Drainage pipe network clogging processing system and method based on internet of things large model

Abstract

This invention provides a drainage pipe network siltation treatment system and method based on an Internet of Things (IoT) big data model, relating to the field of pipe maintenance. The method includes: determining a sequence of water-passing areas for multiple adjacent pipe areas based on flow data of pipe areas uploaded by acquisition equipment; identifying abnormal pipe areas and abnormal water-passing times based on the water-passing area sequence; determining a target detection area and target detection time based on the abnormal pipe areas and abnormal water-passing times; performing sonar detection on the target detection area and collecting sonar detection data; generating an estimated siltation thickness, siltation type, and siltation risk for the target detection area based on the sonar detection data and pipe characteristics; and controlling automated siltation equipment to perform siltation operations based on the siltation risk and siltation parameters. This method solves the problems of disconnected workflows, delayed response, and heavy reliance on manual experience in pipe network maintenance, improving the systematization, intelligence, and operational efficiency of drainage pipe network management.

Description

Technical Field

[0001] This specification relates to the field of pipeline maintenance, and in particular to a drainage network siltation treatment system and method based on an Internet of Things (IoT) big data model. Background Technology

[0002] Urban drainage networks are critical infrastructure for ensuring the normal operation of cities, and are related to urban flood control and drainage capabilities as well as environmental safety. The assessment of siltation in existing drainage networks mainly relies on traditional detection methods such as manual inspection, closed-circuit television, or pipe endoscopy, which can only provide qualitative and two-dimensional image information and cannot provide non-destructive and quantitative assessments of the thickness and volume of silt.

[0003] Therefore, there is a need for a drainage network siltation treatment system and method based on the Internet of Things (IoT) big data model to achieve accurate quantitative assessment of siltation, intelligent and efficient dredging operations, and intelligent management and monitoring of the drainage network. Summary of the Invention

[0004] The invention includes a drainage network siltation treatment system based on an Internet of Things (IoT) big data model, comprising an emergency monitoring and management platform and an emergency monitoring object platform, wherein the emergency monitoring and management platform is configured to execute a drainage network siltation treatment method based on an IoT big data model.

[0005] The invention also includes a method for treating siltation in drainage pipe networks based on a large-scale Internet of Things (IoT) model, comprising: collecting flow data of pipe areas using acquisition devices deployed in the drainage pipe network, and acquiring the flow data uploaded by the acquisition devices; determining a sequence of water-passing areas of multiple adjacent pipe areas based on the flow data of the pipe areas; determining abnormal pipe areas and abnormal water-passing times based on the sequence of water-passing areas of the multiple adjacent pipe areas; determining a target detection area and a target detection time based on the abnormal pipe areas and the abnormal water-passing times; controlling a robot equipped with a sonar sensor to perform sonar detection on the target detection area at the target detection time through an emergency monitoring platform, and collecting sonar detection data; generating an estimated siltation thickness and siltation type for the target detection area based on the sonar detection data and pipe characteristics; determining siltation risk based on the estimated siltation thickness, the siltation type, and the pipe characteristics; automatically generating a dredging path and dredging parameters based on the siltation risk; and controlling an automated dredging device to proceed along the dredging path to the dredging operation point and to perform dredging operations based on the dredging parameters through the emergency monitoring platform.

[0006] Beneficial effects: By collecting flow data and sonar detection data, the risk of siltation can be assessed, and the dredging of pipeline areas can be completed automatically. This solves the problems of disconnected workflow, delayed response, and heavy reliance on manual experience in traditional pipeline maintenance. Through data-driven decision-making, the systematization, intelligence and overall operation and maintenance efficiency of drainage pipeline management are greatly improved. Attached Figure Description

[0007] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0008] Figure 1 This is a schematic diagram of the platform structure of a drainage network siltation treatment system based on an Internet of Things large model, as shown in some embodiments of this specification.

[0009] Figure 2 This is an exemplary flowchart of a drainage network siltation treatment method according to some embodiments of this specification;

[0010] Figure 3 This is an exemplary schematic diagram illustrating the determination of a target detection area according to some embodiments of this specification;

[0011] Figure 4 This is an exemplary schematic diagram of a siltation model shown according to some embodiments of this specification.

