Iot-based assembly type pipe gallery splicing construction intelligent monitoring method and system

Abstract

The application relates to the technical field of pipe gallery leakage monitoring, in particular to an intelligent monitoring method and system for assembly type pipe gallery splicing construction based on the Internet of Things, which comprises the following steps: collecting all inner wall gray scale images of the pipe gallery at each time, extracting the areas of each splicing joint in the inner wall gray scale images, and recording the areas of each splicing joint at each time as each splicing joint area; collecting the humidity of the space position of each splicing joint in the pipe gallery at each time; calculating a gray scale deviation amount, calculating a first evaluation value of each splicing joint area at each time; calculating a direction consistency degree, determining a second evaluation value and a leakage risk value of each splicing joint area at each time; calculating a humidity deviation degree to obtain a discrimination coefficient, and performing real-time monitoring and evaluation on the leakage of the splicing joint in the pipe gallery. The application can reduce the interference of structural joints, fracturing joints and cracking joints on detection, and improve the accuracy of detection on the leakage of the splicing joint in the pipe gallery through multi-dimensional evaluation of the leakage risk of the splicing joint in the pipe gallery.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of pipe gallery leakage monitoring, in particular to a smart monitoring method and system for assembled pipe gallery splicing construction based on Internet of Things. BACKGROUND

[0002] In urban infrastructure construction, as an important underground facility, the assembled pipe gallery plays a key role in accommodating and protecting various pipelines. The assembled pipe gallery is spliced by multiple prefabricated concrete segments. The pipe gallery splicing joint is a weak link of the prefabricated assembled structure. Due to the large number of pipe gallery splicing joints, the underground water pressure and geological soil have an impact on the pipe gallery structure, causing cracks in the pipe gallery structure and easy leakage, which threatens the safety of the internal pipelines.

[0003] When the traditional method detects the leakage of the assembled pipe gallery, due to the complex internal environment of the pipe gallery, only the edge feature information in the single internal image of the pipe gallery is relied on, and the interference of the inherent structural joints and concrete cracking in the internal wall of the pipe gallery is not considered. Early signs of leakage cannot be found in time, resulting in misjudgment of the leakage of the splicing joint in the pipe gallery and affecting the accuracy of the monitoring of the pipe gallery leakage. SUMMARY

[0004] In order to solve the above technical problems, the smart monitoring method and system for assembled pipe gallery splicing construction based on Internet of Things are provided to solve the existing problems.

[0005] The technical problem of the application is solved by providing a smart monitoring method and system for assembled pipe gallery splicing construction based on Internet of Things, which comprises the following steps:

[0006] In the first aspect, the application provides a smart monitoring method for assembled pipe gallery splicing construction based on Internet of Things, which comprises the following steps:

[0007] Collect all internal wall gray scale images of the pipe gallery at each time, label the internal wall gray scale images, extract the regions of each splicing joint in all internal wall gray scale images at each time, and record them as the regions of each splicing joint at each time. Select a splicing joint region that does not appear leakage, record it as a standard joint region, and collect the humidity of the space position of each splicing joint in the pipe gallery at each time.

[0008] Edge detection is performed on the splicing joint region, the difference in gray scale value distribution between each splicing joint region and the standard joint region at each time is analyzed, the gray scale deviation is calculated, and the first evaluation value of each splicing joint region at each time is calculated in combination with the irregular distribution of the edge pixels in the splicing joint region.

[0009] extracting connected domains in each splicing joint region at each time, and obtaining a main direction of each connected domain; analyzing consistency of the main direction of each connected domain with a direction of a splicing joint at a position where the connected domain is located, calculating a direction consistency degree, determining a second evaluation value of each splicing joint region at each time in combination with a change trend of a gray value of a pixel point in the main direction of different connected domains, and obtaining a leakage risk value of each splicing joint region at each time in combination with a first evaluation value;

[0010] calculating a humidity deviation degree through a humidity deviation condition of a space position of each splicing joint at each time, obtaining a discrimination coefficient of each splicing joint region at each time in combination with the leakage risk value, and performing real-time monitoring and evaluation on leakage of the splicing joint in the pipe gallery.

