An intelligent detection method and device for the bonding area ratio of thermal insulation boards

Abstract

The present invention belongs to the technical field of thermal insulation board detection, and specifically relates to an intelligent detection method and device for the bonding area ratio of thermal insulation boards. The method includes: collecting infrared images of the external thermal insulation system of a building exterior wall, determining multiple segmentation thresholds according to local regions of different sizes of pixel points, obtaining temperature characteristic values according to the size relationship between the pixel values of the pixel points and each segmentation threshold, dividing the infrared images into multiple superpixel blocks according to the pixel values and temperature characteristic values, calculating the temperature anomaly degree of each thermal insulation board according to the number of all superpixel blocks included in each thermal insulation board and the central tendency and difference of the pixel values, and determining the bonding strength of the target thermal insulation board according to the position and area ratio of the target sub-blocks with the sound velocity within the sound velocity range at the bonding part and the bonding state being bonded in the target thermal insulation board with the temperature anomaly degree greater than the preset threshold, and judging whether it is qualified in combination with the vertical height. The present invention improves the accuracy of the quality detection of thermal insulation boards.

Description

Technical Field

[0001] The present invention relates to the technical field of insulation board detection. More specifically, the present invention relates to an intelligent detection method and device for the bonding area ratio of insulation boards. Background Art

[0002] The external thermal insulation system (ETICS) of building exterior walls is a comprehensive system designed to improve the energy efficiency of buildings, reduce heat loss, and provide a good indoor environment; it mainly includes the following components: insulation boards, bonding layers, plastering layers, anchor fittings, protective layers, finishing layers, sealing materials, breathable layers, and fire isolation belts. Among them, the insulation board is the core of the external thermal insulation system; having a good bonding effect of the insulation board is the key to ensuring that the external thermal insulation system fully exerts its insulation function. Therefore, in order to prevent heat loss from building exterior walls, it is necessary to detect and determine the bonding effect of the insulation board.

[0003] In related technologies, for example, the Chinese patent application document with the publication number CN118858453A discloses an ultrasonic image detection method and device for exterior wall insulation boards, belonging to the technical field of ultrasonic image detection. The method includes: determining a first detection area based on the surface thermal image of the exterior wall insulation board; obtaining the ultrasonic image of the first detection area; calculating the insulation board area and the bonding area based on the ultrasonic image; and evaluating the exterior wall insulation board based on the insulation board area and the bonding area. The ultrasonic image detection method and device for exterior wall insulation boards provided by this application can solve the problem that traditional exterior wall insulation board detection technologies are difficult to meet actual needs.

[0004] In related technologies, only the bonding area ratio calculated by the bonding area and the insulation board area is used to detect the quality of the insulation board, and the detection result is inaccurate, which in turn affects the construction quality and building safety. Summary of the Invention

[0005] To solve the technical problem of inaccurate detection results of detecting the quality of insulation boards only by the bonding area ratio calculated by the bonding area and the insulation board area, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides an intelligent detection method for the bonding area ratio of thermal insulation boards, including: collecting infrared images of the external thermal insulation system of a building exterior wall, where the external thermal insulation system includes a number of identically sized thermal insulation boards bonded and fixed; for any pixel point in the infrared image: obtaining local regions of different sizes centered on this pixel point, obtaining multiple segmentation thresholds based on the pixel values of all pixel points within each local region, obtaining multiple binary feature values of this pixel point according to the magnitude relationship between the pixel value of this pixel point and different segmentation thresholds, and taking the decimal data corresponding to the binary data composed of all binary feature values as the temperature feature value of this pixel point; dividing the infrared image into multiple superpixel blocks according to the pixel value and the temperature feature value; calculating the temperature anomaly degree of each thermal insulation board according to the number of all superpixel blocks included in each thermal insulation board, as well as the central tendency and difference of the pixel values; evenly dividing the target thermal insulation board with a temperature anomaly degree greater than a preset threshold into multiple target sub-blocks; performing ultrasonic detection on the target thermal insulation board to obtain the sound velocity of each target sub-block, and recording the bonding state of the target sub-block with a sound velocity within the sound velocity range at the bonding part as bonded; determining the bonding strength of the target thermal insulation board from the bonding strength detection values at different bonding positions under different bonding area ratios according to the proportion and position of the number of target sub-blocks with a bonded state among all target sub-blocks; determining the bonding strength threshold corresponding to the target thermal insulation board according to the vertical height of the target thermal insulation board, and determining that the target thermal insulation board with a bonding strength less than the bonding strength threshold is unqualified.

[0007] The present invention combines infrared thermal imaging method with ultrasonic detection. By using the infrared thermal imaging method, it quickly locates the target thermal insulation board with a relatively large temperature anomaly degree. Subsequently, only ultrasonic detection is performed on the target thermal insulation board. The bonding state of each target sub-block is determined according to the sound velocity of each target sub-block in the target thermal insulation board. Furthermore, according to the proportion and position of the number of all target sub-blocks with a bonded state in the target thermal insulation board, detailed information on the area ratio and distribution position of the bonding area in the target thermal insulation board is provided, so as to determine the bonding strength of the target thermal insulation board from the bonding strength detection values at different bonding positions under different bonding area ratios. At the same time, considering the different requirements for the bonding strength of thermal insulation boards with different vertical heights, the bonding strength threshold corresponding to the target thermal insulation board is determined according to the vertical height of the target thermal insulation board, and different standards are used to measure and detect thermal insulation boards with different vertical heights. Therefore, the present invention improves the accuracy of the quality detection of thermal insulation boards and enhances the construction quality and building safety.