[0012] Attached labeling: 100 represents the drainage network siltation treatment system based on the Internet of Things large-scale model; 110 represents the emergency monitoring service platform; 120 represents the emergency monitoring management platform; 121 represents the data center; 1211 represents the database; 1212 represents the data processing model library; 1213 represents the computing unit; 130 represents the emergency monitoring sensor network platform; 140 represents the emergency monitoring object platform; 311 represents rainfall; 312 represents catering wastewater discharge; 313 represents construction wastewater discharge; 310 represents preset screening conditions; 320 represents abnormal pipe areas (including abnormal pipe area 1, abnormal pipe area 2, ..., abnormal pipes). Region N), 330 is the screened abnormal pipeline region, 340 is the abnormal water flow area sequence, 350 is the flow fluctuation information, 351 is the historical rainfall, 352 is the historical catering sewage discharge, 353 is the historical construction sewage discharge, 360 is the updated abnormal water flow area sequence, 370 is the target detection area, 410 is the normal water flow area sequence, 420 is the detection density, 430 is the sonar detection data, 440 is the pipeline characteristics, 450 is the siltation model, 451 is the estimated siltation thickness, 452 is the siltation type, 460 is the dredging accuracy rate, and 470 is the associated pipeline region. Detailed Implementation

[0013] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0014] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or subsequent operations are not necessarily performed in exact order.

[0016] Figure 1 This is a schematic diagram of the platform structure of a drainage network siltation treatment system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification.

[0017] In some embodiments, such as Figure 1 As shown, the drainage pipe network siltation treatment system 100 based on the Internet of Things (IoT) big data model (hereinafter referred to as system 100) may include an emergency monitoring service platform 110, an emergency monitoring management platform 120, an emergency monitoring sensor network platform 130, and an emergency monitoring object platform 140. In some embodiments, the emergency monitoring service platform 110, the emergency monitoring management platform 120, the emergency monitoring sensor network platform 130, and the emergency monitoring object platform 140 may be interconnected sequentially. The IoT big data model refers to the IoT model architecture used to enable the efficient operation of large amounts of data in system 100. In some embodiments, artificial intelligence models (e.g., ChatGPT, Gemini, Deepseek) may be applied to the IoT model architecture for data perception and processing.

[0018] Emergency monitoring service platform 110 refers to a platform that provides emergency monitoring services, such as providing intelligent monitoring services for urban drainage pipe network siltation treatment. In some embodiments, emergency monitoring service platform 110 is configured as a server and / or processor, etc. Emergency monitoring service platform 110 can interact bidirectionally with data center 121 in emergency monitoring management platform 120. In some embodiments, emergency monitoring management platform 120 can obtain external environmental data (e.g., rainfall data released by meteorological departments, etc.) from emergency monitoring service platform 110 and store the obtained external environmental data in database 1211.

[0019] The emergency monitoring and management platform 120 refers to a comprehensive management platform that coordinates and integrates the connections and collaboration among multiple platforms. In some embodiments, the emergency monitoring and management platform 120 may be a platform for monitoring and managing information related to urban drainage network siltation. In some embodiments, the emergency monitoring and management platform 120 may include servers, processors, data storage systems, large-screen display systems, IoT platform software, communication components (e.g., communication interfaces, gateways), etc. In some embodiments, the emergency monitoring and management platform 120 may be a software platform running on a server or in the cloud, used to process data and / or information obtained from other platforms (e.g., emergency monitoring service platform 110, emergency monitoring sensor network platform 130).

[0020] In some embodiments, the emergency monitoring and management platform 120 may include a data center 121. The data center 121 may include a database 1211, a data processing model library 1212, and a computing unit 1213.

[0021] Database 1211 is used to collect, store, and manage data related to siltation in drainage pipe networks, such as flow data and sonar detection data for the pipe area. Database 1211 may include relational databases (such as MySQL and PostgreSQL) and time-series databases (such as InfluxDB). In some embodiments, database 1211 may include a Geographic Information System (GIS) database for the drainage pipe network, a siltation database, and a first preset table. For more information on flow data, sonar detection data, pipe characteristics, drainage pipe network information, the siltation database, and the first preset table, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0022] The data processing model library 1212 is used to store trained large data processing models. In some embodiments, the data processing model library 1212 may include silo models, image processing models, chatbots, etc. For more information on image processing models and silo models, please refer to [link to relevant documentation]. Figure 2 , Figure 3 And its related descriptions.

[0023] The computing unit 1213 refers to a functional module that performs arithmetic, logical, and other instruction operations. The computing unit 1213 may include a processor, such as a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), etc.

[0024] The emergency monitoring sensor network platform 130 refers to a platform used for the comprehensive management of sensor information. In some embodiments, the emergency monitoring sensor network platform 130 can be configured as a communication network and / or an Internet of Things gateway, etc. The emergency monitoring sensor network platform 130 can interact bidirectionally with the data center 121 and the emergency monitoring object platform 140. In some embodiments, the emergency monitoring sensor network platform 130 can acquire and store uploaded real-time data from sensors and acquisition devices deployed in the drainage pipe network, and send the received real-time data to the emergency monitoring management platform 120. The emergency monitoring management platform 120 can store the received real-time data in the database 1211.

