Fabricated pipe gallery splicing construction intelligent monitoring method and system based on Internet of Things

Abstract

The invention 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, and the method comprises the steps: collecting all inner wall grayscale images of a pipe gallery at each moment, extracting an area where each splicing seam is located in the inner wall grayscale images, and recording the area as each splicing seam area at each moment; the humidity of the spatial position where each splicing seam in the pipe gallery is located at each moment is collected; calculating a gray scale deviation value, and calculating a first evaluation value of each splicing seam area at each moment; the direction consistency degree is calculated, and a second evaluation value and a leakage risk value of each splicing seam area at each moment are determined; the humidity deviation degree is calculated, a discrimination coefficient is obtained, and real-time monitoring and evaluation are conducted on leakage occurring in the splicing seam in the pipe gallery. According to the method, the leakage risk of the splicing seam in the pipe gallery is evaluated in a multi-dimensional manner, so that the interference of a structural seam, a fracturing seam and a cracking seam on detection can be reduced, and the accuracy of detecting the leakage condition of the splicing seam in the pipe gallery is improved.

Description

Technical Field

[0001] The present application relates to the technical field of pipeline corridor leakage monitoring, and specifically to an intelligent monitoring method and system for the splicing construction of prefabricated pipeline corridors based on the Internet of Things. Background Art

[0002] In urban infrastructure construction, prefabricated pipe corridors, as important underground facilities, play a key role in accommodating and protecting various pipelines. Prefabricated pipe corridors are composed of multiple prefabricated concrete segments. The joints of the pipe corridors are the weak links of the prefabricated assembled structure. Due to the large number of joints in the pipe corridors, they are affected by groundwater pressure and geological soil, resulting in gaps in the pipe corridor structure, which is prone to leakage and threatens the safety of internal pipelines.

[0003] When traditional methods are used to detect leakage in prefabricated pipe corridors, due to the complex internal environment of the pipe corridor, they only rely on the edge feature information in a single internal image of the pipe corridor. They do not consider the interference of complex conditions such as the inherent structural joints in the inner wall of the pipe corridor and concrete cracks. As a result, early signs of leakage cannot be detected in time, resulting in misjudgment of leakage detection at the joints in the pipe corridor, affecting the accuracy of pipe corridor leakage monitoring. Summary of the Invention

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

[0005] The solution to the technical problem in this application is to provide an intelligent monitoring method and system for the splicing construction of prefabricated pipe corridors based on the Internet of Things, including the following steps: In a first aspect, an embodiment of the present application provides an intelligent monitoring method for the splicing construction of an assembled pipe gallery based on the Internet of Things, the method comprising the following steps: Collect all grayscale images of the inner wall of the pipe gallery at each time, annotate the grayscale images, extract the area where each joint is located in all the grayscale images of the inner wall at each time, and record it as the joint area at each time; select a joint area without leakage and record it as the standard joint area, and collect the humidity of each joint in the pipe gallery at each time. Perform edge detection on the seam area, analyze the difference in grayscale value distribution of pixels between each seam area and the standard seam area at each moment, calculate the grayscale deviation, and calculate the first evaluation value of each seam area at each moment based on the irregular distribution of edge pixels in the seam area; The connected domains within each seam area at each moment are extracted, and the main direction of each connected domain is obtained. The consistency between the main direction of each connected domain and the direction of the seam at its location is analyzed, and the direction consistency is calculated. The second evaluation value of each seam area at each moment is determined by combining the changing trend of the grayscale values ​​of the pixels in the main directions of different connected domains. Combined with the first evaluation value, the leakage risk value of each seam area at each moment is obtained. The humidity deviation is calculated by analyzing the humidity deviation of the spatial position of each joint at each moment. Combined with the leakage risk value, the discrimination coefficient of each joint area at each moment is obtained, and the leakage of the joints in the pipeline corridor is monitored and evaluated in real time.

