A wastewater treatment pipeline monitoring system, method, equipment, and medium.

Abstract

This application discloses a wastewater treatment pipeline network monitoring system, method, equipment, and medium, relating to the field of pipeline network monitoring technology. The system includes a liquid level monitoring module, a maintenance robot, and a monitoring mechanism. The liquid level monitoring module is located in the bottom water tank of the target monitoring pipeline corridor. The maintenance robot acquires multi-angle maintenance videos. The monitoring mechanism analyzes the first predicted leak location and the second predicted leak location detected by the maintenance robot when a detection request is triggered, based on pipeline coding identification information and pipeline design parameters. Based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location, a fault identification model is generated to guide the operation of the maintenance robot. Based on liquid level change information, the reference range of detection accuracy change, and multi-angle maintenance videos, a comprehensive analysis of the pipeline leak location is performed to determine the final leak location analysis result. This application has the effect of improving the monitoring efficiency of wastewater treatment pipeline network monitoring.

Description

Technical Field

[0001] This application relates to the field of pipeline monitoring technology, and in particular to a sewage treatment pipeline monitoring system, method, equipment and medium. Background Technology

[0002] With the acceleration of urbanization, urban drainage pipe networks are becoming increasingly complex and extensive. In electroplating and PCB (printed circuit board) industrial parks, due to the wide variety of pollutants entering the water and the strict requirements of the treatment process, sewage and wastewater need to be collected and treated separately. This results in the sewage pipe network in the park being not only huge in scale but also complex in structure, which puts forward higher requirements for the maintenance of the pipe network.

[0003] However, traditional maintenance and management models are no longer sufficient to meet current needs. The existing pipeline network is slow to react when leaks or bursts are detected, making it difficult to locate the problem and repair it quickly. The entire process from problem detection to final repair is too time-consuming. In addition, in the existing enclosed pipe corridors, due to the dense network of pipes, while inspection robots can detect the general location of leaks, they cannot accurately pinpoint the specific leaking pipe or distinguish between a dripping or burst pipe. This requires staff to personally visit the site to check each pipe, significantly reducing maintenance efficiency and increasing the park's operating costs.

[0004] In summary, the current monitoring of sewage treatment pipeline networks suffers from low monitoring efficiency and urgently needs improvement. Summary of the Invention

[0005] To improve the monitoring efficiency of sewage treatment pipeline networks, this application provides a sewage treatment pipeline network monitoring system, method, equipment, and medium.

[0006] Firstly, the objective of this invention is achieved through the following technical solution:

[0007] A wastewater treatment pipeline network monitoring system includes a liquid level monitoring module, a maintenance robot, and a monitoring mechanism; the liquid level monitoring module is located in the bottom water tank of the target monitoring pipeline corridor; the maintenance robot is used to acquire multi-angle maintenance videos of the pipelines in the target monitoring pipeline corridor.

[0008] The monitoring agency obtains pipeline identification information and pipeline design parameters, and analyzes the first predicted leak location and the second predicted leak location detected by the maintenance robot when the detection request is triggered based on the pipeline identification information and pipeline design parameters.

[0009] Based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location, a fault identification model is generated to guide the operation of the maintenance robot.

[0010] The system obtains a reference range for the change in detection accuracy, which represents the threshold of the change in the detection accuracy of the maintenance robot, and acquires information on the change in liquid level in the water tank at the bottom of the closed pipe gallery through a liquid level monitoring module. Based on the liquid level change information, the reference range for the change in detection accuracy, and the multi-angle maintenance video, the system performs a comprehensive analysis of the location of the pipe leak and determines the final leak location analysis result.

[0011] By adopting the above technical solutions, the leakage location analysis results include the specific leakage type and location. The pipeline coding identification information is the unique coding identifier of the pipelines in the target monitoring pipe gallery. To improve the accuracy of fault location, a fault identification model is generated to guide the operation of the maintenance robot by combining the pipeline coding identification information and the pipe network design parameters. This not only improves the accuracy of leakage location prediction, but also allows for dynamic adjustment of the detection strategy according to the actual situation, which is conducive to improving the maintenance efficiency of the maintenance robot. The liquid level monitoring module of this application is located in the bottom water tank of the target monitoring pipe gallery, which can monitor the liquid level changes in real time and distinguish different types of leaks such as dripping and bursting pipes based on the liquid flow characteristics. Combined with the reference range of detection accuracy changes, the system can more accurately determine the specific type of leakage. Then, the fault identification model is used to guide the operation of the maintenance robot. With the real-time liquid level change analysis, the leakage location and type can be determined in the shortest time, improving the specific positioning accuracy of the leakage location and shortening the time from fault discovery to repair. At the same time, this application can complete most of the fault detection and preliminary analysis work, reducing the dependence on human resources. While improving the monitoring efficiency of sewage treatment pipe network monitoring, it effectively reduces operating costs.

