CN-121304576-B - Slurry stirring consistency monitoring method for autoclaved aerated concrete blocks

CN121304576BCN 121304576 BCN121304576 BCN 121304576BCN-121304576-B

Abstract

The invention relates to the technical field of image processing, in particular to a slurry stirring consistency monitoring method for autoclaved aerated concrete blocks, which comprises the steps of obtaining continuous multi-frame nodding images of slurry to obtain gray images; the method comprises the steps of respectively carrying out edge detection on each gray level image, screening to obtain at least one suspected slurry stirring texture edge in each gray level image, dividing all suspected slurry stirring texture edges into at least two groups of texture edge sets, splicing all suspected slurry stirring texture edges in each group of texture edge sets, obtaining a possibility index that a target texture edge corresponding to each group of texture edge sets is a real stirring texture, obtaining at least one stirring texture edge, obtaining a slurry stirring consistency coefficient according to texture characteristics and recovery speed of all stirring texture edges, and determining slurry stirring consistency level, thereby reducing texture interference generated by reflection and machine vibration and improving slurry stirring consistency monitoring accuracy.

Inventors

LI SHAOFENG
DU NING
ZHANG JIANPENG

Assignees

陕西新航峰环保科技有限公司

Dates

Publication Date: 20260508
Application Date: 20250930

Claims (9)