[0025] The emergency monitoring object platform 140 refers to a platform for monitoring physical entities or systems, used to display, manage, and analyze the operational status and data of the monitored entities or systems. In some embodiments, the emergency monitoring object platform 140 may include a processor, embedded controller, server, gateway, etc. In some embodiments, the monitored entity may be deployed at the dredging operation site. In some embodiments, the emergency monitoring object platform 140 may be used to manage and control robots and automated dredging equipment. For example, the emergency monitoring object platform 140 may communicate with robots and automated dredging equipment to achieve bidirectional data and command interaction.

[0026] A robot is a specialized robotic device that uses automated and intelligent technologies to clean up sludge, garbage, and sediment. For example, robots may include jet-type pipeline dredging robots, intelligent pipeline dredging robots, and all-terrain pipeline dredging robots. In some embodiments, the robot is equipped with a sonar sensor. A sonar sensor is an electronic device that uses sound waves for detection, positioning, navigation, and imaging.

[0027] Automated dredging equipment refers to devices that use mechanical, hydraulic, electrical control, sensors, and artificial intelligence to automatically detect, clean, transport, or treat deposits inside pipelines. Examples of automated dredging equipment include high-pressure water jet equipment, vacuum suction equipment, and winch equipment.

[0028] In the embodiments described in this specification, system 100 can automatically and intelligently handle siltation in urban drainage networks. Through real-time monitoring, intelligent analysis, and risk prediction, system 100 can achieve precise control of robots and automated dredging equipment, significantly improving the accuracy of siltation assessment and the efficiency of dredging operations, realizing intelligent closed-loop management from passive response to proactive prevention. Simultaneously, the use of a large-scale IoT model makes the fusion, analysis, and decision-making of multi-source data more efficient and comprehensive.

[0029] Figure 2 This is an exemplary flowchart illustrating a method for treating siltation in drainage pipe networks according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by an emergency monitoring and management platform.

[0030] Step 210: Collect flow data of the pipeline area using the acquisition equipment deployed in the drainage network, and obtain the flow data uploaded by the acquisition equipment.

[0031] A drainage network is a system consisting of pipes, channels, and ancillary facilities (such as manholes, storm drains, and pumping stations). Drainage networks are used to collect, transport, and discharge sewage, wastewater, and rainwater.

[0032] Data acquisition equipment refers to equipment used to collect drainage data. For example, the acquisition equipment may be a pressure level gauge. In some embodiments, drainage data may include flow rate, water level, water quality, rainfall, pipeline status data, etc. Pipeline status data may include siltation level, flow velocity, etc.

[0033] A pipe area refers to the physical space occupied by pipes and ancillary facilities. In some embodiments, multiple pipe areas may constitute a drainage network. Pipe areas may be preset by the system. In some embodiments, pipe areas may be determined through drainage network information. For more information on drainage network information, please refer to step 280 and its related description.

[0034] Flow data refers to data related to fluids (e.g., rainwater and sewage) within a pipe. In some embodiments, flow data may include fluid pressure, the volume of fluid passing through the pipe per unit time (e.g., cubic meters per second), flow velocity (m / s), etc.

[0035] In some embodiments, the data acquisition device can be deployed within pipelines in multiple pipeline regions to collect flow data from these regions in real time. In some embodiments, the data acquisition device can periodically collect flow data from multiple pipeline regions based on a preset acquisition period. The preset acquisition period can be set manually or through a system setting.

[0036] In some embodiments, the data acquisition device can monitor control signals from the emergency monitoring and management platform based on a preset monitoring period. Upon receiving a control signal, the data acquisition device can upload traffic data to the emergency monitoring and management platform. The preset monitoring period can be set manually or through a system configuration.

[0037] Step 220: Based on the flow data of the pipeline area, determine the sequence of water flow areas of multiple adjacent pipeline areas.

[0038] Adjacent pipe zones refer to at least two pipe zones that are physically connected. For example, upstream and downstream pipe zones connected by the same manhole.

[0039] A water flow area sequence refers to a numerical sequence consisting of at least one water flow area. Water flow area refers to the area occupied by a fluid (e.g., rainwater and sewage) on the cross-section of a pipe. In some embodiments, the water flow area sequence may include the water flow areas corresponding to multiple pipe regions at the same time or within the same time period. In some embodiments, the water flow area sequence may include the water flow area of ​​a pipe region at multiple times or the water flow area of ​​the pipe region within multiple time periods.

[0040] In some embodiments, the emergency monitoring and management platform can determine the sequence of water-passing areas of multiple adjacent pipeline areas based on the fluid pressure in the flow data of the pipeline area. The emergency monitoring and management platform can obtain the fluid pressure of the pipeline area by deploying pressure level gauges in the pipeline area; based on the fluid pressure of the pipeline area, the water level height of the pipeline area is determined by formula (1); based on the water level height of the pipeline area and pipeline data (e.g., pipeline diameter), the water-passing area of ​​the pipeline area is determined by geometric formula (e.g., the formula for the area of ​​a circular arc).