[0012] In a preferred embodiment of this application: the step of obtaining pipeline identification information and pipeline network design parameters, and analyzing the first predicted leak location and the second predicted leak location detected by the maintenance robot based on the pipeline identification information and pipeline network design parameters, specifically includes:

[0013] Obtain pipeline coding identification information and pipeline network design parameters. The pipeline coding identification information includes pipeline type, pipeline diameter, pipeline installation angle, and the relative position of the pipeline in the pipe gallery. The pipeline network design parameters include pipeline network layout diagram, historical fault data, and design pressure resistance value.

[0014] Based on the pipe type, pipe diameter, pipe installation angle, and pipe relative position in the pipe gallery, combined with historical fault data, the first predicted leak location when the detection request is triggered is determined.

[0015] Based on the pipeline layout diagram, the design pressure resistance value, the pipeline installation angle, and the relative position of the pipeline in the pipe gallery, the second predicted leak location detected by the maintenance robot is determined by combining the multi-angle maintenance video provided by the maintenance robot.

[0016] By adopting the above technical solution, detailed pipeline structure and historical operation data of the target monitoring pipeline corridor are obtained based on pipeline coding identification information and pipeline design parameters, so as to accurately predict possible leakage locations. By combining historical fault data, high-risk leakage areas can be identified, so as to quickly locate the first predicted leakage location when a detection request is triggered. Furthermore, by using multi-angle inspection videos from different angles of the inspection robot, the actual condition of the pipeline can be observed intuitively. Combined with the pipeline layout diagram and design pressure resistance value, it is helpful to confirm the second predicted leakage location. Unlike the problem of inaccurate leakage location due to the lack of detailed pipeline information in the prior art, this application can improve the accuracy of leakage prediction and the speed of leakage response.

[0017] In a preferred embodiment of this application, the step of generating a fault identification model to guide the operation of a maintenance robot based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location specifically includes:

[0018] The possible leakage path length is calculated based on the pipeline layout diagram, the first predicted leakage location, and the second predicted leakage location. The corresponding leakage risk assessment value is obtained based on the pipeline type and the design pressure resistance value.

[0019] Based on the length of the leakage path and the leakage risk assessment value, a preliminary fault identification model is generated;

[0020] Obtain the reference range of detection accuracy change, which represents the threshold of change in the detection accuracy of the maintenance robot, and obtain the liquid level change information in the water tank at the bottom of the closed pipe gallery through the liquid level monitoring module;

[0021] Based on the liquid level change information, the detection accuracy change reference range, and the multi-angle inspection video, the leakage rate and leakage volume of the leak point are analyzed; the ratio of the leakage rate to the leakage volume is calculated to obtain a leakage ratio value used to predict the severity of the leak.

[0022] Based on the leakage path length, the leakage risk assessment value, and the leakage ratio, a leakage level is obtained to determine the specific circumstances of the leakage.

[0023] Based on the leakage level and the preliminary fault identification model, the final fault identification model is generated.

[0024] By adopting the above technical solution, the possible leakage path length is first calculated using the pipeline layout diagram, the first predicted leakage location, and the second predicted leakage location. Then, based on the pipeline type and design pressure resistance value, the corresponding leakage risk assessment value is obtained. Next, by combining the reference range for changes in detection accuracy and the liquid level change information provided by the liquid level monitoring module with multi-angle inspection videos, the specific situation of the leakage point is comprehensively analyzed, such as the leakage rate and leakage volume. The ratio of leakage rate to leakage volume is then calculated to form a leakage ratio, which is used to predict the severity of the leakage. Combining the leakage path length, leakage risk assessment value, and leakage ratio, the leakage level can be determined, generating the final fault identification model. Multi-source data fusion solves the problem of inaccurate fault identification caused by a single data source, thereby achieving more accurate fault location and classification.

[0025] In a preferred embodiment of this application: the step of analyzing the leakage rate and leakage amount of the leak point based on the liquid level change information, the detection accuracy change reference range, and the multi-angle inspection video includes:

[0026] The liquid level change information of the bottom water tank of the target monitoring pipe gallery is segmented to obtain multiple continuous time series data. Time series analysis algorithms are then used to predict the future liquid level change trend.

[0027] Convolutional neural networks in deep learning are used to perform image recognition on multi-angle maintenance videos provided by the maintenance robot, extract possible leakage areas, and determine the image recognition results by comparing the leakage pipe areas determined by video frames from different angles.

[0028] By combining the liquid level change information with the image recognition results, the actual leakage rate and leakage volume are calculated using fluid mechanics principles.

[0029] By adopting the above technical solution, the potential leakage risk of the enclosed pipe gallery is predicted through time series analysis algorithm. At the same time, the image recognition of the multi-angle inspection video provided by the inspection robot is performed by using convolutional neural network (CNN) in deep learning to extract possible leakage areas. By comparing video frames from different angles, the specific leakage pipe area is determined, which is conducive to the accurate identification of the pipe leakage location. Then, the actual leakage speed and leakage volume are calculated by applying fluid mechanics principles to improve the accuracy and reliability of leakage detection.

[0030] In a preferred embodiment, this application also includes:

[0031] The monitoring mechanism and the maintenance robot are connected using a preset communication protocol and a preset communication interaction middleware.

[0032] Based on the collected detection requests, the monitoring agency generates corresponding detection instructions and assigns them to the corresponding maintenance robots. The detection instructions include first confirmation information with a unique communication identifier.