[0011] Preferably, the calculation of the gray deviation amount comprises:

[0012] extracting a gray histogram of each splicing joint region at each time, and composing a gray distribution sequence from pixel point numbers of all gray levels in the gray histogram; extracting a gray histogram of a standard joint region, and composing a standard distribution sequence from pixel point numbers of all gray levels in the gray histogram;

[0013] calculating a distance between the gray distribution sequence of each splicing joint region at each time and the standard distribution sequence as a gray deviation amount of each splicing joint region at each time.

[0014] Preferably, the calculation of the first evaluation value of each splicing joint region at each time comprises:

[0015] calculating a fractal dimension of all edge pixel points in each splicing joint region at each time;

[0016] the first evaluation value is a product of the gray deviation amount and the fractal dimension.

[0017] Preferably, the calculation of the direction consistency degree comprises:

[0018] an angle between the main direction of each connected domain and a horizontal direction is recorded as a first angle;

[0019] a corresponding position of each connected domain in the standard joint region is recorded as a sub-region, linear fitting is performed on all edge pixel points in the sub-region, and an angle between a fitting straight line and the horizontal direction is recorded as a second angle;

[0020] a cosine value of a difference between the first angle and the second angle is calculated as the direction consistency degree of each connected domain.

[0021] Preferably, the determination of the second evaluation value of each splicing joint region at each time comprises:

[0022] extracting a skeleton line of each connected domain, performing trend decomposition on the gray value of all pixel points on the skeleton line, and calculating a trend intensity;

[0023] The second evaluation value is the average of the product of the direction consistency degree and the trend intensity of all connected domains in each joint region at each time.

[0024] Preferably, the leakage risk value is the product of the first evaluation value and the second evaluation value.

[0025] Preferably, the calculation of the humidity deviation degree comprises: obtaining a segmentation threshold of the humidity of the space position of each joint at each time; calculating the difference between the humidity of the space position of each joint at each time and the segmentation threshold, denoted as a deviation amount, and performing positive mapping on the deviation amount as the humidity deviation degree of the space position of each joint at each time.

[0026] Preferably, the discrimination coefficient is the normalized result of the product of the humidity deviation degree and the leakage risk value.

[0027] Preferably, the real-time monitoring and evaluation of the leakage of the joints in the pipe gallery comprises: if the discrimination coefficient of each joint region at each time is greater than a preset threshold, then the joint region leaks at this time, otherwise, no leakage occurs.

[0028] In a second aspect, the embodiments of the present application also provide an intelligent monitoring system for the joint construction of the fabricated pipe gallery based on the Internet of Things, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the intelligent monitoring method for the joint construction of the fabricated pipe gallery based on the Internet of Things.

[0029] The present application has at least the following beneficial effects:

[0030] The application calculates the gray deviation amount by analyzing the deviation of the gray values of the pixel points in the splicing joint area, which has the beneficial effect of considering the gray difference between the splicing joint area and the non-leaked splicing joint area to preliminarily reflect the possibility of the abnormality of the splicing joint area; calculates the first evaluation value of each splicing joint area at each time, which has the beneficial effect of considering the complex situation and irregular features of the edge in the splicing joint area to preliminarily evaluate the leakage risk situation of the splicing joint area; analyzes the consistency of the main direction of each connected domain and the direction of the splicing joint at the position, calculates the direction consistency degree, which has the beneficial effect of considering the consistency of the main direction of the connected domain and the direction of the splicing joint to reflect the possibility of the connected domain being a leakage area, thereby distinguishing the interference of the structural joint and the concrete cracking joint on the leakage phenomenon of the splicing joint and avoiding the interference of the structural joint and the concrete cracking joint on the leakage phenomenon of the splicing joint; determines the second evaluation value of each splicing joint area at each time in combination with the change trend of the gray values of the pixel points in the main direction of different connected domains, which has the beneficial effect of considering the trend change of the gray values of the pixel points caused by the diffusion and distribution of water drops at the leakage position, reducing the interference of the pressure cracks and the cracking joints; obtains the leakage risk value of each splicing joint area at each time, which has the beneficial effect of comprehensively evaluating the risk degree of the leakage of the splicing joint area; secondly, the humidity deviation degree is calculated to obtain the discrimination coefficient of each splicing joint area at each time, the leakage of the splicing joint in the pipe gallery is monitored and evaluated in real time, which has the beneficial effect of combining the deviation of the real-time humidity in the air at the space position of the splicing joint, comprehensively considering the image feature information and the humidity change in the space, and evaluating the leakage risk of the splicing joint in the pipe gallery in multiple dimensions, which can reduce the interference of the structural joint, the pressure cracks and the cracking joints on the detection, improve the accuracy of the detection of the leakage of the splicing joint in the pipe gallery, and timely find the early signs of the leakage. BRIEF DESCRIPTION OF DRAWINGS