[0008] Preferably, obtaining local regions of different sizes centered on this pixel point includes: according to each odd number within the range of , obtaining a local region centered on this pixel point and with a size equal to , then a total of local regions of different sizes are obtained, and the The size of a local area is equal to , .

[0009] Preferably, the obtaining of multiple segmentation thresholds includes: designating any pixel point in the infrared image as a target pixel point; designating the maximum value and the minimum value of the pixel values of all pixel points in the th local area of the target pixel point as and , , when , the th segmentation threshold is equal to , when , the th segmentation threshold is equal to the th percentile of the pixel values of all pixel points in the th local area of the target pixel point, and ; the th percentile refers to the pixel value at the th position after arranging the pixel values of all pixel points in the th local area of the target pixel point in ascending order.

[0010] Preferably, the obtaining of multiple binary feature values of the pixel point includes: when the pixel value of the pixel point is greater than or equal to the th segmentation threshold, the th binary feature value of the pixel point is 1, otherwise, the th binary feature of the pixel point is 0, .

[0011] The present invention obtains multiple segmentation thresholds through the distribution of the pixel values of all pixel points in local areas of different sizes of pixel points to reflect the temperature distribution around the pixel points, and then compares the pixel value of the pixel point with the multiple segmentation thresholds to obtain the temperature feature value of the pixel point to reflect the difference between the pixel point and the surrounding temperature distribution, thereby improving the accuracy of subsequent division of the infrared image.

[0012] Preferably, the dividing the infrared image into multiple superpixel blocks includes: calculating the spatial distance between the th pixel point and the , being the abscissa and ordinate of the th pixel point respectively, being the abscissa and ordinate of the th pixel point respectively; calculating the between the Color distance of a pixel , are respectively the pixel values of the -th pixel and the -th pixel; is to take the absolute value; calculate the feature distance between the -th pixel and the -th pixel , are respectively the temperature feature values of the -th pixel and the -th pixel; then the distance metric between the -th pixel and the -th pixel is calculated as follows: , , is the size of the area corresponding to a single insulation board in the infrared image; according to the distance metric between every two pixels, the infrared image is segmented into superpixels, and the infrared image is divided into multiple superpixel blocks.

[0013] Preferably, calculating the temperature anomaly degree of each insulation board includes: all superpixel blocks included in each insulation board refer to all superpixel blocks included in the area corresponding to each insulation board in the infrared image; for any insulation board, the temperature anomaly degree of this insulation board is calculated as follows: ; in the formula, is the temperature anomaly degree of this insulation board, is the number of all superpixel blocks included in this insulation board, is the variance of the representative pixel values of all superpixel blocks included in this insulation board, representing the difference in pixel values of all superpixel blocks, is the mean of the representative pixel values of all superpixel blocks included in this insulation board, representing the central tendency of the pixel values of all superpixel blocks, is the natural exponential function; the representative pixel value of the superpixel block is the mean of the pixel values of all pixels in the superpixel block.

[0014] The present invention divides the infrared image and calculates the temperature anomaly degree of each insulation board according to the division result, so as to quickly locate the target insulation board with a larger temperature anomaly degree from all insulation boards, and only perform ultrasonic detection on the target insulation board subsequently, thereby improving the detection speed.

[0015] Preferably, the method for obtaining the sound velocity range of the bonding part is as follows: By performing ultrasonic detection on multiple insulation board samples, obtaining the sound velocity of each insulation board sample, and forming the sound velocity range of the bonding part with the minimum and maximum values of the sound velocity. The process of the ultrasonic detection is as follows: Bond and fix the insulation board sample on the concrete cube specimen with the bonding agent sample, and use an ultrasonic detector to measure the sound velocity of the insulation board sample.

[0016] Preferably, the method for obtaining the bonding strength detection values at different bonding positions under different bonding area ratios is as follows: Divide the surface of the bonding agent sample into sub-blocks, where is a preset quantity; Select sub-blocks from sub-blocks as the bonding positions. At this time, the bonding area ratio is equal to , where , then there are kinds of different bonding area ratios; When selecting sub-blocks from sub-blocks as the bonding positions, there are kinds of different bonding positions; For the th bonding position under the bonding area ratio equal to , , apply the bonding agent sample to the bonding position, then bond and fix the insulation board sample on the concrete cube specimen, and then use a bonding strength detector to perform a bonding strength detection on the insulation board sample to obtain the bonding strength detection value of the th bonding position under the bonding area ratio equal to

[0017] The traditional method of evaluating the bonding quality of insulation boards by the bonding area ratio cannot provide detailed information on the distribution position of the bonding area, and the distribution position of the bonding area is an important factor affecting the bonding strength. Therefore, the present invention performs bonding strength detection on insulation board samples at multiple bonding positions under different bonding area ratios to obtain the bonding strength detection values at different bonding positions under different bonding area ratios, so as to subsequently determine the bonding strength of the target insulation board according to the ratio and position of the number of target sub-blocks in all target sub-blocks that are in the bonded state, thereby improving the accuracy of the insulation board quality detection.

