CN103578111B - Rotary kiln based on flame image structural similarity burns till state identification method - Google Patents
Rotary kiln based on flame image structural similarity burns till state identification method Download PDFInfo
- Publication number
- CN103578111B CN103578111B CN201310567666.0A CN201310567666A CN103578111B CN 103578111 B CN103578111 B CN 103578111B CN 201310567666 A CN201310567666 A CN 201310567666A CN 103578111 B CN103578111 B CN 103578111B
- Authority
- CN
- China
- Prior art keywords
- flame
- image
- standard
- gray level
- sigma
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 230000005856 abnormality Effects 0.000 claims 3
- 238000000205 computational method Methods 0.000 claims 2
- 230000001186 cumulative effect Effects 0.000 claims 1
- 238000010304 firing Methods 0.000 abstract description 48
- 238000004364 calculation method Methods 0.000 abstract description 10
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 7
- PNEYBMLMFCGWSK-UHFFFAOYSA-N aluminium oxide Inorganic materials [O-2].[O-2].[O-2].[Al+3].[Al+3] PNEYBMLMFCGWSK-UHFFFAOYSA-N 0.000 description 5
- 239000004568 cement Substances 0.000 description 5
- 238000002485 combustion reaction Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000004566 building material Substances 0.000 description 1
- 238000001354 calcination Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Landscapes
- Radiation Pyrometers (AREA)
Abstract
本发明涉及一种基于火焰图像结构相似性的回转窑烧成状态识别方法。其技术方案是,设定标准火焰灰度图像y、正常火焰灰度图库FN和异常火焰灰度图库FA。获取待测火焰图像P,对待测火焰图像P进行滤波和灰度变换,得到待测火焰灰度图像x;将待测火焰灰度图像x与所有标准火焰灰度图像y进行平均结构相似性系数计算,得到a+b个平均结构相似性系数MSSIM(x,y);取平均结构相似性系数最大值MAXmssim,若平均结构相似性系数最大值MAXmssim所对应的标准火焰灰度图像y属于正常火焰灰度图库FN,待测火焰图像P属于正常状态;反之属于异常状态。本发明具有精度高、计算复杂度低、处理过程短和能实现在线实时监测火焰状态变化的特点。
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
技术领域technical field
本发明属于回转窑烧成状态识别的技术领域。特别涉及一种基于火焰图像结构相似性的回转窑烧成状态识别方法。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.
背景技术Background technique
回转窑是煅烧或焙烧及其他方式加工各种工业原料工艺中所用的热工设备,用于对输入的物料进行机械、物理或化学处理,在建材、化工、冶金等行业中有着广泛的应用。受回转窑结构的特殊性和工艺复杂性的影响,所得熟料质量指标难以在线测量,熟料的烧成状态也难以准确识别,加上回转窑过程的多变量强耦合特性以及不确定干扰等因素,使得回转窑运转过程仍然处于“人工看火”的开环操作阶段,难以实现回转窑控制系统的自动控制,长期运行易造成熟料质量指标不稳定、产能低、能耗高和人工劳动强度大等问题。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.
火焰图像是燃烧过程的有效反应,亮度信息反映了燃烧过程中的辐射热度和燃烧效果,火焰形状则反映了燃烧反应发生区域的形状。因此,利用合理的技术判断火焰图像的烧成状态,从而确定回转窑的运行状态和燃烧稳定性,具有十分重要的意义。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.
近年来,回转窑烧成状态识别技术的研究热点之一是数字图像处理技术。经过图像预处理、图像分割后对图像进行特征提取和选取,将所提取和选取的图像特征送入模式分类器中进行目标的模式识别,从而判定火焰烧成状态。到目前为止,众多学者对数字图像处理的各个模块都做了大量且深入的研究,运用数字图像处理技术判断火焰图像烧成状态的识别方法虽有识别精度高、算法多样且成熟的优点,但这类方法不可避免的存在着计算复杂度高、处理时间长、无法在线实时监测的缺陷,没有从根本上改变“人工看火”的模式,并且影响回转窑控制系统的安全性和可靠性,引起熟料质量指标不稳定、产能低和成本高等一系列问题。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.