[0006] Preferably, the calculating of the grayscale deviation comprises: Extract the grayscale histogram of each joint area at each moment, and form a grayscale distribution sequence with the number of pixels of all gray levels in the grayscale histogram; extract the grayscale histogram of the standard joint area, and form a standard distribution sequence with the number of pixels of all gray levels in the grayscale histogram; The distance between the grayscale distribution sequence of each seam region at each moment and the standard distribution sequence is calculated as the grayscale deviation of each seam region at each moment.

[0007] Preferably, the calculating of the first evaluation value of each seam area at each moment includes: Calculate the fractal dimension of all edge pixels in each seam area at each moment; The first evaluation value is the product of the grayscale deviation and the fractal dimension.

[0008] Preferably, the calculating direction consistency includes: The angle between the main direction of each connected domain and the horizontal direction is recorded as the first angle; The corresponding position of each connected domain in the standard seam area is recorded as a sub-region, and a linear fit is performed on all edge pixels in the sub-region. The angle between the fitted line and the horizontal direction is calculated and recorded as the second angle; The cosine value of the difference between the first angle and the second angle is calculated as the direction consistency of each connected domain.

[0009] Preferably, determining the second evaluation value of each seam area at each moment includes: Extract the skeleton line of each connected domain, perform trend decomposition on the grayscale values ​​of all pixels on the skeleton line, and calculate the trend intensity; The second evaluation value is the average of the product of the direction consistency and the trend strength of all connected domains in each joint seam area at each moment.

[0010] Preferably, the leakage risk value is the product of the first assessment value and the second assessment value.

[0011] Preferably, the calculation of the humidity deviation includes: obtaining a segmentation threshold of the humidity of the spatial positions of all seams at each moment; calculating the difference between the humidity of the spatial position of each seam at each moment and the segmentation threshold, recording it as the deviation, and performing positive mapping on the deviation as the humidity deviation of the spatial position of each seam at each moment.

[0012] Preferably, the discrimination coefficient is a normalized result of the product of the humidity deviation and the leakage risk value.

[0013] Preferably, the real-time monitoring and evaluation of leakage at the joints in the pipe gallery includes: if the discrimination coefficient of each joint area at each moment is greater than a preset threshold, leakage occurs in the joint area at that moment; otherwise, no leakage occurs.

[0014] On the second aspect, an embodiment of the present application also provides an intelligent monitoring system for the splicing construction of prefabricated pipe corridors based on the Internet of Things, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned intelligent monitoring methods for the splicing construction of prefabricated pipe corridors based on the Internet of Things.

[0015] This application has at least the following beneficial effects: The present application calculates the grayscale deviation by analyzing the deviation of the grayscale values ​​of the pixels in the joint seam area, and its beneficial effect is that it takes into account the grayscale difference between the joint seam area and the non-leaking joint seam area, so as to preliminarily reflect the possibility of abnormality in the joint seam area; calculates the first evaluation value of each joint seam area at each moment, and its beneficial effect is that it takes into account the complex situation and irregular characteristics of the edges in the joint seam area, so as to preliminarily evaluate the leakage risk of the joint seam area; analyzes the consistency of the main direction of each connected domain with the direction of the joint at its location, and calculates the direction consistency, and its beneficial effect is that it takes into account the consistency of the main direction of the connected domain with the direction of the joint, so as to reflect the possibility that the connected domain is a leakage area, thereby distinguishing the interference of structural joints and concrete cracks, and avoiding the interference of structural joints and concrete cracks on the leakage phenomenon at the joint seam; combines the pixel points in the main direction of different connected domains to calculate the direction consistency. The changing trend of the grayscale value is used to determine the second evaluation value of each joint area at each moment. Its beneficial effect is that it takes into account the trend change of the grayscale value of the pixel point caused by the diffusion distribution of water droplets at the leakage point, thereby reducing the interference of compression cracks and open cracks; the leakage risk value of each joint area at each moment is obtained, and its beneficial effect is that the risk degree of leakage in the joint area is comprehensively evaluated; secondly, the humidity deviation is calculated to obtain the discrimination coefficient of each joint area at each moment, and the leakage occurring in the joints in the corridor is monitored and evaluated in real time. Its beneficial effect is that it combines the deviation of the real-time humidity in the air at the spatial position of the joint, and comprehensively evaluates the risk of leakage in the joints in the corridor in multiple dimensions based on the comprehensive image feature information and humidity changes in space, which can reduce the interference of structural joints, compression cracks and open cracks on detection, improve the accuracy of leakage detection in the joints in the corridor, and promptly discover early signs of leakage. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The IoT-based intelligent monitoring method for prefabricated pipe gallery splicing construction of this application is further described in detail below with reference to the accompanying drawings.