[0018] Preferably, the calculation formula for the bonding strength threshold corresponding to the target insulation board is: ; In the formula, is the bonding strength threshold corresponding to the target insulation board, is the vertical height of the target insulation board, is the height reference value, is the bonding strength reference value, and Equal to the bonding area ratio equal to is the mean value of the bonding strength detection values at all the following bonding positions, is the function to take the minimum value.

[0019] Considering the different requirements for the bonding strength of insulation boards at different vertical heights, the present invention determines the bonding strength threshold corresponding to the target insulation board according to the vertical height of the target insulation board, and measures and detects the insulation boards at different vertical heights with different standards, so as to improve the accuracy of the quality detection of insulation boards.

[0020] In a second aspect, the present invention provides an intelligent detection device for the bonding area ratio of an insulation board, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent detection method for the bonding area ratio of an insulation board is realized.

[0021] By adopting the above technical solution, the above-mentioned intelligent detection method for the bonding area ratio of an insulation board is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0022] The beneficial effects of the present invention are as follows:

[0023] The present invention combines the infrared thermal imaging method with the ultrasonic detection. By using the infrared thermal imaging method, the target insulation board with a larger degree of abnormal temperature is quickly located, and then only the target insulation board is subjected to ultrasonic detection. According to the sound velocity of each target sub-block in the target insulation board, the bonding state of each target sub-block is determined. Furthermore, according to the proportion and position of the number of all target sub-blocks with the bonded state in the target insulation board, the area ratio and distribution position of the bonding area in the target insulation board are provided, so as to determine the bonding strength of the target insulation board from the bonding strength detection values at different bonding positions under different bonding area ratios; at the same time, considering the different requirements for the bonding strength of insulation boards at different vertical heights, the bonding strength threshold corresponding to the target insulation board is determined according to the vertical height of the target insulation board, and different standards are used to measure and detect the insulation boards at different vertical heights; therefore, the present invention improves the accuracy of the quality detection of insulation boards and enhances the construction quality and building safety. Description of the Drawings

[0024] By reading the following detailed description with reference to the drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become easily understandable. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0025] Figure 1It is a flowchart schematically showing a method for intelligently detecting the bonding area ratio of insulation boards in the present invention;

[0026] Figure 2 It is a flowchart schematically showing step S3;

[0027] Figure 3 It is a flowchart schematically showing step S4;

[0028] Figure 4 It is schematically showing that the bonding area ratio is equal to A schematic diagram of the insulation board at the next bonding position;

[0029] Figure 5 It is schematically showing that the bonding area ratio is equal to A schematic diagram of the insulation board at another bonding position;

[0030] Figure 6 It is schematically showing that the bonding area ratio is equal to A schematic diagram of the insulation board at the next bonding position;

[0031] Figure 7 It is schematically showing that the bonding area ratio is equal to A schematic diagram of the insulation board at another bonding position. Detailed implementation manners

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present invention.

[0033] The following will describe in detail the specific implementation manners of the present invention in conjunction with the accompanying drawings.

[0034] An embodiment of the present invention discloses a method for intelligently detecting the bonding area ratio of insulation boards. Referring to Figure 1 , it includes steps S1 - step S6:

[0035] S1. Collect infrared images of the external thermal insulation system of the building exterior wall.

[0036] It should be noted that the external thermal insulation system (ETICS) of building exterior walls is a comprehensive system designed to improve the energy efficiency of buildings, reduce heat loss, and provide a good indoor environment. It mainly consists of the following components: insulation boards, adhesive layers, rendering layers, anchor fasteners, protective layers, finishing layers, sealing materials, air permeable layers, and fire separation belts. Among them, the insulation board is the core of the external thermal insulation system, usually including expanded polystyrene board (EPS), extruded polystyrene board (XPS), polyurethane foam (PU), etc., which is used to reduce the heat conduction of the wall. The adhesive layer is the binder used to fix the insulation board on the exterior wall, which can be mortar, adhesive, or other special adhesive materials. The rendering layer is the protective layer covering the outer layer of the insulation material, usually made of polymer mortar or cement-based materials, providing additional protection and decorative effects. Anchor fasteners are used to enhance the connection strength between the insulation system and the wall, which is particularly important in areas with high wind pressure or seismic regions. The protective layer includes a waterproof and breathable membrane, a waterproof layer, etc., which is used to protect the insulation system from moisture intrusion and at the same time allow water vapor to escape. The finishing layer is the outermost layer of the external thermal insulation system, which can be made of various materials such as paint, tiles, stone, metal plates, etc., providing an aesthetic appearance and additional protection. Sealing materials are used for sealing joints and edges to ensure the airtightness and waterproofness of the insulation system. The air permeable layer is used to regulate the humidity inside the wall. The fire separation belt refers to the separation belt made of fireproof materials added to the insulation system, which is used to improve the fire resistance of buildings.

[0037] Among them, the good bonding effect of the insulation board is the key to ensuring that the external thermal insulation system fully exerts its insulation function. Therefore, in order to prevent the heat loss of the building exterior wall, it is necessary to detect and determine the bonding effect of the insulation board. The infrared thermal imaging method is based on the infrared radiation emitted by an object to form an image, and shows the temperature change and heat distribution on the object surface by providing a temperature distribution map. The infrared thermal imaging method is a non-contact measurement, without the need for destructive sampling, and can respond quickly. Therefore, it is considered to obtain the temperature characteristics of the external thermal insulation system of the building exterior wall through the infrared thermal imaging method, and then identify the insulation boards with poor bonding.