[0033] The maintenance robot performs the corresponding detection operation based on the received detection command, generates execution confirmation information based on the first confirmation information, and sends the execution confirmation information to the monitoring agency according to the unique communication identifier.

[0034] The monitoring agency obtains the corresponding detection results based on the execution confirmation information, and performs fault location simulation display based on the detection results;

[0035] The maintenance robot sends a first reception status message to the monitoring agency within a preset first confirmation time period based on the received first confirmation message. The monitoring agency determines whether it has received the first reception status message within a preset second confirmation time period. If the monitoring agency does not receive the first reception status message within the preset second confirmation time period, the monitoring agency resends the first confirmation message according to a preset first information retransmission condition.

[0036] By adopting the above technical solution, the data interaction between the monitoring agency and the maintenance robot, as well as the robot's command reception and execution status, are verified; this records and tracks the maintenance status and effectiveness of the robot. Specifically, the monitoring agency and the maintenance robot are connected using a preset communication protocol and a preset communication interaction middleware, which facilitates efficient communication between the two. Since in practical applications, the number and distribution of pipes in enclosed pipe corridors are large and complex, and a large number of robots are used for maintenance, to improve the monitoring effect of sewage treatment pipe network monitoring in complex enclosed pipe corridors, this application also ensures accurate transmission of commands through a first confirmation information with a unique communication identifier. The maintenance robot executes the corresponding detection operation based on the received detection command, and based on... The first confirmation information generates execution confirmation information, which is then sent to the monitoring agency based on a unique communication identifier, thereby realizing a two-way confirmation mechanism and enhancing the reliability and traceability of the pipeline monitoring system. The monitoring agency obtains the corresponding detection results based on the execution confirmation information and performs fault location simulation display based on the detection results, so that monitoring personnel can understand the real-time abnormal situation of the pipeline. Furthermore, the maintenance robot sends first reception status information to the monitoring agency within the preset first confirmation time period to determine the reception status of the first confirmation information. If the monitoring agency does not receive the information within the preset time, it resends the first confirmation information according to the preset first information retransmission conditions, ensuring the integrity of information transmission and facilitating the tracking and recording of the maintenance robot's instruction execution.

[0037] In a preferred embodiment of this application: the maintenance robot performs a corresponding detection operation based on the received detection instruction, generates execution confirmation information based on the first confirmation information, and sends the execution confirmation information to the monitoring agency according to the unique communication identifier, including:

[0038] Within a preset execution time period, the maintenance robot sends the execution confirmation information to the monitoring agency based on the unique communication identifier.

[0039] Based on the received execution confirmation information, the monitoring agency sends second reception status information to the maintenance robot within a preset third confirmation time period to determine the reception status of the execution confirmation information.

[0040] The maintenance robot determines whether it has received the second reception status information within the preset second confirmation time period.

[0041] If the maintenance robot does not receive the second reception status information within the preset second confirmation time period, the maintenance robot will resend the execution confirmation information according to the preset second information retransmission conditions.

[0042] By adopting the above technical solution, the execution confirmation information is sent to the monitoring agency based on a unique communication identifier, which helps to ensure that the results of each detection operation are accurately recorded and transmitted, reducing operational errors caused by data loss or errors. Furthermore, by sending a second reception status information to the maintenance robot within a preset third confirmation time period to determine the reception status of the execution confirmation information, a two-way confirmation mechanism is adopted to improve the reliability of information exchange and transmission between the monitoring agency and the maintenance robot, so as to facilitate real-time monitoring of the status of each step of the operation and improve the efficiency of pipeline monitoring. At the same time, if the maintenance robot fails to receive the second reception status information, it will automatically trigger a retransmission mechanism to ensure the integrity and accuracy of the detection instructions and detection information.

[0043] Secondly, the objective of this invention is achieved through the following technical solution:

[0044] A method for monitoring a wastewater treatment pipeline network, applied to a wastewater treatment pipeline network monitoring system as described above, the method comprising:

[0045] Multi-angle inspection videos of pipelines in the target monitoring tunnel are obtained through inspection robots;

[0046] Based on the pipeline identification information and pipeline design parameters obtained by the monitoring agency, the first predicted leak location and the second predicted leak location detected by the maintenance robot are analyzed according to the pipeline identification information and pipeline design parameters when the detection request is triggered.

[0047] Based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location, a fault identification model is generated to guide the operation of the maintenance robot.

[0048] The system obtains a reference range for the change in detection accuracy, which represents the threshold of the change in the detection accuracy of the maintenance robot, and acquires information on the change in liquid level in the water tank at the bottom of the closed pipe gallery through a liquid level monitoring module. Based on the liquid level change information, the reference range for the change in detection accuracy, and the multi-angle maintenance video, the system performs a comprehensive analysis of the location of the pipe leak and determines the final leak location analysis result.

[0049] In a preferred embodiment of this application, the method further includes: when the maintenance robot receives a maintenance instruction, it sends an execution confirmation message to the monitoring agency;

[0050] Based on the collected detection requests, the monitoring agency records the time data of the corresponding first confirmation information, first reception status information, second confirmation information, and second reception status information, as well as the corresponding transmission output status information, into a preset record list.