[0017] Figure 1 A flowchart of the steps of the intelligent monitoring method for the splicing construction of prefabricated pipe corridors based on the Internet of Things provided in an embodiment of the present application; Figure 2 A flowchart of the steps of the method for obtaining the discriminant coefficient provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions, and advantages of this application more clearly understood, the following, in conjunction with the accompanying drawings and implementation examples, further details are provided on the IoT-based intelligent monitoring method and system for prefabricated pipe gallery splicing construction proposed in this application. It should be understood that the specific embodiments described herein are intended only to explain this application and are not intended to limit this application.

[0019] Unless defined otherwise, 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.

[0020] See also Figure 1 , which shows a flowchart of a method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things provided by one embodiment of the present application, the method comprising the following steps: Step 1: Collect all grayscale images of the inner wall of the pipe gallery at each time, mark the grayscale images of the inner wall, extract the area where each splicing seam is located in all the grayscale images of the inner wall at each time, and record it as the splicing seam area at each time; select a splicing seam area without leakage, record it as the standard seam area, and collect the humidity of the spatial position of each splicing seam in the pipe gallery at each time.

[0021] High-voltage, communication, and other cables in prefabricated pipe corridors are susceptible to moisture interference. Water leakage can significantly impact the normal operation of internal pipelines and threaten their safe use. Prefabricated pipe corridors are composed of multiple precast concrete segments. Each precast segment is typically joined at a flat joint, with two grooves reserved at one end for the installation of a sealing strip. The other end does not have a groove. The sealing strip is made of a composite elastic rubber seal. When two precast segments are aligned and spliced, the sealing strip between the two precast segments is squeezed. The compressed sealing strip expands to both sides, filling the tiny gap between the groove and the joint surface.

[0022] Among them, the joints between two prefabricated pipe segments are the most prone to leakage in the tunnel. Affected by the rising groundwater level during the rainy season, the joints in the tunnel present a safety risk of sudden large flow and jet-like leakage due to the large head difference. Prefabricated tunnels are prone to leakage 7 to 14 days after construction. Therefore, it is necessary to monitor the prefabricated tunnels after construction. Due to the dim ambient light inside the tunnel, an infrared camera is installed at a certain interval in the middle of the tunnel top along the tunnel extension direction. The lens's field of view can capture the joint area of ​​the inner walls on both sides of the tunnel. Through all infrared cameras, all images of the inner walls of the tunnel at all times are collected in real time. The images of the inner walls of the tunnel are grayscaled to obtain all grayscale images of the inner walls at all times. Humidity sensors are deployed at the top of each joint in the tunnel to collect the humidity of each joint in the tunnel at each time. In this embodiment, an infrared camera is installed in the middle of the top of the tunnel every 20 meters along the extension direction of the tunnel, and the lens is tilted downward by 30° so that the field of view of the lens can capture the joint seam area of ​​the inner walls on both sides of the tunnel; secondly, the collection time interval of the camera and the humidity sensor is 1s. As other implementation methods, the implementer can set it according to actual conditions; secondly, grayscale processing is a well-known technology and will not be repeated here.

[0023] Secondly, since the camera may have a viewing angle deviation, the corridor joints in the grayscale image of the inner wall are deformed. The viewing angle of the inner wall grayscale image is corrected through a distortion correction algorithm.

