="notranslate">\; )</span>$

In the formulas (3) to (7): N=16, which is the number of pixel points of the flame gray image block x _j to be tested and the standard flame gray image block y _j ;

x _{j, i} is the value of the i-th pixel of the flame gray image block x _j to be tested;

y _j,i is the value of the i-th pixel of the standard flame gray image block y _j .

Example 2

A method for identifying the firing state of an alumina rotary kiln based on the structural similarity of flame images. The specific steps of the rotary kiln firing state identification method are shown in Figure 1:

The first step, the filtering described in this step is filtering with a 20-order Butterworth low-pass filter; the size of the standard flame gray image y is 512×384. All the other are the same as the first step of embodiment 1.

The second step is to obtain a color flame image P to be tested as shown in Figure 4 from the collected flame video of the alumina rotary kiln. The size of the flame image P to be tested is 512×384×3; The image P is filtered with a 20-order Butterworth low-pass filter and subjected to grayscale transformation, and the grayscale image x of the flame to be tested with a size of 512×384 is obtained as shown in Figure 5 .

The third step, this step is the same as the third step of Embodiment 1 except that the 40 average structure similarity coefficients MSSIM(x, y) are shown in Table 2.

Table 2

The fourth step, as shown in Table 2, compares the 40 average structural similarity coefficients MSSIM(x, y) obtained in the third step, and selects the maximum value of the average structural similarity coefficient MAXmssim as 0.6439. Since the standard flame grayscale image y corresponding to the maximum value of the average structural similarity coefficient MAXmssim belongs to the abnormal flame grayscale library FA, it is determined that the firing state of the flame image P to be tested is an abnormal state.

The fifth step, if it is judged that the firing state of the flame image P to be tested is normal, the recognition of the firing state of the next flame image is performed directly;

If it is judged that the firing state of the flame image P to be measured is abnormal, the system will give an alarm, and after the flame firing state of the rotary kiln is improved, the recognition of the firing state of the next flame image will be carried out.

Since the firing state of the flame image P to be measured is judged to be abnormal, the system alarms, and after the flame firing state of the rotary kiln is improved, the firing state of the next flame image is identified.

The sixth step, repeat the second to fifth steps until the end.

The calculation method of the average structure similarity coefficient described in this embodiment is as follows: the flame gray image x to be tested and the standard flame gray image y are moved pixel by pixel from the upper left corner to the lower right corner in an 8×8 window to obtain 190385 flame gray image blocks x _j to be tested and 190385 standard flame gray image blocks y _j , calculate the structure between each flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j Similarity coefficient SSIM(x _j ,y _j ), to get 190385 structural similarity coefficients SSIM(x _j ,y _j ), and then accumulate and average the 190385 structural similarity coefficients SSIM(x _j ,y _j ), to obtain The average structural similarity coefficient MSSIM(x,y) of the measured flame grayscale image x and the standard flame grayscale image y:

$\mathrm{<span\; class="notranslate">\; MS\; SIM</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

In formula (1): M=190385;

SSIM(x _j ,y _j ) is the structural similarity coefficient of the flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j :

$\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{<span\; class="notranslate">\; (</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; \&Center\; Dot;</span>\frac{{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; )</span>$

In formula (2): C ₁ =6.5025, C ₂ =58.5225;

u _x,j is the mean value of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 3</span>}<span\; class="notranslate">\; )</span>$

u _{y, j} is the mean value of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; )</span>$

σ _x,j is the standard deviation of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 5</span>}<span\; class="notranslate">\; )</span>$

σ _{y, j} is the standard deviation of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 6</span>}<span\; class="notranslate">\; )</span>$

σ _xy,j is the covariance between the standard flame gray image block y _j and the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 7</span>}<span\; class="notranslate">\; )</span>$

In formulas (3) to (7): N=64, which is the number of pixels of the flame gray image block x _j to be tested and the standard flame gray image block y _j ;

x _{j, i} is the value of the i-th pixel of the flame gray image block x _j to be tested;

y _j,i is the value of the i-th pixel of the standard flame gray image block y _j .