发明内容Contents of the invention
本发明旨在克服现有技术缺陷,目的是提供一种精度高、计算复杂度低、处理过程短和能实现在线实时监测的基于火焰图像结构相似性的回转窑烧成状态识别方法。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.
为完成上述任务,本发明采用的技术方案的具体步骤是:For accomplishing above-mentioned task, the concrete steps of the technical solution that the present invention adopts are:
第一步、标准火焰图像Q由回转窑操作专家标定;标准火焰图像Q组成标准火焰图库L,标准火焰图库L分为正常火焰图库LN和异常火焰图库LA,正常火焰图库LN由a幅正常状态的标准火焰图像Q组成,异常火焰图库LA由b幅异常状态的标准火焰图像Q组成;将标准火焰图像Q进行滤波处理和灰度变换,得到标准火焰灰度图像y;所有标准火焰灰度图像y组成标准火焰灰度图库F,标准火焰灰度图库F分为正常火焰灰度图库FN和异常火焰灰度图库FA。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.
第二步、从采集的回转窑烧成带的火焰视频中获取一幅待测火焰图像P;将待测火焰图像P进行滤波处理和灰度变换,得到待测火焰灰度图像x。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.
第三步、采用平均结构相似性系数的计算方法,计算一幅待测火焰灰度图像x与每一幅标准火焰灰度图像y之间的平均结构相似性系数MSSIM(x,y),得到a+b个平均结构相似性系数MSSIM(x,y)。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).
第四步、对第三步得到的a+b个平均结构相似性系数MSSIM(x,y)进行比较,选取平均结构相似性系数最大值MAXmssim;如果平均结构相似性系数最大值MAXmssim所对应的标准火焰灰度图像y属于正常火焰灰度图库FN,则判定待测火焰图像P的烧成状态为正常状态;如果平均结构相似性系数最大值MAXmssim所对应的标准火焰灰度图像y属于异常火焰灰度图库FA,则判定待测火焰图像P的烧成状态为异常状态。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.
第五步、若判定待测火焰图像P的烧成状态为正常状态,直接进行下一幅火焰图像烧成状态的识别;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;
若判定待测火焰图像P的烧成状态为异常状态,系统报警,改善回转窑火焰烧成状态后,再进行下一幅火焰图像烧成状态的识别。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.
第六步、重复第二~第五步,直至结束。The sixth step, repeat the second to fifth steps until the end.
所述a为1~1000的自然数;所述b为1~1000的自然数。The a is a natural number from 1 to 1000; the b is a natural number from 1 to 1000.
所述的平均结构相似性系数的计算方法是:将待测火焰灰度图像x和标准火焰灰度图像y分别以相同大小的窗口逐像素地从左上角向右下角移动,得到M个待测火焰灰度图像块xj和M个标准火焰灰度图像块yj,计算每个待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj之间的结构相似性系数SSIM(xj,yj),得到M个结构相似性系数SSIM(xj,yj),然后对M个结构相似性系数SSIM(xj,yj)进行累加平均,得到待测火焰灰度图像x和标准火焰灰度图像y的平均结构相似性系数MSSIM(x,y):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:
式(1)中:SSIM(xj,yj)为待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj的结构相似性系数: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 :
式(2)中:C1=6.5025,C2=58.5225;In formula (2): C 1 =6.5025, C 2 =58.5225;
ux,j为待测火焰灰度图像块xj的均值:u x, j is the mean value of the flame gray image block x j to be tested:
uy,j为标准火焰灰度图像块yj的均值:u y, j is the mean value of the standard flame gray image block y j :
σx,j为待测火焰灰度图像块xj的标准差:σ x,j is the standard deviation of the flame gray image block x j to be tested:
σy,j为标准火焰灰度图像块yj的标准差:σ y,j is the standard deviation of the standard flame gray image block y j :
σxy,j为标准火焰灰度图像块yj与待测火焰灰度图像块xj之间的协方差: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:
式(3)~(7)中:N为待测火焰灰度图像块xj和标准火焰灰度图像块yj像素点个数;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 ;
xj,i为待测火焰灰度图像块xj的第i个像素点的值;x j, i is the value of the i-th pixel of the flame gray image block x j to be tested;
yj,i为标准火焰灰度图像块yj的第i个像素点的值。y j,i is the value of the i-th pixel of the standard flame gray image block y j .