[0024] It should be noted that the distortion correction algorithm is a well-known technology and will not be described in detail here.

[0025] Then, the grayscale images of the inner wall are manually labeled. The areas where the joints are located are extracted from all the grayscale images of the inner wall at each moment, and recorded as the joint areas at each moment. A joint area without leakage is manually selected and recorded as the standard joint area. It should be noted that when marking, with each joint seam in the grayscale image of the inner wall as the center, the area extending 50 cm to the left and right is recorded as each joint seam area. As other implementation methods, the implementer can set it according to the actual situation. Since the viewing angle of the camera is fixed, it is only necessary to mark the area range of each joint seam in the first acquisition of the inner wall grayscale image by each infrared camera once. Subsequently, long-term dynamic monitoring can be carried out to match each joint seam area in the grayscale image of the inner wall with the spatial position of each joint seam corresponding to the installation position of the humidity sensor.

[0026] At this point, the humidity of each joint area in all inner wall grayscale images at each moment and the spatial position of each joint in the pipe gallery at each moment are obtained.

[0027] Step 2: Perform edge detection on the seam area, analyze the difference in grayscale value distribution of pixels between each seam area and the standard seam area at each moment, calculate the grayscale deviation, and calculate the first evaluation value of each seam area at each moment based on the irregular distribution of edge pixels in the seam area.

[0028] Furthermore, in the joint area of ​​the pipe corridor, due to the presence of sealing strips inside the joint, the joint appears as a vertical black line, occupying a smaller width, while the remaining non-joint areas are mainly structures formed after concrete pouring, and are overall grayish white; secondly, for the joint areas without leakage, the edges of the joints are relatively regular, showing a regular rectangular distribution. For the joint areas with leakage, water droplets or water flows will spread to both sides along the joints, and the edges of the joints are blurred and show an irregular edge distribution. Therefore, by analyzing the grayscale differences between each joint area and the standard joint area at each moment, as well as the regularity of the edges within the joint area, the first evaluation value is calculated, specifically: Extract the grayscale histogram of each joint area at each moment, and form a grayscale distribution sequence with the number of pixels of all gray levels in the grayscale histogram; Extract the grayscale histogram of the standard seam area and form a standard distribution sequence with the number of pixels of all gray levels in the grayscale histogram; It should be noted that the process of obtaining the grayscale histogram is a well-known technology and will not be described in detail here.

[0029] Calculate the distance between the grayscale distribution sequence of each seam area at each moment and the standard distribution sequence as the grayscale deviation of each seam area at each moment; In this embodiment, the distance is measured by calculating the DTW distance between the grayscale distribution sequence of each seam region at each moment and the standard distribution sequence, wherein the DTW distance is a well-known technology and will not be described in detail here.

[0030] Perform edge detection on each seam area at each moment, extract all edge pixels, and calculate the fractal dimension of all edge pixels; In this embodiment, the Canny edge detection algorithm is used to perform edge detection. The Canny edge detection algorithm and the calculation of the fractal dimension are both well-known technologies and will not be described in detail here.

[0031] The product of the grayscale deviation and the fractal dimension is used as the first evaluation value of each joint seam area at each moment; It should be noted that the larger the grayscale deviation is, the greater the difference in grayscale distribution between the joint area and the standard joint area is, which reflects that the possibility of abnormality in the joint area is greater. Secondly, the larger the fractal dimension is, the more complex and irregular the edge of the joint area is. The larger the first evaluation value is, the more significant the grayscale abnormality in the joint area is, and the more irregular the edge is, which reflects that the risk of leakage in the joint area is higher.

[0032] At this point, the first evaluation value of each joint seam area at each time is obtained.

[0033] Step 3: Extract the connected domains in each seam area at each moment and obtain the main direction of each connected domain; analyze the consistency between the main direction of each connected domain and the direction of the seam at its location, calculate the direction consistency, and combine the changing trend of the grayscale value of the pixel points in the main direction of different connected domains to determine the second evaluation value of each seam area at each moment.