[0038] Specifically, an infrared camera is used to collect the infrared image of the external thermal insulation system of the building exterior wall. The external thermal insulation system includes several uniformly sized insulation boards bonded and fixed. The pixel value of the pixel points in the infrared image can reflect the temperature of each position.

[0039] Among them, it is required that the infrared camera has sufficient resolution and sensitivity to capture the temperature changes of the external thermal insulation system of the building exterior wall, and it is necessary to select appropriate weather and time for shooting to avoid direct sunlight and extreme temperatures; during the process of collecting infrared images: First, according to the layout and characteristics of the building exterior wall, plan the shooting route and perspective; Second, adjust the settings of the infrared camera according to the environmental conditions, including parameters such as measurement range, emissivity, reflected temperature, etc.; In addition, it is necessary to determine the shooting angle and distance to ensure that each part of the external thermal insulation system of the building exterior wall can be clearly captured. During this process, ladders or lifting platforms can be used to approach the building exterior wall; Finally, by smoothly moving the infrared camera, cover the entire outer surface of the building exterior wall to obtain an infrared image of the external thermal insulation system of the building exterior wall.

[0040] S2. Obtain local regions of different sizes centered on any pixel point in the infrared image, obtain multiple segmentation thresholds according to the pixel values of all pixel points in each local region, and obtain the temperature characteristic value of the pixel point according to the size relationship between the pixel value of the pixel point and each segmentation threshold.

[0041] It should be noted that the pixel value of a pixel point in the infrared image represents the temperature characteristic of the position where the pixel point is located. In the present invention, the temperature characteristic value of the pixel point is obtained by analyzing and comparing the pixel value of the pixel point with the pixel values of other pixel points in the local region of the pixel point.

[0042] Specifically, for any pixel point in the infrared image, denote the pixel point as the target pixel point; centered on the target pixel point, obtain local regions of different sizes of the target pixel point, including: according to each odd number within the range obtain a local region centered on the target pixel point and with a size equal to , then a total of local regions of different sizes are obtained, and the size of the th local region of the target pixel point is equal to , , exemplarily, the size of the th local region of the target pixel point is equal to .

[0043] Furthermore, according to the local regions of different sizes of the target pixel point, calculate different segmentation thresholds. Among them, according to the pixel values of all pixel points in the th local region of the target pixel point, calculate the th segmentation threshold, including: denote the maximum value and the minimum value of the pixel values of all pixel points in the th local region of the target pixel point as and , when When the th segmentation threshold is equal to ; when the th segmentation threshold is equal to the th percentile of the pixel values of all pixel points in the th local region of the target pixel point, and

[0044] It should be noted that for the unbonded position on the insulation board, its insulation effect is poor and its temperature is lower than that of other adjacent positions; on the contrary, the lower the temperature compared to other adjacent positions, the more likely it is an abnormal temperature; when the difference between the maximum and minimum pixel values of all pixel points in the local region is small, it indicates that the temperature difference at each position in the local region is small, and there is no abnormal temperature in the local region. Therefore, the minimum pixel value is used as the segmentation threshold, so that the pixel value of the target pixel point must be greater than or equal to the segmentation threshold, and the temperature of the target pixel point is a normal temperature; when the difference between the maximum and minimum pixel values of all pixel points in the local region is large, it indicates that the temperature difference at each position in the local region is large, and there may be abnormal temperature in the local region. Moreover, the larger the difference between the maximum and minimum values, the more abnormal temperatures may exist in the local region. Therefore, the segmentation threshold is determined according to the difference between the maximum and minimum values, and the larger the difference between the maximum and minimum values, the closer the determined segmentation threshold is to the larger pixel value among all pixel values. Furthermore, the temperature of the target pixel point is determined to be a normal temperature or an abnormal temperature by the determined segmentation threshold.

[0045] Furthermore, according to the magnitude relationship between the pixel value of the target pixel point and different segmentation thresholds, multiple binary feature values of the target pixel point are obtained; the decimal data corresponding to the binary data composed of all binary feature values is used as the temperature feature value of the target pixel point.

[0046] It should be noted that in the present invention, multiple segmentation thresholds are obtained through the distribution of pixel values of all pixel points in local regions of different sizes of the pixel point, which is used to reflect the temperature distribution around the pixel point. Furthermore, by comparing the pixel value of the pixel point with multiple segmentation thresholds, the temperature feature value of the pixel point is obtained, which is used to reflect the difference between the pixel point and the surrounding temperature distribution, thereby improving the accuracy of subsequent division of the infrared image.

[0047] Among them, according to the magnitude relationship between the pixel value of the target pixel point and the The size relationship of the segmentation thresholds is used to obtain the binary feature value of the target pixel, including: when the pixel value of the target pixel is greater than or equal to the th segmentation threshold, the th binary feature value of the target pixel is 1; when the pixel value of the target pixel is less than the th segmentation threshold, the th binary feature of the target pixel is 0.

[0048] It should be noted that the smaller the pixel value of the target pixel, the lower the temperature of the target pixel, the more likely the obtained binary feature value is 0, the smaller the decimal data corresponding to the binary data composed of the binary feature values, and the smaller the temperature feature value of the target pixel.