Example 3

A method for identifying the firing state of a cement rotary kiln based on the structural similarity of flame images. The specific steps of the rotary kiln firing state identification method are shown in Figure 1:

The first step, the standard flame image Q is calibrated by cement rotary kiln operation experts, and the size of the standard flame image Q is 352×288×3. The standard flame image Q constitutes the standard flame image library L, and the standard flame image library L is divided into the normal flame image library LN and the abnormal flame image image library LA. The standard flame image Q is composed of the standard flame image Q; the standard flame image Q is filtered and grayscale transformed to obtain the standard flame grayscale image y; all the standard flame grayscale images y form the standard flame grayscale library F, and the standard flame grayscale library F is divided into It is the normal flame gray scale gallery FN and the abnormal flame gray scale gallery FA.

The filtering is threshold filtering.

The size of the standard flame grayscale image y is 352×288.

The second step is to obtain a color flame image P to be tested as shown in Figure 6 from the collected flame video of the cement rotary kiln. The size of the flame image P to be tested is 352×288×3; P performs threshold filtering and grayscale transformation to obtain a flame grayscale image x with a size of 352×288 as shown in Figure 7 .

The third step is to use the calculation method of the average structural similarity coefficient to calculate the average structural similarity coefficient MSSIM(x, y) between a flame gray image x to be tested and each standard flame gray image y, and obtain The 15 average structural similarity coefficients MSSIM(x, y) between the flame gray image x to be tested and the 15 standard flame gray images y in the normal flame gray library FN, and the flame gray image to be tested are obtained at the same time 10 average structural similarity coefficients MSSIM(x,y) between the high-degree image x and the standard flame gray-scale image y in the 10 abnormal flame gray-scale image library FA.

The 25 average structural similarity coefficients MSSIM(x,y) are shown in Table 3.

table 3

In the fourth step, according to Table 3, compare the 25 average structural similarity coefficients MSSIM(x, y) obtained in the third step, and select the maximum value of the average structural similarity coefficient MAXmssim as 0.7616. Since the standard flame grayscale image y corresponding to the maximum value of the average structural similarity coefficient MAXmssim belongs to the normal flame grayscale library FN, it is determined that the firing state of the flame image P to be tested is a normal state.

The 5th step, with the 5th step of embodiment 1.

The 6th step, with the 6th step of embodiment 1.

The calculation method of the average structure similarity coefficient is as follows: the flame gray image x to be tested and the standard flame gray image y are moved pixel by pixel from the upper left corner to the lower right corner in a window of 11×11, and 95076 flame gray images to be tested are obtained. Measure the flame gray image block x _j and 95076 standard flame gray image blocks y _j , and calculate the structural similarity coefficient between each flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j SSIM(x _j ,y _j ), get 95076 structural similarity coefficients SSIM(x _j ,y _j ), and then accumulate and average the 95076 structural similarity coefficients SSIM(x _j ,y _j ), get the flame ash to be tested The average structural similarity coefficient MSSIM(x,y) of the degree image x and the standard flame gray image y:

$\mathrm{<span\; class="notranslate">\; MS\; SIM</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

In formula (1): M=95076;

SSIM(x _j ,y _j ) is the structural similarity coefficient of the flame gray image block x _j to be tested and the corresponding standard flame gray image block y _j :

$\mathrm{<span\; class="notranslate">\; SSIM</span>}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; ,</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span>\frac{{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{<span\; class="notranslate">\; (</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; \&Center\; Dot;</span>\frac{{\mathrm{<span\; class="notranslate">\; 2</span>}\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; C</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; )</span>$

In formula (2): C ₁ =6.5025, C ₂ =58.5225;

u _x,j is the mean value of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 3</span>}<span\; class="notranslate">\; )</span>$

u _{y, j} is the mean value of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; )</span>$

σ _x,j is the standard deviation of the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 5</span>}<span\; class="notranslate">\; )</span>$

σ _y,j is the standard deviation of the standard flame gray image block y _j :

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>{<span\; class="notranslate">\; (</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 6</span>}<span\; class="notranslate">\; )</span>$

σ _xy,j is the covariance between the standard flame gray image block y _j and the flame gray image block x _j to be tested:

${\mathrm{<span\; class="notranslate">\; \&sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; xy</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; u</span>}}_{\mathrm{<span\; class="notranslate">\; the\; y</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 7</span>}<span\; class="notranslate">\; )</span>$

In the formulas (3) to (7): N=121, which is the number of pixels of the flame gray image block x _j to be tested and the standard flame gray image block y _j ;

x _{j, i} is the value of the i-th pixel of the flame gray image block x _j to be tested;

y _j,i is the value of the i-th pixel of the standard flame gray image block y _j .