[0034] Furthermore, due to uneven stress or large stress variations at the joints, when compression cracks and open cracks appear at the joints, their grayscale will deviate significantly from the standard joint area. Therefore, judging the leakage status based solely on the first evaluation value will result in a certain error. When leakage occurs in the joint area, the water droplets, affected by gravity, tend to diffuse from top to bottom, essentially spreading from the stress point to both sides, resulting in a narrow upper portion and a wide lower portion due to convergence and diffusion. Furthermore, when leakage occurs in the joints at the top of the tunnel, it will also spread to both sides along the joints, and the distribution direction of the resulting leakage area will also be consistent with the direction of the joints. However, the direction of the compression cracks and open cracks is related to the stress, and the direction of the cracks deviates significantly from the direction of the joints.

[0035] Therefore, the consistency between the main direction of the connected domain in the seam area and the direction of the seam at its location is analyzed, and the direction consistency is calculated, specifically: Obtain all connected domains in each joint area at each moment and extract the main direction of each connected domain; In this embodiment, the halcon area direction operator is used to obtain the main direction of the connected domain. The halcon area direction operator and the extraction of the connected domain are well-known technologies and will not be repeated here.

[0036] The angle between the main direction of each connected domain and the horizontal direction is recorded as the first angle; The corresponding position of each connected domain in the standard seam area is recorded as a sub-region, and a linear fit is performed on all edge pixels in the sub-region. The angle between the fitted line and the horizontal direction is calculated and recorded as the second angle; In this embodiment, the least square method is used for linear fitting, wherein the least square method is a well-known technology and will not be described in detail here.

[0037] It should be noted that if leakage occurs in the connected domain, there will be some seams in the connected domain. The edge pixels caused by leakage are mainly distributed along the direction of the seams. Therefore, the direction of the fitted straight line can reflect the direction of the seams in this segment.

[0038] Calculating the cosine value of the difference between the first angle and the second angle as the direction consistency of each connected domain; In this 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 of each connected domain.

[0039] It should be noted that if leakage occurs in the connected domain, the direction of the area formed by the leakage is consistent with the direction of the joint. The smaller the difference between the first angle and the second angle, the greater the resulting direction consistency.

[0040] Secondly, due to the diffusion of water droplets, the grayscale of the pixels at the leakage point gradually changes from black to light due to diffusion, showing a clear trend. However, the gaps of the pressure cracks and open cracks have uneven trends, and the grayscale changes of the pixels at the cracks fluctuate relatively greatly without a clear trend. Therefore, by analyzing the distribution trend of the grayscale values ​​of the pixels in the connected domain and combining the directional consistency, the second evaluation value is calculated, which is specifically: Extract the skeleton line of each connected domain, perform trend decomposition on the grayscale values ​​of all pixels on the skeleton line, and calculate the trend intensity; It should be noted that skeleton line extraction is a well-known technique and will not be described in detail here. Secondly, the STL (Seasonal and Trend decomposition using Loess) trend decomposition algorithm is used for trend decomposition. The STL trend decomposition algorithm and the calculation process of trend strength are well-known techniques and will not be described in detail here. The grayscale values ​​of all pixels on the skeleton line are decomposed into trend terms and residual terms using the STL trend decomposition algorithm. The calculation formula of trend strength is: ,in, is the trend strength, is the variance of the residual term, is the variance of the trend term and the residual term, To find the maximum value.

[0041] Taking the average of the product of the directional consistency and the trend strength of all connected domains in each seam area at each moment as the second evaluation value of each seam area at each moment; It should be noted that the greater the trend intensity, the more significant the trend of the grayscale change of the pixels on the skeleton line in the connected domain. The larger the second evaluation value obtained, the greater the possibility that the joint seam area is abnormal, indicating the possibility of leakage.

[0042] At this point, the second evaluation value of each joint seam area at each time is obtained.