1. A method for monitoring the consistency of slurry agitation for autoclaved aerated concrete blocks, characterized in that the method comprises: Acquiring continuous multi-frame nodding images of the slurry, and respectively graying each frame of nodding images to correspondingly acquire gray images; respectively carrying out edge detection on each gray level image to obtain edges in each gray level image, and screening to obtain at least one suspected slurry stirring texture edge in each gray level image according to gray level differences among pixel points on each edge in each gray level image; Carrying out the same texture edge evaluation on every two suspected slurry stirring texture edges between two adjacent gray images, and dividing all the suspected slurry stirring texture edges into at least two texture edge sets; for any group of texture edge sets, all suspected slurry stirring texture edges in the any group of texture edge sets are spliced to obtain target texture edges, template images of slurry stirring tracks are obtained, the target texture edges are matched with the template texture edges in the template images, and a possibility index that the target texture edges are real stirring textures is obtained; obtaining a probability index that a target texture edge corresponding to each texture edge set is a real stirring texture, obtaining at least one stirring texture edge, and obtaining a slurry stirring consistency coefficient according to texture characteristics and recovery speed of all stirring texture edges, wherein the slurry stirring consistency coefficient is used for determining a slurry stirring consistency grade; the step of evaluating the same texture edge for every two suspected slurry stirring texture edges between two adjacent gray images, the step of dividing all suspected slurry stirring texture edges into at least two texture edge sets comprises the following steps: Aiming at the (x) suspected slurry stirring texture edge in the (i) gray level image, acquiring suspected slurry stirring texture edges which are overlapped with the (x) suspected slurry stirring texture edge or are within a preset number of pixel points from edge end points in the (i+1) gray level image, marking the suspected slurry stirring texture edges as edges to be analyzed, and acquiring the same texture possibility index between the (x) suspected slurry stirring texture edges and each edge to be analyzed if at least one edge to be analyzed is acquired; Respectively acquiring the same texture possibility index between each suspected slurry stirring texture edge in the ith gray level image and the corresponding edge to be analyzed in the (i+1) th gray level image, and obtaining an edge pair formed by at least one group of two suspected slurry stirring texture edges belonging to the same texture between the ith gray level image and the (i+1) th gray level image; and respectively acquiring all edge pairs between every two adjacent gray images, and forming a group of texture edge sets by the edge pairs belonging to the same texture according to the transmissibility of parallel lines to obtain at least one group of texture edge sets, wherein one group of texture edge sets corresponds to one texture.
2. The method for monitoring the stirring consistency of slurry for autoclaved aerated concrete blocks as recited in claim 1, wherein the step of screening at least one suspected slurry stirring texture edge in each gray image according to gray differences among pixel points on each edge in each gray image comprises the steps of: For any edge in any gray level image, taking any edge pixel point on any edge as an analysis pixel point, acquiring two non-edge pixel points with symmetrical positions in the four adjacent areas of the analysis pixel point, marking the non-edge pixel points as pixel points on two sides of the analysis pixel point, calculating the gray level value difference absolute value between the pixel points on two sides of the analysis pixel point, and taking the inverse of the sum of the gray level value difference absolute value and a preset value as the gray level difference degree on two sides of the edge of the analysis pixel point; Acquiring the gray scale difference degree of two sides of each edge pixel point on any edge, normalizing the accumulated value of the gray scale difference degree of two sides of the edges of all the edge pixel points on any edge to obtain a probability index that any edge belongs to a slurry stirring texture edge; And traversing each edge in each gray level image to obtain at least one suspected slurry stirring texture edge in each gray level image.
3. The method for monitoring the slurry stirring consistency of autoclaved aerated concrete blocks as recited in claim 1, wherein said obtaining an index of the same texture likelihood between an xth suspected slurry stirring texture edge and each edge to be analyzed, respectively, comprises: For any edge to be analyzed, calculating the distance between the edge end point of the edge to be analyzed and the edge end point of the x suspected slurry stirring texture edge, obtaining two edge end points corresponding to the minimum distance, marking the two edge end points as edge end points, taking the edge end points as the last edge pixel points, obtaining a first preset number of edge pixel points on the edge to be analyzed to form a first pixel point sequence, and obtaining a first preset number of edge pixel points on the x suspected slurry stirring texture edge to form a second pixel point sequence; According to the change slope of the first pixel point sequence and the change slope of the second pixel point sequence, acquiring a first possibility index that the edge to be analyzed and the x suspected slurry stirring texture edge belong to the same texture in the edge extending direction, and according to the difference between the fitting position and the actual position of the first pixel point sequence, acquiring a second possibility index that the edge to be analyzed and the x suspected slurry stirring texture edge belong to the same texture in the relative position by taking the position of the second pixel point sequence as a reference; And normalizing the product between the first probability index and the second probability index to obtain the same texture probability index between the (x) th suspected slurry stirring texture edge and any one edge to be analyzed.
4. A method for monitoring the stirring consistency of slurry for autoclaved aerated concrete blocks as recited in claim 3, wherein said obtaining a first probability indicator that said edge to be analyzed and said x-th suspected slurry stirring texture edge belong to the same texture in the edge extension direction according to the change slope of the first pixel point sequence and the change slope of the second pixel point sequence comprises: Calculating the slope of a straight line between two adjacent pixels in a first pixel sequence to obtain an average slope of the straight line, marking the average slope as a first slope, calculating the slope of the straight line between two adjacent pixels in a second pixel sequence to obtain an average slope of the straight line, marking the average slope as a second slope, calculating the absolute value of the difference between the first slope and the second slope, and taking the inverse of the sum of the absolute value of the difference and a preset value as a first probability index that any edge to be analyzed and the x suspected slurry stirring texture edge belong to the same texture in the edge extending direction.
5. A method for monitoring the stirring consistency of slurry for autoclaved aerated concrete blocks as recited in claim 3, wherein the step of obtaining a second probability index that the edge to be analyzed and the x-th suspected slurry stirring texture edge belong to the same texture in relative positions according to the difference between the fitting position and the actual position of the first pixel point sequence by taking the position of the second pixel point sequence as a reference comprises the steps of: And carrying out least square fitting on the ordinate values of all the pixel points according to the abscissa value of each pixel point in the second pixel point sequence to obtain a fitting curve, acquiring the fitting value of the ordinate of each pixel point in the first pixel point sequence by using the fitting curve, differencing the fitting value of the ordinate of each pixel point in the first pixel point sequence with the actual value to obtain the absolute value of the difference value of each pixel point, acquiring the average value of the absolute values of the differences of all the pixel points in the first pixel point sequence, and taking the reciprocal of the sum of the average value and the preset value as a second probability index of the same texture at the relative position of any edge to be analyzed and the x suspected slurry stirring texture edge.
6. The method for monitoring the slurry stirring consistency of autoclaved aerated concrete blocks as recited in claim 1, wherein the method for acquiring edge pairs of two suspected slurry stirring texture edges belonging to the same texture of at least one group between the ith gray scale image and the (i+1) th gray scale image comprises: If any suspected slurry stirring texture edge in the ith gray level image and any corresponding edge to be analyzed in the (i+1) th gray level image are larger than a preset threshold value of the same texture possibility index, taking any edge to be analyzed as a target edge, and if any suspected slurry stirring texture edge in the ith gray level image is detected to correspond to at least two target edges, selecting the target edge corresponding to the maximum same texture possibility index and any suspected slurry stirring texture edge in the ith gray level image to form a group of edge pairs.
7. The method for monitoring the slurry stirring consistency of autoclaved aerated concrete blocks as recited in claim 1, wherein said matching the target texture edge with a template texture edge in the template image, obtaining a likelihood indicator that the target texture edge is a true stirring texture, comprises: For any template texture edge in the template image, according to the length between the target texture edge and any template texture edge, acquiring the minimum length as the size of a sliding window, taking the edge corresponding to the minimum length as the target window, sliding on the edge corresponding to the maximum length based on the size of the sliding window and a preset sliding step length to obtain at least two sliding windows, calculating normalized correlation coefficients between the target window and each sliding window, and taking the maximum normalized correlation coefficient as the matching degree between the target texture edge and any template texture edge; and obtaining the matching degree between the target texture edge and each template texture edge in the template image, and taking the maximum matching degree as a possibility index of the target texture edge being a real stirring texture.
8. The method for monitoring the stirring consistency of slurry for autoclaved aerated concrete blocks as recited in claim 1, wherein said obtaining a probability indicator that a target texture edge corresponding to each set of texture edges is a true stirring texture, obtaining at least one stirring texture edge, comprises: Acquiring a preset probability index threshold, and determining that the target texture edge corresponding to any group of texture edge sets is a stirring texture edge if the probability index of the target texture edge corresponding to any group of texture edge sets being a real stirring texture is greater than or equal to the probability index threshold.
9. The method for monitoring the stirring consistency of slurry for autoclaved aerated concrete blocks as recited in claim 8, wherein said obtaining a stirring consistency coefficient of slurry based on the texture characteristics and recovery speed of all stirring texture edges comprises: For any stirring texture edge, marking each suspected slurry stirring texture edge in a texture edge set corresponding to the any stirring texture edge as a marking edge, marking edge pixel points of each marking edge in a corresponding gray level image according to the gray level image to which each marking edge belongs, obtaining marking pixel points, and obtaining the duration between the maximum sampling time and the minimum sampling time according to the sampling time of the gray level image to which each marking edge belongs, and marking as the stirring texture duration; Obtaining a stirring texture duration corresponding to each stirring texture edge, obtaining a stirring texture duration average value, carrying out normalization processing on the stirring texture duration average value to obtain a normalized value, obtaining all marked pixel points in each gray level image according to each suspected slurry stirring texture edge in a texture edge set corresponding to each stirring texture edge, obtaining the number proportion of marked pixel points in each gray level image, obtaining an average value of the number proportion, and marking the average value as a texture characteristic value; taking the product of the normalized value and the texture characteristic value as a slurry stirring consistency coefficient.