由于采用上述技术方案,本发明与现有技术相比具有如下优点:Owing to adopting above-mentioned technical scheme, the present invention has following advantage compared with prior art:
本发明首次在回转窑火焰图像识别的技术领域中采用结构相似性指标,从亮度、对比度和结构三种不同角度来判别回转窑烧成状态,判别精度较高;另外,该方法属于一种更符合人眼视觉系统基本原理的图像质量评价方法,判别结果更贴合主观评价。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.
本发明所运用的判别方法无需对火焰图像进行特殊训练和学习,大大降低了计算复杂度,缩小了处理时长。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.
本发明能够独立判别单幅火焰图像的烧成状态,满足在线实时监测回转窑中火焰变化的条件,能在极短的时间内发现回转窑火焰烧成状态的变化,并及时作出相应调整,从而增加回转窑控制系统的安全性和可靠性,使生产的熟料质量更加稳定,能够极大的缩减工业生产成本,为实现对整个回转窑系统实时监控的闭环控制奠定基础,为真正实现以“机器看火”代替“人工看火”提供了基本保障。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.
因此,本发明具有精度高、计算复杂度低、处理过程短和能实现在线实时监测火焰状态变化的特点。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.
附图说明Description of drawings
下面结合附图及实施方式对本发明作进一步详细说明:Below in conjunction with accompanying drawing and embodiment the present invention is described in further detail:
图1为本发明的一种流程图;Fig. 1 is a kind of flowchart of the present invention;
图2为实施例1中的待测火焰图像P;Fig. 2 is the flame image P to be measured in embodiment 1;
图3为实施例1中的待测火焰灰度图像x;Fig. 3 is the flame grayscale image x to be measured in embodiment 1;
图4为实施例2中的待测火焰图像P;Fig. 4 is the flame image P to be measured in embodiment 2;
图5为实施例2中的待测火焰灰度图像x;Fig. 5 is the flame grayscale image x to be measured in embodiment 2;
图6为实施例3中的待测火焰图像P;Fig. 6 is the flame image P to be measured in embodiment 3;
图7为实施例3中的待测火焰灰度图像x;Fig. 7 is the flame grayscale image x to be measured in embodiment 3;
图8为实施例4中的待测火焰图像P;Fig. 8 is the flame image P to be measured in embodiment 4;
图9为实施例4中的待测火焰灰度图像x。FIG. 9 is the grayscale image x of the flame to be tested in Example 4.
具体实施方式detailed description
下面结合附图和具体实施方式对本发明作进一步的描述,并非对其保护范围的限制:Below in conjunction with accompanying drawing and specific embodiment, the present invention will be further described, not limitation to its protection scope:
实施例1Example 1
一种基于火焰图像结构相似性的氧化铝回转窑烧成状态识别方法。该回转窑烧成状态识别方法的具体步骤如图1所示: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:
第一步、标准火焰图像Q由氧化铝回转窑操作专家标定,标准火焰图像Q的尺寸为512×384×3。标准火焰图像Q组成标准火焰图库L,标准火焰图库L分为正常火焰图库LN和异常火焰图库LA,正常火焰图库LN由20幅正常状态的标准火焰图像Q组成,异常火焰图库LA由20幅异常状态的标准火焰图像Q组成;将标准火焰图像Q进行滤波和灰度变换,得到标准火焰灰度图像y;所有标准火焰灰度图像y组成标准火焰灰度图库F,标准火焰灰度图库F分为正常火焰灰度图库FN和异常火焰灰度图库FA。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.