[0031] The application will be further described in detail below with reference to the accompanying drawings.

[0032] Figure 1 The step flow chart of the method for monitoring the intelligent construction of the fabricated pipe gallery based on the Internet of Things provided by the embodiment of the application is shown in the figure.

[0033] Figure 2 The step flow chart of the method for obtaining the discrimination coefficient provided by the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical scheme and advantages of the application more clear, the method and system for monitoring the intelligent construction of the fabricated pipe gallery based on the Internet of Things proposed by the application will be further described in detail below with reference to the accompanying drawings and implementation examples. It should be understood that the specific embodiments described herein are only used to explain the application and not to limit the application.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0036] Please refer to Figure 1 , which shows the step flow chart of the Internet of Things-based prefabricated pipe gallery splicing construction intelligent monitoring method provided by an embodiment of the application. The method comprises the following steps:

[0037] Step 1, collect all the inner wall gray scale images of the pipe gallery at each time, label the inner wall gray scale images, extract the area of each splicing joint in all the inner wall gray scale images at each time, and mark it as the area of each splicing joint at each time. Select a splicing joint area that does not appear to leak, mark it as a standard joint area, and collect the humidity of the space position of each splicing joint in the pipe gallery at each time.

[0038] The high-voltage, communication and other cables in the prefabricated pipe gallery pipeline are easily disturbed by water vapor, and the leakage of water has a huge impact on the normal operation of the internal pipeline, which can threaten the safe use of the pipeline. The prefabricated pipe gallery is composed of a plurality of prefabricated concrete pipe pieces. The connection between each prefabricated pipe piece is usually in the form of a flat mouth. Two grooves are reserved at one end of the connection for the installation of a sealing strip, and no groove is reserved at the other end. The sealing strip is a composite elastic sealing strip. When the two prefabricated pipe pieces are aligned and spliced, the sealing strip in the middle of the two prefabricated pipe pieces is squeezed, and the compressed sealing strip expands to both sides to fill the small gap between the groove and the butt joint surface.

[0039] Among them, the splicing joint between the two prefabricated pipe pieces is the most likely place for leakage in the pipe gallery. Affected by the rising underground water level in the rainy season, the splicing joint in the pipe gallery has the risk of sudden large flow and jet leakage under the action of a large water head difference. Therefore, it is necessary to monitor the prefabricated pipe gallery after construction. Since the ambient light in the pipe gallery is dark, an infrared camera is installed at a certain distance along the extension direction of the pipe gallery at the middle position of the top of the pipe gallery, so that the field of view of the lens can capture the splicing joint area of the inner wall on both sides of the pipe gallery. Through all the infrared cameras, the inner wall images of the pipe gallery at each time are collected in real time, the inner wall images of the pipe gallery are processed by gray scale, all the inner wall gray scale images at each time are obtained, and a humidity sensor is arranged at the top position of each splicing joint in the pipe gallery to collect the humidity of the space position of each splicing joint in the pipe gallery at each time.

[0040] In the embodiment, an infrared camera is installed every 20 meters along the extension direction of the pipe gallery at the middle position of the top of the pipe gallery, the lens is inclined downward by 30°, so that the field of view of the lens can capture the spliced joint area of the inner wall on both sides of the pipe gallery; secondly, the collection time interval of the camera and the humidity sensor is 1s, as other implementation manners, the implementer can set it according to the actual situation; thirdly, the grayscale processing is a known technology, which will not be described here.

