Pipe gallery comprehensive monitoring and early warning method and system based on data analysis

Through data analysis, the inspection scale and control strategy are generated, and the problems of monitoring blind spots and waste of inspection resources in the pipeline corridor monitoring system are solved, and the stability and safety of the pipeline corridor are guaranteed.

CN119004392AActive Publication Date: 2024-11-22JIANGXI SIYUAN TECH CO LTD

Patent Information

Application Number
CN202411480425.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-23
Publication Date
2024-11-22
Estimated Expiration
2044-10-23

AI Technical Summary

Technical Problem

The existing pipeline monitoring system has problems such as blind spots in monitoring between nodes and limited number of inspection robots, which may not be detected and warned in time, and resource waste is common.

Method used

Through the comprehensive monitoring and early warning method of pipeline corridors based on data analysis, the abnormal monitoring results of the monitoring point are used to generate inspection scales, intelligently regulate the inspection speed and route of the inspection robot, and conduct abnormal analysis based on the monitoring point and the monitoring information of the inspection robot. , generate control strategies to ensure the stability and security of the pipeline corridor.

Benefits of technology

It effectively solves the problems of monitoring blind spots and resource waste, improves the stability and safety of pipeline operation, and ensures timely fault detection and early warning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004392A_ABST
    Figure CN119004392A_ABST
Patent Text Reader

Abstract

The invention discloses a pipe gallery comprehensive monitoring and early warning method and system based on data analysis, and relates to the technical field of pipe gallery monitoring, a fusion model analyzes multiple items of data and outputs an abnormal factor for each monitoring point, the monitoring points are subjected to abnormal analysis according to the abnormal factors, and the monitoring points are subjected to abnormal analysis according to the abnormal factors; and generating an inspection scale for each pipe gallery section in combination with the abnormal factors of the two adjacent monitoring points, generating a corresponding control strategy for the inspection robot based on the inspection scale of the pipe gallery section, comprehensively analyzing the inspection data of the inspection robot on the pipe gallery section and the inspection scale, and analyzing the abnormal condition of the pipe gallery section. And sending the abnormal analysis result of the monitoring point and the abnormal condition of the pipe gallery section to a pipe gallery management platform. The early warning system can intelligently regulate and control the inspection speed and the inspection route of the inspection robot in combination with the abnormity monitoring result of the monitoring point, and performs abnormity analysis on the pipe gallery section in combination with the monitoring information of the monitoring point and the inspection robot, so that the stability and the safety of the operation of the comprehensive pipe gallery are effectively guaranteed.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of pipe gallery monitoring, and in particular to a pipe gallery comprehensive monitoring and early warning method and system based on data analysis. Background Art

[0002] The utility corridor integrated monitoring system is a comprehensive system used to manage and monitor underground utility corridors. Underground utility corridors are a type of intensive urban infrastructure that centrally lays various municipal pipelines such as electricity, telecommunications, gas, water supply, drainage, and heat in an underground space. Through this integrated approach, utility corridors can improve the efficiency of urban space utilization, reduce the risk of pipeline accidents, and facilitate maintenance and management.

[0003] The existing early warning system usually sets up monitoring points at the preset nodes of the integrated pipe corridor (the monitoring points monitor multiple data of the pipe corridor in real time by setting up sensor equipment), and cooperates with the inspection robots inside the integrated pipe corridor to realize the overall monitoring of the pipe corridor. Generally speaking, the monitoring points can only monitor whether there are abnormalities at the pipe corridor nodes. For the pipe corridor sections between the nodes, the inspection robots are mainly relied on for abnormal monitoring. However, due to the limited number of inspection robots, and the existing early warning system adopts the preset inspection speed to control the inspection robot's mobile detection, there are the following defects: 1. Since the monitoring points are mainly distributed at the preset nodes, the areas between the nodes become monitoring blind areas. The monitoring points can usually only monitor the parameters at the corridor nodes, but cannot monitor the corridor sections between the nodes in real time. Therefore, if problems occur in these areas, faults or accidents may not be detected and warned in time (for example, when there are serious abnormalities in the corridor section, the sensor equipment at the node may only detect minor abnormalities); 2. Due to the limited number of inspection robots and the fixed inspection speed, the inspection frequency may not meet actual needs. Before the inspection robot arrives, the abnormalities in the tunnel section may have expanded or intensified. The inspection robot cannot dynamically adjust the inspection route and frequency according to the real-time situation, which may lead to waste of resources. For example, a lot of time is spent in low-risk areas without abnormalities, while high-risk areas cannot be inspected in time. Summary of the invention