[0051] If the number of times the maintenance robot resends the execution confirmation information equals the preset second resend threshold, and the monitoring agency does not receive the execution confirmation information within the preset second confirmation time period, the monitoring agency outputs an abnormal prompt message corresponding to the detection request.

[0052] Thirdly, the objective of this invention is achieved through the following technical solution:

[0053] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described wastewater treatment pipeline monitoring method.

[0054] Fourthly, the objective of this invention is achieved through the following technical solution:

[0055] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described wastewater treatment pipeline monitoring method.

[0056] In summary, this application includes at least one of the following beneficial technical effects:

[0057] 1. The fault identification model not only considers the overall layout and design parameters of the pipeline network, but also combines actual detection results, making the maintenance strategy more scientific and reasonable, improving maintenance efficiency and success rate. At the same time, it integrates multiple data sources and uses fluid mechanics principles and image recognition technology to accurately calculate the leakage rate and leakage volume, further optimizing the accuracy of fault location.

[0058] 2. It effectively solves the problems of operational errors and task delays caused by unstable communication, inaccurate information transmission, and lack of effective retransmission mechanisms in existing technologies, thereby improving the stability and reliability of system communication, enhancing the accuracy of operation and the timeliness of fault response, and improving the overall operation and maintenance efficiency and technical management level. Attached Figure Description

[0059] Figure 1 This is a framework diagram of a sewage treatment pipeline monitoring system according to one embodiment of this application;

[0060] Figure 2 This is a flowchart of a sewage treatment pipeline monitoring method according to one embodiment of this application;

[0061] Figure 3 This is a schematic diagram of a device according to one embodiment of this application. Detailed Implementation

[0062] The present application will be further described in detail below with reference to the accompanying drawings.

[0063] In one embodiment, such as Figure 1 As shown, this application discloses a sewage treatment pipeline network monitoring system, which includes a liquid level monitoring module, a maintenance robot, and a monitoring mechanism. The liquid level monitoring module is located in the bottom water tank of the target monitoring pipeline corridor. The bottom water tank is located at the bottom of the pipeline corridor and is used to collect and temporarily store sewage. The liquid level monitoring module typically uses an ultrasonic sensor or a pressure sensor. The maintenance robot is an automated device that can move in a narrow space and carry detection equipment such as cameras. The maintenance robot is used to acquire multi-angle maintenance videos and pipeline images from different angles of the pipeline in the target monitoring pipeline corridor. The movement path of the maintenance robot can cover the entire pipeline area of ​​the target monitoring pipeline corridor.

[0064] The monitoring agency obtains pipeline identification information and pipeline network design parameters. Based on these parameters, it analyzes the first predicted leak location and the second predicted leak location detected by the maintenance robot when the detection request is triggered. Based on the pipeline network design parameters, the first and second predicted leak locations, a fault identification model is generated to guide the operation of the maintenance robot. A reference range for detection accuracy variation, representing the threshold of change in the maintenance robot's detection accuracy, is obtained. Liquid level change information in the water tank at the bottom of the enclosed pipe gallery is acquired through a liquid level monitoring module. Based on the liquid level change information, the reference range for detection accuracy variation, and multi-angle maintenance videos, a comprehensive analysis of the pipeline leak location is performed to determine the final leak location analysis result.

[0065] In this embodiment, pipeline identification information and pipeline network design parameters are obtained. Based on the pipeline identification information and pipeline network design parameters, the first predicted leak location when the detection request is triggered and the second predicted leak location detected by the maintenance robot are analyzed. Specifically, the steps include the following:

[0066] S1: Obtain pipeline coding identification information and pipeline design parameters. Pipeline coding identification information includes pipeline type, pipeline diameter, pipeline installation angle, and the relative position of the pipeline in the pipe gallery. Pipeline design parameters include pipeline layout diagram, historical fault data, and design pressure resistance value.

[0067] In this embodiment, the pipeline coding identification information is used to uniquely identify the detailed information of each pipeline segment.

[0068] Specifically, each pipe section is numbered and its type (e.g., PVC, cast iron, etc.), diameter, installation angle, and relative position in the pipe gallery are recorded; pipe network layout diagrams are collected and organized to ensure that the location and connection of all pipes are accurately recorded; historical fault data are summarized to analyze which areas or types of pipes are more prone to problems; and the design pressure resistance value of each pipe section is confirmed to assess its pressure resistance capacity.

[0069] S2: Based on the pipe type, pipe diameter, pipe installation angle, and the relative position of the pipe in the pipe gallery, combined with historical fault data, determine the first predicted leak location when the detection request is triggered.

[0070] In this embodiment, the first predicted leak location is the location most likely to leak based on existing data and analysis results. This application uses machine learning algorithms (such as decision trees and random forests) to analyze historical fault data and identify high-risk factors (such as specific types of pipes, problems at certain installation angles, etc.). When a detection request is triggered, the area with the highest score is prioritized for inspection as the first predicted leak location based on the above-mentioned predicted leak location analysis results.