[0041] Secondly, due to the existence of the visual angle deviation of the camera, the spliced joint of the pipe gallery in the inner wall grayscale image is deformed, and the visual angle correction of the inner wall grayscale image is performed through the distortion correction algorithm.

[0042] It should be noted that the distortion correction algorithm is a known technology, which will not be described here.

[0043] Further, the inner wall grayscale image is artificially labeled, the area where each spliced joint is located is extracted from all the inner wall grayscale images at each time, which is recorded as each spliced joint area at each time, and a spliced joint area without leakage is artificially selected, which is recorded as a standard joint area.

[0044] It should be noted that when labeling, the area where each spliced joint is located in the inner wall grayscale image is recorded as each spliced joint area, as other implementation manners, the implementer can set it according to the actual situation, since the visual angle of the camera is fixed, only the area where each spliced joint is located in the first collected inner wall grayscale image needs to be labeled once, and subsequent dynamic monitoring can be performed, so that the area where each spliced joint is located in the inner wall grayscale image and the humidity of the space position corresponding to each spliced joint are matched.

[0045] At this point, the area of each spliced joint in all the inner wall grayscale images at each time and the humidity of the space position of each spliced joint in the pipe gallery at each time are obtained.

[0046] Step 2, edge detection is performed on the spliced joint area, the difference between the pixel grayscale value distribution of each spliced joint area and the standard joint area at each time is analyzed, the grayscale deviation is calculated, and the first evaluation value of each spliced joint area at each time is calculated in combination with the irregular distribution of the edge pixels in the spliced joint area.

[0047] Further, in the splicing joint area in the pipe gallery, due to the existence of the sealing strip inside the joint, the joint presents a vertical black line occupying a small width, and the remaining non-joint is mainly the structure formed after the concrete pouring, which presents a grayish white color as a whole; secondly, for the splicing joint area without leakage, the edge of the splicing joint is relatively regular, presenting a regular rectangular distribution, and for the splicing joint area with leakage, water droplets or water flow will spread along the splicing joint to both sides, the edge of the splicing joint is blurred and presents an irregular edge distribution. Therefore, by analyzing the gray difference between each splicing joint area and the standard joint area at each time, and the regularity of the edge in the splicing joint area, a first evaluation value is calculated, specifically:

[0048] extracting the gray level histogram of each splicing joint area at each time, and the pixel point number of all gray levels in the gray level histogram forms a gray distribution sequence;

[0049] extracting the gray level histogram of the standard joint area, and the pixel point number of all gray levels in the gray level histogram forms a standard distribution sequence;

[0050] It should be noted that the process of obtaining the gray level histogram is a known technology, which will not be repeated here.

[0051] The distance between the gray distribution sequence of each splicing joint area at each time and the standard distribution sequence is calculated as the gray deviation of each splicing joint area at each time;

[0052] In this embodiment, the distance is measured by calculating the DTW distance between the gray distribution sequence of each splicing joint area at each time and the standard distribution sequence, wherein the DTW distance is a known technology, which will not be repeated here.

[0053] Edge detection is performed on each splicing joint area at each time, all edge pixels are extracted, and the fractal dimension of all edge pixels is calculated;

[0054] In this embodiment, Canny edge detection algorithm is used for edge detection, wherein the Canny edge detection algorithm and the calculation of fractal dimension are both known technologies, which will not be repeated here.

[0055] The product of the gray deviation and the fractal dimension is taken as the first evaluation value of each splicing joint area at each time;

[0056] It should be noted that the greater the gray scale deviation amount, the greater the difference between the gray scale distribution of the splicing seam area and the standard seam area at this time, and the greater the possibility of abnormality of the splicing seam area. Secondly, the greater the fractal dimension, the more complex and irregular the edge of the splicing seam area. The greater the first evaluation value, the more significant the gray scale abnormality in the splicing seam area at this time, and the more irregular the edge, and the higher the possibility of leakage risk of the splicing seam area.

[0057] At this point, the first evaluation value of each splicing seam area at each time is obtained.

[0058] Step 3, extracting the connected domains in each splicing seam area at each time, and obtaining the main direction of each connected domain; analyzing the consistency of the main direction of each connected domain and the direction of the splicing seam at its location, calculating the direction consistency degree, and combining the change trend of the gray scale values of the pixels in the main direction of different connected domains to determine the second evaluation value of each splicing seam area at each time.