[0004] The purpose of the present invention is to provide a comprehensive monitoring and early warning method and system for a pipeline corridor based on data analysis, which can combine the abnormal monitoring results of the monitoring points, intelligently adjust the inspection speed and inspection route of the inspection robot, and combine the monitoring information of the monitoring points and the inspection robot to perform abnormal analysis on the pipeline corridor section, effectively ensuring the stability and safety of the operation of the comprehensive pipeline corridor, so as to solve the shortcomings of the background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a pipeline corridor comprehensive monitoring and early warning method based on data analysis, the early warning method comprising the following steps: The early warning system obtains the monitoring point information of the corridor through the corridor management platform, numbers each monitoring point, and divides the corridor into several corridor sections according to the monitoring points; After obtaining multiple data through the sensor equipment set at the monitoring point at regular intervals, the fusion model is used to analyze the multiple data and output the abnormal factor for each monitoring point. During the monitoring period, the voltage value, signal strength, water pressure value, air pressure value and temperature value at multiple time points are obtained, and the standard deviation of the voltage value, signal strength standard deviation, water pressure value standard deviation, air pressure value standard deviation and temperature value are calculated. The standard deviation of the voltage value, signal strength standard deviation, water pressure value standard deviation, air pressure value standard deviation and temperature value are substituted into the fusion model to calculate the abnormal factor. The fusion model expression is: , where is the abnormal factor, is the environmental impact factor, with a value of 0.162, indicating the impact of environmental parameters on the safety of the integrated pipeline corridor. is a variable, is the regression coefficient of each variable, and the regression coefficient is greater than 0. The monitoring point is analyzed for abnormality based on the abnormal factor; An inspection scale is generated for each tunnel section by combining the abnormal factors of two adjacent monitoring points. A corresponding control strategy is generated for the inspection robot based on the inspection scale of the tunnel section, and the inspection robot is controlled to inspect the tunnel section according to the control strategy. The inspection data of the inspection robot on the corridor section is comprehensively analyzed with the inspection scale to analyze the abnormal conditions of the corridor section. When there is an abnormality in the analysis monitoring point or the corridor section, the early warning system sends an early warning signal to the corridor management platform.

[0006] In a preferred embodiment, the monitoring point monitors the voltage value of the power pipeline through a voltage sensor, monitors the signal strength of the communication pipeline through an optical power meter, monitors the water pressure value of the water supply pipeline through a pressure sensor, monitors the air pressure value of the gas pipeline through an air pressure sensor, and monitors the temperature value of the heating pipeline through a temperature sensor.

[0007] In a preferred embodiment, performing abnormal analysis on the monitoring point according to the abnormal factor comprises the following steps: The obtained abnormal factor is compared with the preset abnormal threshold. The abnormal threshold is used to analyze whether there is an abnormality at the monitoring point. If the abnormal factor is less than or equal to the abnormal threshold, there is no abnormality at the monitoring point. If the abnormal factor is greater than the abnormal threshold, there is an abnormality at the monitoring point.

[0008] In a preferred embodiment, the inspection scale is generated for each tunnel section by combining the abnormal factors of two adjacent monitoring points, including the following steps: Obtain the weight of each monitoring point relative to the integrated pipe gallery, and calculate the weighted abnormal factors of two adjacent monitoring points to obtain the inspection scale of the corresponding pipe gallery section. The function expression is: , where is the inspection scale, is the abnormal factor of the monitoring point at one end of the corridor section, is the abnormal factor of the monitoring point at the other end of the corridor section, is the weight of the monitoring point at one end of the corridor section, It is the weight of the monitoring point at the other end of the corridor section.

[0009] In a preferred embodiment, generating a corresponding control strategy for the inspection robot based on the inspection scale of the tunnel section includes the following steps: The obtained inspection scale is compared with the preset inspection threshold. The inspection threshold is used to predict whether there is an abnormality in the corridor section. If the inspection scale is less than or equal to the inspection threshold, it is predicted that there is no abnormality in the corridor section. If the inspection scale is greater than the inspection threshold, it is predicted that there is an abnormality in the corridor section. When it is predicted that there are no abnormalities in all tunnel sections, the generated control strategy is: the inspection robot is not controlled, and the inspection robot performs inspections at the preset inspection path and inspection speed; When it is predicted that at least one pipe gallery section has an abnormality, the generated control strategy is as follows: sort all pipe gallery sections with abnormalities from large to small according to the inspection scale, generate an inspection list, generate the inspection order of the pipe gallery sections according to the inspection list in positive order, send the inspection order to all inspection robots in the integrated pipe gallery, and the inspection robots will give priority to inspecting the pipe gallery sections predicted to have abnormalities according to the inspection order; For the corridor sections in the inspection list, the inspection speed of the inspection robot is adjusted according to the inspection scale. The expression is: , where is the inspection speed after adjustment. To adjust the inspection speed before, For inspection scale.

[0010] In a preferred embodiment, the inspection data of the inspection robot on the pipe gallery section is comprehensively analyzed with the inspection scale to analyze the abnormal condition of the pipe gallery section, including the following steps: The inspection data of the inspection robot on the pipeline corridor section includes the image abnormality ratio index and the harmful gas concentration index; The inspection data and inspection scale are combined to obtain the abnormal coefficient, which is expressed as: , where is the abnormal coefficient, is the inspection scale, For inspection data, , are the inspection scale and the adjustment coefficient of the inspection data, respectively, and , are greater than 0, For the Abnormal image grid ratio, For the The concentration of harmful gases, is the number of harmful gases detected, is the number of abnormal images obtained; The abnormal coefficient is compared with the preset coefficient threshold. The coefficient threshold is used to determine whether there is an abnormality in the pipe gallery section. If the abnormal coefficient is less than or equal to the coefficient threshold, it is determined that there is no abnormality in the pipe gallery section. If the abnormal coefficient is greater than the coefficient threshold, it is determined that there is an abnormality in the pipe gallery section. The abnormal analysis results of the monitoring points and the abnormal conditions of the tunnel sections are sent to the tunnel management platform.