[0071] S3: Based on the pipeline layout diagram, design pressure resistance value, pipeline installation angle, and the relative position of the pipeline in the pipe gallery, combined with the multi-angle inspection video provided by the inspection robot, determine the second predicted leak location detected by the inspection robot.

[0072] In this embodiment, the second predicted leak location is determined based on the robot's movement path and the video captured by the robot to identify potential leak points.

[0073] Specifically, image processing techniques (such as convolutional neural networks CNN) are used to analyze multi-angle inspection videos to identify possible leakage areas; combined with the pipeline layout diagram, design pressure resistance value and specific pipeline installation conditions, the actual risk of these areas is assessed, and specific leakage points are determined as secondary predicted leakage locations.

[0074] In one embodiment, based on liquid level change information, reference range for changes in detection accuracy, and multi-angle inspection videos, the leakage rate and leakage volume at the leak point are analyzed, specifically including the following steps:

[0075] S101: The liquid level change information of the bottom water tank of the target monitoring pipe gallery is segmented to obtain multiple continuous time series data, and the future liquid level change trend is predicted by time series analysis algorithm.

[0076] In this embodiment, the liquid level change information is the data on the liquid level change in the water tank at the bottom of the closed pipe gallery within a specific time period; time series data refers to a series of observations arranged in chronological order, used to analyze and predict future trends; the time series analysis algorithm uses a Long Short-Term Memory (LSTM) network.

[0077] Specifically, a high-precision liquid level sensor is installed in the bottom water tank, and the sampling frequency of the liquid level sensor is set (e.g., once every 5 minutes) to obtain continuous liquid level data.

[0078] S102: The convolutional neural network in deep learning is used to perform image recognition on the multi-angle maintenance video provided by the maintenance robot, extract the possible leakage areas, and determine the image recognition results by comparing the leakage pipe areas determined by video frames from different angles.

[0079] In this embodiment, Convolutional Neural Network (CNN) is a deep learning algorithm suitable for image recognition tasks and capable of automatically extracting image features; multi-angle inspection video refers to video clips taken by the inspection robot from different angles inside the pipe to provide comprehensive visual information; the image is the result, which refers to the conclusions about the location and severity of the leak area output after CNN processing.

[0080] S103: Combining liquid level change information with image recognition results, the actual leakage rate and leakage volume are calculated using fluid mechanics principles.

[0081] In this embodiment, the leakage rate refers to the amount of water flowing out from the leakage point per unit time; the leakage amount refers to the total leakage amount within a specific time period.

[0082] Furthermore, in practical applications, multiple baffles can be installed in the water tank at the bottom of the enclosed pipe gallery. Each baffle is spaced apart from the bottom wall of the water tank. The change in the liquid level in the water tank can be used to determine whether the pipe is dripping or bursting. If the liquid flows slowly along the different baffles, it indicates a dripping situation. If the water level at the baffles rises too quickly, it may indicate a burst pipe.

[0083] In one embodiment, a sewage treatment pipeline monitoring system further includes: a connection between the monitoring agency and the maintenance robot using a preset communication protocol and a preset communication interaction middleware, such as MQTT, AMQP, etc.; and communication interaction middleware such as Apache Kafka, RabbitMQ, etc.

[0084] Based on the collected detection requests, the monitoring agency generates corresponding detection instructions and assigns them to the corresponding maintenance robots. The detection instructions include a first confirmation message with a unique communication identifier. The detection request is a request issued by the operator or the automated system to start a specific detection task. The first confirmation message is a message fragment containing a unique communication identifier, used to confirm whether subsequent messages have been received correctly.

[0085] The maintenance robot executes corresponding detection operations based on the received detection instructions, generates execution confirmation information based on the first confirmation information, and sends the execution confirmation information to the monitoring agency according to the unique communication identifier. The execution confirmation information is the feedback information generated by the maintenance robot after completing the detection task, and contains the unique communication identifier in the first confirmation information. After receiving the detection instructions, the maintenance robot executes the corresponding detection operations according to the instructions (such as taking multi-angle videos, measuring liquid levels, etc.). The monitoring agency obtains the corresponding detection results based on the execution confirmation information, and performs fault location simulation display based on the detection results. That is, according to the detection results, the fault location is marked on a GIS or other visualization platform, and the severity of the fault is indicated by color coding or other methods.

[0086] The maintenance robot, based on the received first confirmation information, sends a first reception status message to the monitoring agency within a preset first confirmation time period to determine the reception status of the first confirmation information. The monitoring agency then determines whether it has received the first reception status message within a preset second confirmation time period. If the monitoring agency does not receive the first reception status message within the preset second confirmation time period, it retransmits the first confirmation information according to preset first information retransmission conditions. The first information retransmission conditions satisfy that the number of retransmissions of the first confirmation information does not exceed a preset first retransmission threshold and that the monitoring agency's information reception waiting time does not exceed a preset first timeout period. If the monitoring agency receives the first reception status message within the preset second confirmation time period, the reception status of the first confirmation information is considered successful.