所述滤波为小波分解提取低通部分。The filtering extracts the low-pass part for wavelet decomposition.
所述标准火焰灰度图像y尺寸为256×192。The y size of the standard flame grayscale image is 256×192.
第二步、从采集的氧化铝回转窑烧成带火焰视频中获取一幅如图2所示的彩色待测火焰图像P,待测火焰图像P尺寸为512×384×3;将待测火焰图像P进行小波分解提取低通部分和灰度变换,得到如图3所示的尺寸为256×192的待测火焰灰度图像x。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 .
第三步、采用平均结构相似性系数的计算方法,计算一幅待测火焰灰度图像x与每一幅标准火焰灰度图像y之间的平均结构相似性系数MSSIM(x,y),得到该幅待测火焰灰度图像x与20幅正常火焰灰度图库FN中标准火焰灰度图像y之间的20个平均结构相似性系数MSSIM(x,y),同时得到该幅待测火焰灰度图像x与20幅异常火焰灰度图库FA中标准火焰灰度图像y之间的20个平均结构相似性系数MSSIM(x,y)。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.
40个平均结构相似性系数MSSIM(x,y)如表1所示。The 40 average structural similarity coefficients MSSIM(x,y) are shown in Table 1.
表1Table 1
第四步、根据表1所示,对第三步得到的40个平均结构相似性系数MSSIM(x,y)进行比较,选取平均结构相似性系数最大值MAXmssim为0.6238。由于平均结构相似性系数最大值MAXmssim所对应的标准火焰灰度图像y属于正常火焰灰度图库FN,则判定待测火焰图像P的烧成状态为正常状态。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.
第五步、若判定待测火焰图像P的烧成状态为正常状态,直接进行下一幅火焰图像烧成状态的识别;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;
若判定待测火焰图像P的烧成状态为异常状态,系统报警,改善回转窑火焰烧成状态后,再进行下一幅火焰图像烧成状态的识别。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.
由于本幅待测火焰图像P的烧成状态判定为正常状态,故直接进行下一幅火焰图像烧成状态的识别。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.
第六步、重复第二~第五步,直至结束。The sixth step, repeat the second to fifth steps until the end.
本实施例所述的平均结构相似性系数的计算方法为:将待测火焰灰度图像x和标准火焰灰度图像y分别以4×4的窗口逐像素地从左上角向右下角移动,得到193929个待测火焰灰度图像块xj和193929个标准火焰灰度图像块yj,计算每个待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj之间的结构相似性系数SSIM(xj,yj),得到193929个结构相似性系数SSIM(xj,yj),然后对193929个结构相似性系数SSIM(xj,yj)进行累加平均,得到待测火焰灰度图像x和标准火焰灰度图像y的平均结构相似性系数MSSIM(x,y):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:
式(1)中:M=193929;In formula (1): M=193929;
SSIM(xj,yj)为待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj的结构相似性系数: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 :
式(2)中:C1=6.5025,C2=58.5225;In formula (2): C 1 =6.5025, C 2 =58.5225;
ux,j为待测火焰灰度图像块xj的均值:u x,j is the mean value of the flame gray image block x j to be tested:
uy,j为标准火焰灰度图像块yj的均值:u y, j is the mean value of the standard flame gray image block y j :
σx,j为待测火焰灰度图像块xj的标准差:σ x,j is the standard deviation of the flame gray image block x j to be tested:
σy,j为标准火焰灰度图像块yj的标准差:σ y,j is the standard deviation of the standard flame gray image block y j :
σxy,j为标准火焰灰度图像块yj与待测火焰灰度图像块xj之间的协方差: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:
式(3)~(7)中:N=16,为待测火焰灰度图像块xj和标准火焰灰度图像块yj像素点个数;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 ;
xj,i为待测火焰灰度图像块xj的第i个像素点的值;x j, i is the value of the i-th pixel of the flame gray image block x j to be tested;
yj,i为标准火焰灰度图像块yj的第i个像素点的值。y j,i is the value of the i-th pixel of the standard flame gray image block y j .