[0011] In a preferred embodiment, obtaining the weight of each monitoring point relative to the integrated pipe gallery comprises the following steps: Get the historical failure rate and fault impact number of the monitoring point, map the value range of the failure rate and the fault impact number to [0,1], get the normalized value of the failure rate and the normalized value of the fault impact number, sum the normalized value of the failure rate and the normalized value of the fault impact number to get the proportion value, sum the proportion values ​​of all monitoring points to get the total proportion value, and get the weight of the monitoring point by dividing the proportion value by the total proportion value.

[0012] In a preferred embodiment, each monitoring point is numbered, and the pipeline corridor is divided into a plurality of pipeline corridor sections according to the monitoring points, including the following steps: Through the tunnel management platform, the total number of currently deployed monitoring points is obtained, recorded as n, all monitoring points are numbered, and the numbering information is associated with the location information of the monitoring point and stored. Each monitoring point is numbered in sequence: {c1, c2, c3, ..., c n}; According to the location of the monitoring points, the corridor area between every two adjacent monitoring points is divided into a corridor section. All corridor sections are numbered, and the numbering information is associated with the corresponding monitoring point information and stored. In the order of the corridor sections, each corridor section is numbered in turn as follows: {d1, d2, d3, ..., d n-1}, the corridor section number corresponds to the monitoring point number one by one; The information of the monitoring point number and the pipeline corridor section number is integrated to form a mapping table of pipeline corridor monitoring points and pipeline corridor sections, and the integrated mapping table is stored in the database of the early warning system.

[0013] The comprehensive monitoring and early warning system of the pipeline corridor based on data analysis includes numbering and marking module, abnormality monitoring module, intelligent control module and abnormality analysis module; Numbering and marking module: The monitoring point information of the corridor is obtained through the corridor management platform. The monitoring point information includes the number of monitoring points and the location of the monitoring points, and each monitoring point is numbered and marked as: {c1, c2, c3, ..., c n}, n represents the number of monitoring points, and the corridor is divided into several corridor sections according to the monitoring points, which are marked as: {d1, d2, d3, ..., d n-1}, the monitoring point information and the corridor section information are sent to the abnormal monitoring module; Abnormal monitoring module: After obtaining multiple data through the sensor equipment set at the monitoring point at regular intervals, the fusion model analyzes the multiple data and outputs abnormal factors for each monitoring point. The monitoring point is first analyzed for abnormalities based on the abnormal factors, and then the abnormal factors of two adjacent monitoring points are combined to generate inspection scales for each tunnel section. The inspection scales are sent to the intelligent control module and the abnormal analysis module; Intelligent control module: Generates corresponding control strategies for the inspection robot based on the inspection scale of the corridor section, and controls the inspection robot to inspect the corridor section according to the control strategy; Abnormal analysis module: Comprehensively analyze the inspection data and inspection scale of the inspection robot on the corridor section, analyze the abnormal conditions of the corridor section, and send the abnormal analysis results of the monitoring points and the abnormal conditions of the corridor section to the corridor management platform.

[0014] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention analyzes multiple data through a fusion model and outputs an abnormal factor for each monitoring point. The monitoring point is first analyzed according to the abnormal factor, and then the inspection scale is generated for each pipe gallery section in combination with the abnormal factors of two adjacent monitoring points. The corresponding control strategy is generated for the inspection robot based on the inspection scale of the pipe gallery section, and the inspection data of the inspection robot on the pipe gallery section and the inspection scale are comprehensively analyzed, the abnormal condition of the pipe gallery section is analyzed, and the abnormal analysis results of the monitoring point and the abnormal condition of the pipe gallery section are sent to the pipe gallery management platform. The early warning system can combine the abnormal monitoring results of the monitoring point, intelligently adjust the inspection speed and inspection route of the inspection robot, and combine the monitoring information of the monitoring point and the inspection robot to perform abnormal analysis on the pipe gallery section, effectively ensuring the stability and safety of the operation of the comprehensive pipe gallery. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0016] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1: Please refer to Figure 1 As shown, the utility tunnel comprehensive monitoring and early warning method based on data analysis described in this embodiment includes the following steps: The early warning system obtains the monitoring point information of the corridor through the corridor management platform. The monitoring point information includes the number of monitoring points and the location of the monitoring points. Each monitoring point is numbered and marked as: {c1, c2, c3, ..., c n}, n represents the number of monitoring points, and the corridor is divided into several corridor sections according to the monitoring points, which are marked as: {d1, d2, d3, ..., d n-1 After obtaining multiple data through the sensor equipment installed at the monitoring point at regular intervals, the multiple data are analyzed through the fusion model and the abnormal factors are output for each monitoring point. The monitoring point is first analyzed for abnormality based on the abnormal factors, and then the abnormal factors of the two adjacent monitoring points are combined to generate an inspection scale for each tunnel section. Based on the inspection scale of the tunnel section, a corresponding control strategy is generated for the inspection robot, and the inspection robot is controlled to inspect the tunnel section according to the control strategy. The inspection data of the tunnel section by the inspection robot and the inspection scale are comprehensively analyzed, the abnormal condition of the tunnel section is analyzed, and the abnormal analysis results of the monitoring point and the abnormal condition of the tunnel section are sent to the tunnel management platform. When it is analyzed that there is an abnormality in the monitoring point or the tunnel section, the early warning system sends an early warning signal to the tunnel management platform.