[0087] Specifically, the first confirmation time period is a set time window during which the maintenance robot must send the first reception status information, for example, within 5 seconds; the second confirmation time period is a set time window during which the monitoring agency must receive the first reception status information, for example, within 5 seconds; the first information retransmission condition specifies under what conditions the first confirmation information can be retransmitted, including the maximum number of retransmissions and waiting time limits, for example, a maximum of 3 retransmissions, with an interval of 10 seconds between each retransmission.

[0088] In this embodiment, the maintenance robot executes the corresponding detection operation based on the received detection command, generates execution confirmation information based on the first confirmation information, and sends the execution confirmation information to the monitoring agency according to the unique communication identifier, including:

[0089] S111: Within the preset execution time period, the maintenance robot sends execution confirmation information to the monitoring agency based on a unique communication identifier.

[0090] In this embodiment, the communication protocol defines the rules, formats, and methods for data transmission to ensure smooth information exchange between the monitoring agency and the maintenance robot.

[0091] S112: Based on the received execution confirmation information, the monitoring agency sends a second reception status information to the maintenance robot within a preset third confirmation time period to determine the reception status of the execution confirmation information.

[0092] In this embodiment, the execution time period is a set time window during which the inspection robot must complete the inspection operation and send the execution confirmation information. In practical applications, a reasonable execution time period (e.g., 5 minutes) can be set according to the complexity of the specific inspection task.

[0093] S113: The maintenance robot determines whether it has received the second reception status information within the preset second confirmation time period.

[0094] In this embodiment, during the second confirmation time period, the maintenance robot continuously listens for the second reception status information from the monitoring agency; if the second reception status information is received within the specified time, the communication is considered successful; otherwise, a retransmission mechanism is triggered.

[0095] S114: If the maintenance robot does not receive the second reception status information within the preset second confirmation time period, the maintenance robot will resend the execution confirmation information according to the preset second information retransmission conditions.

[0096] In this embodiment, the second information retransmission condition specifies the conditions under which the execution confirmation information can be retransmitted, including the maximum number of retransmissions and the waiting time limit.

[0097] Specifically, the second information retransmission condition is that the number of retransmissions of the execution confirmation information does not exceed the preset second retransmission threshold, and the information reception waiting time of the maintenance robot does not exceed the preset second timeout time. If the maintenance robot does not receive the second reception status information within the preset second confirmation time period, the retransmission process is automatically triggered. During retransmission, the maintenance robot uses the same unique communication identifier to retransmit the execution confirmation information and records the number of retransmissions. When the preset maximum number of retransmissions is reached, retransmission stops, and an error log is recorded for subsequent analysis. At the same time, an alarm mechanism is set to remind maintenance personnel to perform manual intervention.

[0098] In one embodiment, such as Figure 2 As shown, a method for monitoring a sewage treatment pipeline network is provided, which is applied to a sewage treatment pipeline network monitoring system.

[0099] A method for monitoring a wastewater treatment pipeline network, specifically including the following steps:

[0100] S10: Obtain multi-angle inspection videos of the pipelines in the target monitoring corridor through the inspection robot.

[0101] S20: Based on the pipeline identification information and pipeline design parameters obtained by the monitoring agency, analyze the first predicted leak location and the second predicted leak location detected by the maintenance robot when the detection request is triggered, according to the pipeline identification information and pipeline design parameters.

[0102] Specifically, the first predicted leak location is based on historical fault data and the current pipeline status, using machine learning algorithms to predict the most likely location of the leak; for example, a specific area may be marked as a high-risk area due to frequent pressure fluctuations; the second predicted leak location refers to multi-angle videos taken by the maintenance robot, for example, a suspected leak point may be initially discovered, located within the aforementioned high-risk area.

[0103] S30: Generate a fault identification model to guide the operation of the maintenance robot based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location.

[0104] In this embodiment, the fault identification model is a pre-trained regression analysis model that can calculate the leakage risk assessment value by combining the pipe type and the design pressure resistance value. Assuming that the calculated risk score is 8 (out of 10), it indicates that there is a high risk of leakage.

[0105] S40: Obtain the reference range of detection accuracy change, which represents the threshold of change in the detection accuracy of the maintenance robot, and obtain the liquid level change information in the water tank at the bottom of the closed pipe gallery through the liquid level monitoring module; based on the liquid level change information, the reference range of detection accuracy change, and the multi-angle maintenance video, conduct a comprehensive analysis of the pipeline leakage location and determine the final leakage location analysis result.

[0106] In this embodiment, the reference range for detection accuracy variation refers to the maximum range of allowable fluctuations in the detection accuracy of the maintenance robot. If this range is exceeded, recalibration is required. The leak location analysis result refers to the final leak location and its severity obtained after comprehensively considering multiple factors.

[0107] In one embodiment, a wastewater treatment pipeline network monitoring method further includes: when a maintenance robot receives a maintenance instruction, it sends an execution confirmation message to the monitoring agency.

[0108] S50: Based on the collected detection request, the monitoring agency records the time data of the corresponding first confirmation information, first reception status information, second confirmation information, and second reception status information, as well as the corresponding transmission output status information, into a preset record list.