[0049] Furthermore, it should be noted that since the target pixel has local regions of different sizes, therefore, according to the pixel values of the pixels in the local regions, a total of segmentation thresholds are obtained; according to the size relationship between the pixel value of the target pixel and these segmentation thresholds, a total of binary feature values of the target pixel are obtained; then the length of the binary data composed of all binary feature values is 8, and the value range of the corresponding decimal data is , so the value range of the temperature feature value of the target pixel is .

[0050] Exemplarily, the pixel value of the target pixel is 109, and according to the local regions of different sizes of the target pixel, the segmentation thresholds calculated are 107, 106, 108, 111, 114, 105, 100, 99 respectively. Then, according to the size relationship between the pixel value of the target pixel and these segmentation thresholds, the binary feature values of the target pixel obtained are 1, 1, 1, 0, 0, 1, 1, 1 respectively. The binary data composed of the binary feature values is 11100111, and the decimal data corresponding to the binary data 11100111 is 231. Then the temperature feature value of the target pixel is equal to 231.

[0051] S3. Divide the infrared image into multiple superpixel blocks according to the pixel value and the temperature feature value, and calculate the temperature abnormality degree of each insulation board according to the division result, so as to screen out the target insulation board from all insulation boards.

[0052] The flowchart of step S3 is referred to Figure 2, including steps S301 to S302, specifically:

[0053] S301. Calculate the distance metric between every two pixel points based on the differences in pixel values, temperature feature values, and positional relationships of every two pixel points; divide the infrared image into multiple superpixel blocks according to the distance metric between pixel points.

[0054] Specifically, calculate the distance metric between every two pixel points based on the differences in pixel values, temperature feature values, and positional relationships of every two pixel points. Among them, according to the th pixel point and the th pixel point's pixel values, temperature feature values, and positional relationship differences, calculate the distance metric between the th pixel point and the th pixel point , then 's calculation formula is:

[0055] ;

[0056] In the formula, is the spatial distance between the th pixel point and the th pixel point, is the color distance between the th pixel point and the th pixel point, is the feature distance between the th pixel point and the th pixel point, is a parameter in the SLlC algorithm, representing the desired size of the superpixel block, , is the size of the area corresponding to a single insulation board in the infrared image.

[0057] Among them, the spatial distance between the th pixel point and the th pixel point , are respectively the abscissa and ordinate of the th pixel point, are respectively the abscissa and ordinate of the th pixel point; the color distance between the th pixel point and the th pixel point , are respectively the pixel values of the th pixel point and the th pixel point, is to take the absolute value; the th pixel point and the Characteristic distance of a pixel point , are respectively the temperature characteristic values of the -th pixel point and the -th pixel point, where taking the absolute value is represented by

[0058] Furthermore, according to the distance metric between every two pixel points, the infrared image is segmented into superpixels by the SLlC (Simple Linear Iterative Clustering) algorithm, and the infrared image is divided into multiple superpixel blocks as the segmentation result; the SLlC algorithm is a well-known technology and will not be elaborated here.

[0059] S302. Calculate the temperature anomaly degree of each insulation board according to the segmentation result, so as to screen out the target insulation board from all insulation boards.

[0060] Specifically, according to the segmentation result, determine all the superpixel blocks included in each insulation board; calculate the temperature anomaly degree of each insulation board according to the number of all the superpixel blocks included in each insulation board and the central tendency and difference of the pixel values; all the superpixel blocks included in each insulation board refer to all the superpixel blocks included in the area corresponding to each insulation board in the infrared image; for any insulation board, the temperature anomaly degree of this insulation board is calculated by the following formula:

[0061] ;

[0062] In the formula, is the temperature anomaly degree of this insulation board, is the number of all the superpixel blocks included in this insulation board, is the variance of the representative pixel values of all the superpixel blocks included in this insulation board, representing the difference of the pixel values of all the superpixel blocks, is the mean value of the representative pixel values of all the superpixel blocks included in this insulation board, representing the central tendency of the pixel values of all the superpixel blocks, is the natural exponential function; the representative pixel value of the superpixel block is the mean value of the pixel values of all the pixel points in the superpixel block.

[0063] It should be noted that the larger the number of all the superpixel blocks included in the insulation board and the variance of the representative pixel values of all the superpixel blocks, the more chaotic the temperature distribution in this insulation board, and correspondingly the greater the temperature anomaly degree of this insulation board; the smaller the mean value of the representative pixel values of all the superpixel blocks included in the insulation board, the greater the temperature anomaly degree of this insulation board.

[0064] Further, target insulation boards are screened out from all the insulation boards according to the degree of temperature anomaly, including: marking the insulation boards with a temperature anomaly degree greater than a preset threshold as target insulation boards, the target insulation boards.

[0065] Among them, the specific value of the preset threshold can be set according to the actual application scenario and requirements, and the value-taking method of the preset threshold is [0.5, 1). In the present invention, the preset threshold is set to 0.55.

[0066] It should be noted that in the present invention, by dividing the infrared image and calculating the degree of temperature anomaly of each insulation board according to the division result, it is convenient to quickly locate the target insulation board with a larger degree of temperature anomaly from all the insulation boards, and subsequently only the target insulation boards are subjected to ultrasonic detection, thereby improving the detection speed.