[0041] (1)

[0042] in, The water level in the pipeline area. This represents the fluid pressure within the pipeline area. The density of water, This is the acceleration due to gravity.

[0043] In some embodiments, the emergency monitoring and management platform can obtain pipeline data from a database. In some embodiments, the emergency monitoring and management platform can determine the water flow area corresponding to multiple adjacent pipeline areas at the same time or within the same time period as a water flow area sequence. In some embodiments, for one pipeline area among multiple adjacent pipeline areas, the emergency monitoring and management platform can determine the water flow area of ​​that pipeline area at multiple times or the water flow area of ​​that pipeline area within multiple time periods as a water flow area sequence.

[0044] Step 230: Based on the water flow area sequence of multiple adjacent pipe areas, determine the abnormal pipe area and the abnormal water flow time.

[0045] An abnormal pipe area refers to a pipe area where the flow rate data is abnormal. For example, the flow rate data in the pipe area is lower than the preset flow rate data. For instance, the preset flow rate per hour for the pipe area is 1000 m³ / h. 3 The actual fluid volume per hour is 500 m³. 3 For example, the water flow area in the pipeline area is reduced, resulting in poor drainage.

[0046] An abnormal flow rate moment refers to a moment when the flow rate data in the pipeline area becomes abnormal. For example, an abnormal flow rate moment could be a moment when the flow rate data in the pipeline area is lower than the preset flow rate data. For more information on flow rate data, please refer to step 210 and its related description.

[0047] In some embodiments, in response to the water flow area sequence being multiple adjacent pipe regions at the same time... t Based on the corresponding water flow areas, the emergency monitoring and management platform can determine the average water flow area. Given two known scenarios—where the water flow area of ​​an adjacent pipeline region is less than or equal to the average, and where the water flow area of ​​an adjacent pipeline region is greater than the average—the emergency monitoring and management platform can identify an adjacent pipeline region as an abnormal pipeline region if its water flow area is significantly less than the average (e.g., less than 80% of the average). t This was determined to be an abnormal water passage moment.

[0048] In some embodiments, it is known that there are two cases: the water flow area of ​​adjacent pipe regions is less than or equal to a water flow area threshold, and the water flow area of ​​adjacent pipe regions is greater than a water flow area threshold. For one of multiple adjacent pipe regions, the response to the water flow area sequence is the water flow area of ​​that adjacent pipe region at multiple times, that is, the water flow area sequence of that adjacent pipe region is {( t 1, a 1), ( t 2, a 2)…( t n , a n )},like t i ( i ) water flow area at time a iIf the area of ​​the adjacent pipeline is significantly smaller than the water flow area threshold (e.g., less than 80% of the water flow area threshold), the emergency monitoring and management platform can identify the area as an abnormal pipeline area and record it at all times. t i The time of abnormal water flow has been identified. The threshold for the water flow area can be set based on experience or by the system.

[0049] Step 240: Determine the target detection area and target detection time based on the abnormal pipeline area and the abnormal water flow time.

[0050] The target detection area refers to the pipeline area that requires dredging operations. For example, the target detection area could be a pipeline area with poor drainage.

[0051] Target detection time refers to the time period or window during which dredging operations are carried out. For example, target detection time can be a time period or window starting from the moment of abnormal water flow.

[0052] In some embodiments, the emergency monitoring and management platform can directly identify abnormal pipeline areas as target detection areas. In other embodiments, the platform can filter abnormal pipeline areas using preset screening criteria and determine target detection areas based on the filtered abnormal pipeline areas. For more details, please refer to [link to relevant documentation]. Figure 3 And its related descriptions.

[0053] In some embodiments, the emergency monitoring and management platform can determine a preset time window, starting from the moment of abnormal water inrush, as the target detection time. The preset time window can be set based on experience or by the system.

[0054] Step 250: Through the emergency monitoring platform, control the robot to perform sonar detection on the target detection area during the target detection time and collect sonar detection data.

[0055] In some embodiments, the robot is equipped with sonar sensors.

[0056] Sonar detection data refers to the data generated after a sonar sensor emits sound waves and receives the echoes. For example, sonar detection data may include the robot's position and attitude data (e.g., pitch angle, roll angle, yaw angle), round-trip time of the sound waves, echo signal strength, echo waveform, robot scanning time in the pipe, sonar scanning angle, etc. In some embodiments, sonar detection data may include sonar detection data for pipe circumferential points. For more information on pipe circumferential points, please refer to [link to relevant documentation]. Figure 4 And its related descriptions.