[0109] Specifically, when the monitoring agency sends the first confirmation message, it records the sending time, the content of the first confirmation message, and the sending status (success / failure); when the maintenance robot sends the first reception status message, it records the reception time, the content of the first reception status message, and the reception status; similarly, when the monitoring agency sends the second confirmation message, it records the sending time, the content of the second confirmation message, and the sending status; when the maintenance robot sends the second reception status message, it records the reception time, the content of the second reception status message, and the reception status.

[0110] S60: If the number of times the inspection robot resends the execution confirmation information is equal to the preset second resend number threshold, and the monitoring agency does not receive the execution confirmation information within the preset second confirmation time period, the monitoring agency outputs the corresponding abnormal prompt information for the detection request.

[0111] In this embodiment, the second retransmission threshold is the set maximum number of retransmissions; exceeding this number indicates a communication failure. The second confirmation time period refers to the time window during which the monitoring agency waits to receive the execution confirmation information. The abnormal prompt information is a notification issued by the monitoring agency when communication fails, reminding operators to pay attention and take measures.

[0112] It should be understood that the sequence number of each step in the above embodiments does not imply 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 this application.

[0113] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores multi-angle inspection videos, liquid level change information, etc. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a wastewater treatment pipeline monitoring method.

[0114] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps:

[0115] S10: Obtain multi-angle inspection videos of the pipelines in the target monitoring corridor through the inspection robot.

[0116] S20: Based on the pipeline identification information and pipeline design parameters obtained by the monitoring agency, the first predicted leak location when the detection request is triggered and the second predicted leak location detected by the maintenance robot are determined according to the pipeline identification information and pipeline design parameters.

[0117] S30: Generate a fault identification model to guide the operation of the maintenance robot based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location.

[0118] S40: Obtain the reference range of detection accuracy change, which represents the threshold of change in the detection accuracy of the maintenance robot, and obtain the liquid level change information in the water tank at the bottom of the closed pipe gallery through the liquid level monitoring module; based on the liquid level change information, the reference range of detection accuracy change, and the multi-angle maintenance video, conduct a comprehensive analysis of the pipeline leakage location and determine the final leakage location analysis result.

[0119] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0120] S10: Obtain multi-angle inspection videos of the pipelines in the target monitoring corridor through the inspection robot.

[0121] S20: Based on the pipeline identification information and pipeline design parameters obtained by the monitoring agency, the first predicted leak location when the detection request is triggered and the second predicted leak location detected by the maintenance robot are determined according to the pipeline identification information and pipeline design parameters.

[0122] S30: Generate a fault identification model to guide the operation of the maintenance robot based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location.

[0123] S40: Obtain the reference range of detection accuracy change, which represents the threshold of change in the detection accuracy of the maintenance robot, and obtain the liquid level change information in the water tank at the bottom of the closed pipe gallery through the liquid level monitoring module; based on the liquid level change information, the reference range of detection accuracy change, and the multi-angle maintenance video, conduct a comprehensive analysis of the pipeline leakage location and determine the final leakage location analysis result.

[0124] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0125] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0126] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A sewage treatment pipeline network monitoring system, characterized in that, It includes a liquid level monitoring module, a maintenance robot, and a monitoring mechanism; the liquid level monitoring module is located in the bottom water tank of the target monitoring pipe gallery; the maintenance robot is used to acquire multi-angle maintenance videos of the pipes in the target monitoring pipe gallery; The monitoring agency obtains pipeline identification information and pipeline design parameters, and analyzes the first predicted leak location and the second predicted leak location detected by the maintenance robot when the detection request is triggered based on the pipeline identification information and pipeline design parameters. Based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location, a fault identification model is generated to guide the operation of the maintenance robot. The system obtains a reference range for the change in detection accuracy, which represents the threshold of the change in the detection accuracy of the maintenance robot, and acquires information on the change in liquid level in the water tank at the bottom of the closed pipe gallery through a liquid level monitoring module. Based on the liquid level change information, the reference range for the change in detection accuracy, and the multi-angle maintenance video, the system performs a comprehensive analysis of the location of the pipe leak and determines the final leak location analysis result. The process of acquiring pipeline identification information and pipeline network design parameters, and analyzing the first predicted leak location and the second predicted leak location detected by the maintenance robot based on the pipeline identification information and pipeline network design parameters, specifically includes: Obtain pipeline coding identification information and pipeline network design parameters. The pipeline coding identification information includes pipeline type, pipeline diameter, pipeline installation angle, and the relative position of the pipeline in the pipe gallery. The pipeline network design parameters include pipeline network layout diagram, historical fault data, and design pressure resistance value. Based on the pipe type, pipe diameter, pipe installation angle, and pipe relative position in the pipe gallery, combined with historical fault data, the first predicted leak location when the detection request is triggered is determined. Based on the pipeline layout diagram, the design pressure resistance value, the pipeline installation angle, and the relative position of the pipeline in the pipe gallery, the second predicted leak location detected by the maintenance robot is determined by combining the multi-angle maintenance video provided by the maintenance robot. The step of generating a fault identification model to guide the operation of the maintenance robot based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location specifically includes: The possible leakage path length is calculated based on the pipeline layout diagram, the first predicted leakage location, and the second predicted leakage location. The corresponding leakage risk assessment value is obtained based on the pipeline type and the design pressure resistance value. Based on the length of the leakage path and the leakage risk assessment value, a preliminary fault identification model is generated; Obtain the reference range of detection accuracy change, which represents the threshold of change in the detection accuracy of the maintenance robot, and obtain the liquid level change information in the water tank at the bottom of the closed pipe gallery through the liquid level monitoring module; Based on the liquid level change information, the detection accuracy change reference range, and the multi-angle inspection video, the leakage rate and leakage volume of the leak point are analyzed; the ratio of the leakage rate to the leakage volume is calculated to obtain a leakage ratio value used to predict the severity of the leak. Based on the leakage path length, the leakage risk assessment value, and the leakage ratio, a leakage level is obtained to determine the specific circumstances of the leakage. Based on the leakage level and the preliminary fault identification model, a final fault identification model is generated; Also includes: The monitoring mechanism and the maintenance robot are connected using a preset communication protocol and a preset communication interaction middleware. Based on the collected detection requests, the monitoring agency generates corresponding detection instructions and assigns them to the corresponding maintenance robots. The detection instructions include first confirmation information with a unique communication identifier. The maintenance robot performs the corresponding detection operation based on the received detection command, generates execution confirmation information based on the first confirmation information, and sends the execution confirmation information to the monitoring agency according to the unique communication identifier. The monitoring agency obtains the corresponding detection results based on the execution confirmation information, and performs fault location simulation display based on the detection results; The maintenance robot sends a first reception status message to the monitoring agency within a preset first confirmation time period based on the received first confirmation message. The monitoring agency determines whether it has received the first reception status message within a preset second confirmation time period. If the monitoring agency does not receive the first reception status message within the preset second confirmation time period, the monitoring agency resends the first confirmation message according to a preset first information retransmission condition.