Description

Slurry stirring consistency monitoring method for autoclaved aerated concrete blocks Technical Field The invention relates to the technical field of image processing, in particular to a slurry stirring consistency monitoring method for autoclaved aerated concrete blocks. Background The autoclaved aerated concrete block is a lightweight and porous environment-friendly building material, has good heat insulation, sound insulation and earthquake resistance, and is widely applied to modern buildings. In the production process, the stirring consistency of the slurry is a key factor affecting the performance, quality and production efficiency of the concrete block, and if the slurry is too thin or too thick, the uniformity of the pore structure of the block can be affected, so that the weight, strength, heat preservation, water absorption and other performances of the block are affected. Therefore, in the production process of autoclaved aerated concrete blocks, monitoring of the stirring consistency of the slurry is an important link. The existing slurry stirring consistency monitoring method mainly utilizes methods such as edge detection and the like to identify texture parts in images, and analyzes the slurry stirring consistency according to stirring texture characteristics of the slurry surface in the stirring process. However, because a certain vibration is inevitably generated by the equipment in the stirring process, and the slurry has certain fluidity, water waves generated by vibration exist in the shot image besides stirring textures, and the water waves do not meet the relation of the stirring textures on the stirring consistence, so that the judgment on the stirring consistence of the slurry can be influenced, and the monitoring accuracy is influenced. Therefore, how to reduce the disturbance of the water ripple generated by vibration to the monitoring of the stirring consistency of the slurry, and to improve the monitoring accuracy become a problem to be solved. Disclosure of Invention In view of the above, the embodiment of the invention provides a slurry stirring consistency monitoring method for autoclaved aerated concrete blocks, which aims to solve the problems of reducing interference of water ripple generated by vibration on slurry stirring consistency monitoring and improving monitoring accuracy. The embodiment of the invention provides a slurry stirring consistency monitoring method for autoclaved aerated concrete blocks, which comprises the following steps: Acquiring continuous multi-frame nodding images of the slurry, and respectively graying each frame of nodding images to correspondingly acquire gray images; respectively carrying out edge detection on each gray level image to obtain edges in each gray level image, and screening to obtain at least one suspected slurry stirring texture edge in each gray level image according to gray level differences among pixel points on each edge in each gray level image; Carrying out the same texture edge evaluation on every two suspected slurry stirring texture edges between two adjacent gray images, and dividing all the suspected slurry stirring texture edges into at least two texture edge sets; for any group of texture edge sets, all suspected slurry stirring texture edges in the any group of texture edge sets are spliced to obtain target texture edges, template images of slurry stirring tracks are obtained, the target texture edges are matched with the template texture edges in the template images, and a possibility index that the target texture edges are real stirring textures is obtained; Obtaining a probability index that a target texture edge corresponding to each texture edge set is a real stirring texture, obtaining at least one stirring texture edge, and obtaining a slurry stirring consistency coefficient according to texture characteristics and recovery speed of all stirring texture edges, wherein the slurry stirring consistency coefficient is used for determining a slurry stirring consistency grade. Preferably, the screening to obtain at least one suspected slurry stirring texture edge in each gray image according to gray differences between pixel points on each edge in each gray image includes: For any edge in any gray level image, taking any edge pixel point on any edge as an analysis pixel point, acquiring two non-edge pixel points with symmetrical positions in the four adjacent areas of the analysis pixel point, marking the non-edge pixel points as pixel points on two sides of the analysis pixel point, calculating the gray level value difference absolute value between the pixel points on two sides of the analysis pixel point, and taking the inverse of the sum of the gray level value difference absolute value and a preset value as the gray level difference degree on two sides of the edge of the analysis pixel point; Acquiring the gray scale difference degree of two sides of each edge pixel point on any edge, normalizing the accumulated