Example 4

A method for identifying the firing state of a cement rotary kiln based on the structural similarity of flame images. The specific steps of the rotary kiln firing state identification method are shown in Figure 1:

The first step, the filtering described in this step is to extract the region of interest; the size of the standard flame grayscale image y is 225×189. All the other are the same as the first step of embodiment 3.

The second step is to obtain a color flame image P to be tested as shown in Figure 8 from the collected flame video of the cement rotary kiln. The size of the flame image P to be tested is 352×288×3; P conducts region-of-interest extraction and grayscale transformation to obtain a grayscale image x of the flame to be tested with a size of 225×189 as shown in Figure 9 .

The third step, this step is the same as the third step of embodiment 3 except that 25 average structure similarity coefficients MSSIM(x, y) are shown in Table 4.

Table 4

The fourth step, as shown in Table 4, compares the 25 average structural similarity coefficients MSSIM(x, y) obtained in the third step, and selects the maximum value of the average structural similarity coefficient MAXmssim as 0.7720. Since the standard flame grayscale image y corresponding to the maximum value of the average structural similarity coefficient MAXmssim belongs to the abnormal flame grayscale library FA, it is determined that the firing state of the flame image P to be tested is an abnormal state.

The 5th step, with the 5th step of embodiment 2.

The 6th step, with the 6th step of embodiment 2.

The calculation method of the average structure similarity coefficient is the same as the calculation method of the average structure similarity coefficient in Example 3.

Compared with the prior art, this specific embodiment has the following advantages:

This specific embodiment adopts structural similarity index for the first time in the technical field of rotary kiln flame image recognition, and judges the firing state of the rotary kiln from three different angles of brightness, contrast and structure, and the discrimination accuracy is high; in addition, the method belongs to a An image quality evaluation method that is more in line with the basic principles of the human visual system, and the judgment results are more in line with subjective evaluation.

The discrimination method used in this specific embodiment does not require special training and learning of the flame image, which greatly reduces the computational complexity and shortens the processing time.

This specific embodiment can independently judge the firing state of a single flame image, meet the conditions for online real-time monitoring of flame changes in the rotary kiln, and can detect changes in the firing state of the rotary kiln flame in a very short period of time, and make corresponding adjustments in time , so as to increase the safety and reliability of the rotary kiln control system, make the quality of the clinker produced more stable, greatly reduce the cost of industrial production, and lay the foundation for the realization of closed-loop control for real-time monitoring of the entire rotary kiln system. The basic guarantee is provided by "machine watching fire" instead of "manual fire watching".

Therefore, this specific embodiment has the characteristics of high precision, low computational complexity, short processing process and the ability to realize online real-time monitoring of flame state changes.

Claims (3)

1. the rotary kiln based on flame image structural similarity burns till a state identification method, and described rotary kiln burns till state recognitionThe concrete steps of method:

The first step, standard flame source image Q are demarcated by kiln operation expert; Standard flame source image Q composition standard flame source picture library L,Standard flame source picture library L is divided into normal flame picture library LN and abnormal flame picture library LA, and normal flame picture library LN is by the normal shape of a widthThe standard flame source image Q composition of state, abnormal flame picture library LA is made up of the standard flame source image Q of b width abnormality; To markAccurate flame image Q carries out filtering processing and greyscale transformation, obtains standard flame source gray level image y; All standard flame source gray level imagesY composition standard flame source gray scale picture library F, standard flame source gray scale picture library F is divided into normal flame gray scale picture library FN and abnormal flame gray scalePicture library FA;

It is characterized in that:

Second step, from the flame video of rotary kiln clinkering zone gathering, obtain a flame image P to be measured; By flame figure to be measuredCarry out filtering processing and greyscale transformation as P, obtain flame gray level image x to be measured;

The computational methods of the 3rd step, employing average structure likeness coefficient, calculate a flame gray level image x to be measured and each widthAverage structure likeness coefficient MSSIM (x, y) between standard flame source gray level image y, obtains a+b average structure similitude systemNumber MSSIM (x, y);

The 4th step, a+b the average structure likeness coefficient MSSIM (x, y) that the 3rd step is obtained compare, and choose average knotStructure likeness coefficient maximum MAXmssim; If the corresponding standard of average structure likeness coefficient maximum MAXmssimFlame gray level image y belongs to normal flame gray scale picture library FN, and the state that burns till of judging flame image P to be measured is normal condition;If the corresponding standard flame source gray level image of average structure likeness coefficient maximum MAXmssim y belongs to abnormal flame gray scalePicture library FA, the state that burns till of judging flame image P to be measured is abnormality;

If it is normal condition that the 5th step is judged the state that burns till of flame image P to be measured, directly carries out next width flame image and burn tillThe identification of state;

If judge, the state that burns till of flame image P to be measured is abnormality, and system alarm, improves rotary kiln flame and burn till after state,Carry out again the identification that next width flame image burns till state;

The 6th step, repetition the second～five step, until finish.