[0019] This application analyzes multiple data through a fusion model and outputs an abnormal factor for each monitoring point. First, the monitoring point is analyzed for abnormality based on the abnormal factor, and then the abnormal factors of two adjacent monitoring points are combined to generate a patrol scale for each tunnel section. Based on the patrol scale of the tunnel section, a corresponding control strategy is generated for the patrol robot, and the patrol robot's patrol data of the tunnel section is comprehensively analyzed with the patrol scale, the abnormal condition of the tunnel section is analyzed, and the abnormal analysis results of the monitoring point and the abnormal condition of the tunnel section are sent to the tunnel management platform. The early warning system can combine the abnormal monitoring results of the monitoring point, intelligently adjust the patrol speed and patrol route of the patrol robot, and combine the monitoring information of the monitoring point and the patrol robot to perform abnormal analysis on the tunnel section, effectively ensuring the stability and safety of the operation of the comprehensive tunnel.

[0020] Embodiment 2: The early warning system obtains the monitoring point information of the pipe gallery through the pipe gallery management platform, and the monitoring point information includes the number of monitoring points and the location of the monitoring points, including the following steps: The early warning system first needs to access the interface or database of the tunnel management platform through authentication and authorization, send a request to the management platform to obtain the latest information related to the monitoring points, and obtain the number of currently configured monitoring points from the tunnel management platform.

[0021] Extract the location information of each monitoring point, including its specific location coordinates in the tunnel (such as X, Y, Z coordinates), hierarchical location (such as above ground or underground), and distance relative to the tunnel section. This information helps to draw a distribution map of monitoring points, which is convenient for subsequent analysis and decision-making.

[0022] Verify the acquired monitoring point information to ensure the integrity and accuracy of the data. For example, check whether the location of the monitoring point is consistent with the existing configuration in the system, or whether there are duplicate or missing monitoring points, verify the timestamp of the data, and ensure that the early warning system uses the latest monitoring point information to avoid misjudgment caused by using outdated data.

[0023] The number and location information of monitoring points obtained are stored in the database of the early warning system as the basic data for subsequent early warning analysis. A regular data update mechanism is set up to ensure that the monitoring point information can be updated to the early warning system in a timely manner when the corridor is adjusted (such as adding or deleting monitoring points).

[0024] Number each monitoring point and mark them as: {c1, c2, c3, ..., c n}, n represents the number of monitoring points, and the corridor is divided into several corridor sections according to the monitoring points, which are marked as: {d1, d2, d3, ..., d n-1}, including the following steps: Through the tunnel management platform, the total number of currently deployed monitoring points is obtained, recorded as n, all monitoring points are numbered, and the numbering information is associated with the location information of the monitoring points for storage. A numbering rule for the monitoring points is formulated, and each monitoring point is numbered in sequence as: {c1, c2, c3, ..., c n}, the numbering can be carried out according to the physical order of the monitoring points in the corridor (such as from the starting point to the end point).

[0025] According to the location of the monitoring points, the corridor area between every two adjacent monitoring points is divided into a corridor segment. Specifically, the corridor segment between monitoring points c1 and c2 is d1, the corridor segment between monitoring points c2 and c3 is d2, and so on, until the last corridor segment d n-1 , which is located at the monitoring point c n-1 and c n between.

[0026] All pipe corridor sections are numbered, and the numbering information is associated with the corresponding monitoring point information and stored. In the order of the pipe corridor sections, each pipe corridor section is numbered as follows: {d1, d2, d3, ..., d n-1}, the corridor section numbers correspond to the monitoring point numbers one by one, so that the scope of each corridor section can be intuitively understood.

[0027] The information of monitoring point number and pipeline corridor section number is integrated to form a complete mapping table of pipeline corridor monitoring points and pipeline corridor sections, and the integrated mapping table is stored in the database of the early warning system for subsequent monitoring and analysis.

[0028] After obtaining multiple data through the sensor equipment set at the monitoring point at regular intervals, the multiple data are analyzed through the fusion model and the abnormal factors are output for each monitoring point, including the following steps: The integrated pipeline corridor usually includes power pipelines, communication pipelines, water pipelines, gas pipelines, heating pipelines, etc. Therefore, in this application, the monitoring point monitors the voltage value of the power pipeline through a voltage sensor, monitors the signal strength of the communication pipeline through an optical power meter, monitors the water pressure value of the water supply pipeline through a pressure sensor, monitors the air pressure value of the gas pipeline through an air pressure sensor, and monitors the temperature value of the heating pipeline through a temperature sensor; During the monitoring period, the voltage value, signal strength, water pressure value, air pressure value and temperature value are obtained at multiple time points, and the standard deviation of the voltage value, signal strength standard deviation, water pressure value standard deviation, air pressure value standard deviation and temperature value standard deviation are calculated; The voltage value standard deviation, signal strength standard deviation, water pressure value standard deviation, air pressure value standard deviation and temperature value standard deviation are calculated using the general standard deviation calculation formula. The general standard deviation calculation formula is as follows: , where is the parameter standard deviation, is the number of time points, For the The parameter value at each time point, is the parameter average value. The larger the parameter standard deviation is, the greater the fluctuation of the parameter is during the detection period, and the more likely it is that there is an abnormality. Specifically, the method for calculating the voltage value standard deviation, signal strength standard deviation, water pressure value standard deviation, air pressure value standard deviation and temperature value standard deviation is the same as the general standard deviation calculation formula, and this application will not introduce them one by one.