[0057] In some embodiments, the emergency monitoring management platform can send guidance instructions to the emergency monitoring target platform via an emergency monitoring sensor network platform. The emergency monitoring target platform then sends guidance instructions to the robot via a wireless network, controlling the robot to perform sonar detection on the target detection area and collect sonar detection data during the target detection time. For more information on robots and sonar sensors, please refer to [link to relevant documentation]. Figure 1 And its related descriptions.

[0058] Step 260: Based on sonar detection data and pipeline characteristics, generate the estimated silt thickness and silt type of the target detection area.

[0059] Pipeline features are used to characterize the physical properties, geographical information, and dimensional parameters of pipelines. In some embodiments, pipeline features may include geometric features (e.g., pipeline diameter, length, shape), material features (e.g., concrete), location features (e.g., manhole number, latitude and longitude, burial depth), and network features (e.g., main pipelines, branch pipelines, upstream and downstream pipelines). In some embodiments, pipeline features can be determined using drainage network information. For more information on drainage network information, please refer to step 280 and its related description.

[0060] Estimated silt thickness refers to the pre-estimated cumulative thickness of sediments (e.g., silt, mud, garbage) in the pipe. For example, the estimated silt thickness is 30% of the pipe diameter (approximately 15 cm).

[0061] Silt type refers to the type of sediment deposited in a pipe. In some embodiments, silt type may include loose sediment (e.g., silt, mud), sticky sediment (e.g., grease, fat, saponification), hard scale (e.g., a hard crust formed by calcium carbonate, calcium sulfate, etc.), foreign matter (e.g., stones, construction waste, plant roots), etc.

[0062] In some embodiments, the emergency monitoring and management platform can construct point clouds of pipes and sediments based on sonar detection data and pipe characteristics of the target detection area, and generate estimated sediment thickness and / or sediment type of the target detection area based on the point clouds of pipes and sediments.

[0063] For example, the emergency monitoring and management platform can determine the distances from multiple echo points (i.e., sound wave reflection points on the pipe wall) to the robot based on the round-trip time and speed of sound. Based on the robot's attitude data (e.g., pitch, roll, yaw angles), the platform can convert the coordinates of these echo points in the robot's coordinate system into coordinates in the pipe's global coordinate system through translation, rotation, scaling, and affine transformations. The coordinates of these echo points in the pipe's global coordinate system constitute the initial 3D point cloud. Random sample consistency is employed. The Consensus (RANSAC) algorithm randomly captures a portion of the initial 3D point cloud and fits it to a cylindrical model. Through multiple iterations of the RANSAC algorithm, a point cloud that fits the cylindrical model is obtained, generating a pipe point cloud. The point cloud constituting the outline of the cylindrical model is the pipe wall point cloud. Point clouds outside the pipe wall point cloud are removed, and those inside the pipe wall point cloud are identified as sediment point clouds. A density-based spatial clustering of applications with noise (DBSCAN) algorithm is used to extract the point cloud layer on the sediment surface. Based on the height of the pipe wall point cloud (e.g., the fitted value of the Z-coordinate of the pipe wall point cloud) and the height of the point cloud layer on the sediment surface (e.g., the fitted value of the Z-coordinate of the point cloud layer on the sediment surface), the estimated sediment thickness is determined.

[0064] For example, an emergency monitoring and management platform can determine the type of sedimentation based on sonar detection data and / or sediment point clouds. For instance, it is known that there are three scenarios: echo signal intensity greater than a first intensity threshold, echo signal intensity greater than or equal to a second intensity threshold, less than or equal to the first intensity threshold, and echo signal intensity less than the second intensity threshold. In response to an echo signal intensity greater than the first intensity threshold and / or an irregular point cloud profile in the sediment point cloud, the emergency monitoring and management platform can determine the sedimentation type as hard structures and foreign matter; in response to an echo signal intensity greater than or equal to the second intensity threshold and less than or equal to the first intensity threshold, the platform can determine the sedimentation type as loose sediment; and in response to an echo signal intensity less than the second intensity threshold, the platform can determine the sedimentation type as viscous sediment. The first intensity threshold is greater than the second intensity threshold, and both thresholds can be set based on experience or by the system.

[0065] In some embodiments, the estimated sediment thickness and sediment type of the target detection area can be rendered and displayed in a GIS system.

[0066] In some embodiments, the sonar frequencies differ across multiple pipeline regions. The emergency monitoring and management platform can determine the sonar frequencies for a pipeline region based on pipeline material, estimated silt thickness, and silt type.

[0067] Sonar frequencies can be categorized into high-frequency and low-frequency sonar. High-frequency sonar has frequencies greater than 1 MHz, short wavelengths, and high resolution, making it suitable for outlining object surfaces. Low-frequency sonar has frequencies less than 500 kHz, long wavelengths, slow energy decay, and strong penetration, making it suitable for detecting the bottom of pipes.

[0068] Pipe material refers to the type of material that makes up the main body of the pipe. For example, pipe materials can include concrete, high-density polyethylene, cast iron, etc.