[0067] S4. By performing ultrasonic detection on the insulation board samples, the sound velocity range of the bonding part is obtained; by performing bonding strength detection on the insulation board samples, the bonding strength detection values at different bonding positions under different bonding area ratios are obtained.

[0068] The flowchart of step S4 refers to Figure 3 , including step S401 to step S402, specifically:

[0069] S401. By performing ultrasonic detection on the insulation board samples, the sound velocity range of the bonding part is obtained.

[0070] It should be noted that since the wave velocity of ultrasonic waves is different when passing through different media, ultrasonic detection can determine the bonding area, thereby estimating the bonding situation of the insulation board; in the present invention, by performing ultrasonic detection on the insulation board samples, the sound velocity range of the bonding part is obtained, and subsequently, the bonding state of the target insulation board is determined directly according to the relationship between the sound velocity of the target insulation board to be detected and the sound velocity range of the bonding part.

[0071] Specifically, by performing ultrasonic detection on multiple insulation board samples, the sound velocity of each insulation board sample is obtained, and the minimum value and the maximum value of the sound velocity are combined to form the sound velocity range of the bonding part. The process of the ultrasonic detection is as follows: on the concrete cube specimen, the insulation board sample is bonded and fixed with the bonding agent sample, and the sound velocity of the insulation board sample is measured using an ultrasonic detector; when performing ultrasonic detection on the insulation board sample, it is required that the insulation board sample has the same specification as the insulation board of the external thermal insulation system of the building exterior wall, and the bonding agent sample is the same as the bonding agent used in the bonding layer of the external thermal insulation system of the building exterior wall.

[0072] S402. By performing bonding strength detection on the insulation board samples, the bonding strength detection values at different bonding positions under different bonding area ratios are obtained.

[0073] It should be noted that the traditional method of evaluating the bonding quality of thermal insulation boards by the bonding area ratio is not accurate enough; this is because this method cannot provide detailed information on the distribution position of the bonding area, and the distribution position of the bonding area is an important factor affecting the bonding strength.

[0074] Specifically, the surface of the binder sample is divided into sub-blocks, which is a preset quantity; select sub-blocks from sub-blocks as the bonding positions. At this time, the bonding area ratio is equal to , where , then there are different bonding area ratios; when selecting sub-blocks from sub-blocks as the bonding positions, there are different bonding positions in total; for the bonding area ratio equal to at the th bonding position, , apply the binder sample on the bonding positions, then bond and fix the thermal insulation board sample on the concrete cube specimen, and then use a bonding strength detector to measure the bonding strength of the thermal insulation board sample to obtain the bonding strength detection value of the th bonding position at the bonding area ratio equal to . In this way, the bonding strength detection values of different bonding positions at different bonding area ratios are obtained.

[0075] Among them, when detecting the bonding strength of the thermal insulation board sample, it is required that the thermal insulation board sample has the same specifications as the thermal insulation board of the external thermal insulation system of the building exterior wall, and the binder sample is the same as the binder used in the bonding layer of the external thermal insulation system of the building exterior wall.

[0076] Among them, the specific value of the preset quantity can be set according to the actual application scenario and requirements, and the value-taking method of the preset quantity is [6, 10]. In the present invention, the preset quantity is set to 8.

[0077] Exemplarily, as Figure 4 is a schematic diagram of a thermal insulation board at a bonding position where the bonding area ratio is equal to , and as Figure 5 is a schematic diagram of a thermal insulation board at another bonding position where the bonding area ratio is equal to ; as Figure 6 is a schematic diagram of a thermal insulation board at a bonding position where the bonding area ratio is equal to , and as Figure 7 is a schematic diagram of a thermal insulation board at a bonding position where the bonding area ratio is equal to Schematic diagram of the insulation board at another bonding position.

[0078] It should be noted that the traditional method of evaluating the bonding quality of the insulation board by the bonding area ratio cannot provide detailed information on the distribution position of the bonding area, and the distribution position of the bonding area is an important factor affecting the bonding strength. Therefore, in the present invention, the bonding strength of the insulation board samples at various bonding positions under different bonding area ratios is detected, and the bonding strength detection values at different bonding positions under different bonding area ratios are obtained, so as to subsequently determine the bonding strength of the target insulation board according to the proportion and position of the number of target sub-blocks in all target sub-blocks with the status of bonded, thereby improving the accuracy of the insulation board quality detection.

[0079] S5. Divide the target insulation board evenly into multiple target sub-blocks, determine the bonding status of the target sub-blocks according to the relationship between the sound velocity of each target sub-block and the sound velocity range of the bonding part, and determine the bonding strength of the target insulation board from the bonding strength detection values at different bonding positions under different bonding area ratios according to the proportion and position of the number of target sub-blocks with the status of bonded.

[0080] It should be noted that since ultrasonic detection is a contact detection method that needs to contact the object to be detected, it is not applicable to the detection of the external insulation system of high-rise building exterior walls, and compared with the infrared thermal imaging method, the coverage area of ultrasonic detection is small and the detection speed is slow. Therefore, by combining the infrared thermal imaging method with ultrasonic detection, the target insulation board with a relatively large degree of abnormal temperature is quickly located by the infrared thermal imaging method, and only the target insulation board is subsequently subjected to ultrasonic detection, thereby improving the detection speed.