[0029] Substitute the voltage standard deviation, signal strength standard deviation, water pressure standard deviation, air pressure standard deviation and temperature standard deviation into the fusion model to calculate the anomaly factor. The fusion model expression is: , where is the abnormal factor, is the environmental impact factor, with a value of 0.162, which indicates the impact of environmental parameters (such as ambient temperature, ambient humidity, etc.) on the safety of the integrated pipe gallery. are variables (voltage standard deviation, signal strength standard deviation, water pressure standard deviation, air pressure standard deviation, and temperature standard deviation), is the regression coefficient of each variable, and the regression coefficient is greater than 0; The logical factors of the abnormal factors when used in the present invention are as follows: taking the influence of variables on the safety of the integrated pipe gallery as an example, the first is the index, that is, the factor that causes the safety of the integrated pipe gallery to decline (the present invention refers to the influence of variables on the safety of the integrated pipe gallery); the second is the weight of these indicators, that is, the proportion of each major influencing data when it is generated; the third is the operation equation, that is, what kind of mathematical operation process is used to obtain the result, and the abnormal factor is obtained by calculating the indicators with their respective weights through the operation equation.

[0030] The main influencing data obtained from the sample were transformed and processed into a data language recognized by computer software; secondly, these evaluation factors were analyzed by Logistic regression using SPSS software to screen out factors and their weights that are significantly correlated with the results; thirdly, the evaluation factors and weights were brought into the Logistic regression equation for calculation to obtain the results, which are as follows: First, ensure the integrity of the main effect data, handle missing values ​​and outliers, and convert the data into a format that SPSS software can recognize. Usually, the data is stored in csv, xlsx and other formats, and then imported into SPSS. Open SPSS software, import the processed data file, and transform the variables as needed. For example, for continuous variables, standardize or normalize them. Select the "Analyze" menu, then select the "Binary Logistic" option under "Regression". In the dialog box, add the dependent variable (outcome) and the independent variable (main effect data) to the corresponding boxes. SPSS will fit the Logistic regression based on the selected variables. Model, in the output results, you will see the factors, standard errors, p-values ​​and other information of the model. Check the factors and p-values ​​in the output results to determine which variables have a significant correlation with the results. Usually, a p-value less than 0.05 is considered significant. While fitting the model, use variable selection methods, such as stepwise regression, to help screen the most relevant factors. According to the coefficients of the Logistic regression model, the size of the coefficients reflects the degree of influence of each factor on the result, and the positive and negative signs of the coefficients indicate the direction of the influence. After obtaining the significant factors and their coefficients, the Logistic regression equation is obtained, which is used to calculate the probability of each sample and then predict the results.

[0031] The abnormal analysis of the monitoring points is carried out according to the abnormal factors, including the following steps: After obtaining the abnormal factor of the monitoring point, the larger the abnormal factor, the more serious the abnormality at the monitoring point. The obtained abnormal factor is compared with the preset abnormal threshold. The abnormal threshold is used to analyze whether there is an abnormality at the monitoring point. If the abnormal factor is less than or equal to the abnormal threshold, it is analyzed that there is no abnormality at the monitoring point. If the abnormal factor is greater than the abnormal threshold, it is analyzed that there is an abnormality at the monitoring point.

[0032] Combining the abnormal factors of two adjacent monitoring points to generate an inspection scale for each tunnel section includes the following steps: Obtain the weight of each monitoring point relative to the integrated pipe gallery, and calculate the weighted abnormal factors of two adjacent monitoring points to obtain the inspection scale of the corresponding pipe gallery section. The function expression is: , where is the inspection scale, is the abnormal factor of the monitoring point at one end of the corridor section, is the abnormal factor of the monitoring point at the other end of the corridor section, is the weight of the monitoring point at one end of the corridor section, It is the weight of the monitoring point at the other end of the corridor section.

[0033] Obtaining the weight of each monitoring point relative to the integrated pipeline corridor includes the following steps: Obtain the historical failure rate and fault impact number of the monitoring point, map the value range of the failure rate and the fault impact number to [0,1], obtain the normalized value of the failure rate and the normalized value of the fault impact number, sum the normalized value of the failure rate and the normalized value of the fault impact number to obtain the proportion value, sum the proportion values ​​of all monitoring points to obtain the total proportion value, and obtain the weight of the monitoring point by dividing the proportion value by the total proportion value. The larger the weight of the monitoring point, the greater the importance of the monitoring point relative to the integrated pipeline corridor.

[0034] The failure rate is equal to the number of historical failures of the monitoring point divided by the monitoring time. The greater the failure rate of the monitoring point, the more attention should be paid to the monitoring point. The number of failure impacts is the number of failures of other monitoring points in the integrated pipeline corridor caused by a failure at the monitoring point. The greater the number of failure impacts of the monitoring point, the greater the impact of the monitoring point on the integrated pipeline corridor, and the more attention should be paid to the monitoring point.