[0069] In some embodiments, the emergency monitoring and management platform can determine the sonar frequency of the pipeline area based on the pipeline material, estimated silt thickness, and silt type using a first preset table.

[0070] The first preset table includes the correspondence between pipe material, estimated silt thickness, silt type, and sonar frequency. For example, {index 1 (pipe characteristics), index 2 (estimated silt thickness), index 3 (silt type) -> query result (sonar frequency)}. The first preset table can be built based on experience. For example, in response to the indexes {index 1 (concrete), index 2 (50 cm), index 3 (silt)}, the query result could be a low-frequency sonar signal of 250 kHz.

[0071] The embodiments in this specification determine the sonar frequency based on the pipe material, estimated silt thickness, and silt type, overcoming the problem of poor adaptability of a single sonar frequency in complex environments, improving the accuracy and reliability of sonar detection data, and enabling precise assessment of the siltation situation in the pipe in the target detection area.

[0072] Step 270: Determine the siltation risk based on the estimated siltation thickness, siltation type, and pipeline characteristics.

[0073] Sedimentation risk refers to the risks caused by deposits in a pipeline area. For example, sedimentation risk can include complete blockage, sewage overflow, and pipe wall damage.

[0074] In some embodiments, the emergency monitoring and management platform can construct siltation vectors based on estimated siltation thickness, siltation type, and pipeline characteristics, and then retrieve these vectors from a siltation database to determine siltation risk. A siltation database is a database used to store, index, and query vectors. Through a siltation database, similarity queries and other vector management can be performed quickly on a large number of vectors. The siltation database can be stored in a database.

[0075] In some embodiments, the emergency monitoring and management platform can obtain the reference siltation thickness, reference siltation type, and reference pipeline characteristics of the reference pipeline area based on historical data, and construct multiple reference siltation vectors based on the reference siltation thickness, reference siltation type, and reference pipeline characteristics, with each reference siltation vector having a corresponding siltation label vector.

[0076] The siltation label vector can include the probability value of siltation risk (e.g., complete blockage, sewage overflow, and pipe wall damage) and is manually labeled based on historical data. For example, if the siltation risk is pipe wall damage, the siltation label vector can be represented as [0, 0, 1], meaning that complete blockage and sewage overflow did not occur, but pipe wall damage did. The emergency monitoring and management platform can store multiple reference siltation vectors and their corresponding siltation label vectors in the siltation database.

[0077] In some embodiments, the computing unit of the emergency monitoring and management platform can calculate the similarity (e.g., cosine similarity, Euclidean distance) between the siltation vector and multiple reference siltation vectors, and identify the siltation label vector of the reference siltation vector with the highest similarity as the siltation risk.

[0078] In some embodiments, the computing unit of the emergency monitoring and management platform can calculate the similarity (e.g., cosine similarity, Euclidean distance) between the silting vector and multiple reference silting vectors, and sort the multiple reference silting vectors from largest to smallest based on the similarity. The emergency monitoring and management platform can determine the silting risk as the mean of the silting label vectors of the first K (K is a positive integer greater than 1) reference silting vectors. K can be set based on experience or by the system. For example, if K is 3, and the silting label vectors of the first 3 reference silting vectors are [1, 1, 0], [1, 0, 0], and [1, 1, 0], then the silting risk is [1, 0.67, 0].

[0079] In some embodiments, the emergency monitoring and management platform can standardize and / or encode the estimated siltation thickness, siltation type, and pipe characteristics through Z-score standardization, Min-Max standardization, one-hot encoding, etc., and construct a siltation vector based on the standardized and / or encoded estimated siltation thickness, siltation type, and pipe characteristics.

[0080] Step 280: Based on the risk of siltation, automatically generate dredging paths and dredging parameters.

[0081] A dredging path refers to a path that includes at least one dredging operation point. In some embodiments, a dredging path may include a dredged path and a path to be dredged. A dredged path refers to a path where dredging operations have been completed at the dredging operation points. A path to be dredged refers to a path where dredging operation points exist and are awaiting dredging operations.

[0082] In some embodiments, at least one dredging operation point may constitute a sequence of operation points. In some embodiments, the dredging path may be the topology of the pipelines at the dredging operation points. The pipeline topology may be obtained based on drainage network information and pipeline characteristics. For more information on pipeline characteristics, please refer to step 260 and its related description. For more information on dredging operation points and drainage network information, please refer to the following and its related description.