[0059] Further, when the stress at the splicing seam is uneven or changes greatly, and when cracks and fractures appear at the splicing seam, the gray scale deviation from the standard seam area will also be greater. There will be some errors in judging the leakage state only by the first evaluation value. When the splicing seam area leaks, due to the influence of gravity, there is a downward diffusion trend, basically showing a diffusion form from the stress point to both sides, forming a narrow upper part and a wide lower part affected by collection and diffusion. In addition, when the splicing seam at the top of the pipe gallery leaks, it will also spread to both sides along the splicing seam, and the distribution direction of the leakage area formed will also be consistent with the direction of the splicing seam. However, the direction of the cracks and fractures is related to the stress, and the deviation between the direction of the cracks and the direction of the splicing seam is large.

[0060] Therefore, the consistency of the main direction of the connected domain in the splicing seam area and the direction of the splicing seam at its location is analyzed, and the direction consistency degree is calculated, which is specifically:

[0061] Obtaining all connected domains in each splicing seam area at each time, and extracting the main direction of each connected domain;

[0062] In this embodiment, the halcon region direction operator is used to obtain the main direction of the connected domain, wherein the halcon region direction operator and the extraction of the connected domain are known technologies, and will not be described here.

[0063] The angle between the main direction of each connected domain and the horizontal direction is denoted as the first angle;

[0064] The corresponding position of each connected domain in the standard seam area is denoted as a sub-area, and linear fitting is performed on all edge pixels in the sub-area to calculate the angle between the fitting straight line and the horizontal direction, which is denoted as the second angle.

[0065] In the embodiment, the least square method is used for linear fitting, which is a known technology and will not be described here.

[0066] It should be noted that if the connected domain appears to be permeated, the connected domain has a splicing joint of a part of the segment. The edge pixel points caused by the leakage are mainly distributed along the splicing joint direction. Therefore, the direction of the fitted straight line can reflect the direction of the splicing joint of the segment.

[0067] The cosine value of the difference between the first angle and the second angle is calculated as the direction consistency degree of each connected domain.

[0068] In the embodiment, the cosine value of the absolute value of the difference between the first angle and the second angle is calculated as the direction consistency degree of each connected domain.

[0069] It should be noted that if the connected domain appears to be permeated, the direction of the region formed by the leakage is consistent with the direction of the splicing joint. The smaller the difference between the first angle and the second angle, the greater the obtained direction consistency degree.

[0070] Secondly, due to the diffusion distribution of water droplets at the leakage, the gray scale of the pixel points gradually becomes lighter from black due to diffusion, which has obvious trend. The crack gap trend of the fracturing crack and the cracking crack is uneven, the change of the gray scale of the pixel points at the crack is relatively large, and has no obvious trend. Therefore, by analyzing the distribution trend of the gray scale of the pixel points in the connected domain, the second evaluation value is calculated in combination with the direction consistency degree, which is specifically:

[0071] The skeleton line of each connected domain is extracted, the trend decomposition of the gray scale of all pixel points on the skeleton line is performed, and the trend intensity is calculated.

[0072] It should be noted that the extraction of the skeleton line is a known technology and will not be described here. Secondly, the STL (Seasonal and Trend decomposition using Loess) trend decomposition algorithm is used for trend decomposition, wherein the STL trend decomposition algorithm and the calculation process of the trend intensity are known technologies and will not be described here. Through the STL trend decomposition algorithm, the gray scale of all pixel points on the skeleton line is decomposed into a trend term and a residual term. The calculation formula of the trend intensity is: , wherein is the trend intensity, is the variance of the residual term, is the variance of the trend term and the residual term, is the maximum value.

[0073] The average of the product of the direction consistency degree and the trend intensity of all connected domains in each splicing seam area at each time is taken as the second evaluation value of each splicing seam area at each time.

[0074] It should be noted that the greater the trend intensity, the greater the gray change of the pixel points on the skeleton line in the connected domain has a significant trend, and the greater the second evaluation value obtained, the greater the possibility of the existence of the abnormal splicing seam area at this time, reflecting the possibility of the existence of the leakage phenomenon.