[0035] Based on the inspection scale of the pipe gallery section, a corresponding control strategy is generated for the inspection robot, and the inspection robot is controlled to inspect the pipe gallery section according to the control strategy, including the following steps: The larger the inspection scale of the corridor section, the greater the possibility that the corridor section has an abnormality (when the monitoring points at both ends of the corridor section are abnormal, the corridor section is more likely to have an abnormality); The obtained inspection scale is compared with the preset inspection threshold. The inspection threshold is used to predict whether there is an abnormality in the corridor section. If the inspection scale is less than or equal to the inspection threshold, it is predicted that there is no abnormality in the corridor section. If the inspection scale is greater than the inspection threshold, it is predicted that there is an abnormality in the corridor section. When it is predicted that there are no abnormalities in all tunnel sections, the generated control strategy is: the inspection robot is not controlled, and the inspection robot performs inspections at the preset inspection path and inspection speed; When it is predicted that at least one pipe gallery section has an abnormality, the generated control strategy is: sort all pipe gallery sections with abnormalities from large to small according to the inspection scale, generate an inspection list, generate the inspection order of the pipe gallery sections according to the inspection list in positive order, send the inspection order to all inspection robots in the integrated pipe gallery, and the inspection robot will give priority to inspecting the pipe gallery sections predicted to have abnormalities according to the inspection order. Moreover, for the pipe gallery sections in the inspection list, the larger the inspection scale, the greater the possibility of predicting that the pipe gallery section has an abnormality. Therefore, the larger the inspection scale of the pipe gallery section, the more the inspection robot needs to slow down the inspection speed of the pipe gallery section. The inspection speed of the inspection robot is adjusted according to the inspection scale. The expression is: , where is the inspection speed after adjustment. To adjust the inspection speed before, For inspection scale; The inspection robot inspects all pipeline corridor sections in the inspection list according to the adjusted inspection speed, and does not inspect pipeline corridor sections that are predicted to have no abnormalities. That is, the inspection robot adopts the minimum inspection speed to pass through pipeline corridor sections that are predicted to have no abnormalities.

[0036] Assuming that the integrated utility corridor is equipped with one inspection robot, then one inspection robot inspects all the utility corridor sections in the inspection list in the correct order and at the adjusted inspection speed; if the integrated utility corridor is equipped with two inspection robots, when the first inspection robot inspects the first utility corridor section in the inspection list, the other inspection robot inspects the second utility corridor section in the inspection list. If the integrated utility corridor is equipped with more than two inspection robots, the inspection is performed according to the above method.

[0037] The inspection data of the inspection robot on the pipe gallery section is comprehensively analyzed with the inspection scale to analyze the abnormal conditions of the pipe gallery section, including the following steps: The inspection data of the inspection robot on the pipeline corridor section includes the image abnormality ratio index and the harmful gas concentration index; The inspection data and inspection scale are combined to obtain the abnormal coefficient, which is expressed as: , where is the abnormal coefficient, is the inspection scale, For inspection data, , are the inspection scale and the adjustment coefficient of the inspection data, respectively, and , are greater than 0, For the Abnormal image grid ratio, For the The concentration of harmful gases, is the number of harmful gases detected, is the number of abnormal images obtained; The larger the abnormal coefficient, the more likely it is that the pipe gallery section has an abnormality. The abnormal coefficient is compared with the preset coefficient threshold. The coefficient threshold is used to determine whether the pipe gallery section has an abnormality. If the abnormal coefficient is less than or equal to the coefficient threshold, it is determined that the pipe gallery section does not have an abnormality. If the abnormal coefficient is greater than the coefficient threshold, it is determined that the pipe gallery section has an abnormality. The abnormal analysis results of the monitoring points and the abnormal conditions of the tunnel sections are sent to the tunnel management platform.

[0038] The logic for obtaining the image anomaly ratio index is as follows: the types of image anomalies include open flame anomalies, damage anomalies, and water seepage anomalies, etc. The abnormal images are divided into several 1×1 grids, and the number of abnormally occupied grids in the abnormal images is identified by using existing image recognition technology. The number of abnormally occupied grids is divided by the total number of grids in the abnormal image to obtain the abnormal image grid ratio. Since the inspection robot may take multiple abnormal images during the inspection of the corridor section, the abnormal image grid ratios of multiple abnormal images are summed to obtain the image anomaly ratio index. The larger the image anomaly ratio index, the more serious the anomaly in the corridor section.

[0039] The logic for obtaining the harmful gas concentration index is as follows: the inspection robot detects the concentration of harmful gases in the pipeline corridor section through the harmful gas monitor equipped by itself. The harmful gases in the pipeline corridor include but are not limited to carbon monoxide, hydrogen sulfide, methane, carbon dioxide, ammonia, etc. After the inspection robot obtains the concentrations of multiple types of harmful gases, the concentrations of multiple types of harmful gases are summed up to obtain the harmful gas concentration index. The larger the harmful gas concentration index, the more serious the abnormality in the pipeline corridor section.