[0083] Dredging parameters refer to the equipment parameters of automated dredging equipment during dredging operations. In some embodiments, dredging parameters may include the forward speed and dredging intensity of the automated dredging equipment. In some embodiments, dredging parameters are related to the type of automated dredging equipment. For example, if the automated dredging equipment is a high-pressure water jet device, the dredging parameters may include hydraulic parameters (e.g., water pressure, flow rate), nozzle parameters (e.g., nozzle type, spray angle), water temperature, etc. The nozzle type may include standard cleaning nozzles, rotary nozzles, etc. As another example, if the automated dredging equipment is a vacuum suction device, the dredging parameters may include the power of the suction pump, the negative pressure value, the diameter of the suction pipe, etc.

[0084] In some embodiments, it is known that there are two scenarios: a siltation risk greater than a preset risk threshold, and a siltation risk less than or equal to the preset risk threshold. In response to a siltation risk greater than the preset risk threshold, the emergency monitoring and management platform can automatically generate a dredging path and dredging parameters based on the target detection area and one or more adjacent pipeline areas upstream of the target detection area. The preset risk threshold can be set based on experience or by the system.

[0085] For example, the emergency monitoring and management platform can obtain drainage network information (e.g., pipe characteristics, design drawings, and network maps) from a database; based on the drainage network information, it can obtain the pipe distribution and pipe identifiers (e.g., manhole identifiers) of the target detection area and one or more adjacent pipe areas upstream of the target detection area; based on the pipe distribution and pipe numbers (e.g., manhole numbers) of the target detection area and one or more adjacent pipe areas upstream of the target detection area, it can generate a dredging path using the Dijkstra algorithm and / or a genetic algorithm. For more information on pipe characteristics, please refer to step 260 and its related description.

[0086] For example, for one or more adjacent pipeline areas located upstream of the target detection area, the emergency monitoring and management platform can set the forward speed and dredging intensity of the automated dredging equipment to medium speed (e.g., 1-2 m / s) and medium dredging (e.g., water pressure 10-20 MPa), respectively; for the target detection area, the emergency monitoring and management platform can set the forward speed and dredging intensity of the automated dredging equipment to low speed (e.g., 0.5-1 m / s) and high dredging (e.g., water pressure 20-30 MPa), respectively. More information about adjacent pipeline areas can be found in step 220 and its related description. More information about the target detection area can be found in step 240 and its related description.

[0087] In some embodiments, the emergency monitoring and management platform can determine dredging operation points based on siltation risk, and automatically generate dredging paths and dredging parameters based on siltation risk, dredging operation points, and siltation type through a second preset table.

[0088] A dredging operation point refers to the location of a pipeline area (e.g., a target detection area, an adjacent pipeline area) where dredging operations are required. In some embodiments, a dredging operation point may include latitude and longitude, elevation, and geological description.

[0089] In some embodiments, in response to a siltation risk exceeding a preset risk threshold, the emergency monitoring and management platform can identify the target detection area and one or more adjacent pipeline areas upstream of the target detection area as dredging operation points. The emergency monitoring and management platform can obtain identifiers for the target detection area (e.g., manhole identifiers) and one or more adjacent pipeline areas upstream of the target detection area from a database. Based on these identifiers, the platform searches the GIS database to obtain the geospatial attributes of the target detection area and the one or more adjacent pipeline areas upstream of the target detection area.

[0090] The second preset table includes the correspondence between dredging operation points, siltation risks, and siltation types, and dredging paths and parameters. For example, {index 1 (dredging operation point), index 2 (siltation risk), index 3 (siltation type) -> query result (dredging path, dredging parameters)}. The second preset table can be built based on historical data. For example, it includes historical dredging operation points, historical siltation risks, and historical siltation types that meet the expected dredging effect (e.g., no siltation residue) and preset speed threshold, as well as the corresponding historical dredging paths and parameters. For example, in response to an index of {index1(MH101-MH102), index2([0.67 (complete blockage), 1 (sewage overflow), 0 (pipe wall damage)]), index3 (viscous deposits)}, the query result can be the topology of the pipes in the adjacent pipe area MH101-MH102 (e.g., the pipe topology with manhole 101 of MH101 as the starting point of the dredging path and manhole 102 of MH102 as the ending point of the dredging path), as well as water pressure, flow rate, jet angle and water temperature.

[0091] In some embodiments, the emergency monitoring and management platform can control the robot to collect dredging data of the actual dredging process through the emergency monitoring object platform; adjust the dredging parameters based on the dredging data; and control the automated dredging equipment to carry out dredging operations based on the adjusted dredging parameters through the emergency monitoring object platform.

[0092] Dredging data refers to data related to dredging operations. For example, dredging data may include dredging duration, dredging power consumption, and dredging volume.

[0093] In some embodiments, the emergency monitoring and management platform can adjust dredging parameters based on dredging data and through preset adjustment rules. The preset adjustment rules may include a percentage of rated power and a preset dredging efficiency (e.g., 0.1 kg / s).