[0081] Specifically, for any target insulation board, divide the target insulation board evenly into target sub-blocks, where is a preset number; perform ultrasonic detection on the target insulation board to obtain the sound velocity of each target sub-block of the target insulation board; record the bonding status of the target sub-blocks with the sound velocity within the sound velocity range of the bonding part as bonded, and record the bonding status of the target sub-blocks with the sound velocity within the sound velocity range of the unbonded part as unbonded.

[0082] Furthermore, take the proportion of the number of target sub-blocks with the status of bonded among all the target sub-blocks of the target insulation board as the bonding area of the target insulation board; determine the bonding strength of the target insulation board from the bonding strength detection values at different bonding positions under different bonding area ratios according to the bonding area of the target insulation board and the positions of all the target sub-blocks with the status of bonded.

[0083] S6. Determine the bonding strength threshold corresponding to the target insulation board according to the vertical height of the target insulation board, and the target insulation board with the bonding strength less than the bonding strength threshold is determined to be unqualified.

[0084] It should be noted that the traditional method of evaluating the bonding quality of insulation boards by the bonding area ratio is not accurate enough; this is because this method ignores the fact that the requirements for the bonding strength of insulation boards at different vertical heights are different, and the insulation boards at different vertical heights cannot be measured and detected by the same standard.

[0085] Furthermore, it should be noted that the insulation boards at higher positions are more easily affected by wind pressure. Especially in high-rise buildings, wind pressure may cause the insulation boards to fall off. Therefore, stronger bonding strength is required to resist this external force; and as the vertical height increases, the insulation boards will experience greater temperature changes, resulting in thermal expansion and contraction. If the bonding strength is insufficient, cracks or detachment may occur due to the stress caused by temperature changes; therefore, the higher the vertical height of the insulation board, the greater the influence of wind pressure and temperature changes, and the higher the corresponding requirement for its bonding strength.

[0086] Specifically, according to the vertical height of the target insulation board, determine the corresponding bonding strength threshold of the target insulation board; if the bonding strength of the target insulation board is less than the corresponding bonding strength threshold of the target insulation board, it is determined that the target insulation board is unqualified and reported to the operation and maintenance personnel for repair or replacement; if the bonding strength of the target insulation board is greater than or equal to the corresponding bonding strength threshold of the target insulation board, it is determined that the target insulation board is qualified.

[0087] It should be noted that considering the different requirements for the bonding strength of insulation boards at different vertical heights, the present invention determines the corresponding bonding strength threshold of the target insulation board according to the vertical height of the target insulation board, and measures and detects the insulation boards at different vertical heights with different standards, so as to improve the accuracy of the quality detection of insulation boards.

[0088] Among them, the calculation formula for the corresponding bonding strength threshold of the target insulation board is:

[0089] ;

[0090] In the formula, is the corresponding bonding strength threshold of the target insulation board, is the vertical height of the target insulation board, is the height reference value, is the bonding strength reference value, and is equal to the bonding area ratio equal to the mean value of the bonding strength detection values of all bonding positions below, is the minimum value function.

[0091] Among them, the specific value of the height reference value can be set according to the actual application scenario and requirements, and the unit is meters. The present invention sets the height reference value to 50 meters.

[0092] It should be noted that the present invention combines infrared thermal imaging method with ultrasonic detection. By using the infrared thermal imaging method, the target insulation board with a relatively large degree of temperature anomaly is quickly located. Subsequently, only the target insulation board is subjected to ultrasonic detection. The bonding state of each target sub-block in the target insulation board is determined according to the sound velocity of each target sub-block in the target insulation board. Furthermore, based on the proportion and position of the number of target sub-blocks with the bonded state in the target insulation board, detailed information on the area ratio and distribution position of the bonded area in the target insulation board is provided, so as to determine the bonding strength of the target insulation board from the bonding strength detection values at different bonding positions with different bonding area ratios. At the same time, considering the different requirements for the bonding strength of insulation boards at different vertical heights, the corresponding bonding strength threshold for the target insulation board is determined according to the vertical height of the target insulation board, and different standards are used to measure and detect insulation boards at different vertical heights. Therefore, the present invention improves the accuracy of the quality detection of insulation boards and enhances the construction quality and building safety.

[0093] An embodiment of the present invention also discloses an intelligent detection device for the bonding area ratio of an insulation board, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent detection method for the bonding area ratio of an insulation board according to the present invention is implemented.

[0094] The above device also includes other components well-known to those skilled in the art, such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0095] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, such as two, three or more, unless otherwise specifically and clearly defined.

[0096] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations and alternative ways without departing from the spirit and idea of the present invention. It should be understood that in the process of practicing the present invention, alternative solutions to the embodiments of the present invention described herein can be adopted.