[0040] Embodiment 3: The pipe gallery comprehensive monitoring and early warning system based on data analysis described in this embodiment includes a numbering and marking module, an abnormality monitoring module, an intelligent control module, and an abnormality analysis module; Numbering and marking module: The monitoring point information of the corridor is obtained through the corridor management platform. The monitoring point information includes the number of monitoring points and the location of the monitoring points, and each monitoring point is numbered and marked as: {c1, c2, c3, ..., c n}, n represents the number of monitoring points, and the corridor is divided into several corridor sections according to the monitoring points, which are marked as: {d1, d2, d3, ..., d n-1}, the monitoring point information and the corridor section information are sent to the abnormal monitoring module; Abnormal monitoring module: After obtaining multiple data through the sensor equipment set at the monitoring point at regular intervals, the fusion model analyzes the multiple data and outputs abnormal factors for each monitoring point. The monitoring point is first analyzed for abnormalities based on the abnormal factors, and then the abnormal factors of two adjacent monitoring points are combined to generate inspection scales for each tunnel section. The inspection scales are sent to the intelligent control module and the abnormal analysis module; Intelligent control module: Generates corresponding control strategies for the inspection robot based on the inspection scale of the corridor section, and controls the inspection robot to inspect the corridor section according to the control strategy; Abnormal analysis module: Comprehensively analyze the inspection data and inspection scale of the inspection robot on the corridor section, analyze the abnormal conditions of the corridor section, and send the abnormal analysis results of the monitoring points and the abnormal conditions of the corridor section to the corridor management platform.

[0041] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0042] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0043] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0044] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0045] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A comprehensive monitoring and early warning method for pipe gallery based on data analysis, characterized by: The early warning method comprises the following steps: The early warning system obtains the monitoring point information of the corridor through the corridor management platform, numbers each monitoring point, and divides the corridor into several corridor sections according to the monitoring points; After obtaining multiple data through the sensor equipment set at the monitoring point at regular intervals, the fusion model is used to analyze the multiple data and output the abnormal factor for each monitoring point. During the monitoring period, the voltage value, signal strength, water pressure value, air pressure value and temperature value at multiple time points are obtained, and the standard deviation of the voltage value, signal strength standard deviation, water pressure value standard deviation, air pressure value standard deviation and temperature value are calculated. The standard deviation of the voltage value, signal strength standard deviation, water pressure value standard deviation, air pressure value standard deviation and temperature value are substituted into the fusion model to calculate the abnormal factor. The fusion model expression is: , where is the abnormal factor, is the environmental impact factor, with a value of 0.162, indicating the impact of environmental parameters on the safety of the integrated pipeline corridor. is a variable, is the regression coefficient of each variable, and the regression coefficient is greater than 0. The monitoring point is analyzed for abnormality based on the abnormal factor; An inspection scale is generated for each tunnel section by combining the abnormal factors of two adjacent monitoring points. A corresponding control strategy is generated for the inspection robot based on the inspection scale of the tunnel section, and the inspection robot is controlled to inspect the tunnel section according to the control strategy. The inspection robot's inspection data on the corridor section is comprehensively analyzed with the inspection scale to analyze the abnormal conditions of the corridor section. When there is an abnormality in the analysis monitoring point or the corridor section, the early warning system sends an early warning signal to the corridor management platform; Combining the abnormal factors of two adjacent monitoring points to generate an inspection scale for each tunnel section includes the following steps: Obtain the weight of each monitoring point relative to the integrated pipe gallery, and calculate the weighted abnormal factors of two adjacent monitoring points to obtain the inspection scale of the corresponding pipe gallery section. The function expression is: , where is the inspection scale, is the abnormal factor of the monitoring point at one end of the corridor section, is the abnormal factor of the monitoring point at the other end of the corridor section, is the weight of the monitoring point at one end of the corridor section, It is the weight of the monitoring point at the other end of the corridor section.

2. The method for comprehensive monitoring and early warning of a pipe gallery based on data analysis according to claim 1 is characterized in that: The monitoring point monitors the voltage value of the power pipeline through a voltage sensor, monitors the signal strength of the communication pipeline through an optical power meter, monitors the water pressure value of the water supply pipeline through a pressure sensor, monitors the air pressure value of the gas pipeline through an air pressure sensor, and monitors the temperature value of the heating pipeline through a temperature sensor.

3. The method for comprehensive monitoring and early warning of a pipe gallery based on data analysis according to claim 2 is characterized in that: The obtained abnormal factor is compared with the preset abnormal threshold. The abnormal threshold is used to analyze whether there is an abnormality at the monitoring point. If the abnormal factor is less than or equal to the abnormal threshold, there is no abnormality at the monitoring point. If the abnormal factor is greater than the abnormal threshold, there is an abnormality at the monitoring point.

4. The method for comprehensive monitoring and early warning of a pipe gallery based on data analysis according to claim 3 is characterized in that: Based on the inspection scale of the corridor section, a corresponding control strategy is generated for the inspection robot, including the following steps: The obtained inspection scale is compared with the preset inspection threshold. The inspection threshold is used to predict whether there is an abnormality in the corridor section. If the inspection scale is less than or equal to the inspection threshold, it is predicted that there is no abnormality in the corridor section. If the inspection scale is greater than the inspection threshold, it is predicted that there is an abnormality in the corridor section. When it is predicted that there are no abnormalities in all tunnel sections, the generated control strategy is: the inspection robot is not controlled, and the inspection robot performs inspections at the preset inspection path and inspection speed; When it is predicted that at least one pipe gallery section has an abnormality, the generated control strategy is as follows: sort all pipe gallery sections with abnormalities from large to small according to the inspection scale, generate an inspection list, generate the inspection order of the pipe gallery sections according to the inspection list in positive order, send the inspection order to all inspection robots in the integrated pipe gallery, and the inspection robots will give priority to inspecting the pipe gallery sections predicted to have abnormalities according to the inspection order; For the corridor sections in the inspection list, the inspection speed of the inspection robot is adjusted according to the inspection scale. The expression is: , where is the inspection speed after adjustment. To adjust the inspection speed before, For inspection scale.