[0043] Step 4: Based on the first evaluation value and the second evaluation value, the leakage risk value of each joint area at each moment is obtained; the humidity deviation is calculated by the humidity deviation of the spatial position of each joint at each moment, and combined with the leakage risk value, the discrimination coefficient of each joint area at each moment is obtained, and the leakage of the joints in the pipeline corridor is monitored and evaluated in real time.

[0044] Furthermore, based on the first evaluation value and the second evaluation value, a leakage risk value is determined, specifically: The product of the first evaluation value and the second evaluation value is used as the leakage risk value of each joint area at each moment; It should be noted that, the greater the leakage risk value, the higher the risk of leakage occurring in the joint seam area.

[0045] Secondly, when leakage occurs in the joint area, the air humidity value is relatively high due to the evaporation and diffusion of water droplets. Therefore, the humidity deviation of each joint in the corridor at each time is analyzed. Combined with the leakage risk value, the discrimination coefficient is determined, which is: Obtain the segmentation threshold of the humidity at the spatial location of all joints at each moment; In this embodiment, the Otsu threshold segmentation algorithm is used to obtain the segmentation threshold, wherein the Otsu threshold segmentation algorithm is a well-known technology and will not be described in detail here.

[0046] Calculating the difference between the humidity of each joint's spatial position at each moment and the segmentation threshold, recording it as a deviation, and performing positive mapping on the deviation to obtain the humidity deviation degree of each joint's spatial position at each moment; In this embodiment, the specific process of positive mapping is: positive mapping is performed through an exponential function, assuming that the deviation is recorded as ,Will The result is the result of the positive mapping, where is an exponential function with a natural constant as its base.

[0047] It should be noted that, since each seam region corresponds to the humidity of the spatial position where the seam is located, the greater the humidity deviation is, the greater the humidity deviation is in the region where the seam is located.

[0048] The normalized result of the product of the humidity deviation and the leakage risk value is used as the discrimination coefficient of each joint area at each moment; In this embodiment, the sigmoid function is used for normalization processing, wherein the sigmoid function is a well-known technology and will not be described in detail here.

[0049] It should be noted that the larger the discrimination coefficient is, the more likely leakage is to occur in the area where the joint is located. The flowchart of the method for obtaining the discrimination coefficient provided in the embodiment of the present application is as follows: Figure 2 shown.

[0050] If the discrimination coefficient of each joint seam area at each moment is greater than a preset threshold, leakage occurs in the joint seam area at this moment; otherwise, no leakage occurs; In this embodiment, the preset threshold is 0.43, and the process of determining the preset threshold is as follows: During the inspection of the pipe corridor in the historical period, all the grayscale images of the inner wall of the pipe corridor with multiple leakage and without leakage and their corresponding humidity were collected, and the discrimination coefficient was calculated respectively. The preset threshold is continuously adjusted within the value range, and the false positive rate and false negative rate corresponding to each threshold are calculated to draw the ROC curve. The threshold corresponding to the minimum false negative rate on the ROC curve is selected as the preset threshold; In this embodiment, by collecting data on 500 leakages and no leakages, the threshold corresponding to the minimum false negative rate is finally selected as 0.43, and the preset threshold value is 0.43. As other implementation methods, 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 all well-known technologies and will not be repeated here.

[0051] The joint areas where leakage occurs in the pipe gallery are marked and located, and the operation and maintenance personnel formulate a reasonable maintenance plan for it.

[0052] Based on the same inventive concept as the above-mentioned method, an embodiment of the present application also provides an intelligent monitoring system for the splicing construction of prefabricated pipe corridors based on the Internet of Things, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned intelligent monitoring methods for the splicing construction of prefabricated pipe corridors based on the Internet of Things are implemented.

[0053] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0054] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the present application. It should be noted that a person skilled in the art can make various modifications and improvements without departing from the spirit of the present application. Therefore, any simple modifications, equivalent variations, and modifications to the above embodiments made in accordance with the technical essence of the present application without departing from the content of the present application's technical solution fall within the scope of protection of the present application's technical solution.