Claims

1. An intelligent detection method for the bonding area ratio of an insulation board, characterized in that: include: Collect an infrared image of an external insulation system of an external wall of a building, wherein the external insulation system includes a plurality of insulation boards of the same specifications that are bonded and fixed; for any pixel point in the infrared image: obtain local areas of different sizes with the pixel point as the center, obtain multiple segmentation thresholds according to the pixel values ​​of all the pixels in each local area, obtain multiple binary feature values ​​of the pixel point according to the size relationship between the pixel value of the pixel point and different segmentation thresholds, and use the decimal data corresponding to the binary data composed of all the binary feature values ​​as the temperature feature value of the pixel point; The infrared image is divided into multiple super-pixel blocks according to the pixel value and the temperature characteristic value; the temperature anomaly degree of each insulation board is calculated according to the number of all super-pixel blocks contained in each insulation board and the central trend and difference of the pixel values; The target insulation board with a temperature anomaly greater than a preset threshold is evenly divided into a plurality of target sub-blocks; ultrasonic testing is performed on the target insulation board to obtain the sound velocity of each target sub-block, and the bonding state of the target sub-block whose sound velocity is within the sound velocity range of the bonding part is recorded as bonded; the bonding strength of the target insulation board is determined according to the number ratio and position of the target sub-blocks in the bonded state among all the target sub-blocks from the bonding strength test values ​​at different bonding positions under different bonding area ratios; According to the vertical height of the target insulation board, a bonding strength threshold corresponding to the target insulation board is determined, and a target insulation board having a bonding strength less than the bonding strength threshold is judged as unqualified.

2. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The obtaining of local areas of different sizes with the pixel point as the center includes: according to Each singular in the range , get the value centered at the pixel and equal to The local area of ​​​​ local areas of different sizes, and the first The size of the local region is equal to , .

3. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The obtaining of multiple segmentation thresholds comprises: Any pixel in the infrared image is recorded as the target pixel; The maximum and minimum values ​​of the pixel values ​​of all pixels in the local area are recorded as and , ,when At that time, The segmentation threshold is equal to ,when At that time, The segmentation threshold is equal to the target pixel The pixel values ​​of all pixels in the local area Percentile, and ; said Percentile refers to the number of pixels in the After the pixel values ​​of all pixels in the local area are arranged in ascending order, The pixel value at the location.

4. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The step of obtaining a plurality of binary feature values ​​of the pixel point comprises: When the pixel value of the pixel is greater than or equal to When the segmentation threshold is The binary feature value of the pixel is 1, otherwise, The binary features are 0, .

5. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The step of dividing the infrared image into a plurality of super pixel blocks comprises: Calculate the pixels and The spatial distance of pixels , Respectively The horizontal and vertical coordinates of the pixel points, Respectively The horizontal and vertical coordinates of the pixel points; calculate the pixels and The color distance of pixels , Respectively pixels and The pixel value of a pixel, To take the absolute value; calculate the pixels and The feature distance of pixels , Respectively pixels and The temperature characteristic value of each pixel; The first pixels and The distance measure between pixels The calculation formula is: , , is the size of the area corresponding to a single insulation board in the infrared image; According to the distance metric between every two pixels, the infrared image is segmented into superpixels and divided into multiple superpixel blocks.

6. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The calculation of the temperature abnormality of each insulation board includes: All superpixel blocks contained in each insulation board refer to all superpixel blocks contained in the area corresponding to each insulation board in the infrared image; for any insulation board, the temperature anomaly degree of the insulation board The calculation formula is: ； In the formula, is the abnormal temperature degree of the insulation board, is the number of all superpixel blocks contained in the insulation board, is the variance of the representative pixel values ​​of all superpixel blocks contained in the insulation board, representing the difference in pixel values ​​of all superpixel blocks. is the mean value of the representative pixel values ​​of all superpixel blocks contained in the insulation board, which represents the central trend of the pixel values ​​of all superpixel blocks. is a natural exponential function; the representative pixel value of the superpixel block is the average of the pixel values ​​of all pixels in the superpixel block.

7. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The method for obtaining the sound velocity range of the bonding part is: By performing ultrasonic testing on multiple insulation board samples, the sound velocity of each insulation board sample is obtained, and the minimum and maximum sound velocity are used to form the sound velocity range of the bonding part. The process of ultrasonic testing is: the insulation board sample is bonded and fixed on the concrete cube specimen with an adhesive sample, and the sound velocity of the insulation board sample is measured using an ultrasonic detector.

8. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The method for obtaining the bonding strength test values ​​at different bonding positions under different bonding area ratios is as follows: The surface of the insulation board sample is divided into Sub-blocks, is the preset quantity; from Select from the sub-blocks The sub-blocks are used as bonding positions. At this time, the bonding area ratio is equal to ,in, , then there are Different bonding area ratios; Select from the sub-blocks When the sub-blocks are used as bonding positions, there are different bonding positions; for bonding area ratio equal to Next The bonding position , apply the adhesive sample to the bonding position, then bond and fix the insulation board sample to the concrete cube specimen, and then use the bonding strength tester to measure the bonding strength of the insulation board sample to obtain the bonding area ratio equal to Next The bonding strength test value of each bonding position.

9. The intelligent detection method of the bonding area ratio of the thermal insulation board according to claim 1 is characterized in that: The calculation formula of the bonding strength threshold corresponding to the target insulation board is: ； In the formula, is the bonding strength threshold corresponding to the target insulation board, is the vertical height of the target insulation board, is the height reference value, is the reference value of bonding strength, and Equal to the bonding area ratio The average of the bond strength test values ​​of all bonding positions is: is the minimum value function.

10. An intelligent detection device for bonding area ratio of thermal insulation board, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent detection method for the bonding area ratio of an insulation board according to any one of claims 1 to 9 is implemented.

Images