2. The sewage treatment pipeline monitoring system according to claim 1, characterized in that, The step of analyzing the leakage rate and leakage volume of the leak point based on the liquid level change information, the detection accuracy change reference range, and the multi-angle inspection video includes: The liquid level change information of the bottom water tank of the target monitoring pipe gallery is segmented to obtain multiple continuous time series data. Time series analysis algorithms are then used to predict the future liquid level change trend. Convolutional neural networks in deep learning are used to perform image recognition on multi-angle maintenance videos provided by the maintenance robot, extract possible leakage areas, and determine the image recognition results by comparing the leakage pipe areas determined by video frames from different angles. By combining the liquid level change information with the image recognition results, the actual leakage rate and leakage volume are calculated using fluid mechanics principles.

3. The sewage treatment pipeline monitoring system according to claim 1, characterized in that, The maintenance robot executes corresponding detection operations based on the received detection instructions, generates execution confirmation information based on the first confirmation information, and sends the execution confirmation information to the monitoring agency according to the unique communication identifier, including: Within a preset execution time period, the maintenance robot sends the execution confirmation information to the monitoring agency based on the unique communication identifier. Based on the received execution confirmation information, the monitoring agency sends second reception status information to the maintenance robot within a preset third confirmation time period to determine the reception status of the execution confirmation information. The maintenance robot determines whether it has received the second reception status information within the preset second confirmation time period. If the maintenance robot does not receive the second reception status information within the preset second confirmation time period, the maintenance robot will resend the execution confirmation information according to the preset second information retransmission conditions.

4. A method for monitoring a sewage treatment pipeline network, characterized in that, Applied to a wastewater treatment pipeline network monitoring system as described in any one of claims 1-3, the method includes: Multi-angle inspection videos of pipelines in the target monitoring tunnel are obtained through inspection robots; Based on the pipeline identification information and pipeline design parameters obtained by the monitoring agency, the first predicted leak location and the second predicted leak location detected by the maintenance robot are analyzed according to the pipeline identification information and pipeline design parameters when the detection request is triggered. Based on the pipeline design parameters, the first predicted leak location, and the second predicted leak location, a fault identification model is generated to guide the operation of the maintenance robot. The system obtains a reference range for the change in detection accuracy, which represents the threshold of the change in the detection accuracy of the maintenance robot, and acquires information on the change in liquid level in the water tank at the bottom of the closed pipe gallery through a liquid level monitoring module. Based on the liquid level change information, the reference range for the change in detection accuracy, and the multi-angle maintenance video, the system performs a comprehensive analysis of the location of the pipe leak and determines the final leak location analysis result.

5. A method for monitoring a sewage treatment pipeline network according to claim 4, characterized in that, The method further includes: when the maintenance robot receives a maintenance instruction, it sends an execution confirmation message to the monitoring agency; Based on the collected detection requests, the monitoring agency records the time data of the corresponding first confirmation information, first reception status information, second confirmation information, and second reception status information, as well as the corresponding transmission output status information, into a preset record list. If the number of times the maintenance robot resends the execution confirmation information equals the preset second resend threshold, and the monitoring agency does not receive the execution confirmation information within the preset second confirmation time period, the monitoring agency outputs an abnormal prompt message corresponding to the detection request.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the wastewater treatment pipeline monitoring method as described in any one of claims 4 to 5.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the wastewater treatment pipeline monitoring method as described in any one of claims 4 to 5.

Images