[0075] At this point, the second evaluation value of each splicing seam area at each time is obtained.

[0076] Step 4, based on the first evaluation value and the second evaluation value, the leakage risk value of each splicing seam area at each time is obtained; the humidity deviation degree is calculated through the humidity deviation of the space position of each splicing seam at each time, and the discrimination coefficient of each splicing seam area at each time is obtained by combining the leakage risk value, so as to monitor and evaluate the leakage of the splicing seam in the pipe gallery in real time.

[0077] Further, based on the first evaluation value and the second evaluation value, the leakage risk value is determined, specifically:

[0078] The product of the first evaluation value and the second evaluation value is taken as the leakage risk value of each splicing seam area at each time.

[0079] It should be noted that the greater the leakage risk value, the higher the risk of leakage of the splicing seam area at this time.

[0080] Secondly, when the splicing seam area leaks, due to the evaporation and diffusion of water droplets, the air humidity value is large, and thus the humidity deviation of the space position of each splicing seam in the pipe gallery at each time is analyzed, and the discrimination coefficient is determined by combining the leakage risk value, specifically:

[0081] The segmentation threshold of the humidity of the space position of all splicing seams at each time is obtained.

[0082] In this embodiment, the segmentation threshold is obtained by using the Otsu threshold segmentation algorithm, and the Otsu threshold segmentation algorithm is a known technology and will not be described here.

[0083] The difference between the humidity of the space position of each splicing seam at each time and the segmentation threshold is calculated, denoted as the deviation amount, and the deviation amount is positively mapped as the humidity deviation degree of the space position of each splicing seam at each time.

[0084] In this embodiment, the specific process of positive mapping is: the positive mapping is performed by using an exponential function, assuming that the deviation amount is denoted as The result of is taken as the result of positive mapping, wherein, an exponential function with a natural constant as a base.

[0085] It should be noted that since each splicing joint area corresponds to the humidity of the space position of the splicing joint, the greater the humidity deviation degree, the greater the humidity deviation of the area where the splicing joint is located.

[0086] The normalized result of the product of the humidity deviation degree and the leakage risk value is used as the discrimination coefficient of each splicing joint area at each time;

[0087] In this embodiment, the sigmoid function is used for normalization processing, wherein the sigmoid function is a known technology and will not be described here.

[0088] It should be noted that the greater the discrimination coefficient, the more likely it is that the area where the splicing joint is located will leak, wherein the step flow chart of the method for obtaining the discrimination coefficient provided in the present application is as shown in Figure 2 .

[0089] If the discrimination coefficient of each splicing joint area at each time is greater than a preset threshold value, then at this time the splicing joint area leaks, otherwise, it does not leak;

[0090] In this embodiment, the preset threshold value is 0.43, and the determination process of the preset threshold value is as follows:

[0091] When the pipe gallery is inspected in the historical period, all the inner wall gray scale images and their corresponding humidity when the pipe gallery leaks multiple times and does not leak are collected, the discrimination coefficients are calculated respectively, and the preset threshold value is selected by continuously adjusting the value range of , the false positive rate and the false negative rate corresponding to each threshold value are calculated, and thus the ROC curve is drawn, and the threshold value corresponding to the minimum false negative rate is selected on the ROC curve as the preset threshold value;

[0092] In this embodiment, by collecting 500 times of leakage and non-leakage data, the threshold value corresponding to the minimum false negative rate is finally selected as 0.43, and the preset threshold value is 0.43. As other implementation manners, the implementer can determine it according to the actual situation. It should be noted that the calculation of the true positive rate and the false positive rate and the drawing of the ROC curve are known technologies and will not be described here.

[0093] The splicing joint area where the pipe gallery leaks is marked and positioned, and the operation and maintenance personnel develop a reasonable maintenance scheme.

[0094] Based on the same inventive concept as the above method, the embodiment of the present application also provides an Internet of Things-based fabricated pipe gallery splicing construction intelligent monitoring system, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above Internet of Things-based fabricated pipe gallery splicing construction intelligent monitoring methods when executing the computer program.