实施例2Example 2
一种基于火焰图像结构相似性的氧化铝回转窑烧成状态识别方法。该回转窑烧成状态识别方法的具体步骤如图1所示: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:
第一步、本步骤所述滤波为用20阶巴特沃斯低通滤波器滤波;所述标准火焰灰度图像y的尺寸为512×384。其余同实施例1第一步。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.
第二步、从采集的氧化铝回转窑烧成带火焰视频中获取一幅如图4所示的彩色待测火焰图像P,待测火焰图像P尺寸为512×384×3;将待测火焰图像P用20阶巴特沃斯低通滤波器滤波并进行灰度变换,得到如图5所示的尺寸为512×384的待测火焰灰度图像x。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 .
第三步、本步骤除40个平均结构相似性系数MSSIM(x,y)如表2所示外,其余同实施例1的第三步。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.
表2Table 2
第四步、根据表2所示,对第三步得到的40个平均结构相似性系数MSSIM(x,y)进行比较,选取平均结构相似性系数最大值MAXmssim为0.6439。由于平均结构相似性系数最大值MAXmssim所对应的标准火焰灰度图像y属于异常火焰灰度图库FA,则判定待测火焰图像P的烧成状态为异常状态。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.
第五步、若判定待测火焰图像P的烧成状态为正常状态,直接进行下一幅火焰图像烧成状态的识别;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;
若判定待测火焰图像P的烧成状态为异常状态,系统报警,改善回转窑火焰烧成状态后,再进行下一幅火焰图像烧成状态的识别。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.
由于本幅待测火焰图像P的烧成状态判定为异常状态,故系统报警,改善回转窑火焰烧成状态后,再进行下一幅火焰图像烧成状态的识别。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.
第六步、重复第二~第五步,直至结束。The sixth step, repeat the second to fifth steps until the end.
本实施例所述的平均结构相似性系数的计算方法为:将待测火焰灰度图像x和标准火焰灰度图像y分别以8×8的窗口逐像素地从左上角向右下角移动,得到190385个待测火焰灰度图像块xj和190385个标准火焰灰度图像块yj,计算每个待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj之间的结构相似性系数SSIM(xj,yj),得到190385个结构相似性系数SSIM(xj,yj),然后对190385个结构相似性系数SSIM(xj,yj)进行累加平均,得到待测火焰灰度图像x和标准火焰灰度图像y的平均结构相似性系数MSSIM(x,y):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:
式(1)中:M=190385;In formula (1): M=190385;
SSIM(xj,yj)为待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj的结构相似性系数: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 :
式(2)中:C1=6.5025,C2=58.5225;In formula (2): C 1 =6.5025, C 2 =58.5225;
ux,j为待测火焰灰度图像块xj的均值:u x,j is the mean value of the flame gray image block x j to be tested:
uy,j为标准火焰灰度图像块yj的均值:u y, j is the mean value of the standard flame gray image block y j :
σx,j为待测火焰灰度图像块xj的标准差:σ x,j is the standard deviation of the flame gray image block x j to be tested:
σy,j为标准火焰灰度图像块yj的标准差:σ y, j is the standard deviation of the standard flame gray image block y j :
σxy,j为标准火焰灰度图像块yj与待测火焰灰度图像块xj之间的协方差: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:
式(3)~(7)中:N=64,为待测火焰灰度图像块xj和标准火焰灰度图像块yj像素点个数;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 ;
xj,i为待测火焰灰度图像块xj的第i个像素点的值;x j, i is the value of the i-th pixel of the flame gray image block x j to be tested;
yj,i为标准火焰灰度图像块yj的第i个像素点的值。y j,i is the value of the i-th pixel of the standard flame gray image block y j .