2. burn till state identification method according to the rotary kiln based on flame image structural similarity claimed in claim 1, its featureBe that described a is 1～1000 natural number; Described b is 1～1000 natural number.

3. burn till state identification method according to the rotary kiln based on flame image structural similarity claimed in claim 1, its featureThe computational methods that are described average structure likeness coefficient are: by flame gray level image x to be measured and standard flame source gray level imageY respectively with the window of formed objects by pixel move to the lower right corner from the upper left corner, obtain M flame gray level image piece x to be measured_jWith M standard flame source gray level image piece y_j, calculate each flame gray level image piece x to be measured_jWith corresponding standard flame source gray-scale mapPicture piece y_jBetween structural similarity coefficient S SIM (x_j,y_j), obtain M structural similarity coefficient S SIM (x_j,y_j); Then rightM structural similarity coefficient S SIM (x_j,y_j) carry out cumulative mean, obtain flame gray level image x to be measured and standard flame source gray-scale mapThe average structure likeness coefficient MSSIM (x, y) of picture y:

$MSSIM(x,y)=\frac{1}{M}\underset{j=1}{\overset{M}{\&Sigma;}}SSIM(x_j,y_j)---\left(1\right)$

In formula (1): SSIM (x_j,y_j) be flame gray level image piece x to be measured_jWith corresponding standard flame source gray level image piece y_jKnotStructure likeness coefficient:

$SSIM(x_j,y_j)=\frac{{(2u_{x,j}{u}_{y,j}+C_1)}^2}{{({u_{x,j}}^2+{u_{y,j}}^2+C_2)}^2}\&CenterDot;\frac{2{\mathrm{\&sigma;}}_{xy,j}+C_2}{{{\mathrm{\&sigma;}}_{x,j}}^2+{{\mathrm{\&sigma;}}_{y,j}}^2+C_2}---\left(2\right)$

In formula (2): C₁＝6.5025，C₂＝58.5225；

u_x,jFor flame gray level image piece x to be measured_jAverage:

$u_{x,j}=\frac{1}{N}\underset{i=1}{\overset{N}{\&Sigma;}}{x}_{j,i}---\left(3\right)$

u_y,jFor standard flame source gray level image piece y_jAverage:

$u_{y,j}=\frac{1}{N}\underset{i=1}{\overset{N}{\&Sigma;}}{y}_{j,i}---\left(4\right)$

σ_x,jFor flame gray level image piece x to be measured_jStandard deviation:

${\mathrm{\&sigma;}}_{x,j}={\left(\frac{1}{N-1}\underset{i=1}{\overset{N}{\&Sigma;}}{\left(x_{j,i}-u_{x,j}\right)}^2\right)}^{1/2}---\left(5\right)$

σ_y,jFor standard flame source gray level image piece y_jStandard deviation:

${\mathrm{\&sigma;}}_{y,j}={\left(\frac{1}{N-1}\underset{i=1}{\overset{N}{\&Sigma;}}{\left(y_{j,i}-u_{y,j}\right)}^2\right)}^{1/2}---\left(6\right)$

σ_xy,jFor standard flame source gray level image piece y_jWith flame gray level image piece x to be measured_jBetween covariance:

${\mathrm{\&sigma;}}_{xy,j}=\frac{1}{N-1}\underset{i=1}{\overset{N}{\&Sigma;}}(x_{j,i}-u_{x,j})(y_{j,i}-u_{y,j})---\left(7\right)$

In formula (3)～(7): N is flame gray level image piece x to be measured_jWith standard flame source gray level image piece y_jPixel number;

x_j,iFor flame gray level image piece x to be measured_jThe value of i pixel;

y_j,iFor standard flame source gray level image piece y_jThe value of i pixel.