[0095] It should be understood that, although Figure 1 The steps in the flowchart of the method can be executed in the order indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, the execution of the steps has no strict order limitation, and the steps can be executed in other orders. Moreover, Figure 1 At least part of the steps in the method can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the sub-steps or stages is not necessarily sequential, but can be alternately executed with other steps or sub-steps or stages of other steps.

[0096] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0097] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation of the present application. It should be pointed out that, for ordinary skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application, without departing from the technical solution of the present application, all belong to the protection scope of the technical solution of the present application.

Claims

1. A smart monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things, characterized in that, The method includes the following steps: Collect all grayscale images of the inner wall of the utility tunnel at each time point, label the grayscale images of the inner wall, extract the area where each splice joint is located in all grayscale images of the inner wall at each time point, and record it as the splice joint area at each time point; select a splice joint area where no leakage occurs, record it as the standard joint area, and collect the humidity of the spatial location of each splice joint in the utility tunnel at each time point. Edge detection is performed on the splicing seam area. The differences in gray value distribution of pixels between each splicing seam area and the standard seam area at each time point are analyzed. The gray value deviation is calculated. Combined with the irregular distribution of edge pixels in the splicing seam area, the first evaluation value of each splicing seam area at each time point is calculated. Extract the connected components within each seam region at each time point and obtain the main direction of each connected component; analyze the consistency between the main direction of each connected component and the direction of the seam at its location, calculate the direction consistency, and combine the gray value change trend of the pixels in the main direction of different connected components to determine the second evaluation value of each seam region at each time point. Combine the first evaluation value to obtain the leakage risk value of each seam region at each time point. By calculating the humidity deviation at each splice location at different times, and combining it with the leakage risk value, the discrimination coefficient of each splice area at different times is obtained, so as to monitor and evaluate the leakage of splices in the pipe gallery in real time.

2. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The calculation of grayscale deviation includes: Extract the grayscale histogram of each splicing seam region at each time point, and form a grayscale distribution sequence by the number of pixels at all gray levels in the grayscale histogram; extract the grayscale histogram of the standard seam region, and form a standard distribution sequence by the number of pixels at all gray levels in the grayscale histogram. Calculate the distance between the grayscale distribution sequence of each splicing seam region and the standard distribution sequence at each time point, and use it as the grayscale deviation of each splicing seam region at each time point.

3. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The calculation of the first evaluation value of each seam area at each time point includes: Calculate the fractal dimension of all edge pixels within each seam region at each time step; The first evaluation value is the product of the grayscale deviation and the fractal dimension.

4. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The calculation of directional consistency includes: The angle between the main direction and the horizontal direction of each connected domain is denoted as the first angle. The corresponding positions of each connected component in the standard seam region are denoted as sub-regions. Linear fitting is performed on all edge pixels within the sub-regions, and the angle between the fitted line and the horizontal direction is calculated and denoted as the second angle. Calculate the cosine of the difference between the first included angle and the second included angle, and use it as the directional consistency of each connected domain.

5. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The determination of the second evaluation value for each seam area at each time point includes: Extract the skeleton lines of each connected component, perform trend decomposition on the gray values ​​of all pixels on the skeleton lines, and calculate the trend intensity. The second evaluation value is the average of the product of the directional consistency and the trend intensity of all connected domains within each seam region at each time point.

6. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The leakage risk value is the product of the first assessment value and the second assessment value.

7. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The calculation of humidity deviation includes: obtaining the humidity segmentation threshold of all splice seams at each time point; calculating the difference between the humidity of each splice seam at each time point and the segmentation threshold, recording it as the deviation, and performing a positive mapping on the deviation to serve as the humidity deviation of each splice seam at each time point.

8. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The discrimination coefficient is the normalized result of the product of the humidity deviation and the leakage risk value.

9. The intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in claim 1, characterized in that, The real-time monitoring and evaluation of leakage at the joints within the utility tunnel includes: if the discrimination coefficient of each joint area at any given time is greater than a preset threshold, then leakage has occurred in that joint area; otherwise, no leakage has occurred.

10. An intelligent monitoring system for prefabricated pipe gallery splicing construction based on the Internet of Things, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent monitoring method for prefabricated pipe gallery splicing construction based on the Internet of Things as described in any one of claims 1-9.

Images