实施例3Example 3
一种基于火焰图像结构相似性的水泥回转窑烧成状态识别方法。该回转窑烧成状态识别方法的具体步骤如图1所示: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:
第一步、标准火焰图像Q由水泥回转窑操作专家标定,标准火焰图像Q的尺寸为352×288×3。标准火焰图像Q组成标准火焰图库L,标准火焰图库L分为正常火焰图库LN和异常火焰图库LA,正常火焰图库LN由15幅正常状态的标准火焰图像Q组成,异常火焰图库LA由10幅异常状态的标准火焰图像Q组成;将标准火焰图像Q进行滤波和灰度变换,得到标准火焰灰度图像y;所有标准火焰灰度图像y组成标准火焰灰度图库F,标准火焰灰度图库F分为正常火焰灰度图库FN和异常火焰灰度图库FA。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.
所述滤波为阈值滤波。The filtering is threshold filtering.
所述标准火焰灰度图像y的尺寸为352×288。The size of the standard flame grayscale image y is 352×288.
第二步、从采集的水泥回转窑烧成带火焰视频中获取一幅如图6所示的彩色待测火焰图像P,待测火焰图像P尺寸为352×288×3;将待测火焰图像P进行阈值滤波和灰度变换,得到如图7所示的尺寸为352×288的待测火焰灰度图像x。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 .
第三步、采用平均结构相似性系数的计算方法,计算一幅待测火焰灰度图像x与每一幅标准火焰灰度图像y之间的平均结构相似性系数MSSIM(x,y),得到该幅待测火焰灰度图像x与15幅正常火焰灰度图库FN中标准火焰灰度图像y之间的15个平均结构相似性系数MSSIM(x,y),同时得到该幅待测火焰灰度图像x与10幅异常火焰灰度图库FA中标准火焰灰度图像y之间的10个平均结构相似性系数MSSIM(x,y)。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.
25个平均结构相似性系数MSSIM(x,y)如表3所示。The 25 average structural similarity coefficients MSSIM(x,y) are shown in Table 3.
表3table 3
第四步、根据表3所示,对第三步得到的25个平均结构相似性系数MSSIM(x,y)进行比较,选取平均结构相似性系数最大值MAXmssim为0.7616。由于平均结构相似性系数最大值MAXmssim所对应的标准火焰灰度图像y属于正常火焰灰度图库FN,则判定待测火焰图像P的烧成状态为正常状态。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.
第五步、同实施例1的第五步。The 5th step, with the 5th step of embodiment 1.
第六步、同实施例1的第六步。The 6th step, with the 6th step of embodiment 1.