5. The method for comprehensive monitoring and early warning of a pipe gallery based on data analysis according to claim 4 is characterized in that: The inspection data of the inspection robot on the pipe gallery section is comprehensively analyzed with the inspection scale to analyze the abnormal conditions of the pipe gallery section, including the following steps: The inspection data of the inspection robot on the pipeline corridor section includes the image abnormality ratio index and the harmful gas concentration index; The inspection data and inspection scale are combined to obtain the abnormal coefficient, which is expressed as: , where is the abnormal coefficient, is the inspection scale, For inspection data, , are the inspection scale and the adjustment coefficient of the inspection data, respectively, and , are greater than 0, For the Abnormal image grid ratio, For the The concentration of harmful gases is the number of harmful gases detected, is the number of abnormal images obtained; The abnormal coefficient is compared with the preset coefficient threshold. The coefficient threshold is used to determine whether there is an abnormality in the pipe gallery section. If the abnormal coefficient is less than or equal to the coefficient threshold, it is determined that there is no abnormality in the pipe gallery section. If the abnormal coefficient is greater than the coefficient threshold, it is determined that there is an abnormality in the pipe gallery section. The abnormal analysis results of the monitoring points and the abnormal conditions of the tunnel sections are sent to the tunnel management platform.

6. The method for comprehensive monitoring and early warning of a pipe gallery based on data analysis according to claim 5 is characterized in that: Obtaining the weight of each monitoring point relative to the integrated pipeline corridor includes the following steps: Get the historical failure rate and fault impact number of the monitoring point, map the value range of the failure rate and the fault impact number to [0,1], get the normalized value of the failure rate and the normalized value of the fault impact number, sum the normalized value of the failure rate and the normalized value of the fault impact number to get the proportion value, sum the proportion values ​​of all monitoring points to get the total proportion value, and get the weight of the monitoring point by dividing the proportion value by the total proportion value.

7. The method for comprehensive monitoring and early warning of a pipe gallery based on data analysis according to claim 6 is characterized in that: Number each monitoring point and divide the corridor into several corridor sections according to the monitoring points, including the following steps: Through the tunnel management platform, the total number of currently deployed monitoring points is obtained, recorded as n, all monitoring points are numbered, and the numbering information is associated with the location information of the monitoring point and stored. Each monitoring point is numbered in sequence: {c1, c2, c3, ..., c n }; According to the location of the monitoring points, the corridor area between every two adjacent monitoring points is divided into a corridor section. All corridor sections are numbered, and the numbering information is associated with the corresponding monitoring point information and stored. In the order of the corridor sections, each corridor section is numbered in turn as follows: {d1, d2, d3, ..., d n-1 }, the corridor section number corresponds to the monitoring point number one by one; The information of the monitoring point number and the pipeline corridor section number is integrated to form a mapping table of pipeline corridor monitoring points and pipeline corridor sections, and the integrated mapping table is stored in the database of the early warning system.

8. A pipeline corridor integrated monitoring and early warning system based on data analysis, used to implement the early warning method according to any one of claims 1 to 7, characterized in that: It includes number marking module, abnormality monitoring module, intelligent control module and abnormality analysis module; Numbering and marking module: The monitoring point information of the corridor is obtained through the corridor management platform. The monitoring point information includes the number of monitoring points and the location of the monitoring points, and each monitoring point is numbered and marked as: {c1, c2, c3, ..., c n }, n represents the number of monitoring points, and the corridor is divided into several corridor sections according to the monitoring points, which are marked as: {d1, d2, d3, ..., d n-1 }, the monitoring point information and the corridor section information are sent to the abnormal monitoring module; Abnormal monitoring module: After obtaining multiple data through the sensor equipment set at the monitoring point at regular intervals, the fusion model analyzes the multiple data and outputs abnormal factors for each monitoring point. The monitoring point is first analyzed for abnormalities based on the abnormal factors, and then the abnormal factors of two adjacent monitoring points are combined to generate inspection scales for each tunnel section. The inspection scales are sent to the intelligent control module and the abnormal analysis module; Intelligent control module: Generates corresponding control strategies for the inspection robot based on the inspection scale of the corridor section, and controls the inspection robot to inspect the corridor section according to the control strategy; Abnormal analysis module: Comprehensively analyze the inspection data and inspection scale of the inspection robot on the corridor section, analyze the abnormal conditions of the corridor section, and send the abnormal analysis results of the monitoring points and the abnormal conditions of the corridor section to the corridor management platform.

Citation Information

Patent Citations

  • City underground comprehensive pipeline monitoring early warning system and method

    CN107424380A

  • Multi-energy system multi-source heterogeneous data fusion method and system

    CN115718906A

  • Point-line network integrated side slope disaster monitoring and early warning method and system

    CN118762493A

  • Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing

    US20190331301A1

  • Method and device for detecting fault of monitoring device

    US20210293651A1

Cited By

  • Intelligent heat supply network cloud control information platform system based on big data analysis

    CN119648190A

  • Safety early warning method and system for multiple risk sources of underground pipe gallery

    CN122114660A