Claims

1. An intelligent monitoring method for the splicing construction of assembled pipe corridors based on the Internet of Things is characterized by: The method comprises the following steps: Collect all grayscale images of the inner wall of the pipe gallery at each time, annotate the grayscale images, extract the area where each joint is located in all the grayscale images of the inner wall at each time, and record it as the joint area at each time; select a joint area without leakage and record it as the standard joint area, and collect the humidity of each joint in the pipe gallery at each time. Perform edge detection on the seam area, analyze the difference in grayscale value distribution of pixels between each seam area and the standard seam area at each moment, calculate the grayscale deviation, and calculate the first evaluation value of each seam area at each moment based on the irregular distribution of edge pixels in the seam area; The connected domains within each seam area at each moment are extracted, and the main direction of each connected domain is obtained. The consistency between the main direction of each connected domain and the direction of the seam at its location is analyzed, and the direction consistency is calculated. The second evaluation value of each seam area at each moment is determined by combining the changing trend of the grayscale values ​​of the pixels in the main directions of different connected domains. Combined with the first evaluation value, the leakage risk value of each seam area at each moment is obtained. The humidity deviation is calculated by analyzing the humidity deviation of the spatial position of each joint at each moment. Combined with the leakage risk value, the discrimination coefficient of each joint area at each moment is obtained, and the leakage of the joints in the pipeline corridor is monitored and evaluated in real time.

2. The method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things according to claim 1 is characterized in that: The calculating of the grayscale deviation comprises: Extract the grayscale histogram of each joint area at each moment, and form a grayscale distribution sequence with the number of pixels of all gray levels in the grayscale histogram; extract the grayscale histogram of the standard joint area, and form a standard distribution sequence with the number of pixels of all gray levels in the grayscale histogram; The distance between the grayscale distribution sequence of each seam region at each moment and the standard distribution sequence is calculated as the grayscale deviation of each seam region at each moment.

3. The method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things according to claim 1 is characterized in that: The calculating of the first evaluation value of each seam area at each moment includes: Calculate the fractal dimension of all edge pixels in each seam area at each moment; The first evaluation value is the product of the grayscale deviation and the fractal dimension.

4. The method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things according to claim 1 is characterized in that: The calculating direction consistency includes: The angle between the main direction of each connected domain and the horizontal direction is recorded as the first angle; The corresponding position of each connected domain in the standard seam area is recorded as a sub-region, and a linear fit is performed on all edge pixels in the sub-region. The angle between the fitted line and the horizontal direction is calculated and recorded as the second angle; The cosine value of the difference between the first angle and the second angle is calculated as the direction consistency of each connected domain.

5. The method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things according to claim 1 is characterized in that: Determining the second evaluation value of each seam area at each moment includes: Extract the skeleton line of each connected domain, perform trend decomposition on the grayscale values ​​of all pixels on the skeleton line, and calculate the trend intensity; The second evaluation value is the average of the product of the direction consistency and the trend strength of all connected domains in each joint seam area at each moment.

6. The method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things according to claim 1 is characterized in that: The leakage risk value is the product of the first evaluation value and the second evaluation value.

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

8. The method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things according to claim 1 is characterized in that: The discrimination coefficient is a normalized result of the product of the humidity deviation and the leakage risk value.

9. The method for intelligent monitoring of assembled pipe gallery splicing construction based on the Internet of Things according to claim 1 is characterized in that: The real-time monitoring and evaluation of leakage occurring at the joints in the pipe gallery includes: if the discrimination coefficient of each joint area at each moment is greater than a preset threshold, then leakage occurs in the joint area at this moment; otherwise, no leakage occurs.

10. An intelligent monitoring system for the splicing construction of assembled pipe corridors 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, the steps of the intelligent monitoring method for the splicing construction of prefabricated pipe corridors based on the Internet of Things as described in any one of claims 1 to 9 are implemented.

Images