所述的平均结构相似性系数的计算方法为:将待测火焰灰度图像x和标准火焰灰度图像y分别以11×11的窗口逐像素地从左上角向右下角移动,得到95076个待测火焰灰度图像块xj和95076个标准火焰灰度图像块yj,计算每个待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj之间的结构相似性系数SSIM(xj,yj),得到95076个结构相似性系数SSIM(xj,yj),然后对95076个结构相似性系数SSIM(xj,yj)进行累加平均,得到待测火焰灰度图像x和标准火焰灰度图像y的平均结构相似性系数MSSIM(x,y):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:
式(1)中:M=95076;In formula (1): M=95076;
SSIM(xj,yj)为待测火焰灰度图像块xj和对应的标准火焰灰度图像块yj的结构相似性系数: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 :
式(2)中:C1=6.5025,C2=58.5225;In formula (2): C 1 =6.5025, C 2 =58.5225;
ux,j为待测火焰灰度图像块xj的均值:u x,j is the mean value of the flame gray image block x j to be tested:
uy,j为标准火焰灰度图像块yj的均值:u y, j is the mean value of the standard flame gray image block y j :
σx,j为待测火焰灰度图像块xj的标准差:σ x,j is the standard deviation of the flame gray image block x j to be tested:
σy,j为标准火焰灰度图像块yj的标准差:σ y,j is the standard deviation of the standard flame gray image block y j :
σxy,j为标准火焰灰度图像块yj与待测火焰灰度图像块xj之间的协方差: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:
式(3)~(7)中:N=121,为待测火焰灰度图像块xj和标准火焰灰度图像块yj像素点个数;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 ;
xj,i为待测火焰灰度图像块xj的第i个像素点的值;x j, i is the value of the i-th pixel of the flame gray image block x j to be tested;
yj,i为标准火焰灰度图像块yj的第i个像素点的值。y j,i is the value of the i-th pixel of the standard flame gray image block y j .
实施例4Example 4
一种基于火焰图像结构相似性的水泥回转窑烧成状态识别方法。该回转窑烧成状态识别方法的具体步骤如图1所示: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:
第一步、本步骤所述滤波为感兴趣区域提取;所述标准火焰灰度图像y的尺寸为225×189。其余同实施例3第一步。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.
第二步、从采集的水泥回转窑烧成带火焰视频中获取一幅如图8所示的彩色待测火焰图像P,待测火焰图像P尺寸为352×288×3;将待测火焰图像P进行感兴趣区域提取和灰度变换,得到如图9所示的尺寸为225×189的待测火焰灰度图像x。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 .
第三步、本步骤除25个平均结构相似性系数MSSIM(x,y)如表4所示外,其余同实施例3的第三步。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.
表4Table 4
第四步、根据表4所示,对第三步得到的25个平均结构相似性系数MSSIM(x,y)进行比较,选取平均结构相似性系数最大值MAXmssim为0.7720。由于平均结构相似性系数最大值MAXmssim所对应的标准火焰灰度图像y属于异常火焰灰度图库FA,则判定待测火焰图像P的烧成状态为异常状态。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.
第五步、同实施例2的第五步。The 5th step, with the 5th step of embodiment 2.
第六步、同实施例2的第六步。The 6th step, with the 6th step of embodiment 2.
所述的平均结构相似性系数的计算方法同实施例3的平均结构相似性系数的计算方法。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.
本具体实施方式与现有技术相比具有如下优点:Compared with the prior art, this specific embodiment has the following advantages:
本具体实施方式首次在回转窑火焰图像识别的技术领域中采用结构相似性指标,从亮度、对比度和结构三种不同角度来判别回转窑烧成状态,判别精度较高;另外,该方法属于一种更符合人眼视觉系统基本原理的图像质量评价方法,判别结果更贴合主观评价。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.
本具体实施方式所运用的判别方法无需对火焰图像进行特殊训练和学习,大大降低了计算复杂度,缩小了处理时长。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.
本具体实施方式能够独立判别单幅火焰图像的烧成状态,满足在线实时监测回转窑中火焰变化的条件,能在极短的时间内发现回转窑火焰烧成状态的变化,并及时作出相应调整,从而增加回转窑控制系统的安全性和可靠性,使生产的熟料质量更加稳定,能够极大的缩减工业生产成本,为实现对整个回转窑系统实时监控的闭环控制奠定基础,为真正实现以“机器看火”代替“人工看火”提供了基本保障。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".
因此,本具体实施方式具有精度高、计算复杂度低、处理过程短和能实现在线实时监测火焰状态变化的特点。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)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310567666.0A CN103578111B (en) | 2013-11-13 | 2013-11-13 | Rotary kiln based on flame image structural similarity burns till state identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310567666.0A CN103578111B (en) | 2013-11-13 | 2013-11-13 | Rotary kiln based on flame image structural similarity burns till state identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103578111A CN103578111A (en) | 2014-02-12 |
CN103578111B true CN103578111B (en) | 2016-05-25 |
Family
ID=50049834
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310567666.0A Expired - Fee Related CN103578111B (en) | 2013-11-13 | 2013-11-13 | Rotary kiln based on flame image structural similarity burns till state identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103578111B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104751471A (en) * | 2015-04-09 | 2015-07-01 | 武汉科技大学 | Rotary kiln flame image recognition method based on complex wavelet domain decomposition |
CN105678295B (en) * | 2016-01-04 | 2019-03-19 | 武汉科技大学 | Gas heating flame method of real-time based on the analysis of ROI the average image |
CN105740866B (en) * | 2016-01-22 | 2018-11-06 | 合肥工业大学 | A kind of rotary kiln firing state identification method with imitative feed-back regulatory mechanism |
CN107886063A (en) * | 2017-11-03 | 2018-04-06 | 御林军生物科技(深圳)有限公司 | Identification check and fast diagnosis reagent interpretation of result method, apparatus and storage medium |
CN108985376B (en) * | 2018-07-17 | 2022-02-01 | 东北大学 | Rotary kiln sequence working condition identification method based on convolution-cyclic neural network |
CN110345090B (en) * | 2019-05-20 | 2020-04-14 | 重庆大学 | Thermal power generation heat source management system |
-
2013
- 2013-11-13 CN CN201310567666.0A patent/CN103578111B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN103578111A (en) | 2014-02-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103578111B (en) | Rotary kiln based on flame image structural similarity burns till state identification method | |
CN105588439B (en) | Sintering machine bogie grates detection method | |
CN104914111B (en) | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method | |
CN104198752B (en) | Many rate detection methods of high temperature billet steel motion state based on machine vision | |
CN104198498B (en) | Cloth defect detection method and device based on adaptive orthogonal wavelet transform | |
CN102673979B (en) | Method and device for judging deviation of conveying belt | |
CN112633292B (en) | Metal surface oxide layer temperature measurement method | |
CN114066820A (en) | A fabric defect detection method based on Swin-Transformer and NAS-FPN | |
CN104574389A (en) | Battery piece chromatism selection control method based on color machine vision | |
CN107749058A (en) | A kind of machine vision detection method and system of boiler tubing surface defect | |
CN102253049A (en) | Method for accurately detecting surface quality on line in production process of band steel | |
CN106373124A (en) | Gray-level co-occurrence matrix and RANSAC-based industrial product surface defect visual detection method | |
CN104899879B (en) | A kind of method of the online outward appearance detection of electric energy meter | |
CN118515040B (en) | Intelligent inspection system and method for coal conveyor belt based on machine vision | |
CN117623735B (en) | Production method of high-strength anti-pollution domestic ceramic | |
CN105572143B (en) | The detection method of rolled material surface periodic defect in calender line | |
CN101457267A (en) | Intelligent extraction method of blast burden temperature field isotherm | |
CN105740866B (en) | A kind of rotary kiln firing state identification method with imitative feed-back regulatory mechanism | |
CN111126206B (en) | Smelting state detection system and method based on deep learning | |
CN106644794A (en) | Method for detecting concrete strength with wall-climbing robot | |
CN110057820A (en) | Method, system and the storage medium of on-line checking hydrogen chloride synthetic furnace chlorine hydrogen proportion | |
CN111967323A (en) | Electric power live working safety detection method based on deep learning algorithm | |
CN104568956A (en) | Machine vision based detection method for strip steel surface defects | |
CN114463296A (en) | Defect detection method for lightweight components based on single-sample learning | |
CN102967265B (en) | Based on the automobile connecting bar splitter detection method of machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160525 Termination date: 20171113 |
|
CF01 | Termination of patent right due to non-payment of annual fee |