[0094] It is known that there are two scenarios: the dredging efficiency is greater than the rated power by a certain percentage, and the dredging efficiency is less than or equal to the rated power by a certain percentage. Furthermore, it is known that there are two scenarios: the dredging efficiency is greater than the preset dredging efficiency, and the dredging efficiency is less than or equal to the preset dredging efficiency. For example, if the dredging power consumption is higher than 80% of the rated power and the dredging efficiency is less than the preset dredging efficiency, the emergency monitoring and management platform can control the automated dredging equipment to stop working through the emergency monitoring object platform and upload the alarm information to the emergency monitoring service platform.

[0095] For example, if the dredging power consumption is higher than 80% of the rated power and the dredging efficiency is greater than the preset dredging efficiency, the emergency monitoring and management platform can reduce the forward speed and increase the dredging intensity. Conversely, if the dredging power consumption is lower than 30% of the rated power, the emergency monitoring and management platform can increase the forward speed and reduce the dredging intensity. The dredging efficiency can be the ratio of the dredging volume to the dredging time.

[0096] The embodiments in this specification dynamically adjust dredging parameters based on dredging power consumption, dredging duration, and dredging volume, thereby improving the ability to respond to emergencies during dredging operations, enhancing the efficiency and safety of dredging operations, reducing the power consumption and ineffective operation time of automated dredging equipment, and realizing intelligent dredging.

[0097] Step 290: Through the emergency monitoring platform, control the automated dredging equipment to travel along the dredging path to the dredging operation point, and carry out dredging operations based on the dredging parameters.

[0098] In some embodiments, the emergency monitoring and management platform can send guidance instructions to the emergency monitoring target platform via the emergency monitoring sensor network platform. The guidance instructions may include dredging parameters. The emergency monitoring target platform sends guidance instructions to the automated dredging equipment via a wireless network, controlling the automated dredging equipment to proceed to the dredging operation point according to the dredging path and perform dredging operations based on the dredging parameters. For more information on the dredging path, dredging parameters, and dredging operation point, please refer to step 280 and its related description.

[0099] In some embodiments, the emergency monitoring and management platform can acquire pipeline image data of a pipeline area using image acquisition devices; determine the estimated siltation rate of the pipelines in the pipeline area based on the pipeline image data; and perform dredging operations on the pipelines in the pipeline area based on the estimated siltation rate. In some embodiments, the image acquisition devices are deployed in the drainage pipe network.

[0100] Image acquisition devices are used to collect images, videos, 3D data, etc., of the interior of pipes in a pipeline area. In some embodiments, the image acquisition device may include a camera, a pipe endoscope, a laser scanner, and a 3D imaging device.

[0101] Pipeline image data is used to assess the structural condition of pipelines (e.g., siltation, cracks, corrosion, deformation, etc.). For example, pipeline image data can include images, videos, 3D data, and acquisition time points of the pipeline interior.

[0102] The process of acquiring pipeline image data through an image acquisition device is similar to the process of acquiring flow data through an acquisition device. For more details, please refer to step 210 and its related description.

[0103] The estimated siltation rate refers to the pre-estimated rate at which sediments (e.g., silt, mud, garbage) accumulate in the pipe, for example, an estimated siltation rate of 0.2 cm / week.

[0104] In some embodiments, the emergency monitoring and management platform can determine the estimated siltation rate of pipelines in a pipeline area based on pipeline image data and through an image processing model. The input to the image processing model may include pipeline image data, and the output is the estimated siltation rate.

[0105] In some embodiments, the image processing model can be obtained through training based on at least one set of first training samples and their corresponding first labels. The first training samples can be constructed based on historical image data, which can be obtained from a database. The first training samples may include at least one set of sample pipe image data for sample pipe regions, and the first label may be the siltation rate of the sample pipe region.

[0106] In some embodiments, the first label can be determined and annotated based on historical data of the sample pipeline region. For example, under conditions similar to sample pipeline image data, the emergency monitoring and management platform can label the historical siltation rate of the sample pipeline region as the siltation rate. The training process of the image processing model is similar to that of the siltation model; for more details, please refer to [link to relevant documentation]. Figure 4 And its related descriptions.

[0107] In some embodiments, it is known that there are two scenarios: the estimated siltation rate is greater than a preset rate threshold, and the estimated siltation rate is less than or equal to the preset rate threshold. In response to the estimated siltation rate being greater than the preset rate threshold, the emergency monitoring and management platform can generate a dredging operation instruction, which is then sent to the emergency monitoring object platform via the emergency monitoring sensor network platform, and further sent to the automated dredging equipment via the emergency monitoring object platform, controlling the automated dredging equipment to perform dredging operations on the pipeline in the pipeline area. In response to the estimated siltation rate being less than or equal to the preset rate threshold, the emergency monitoring and management platform may not issue a dredging operation instruction, and instead, at preset intervals, use a calculation unit to obtain the relationship between the estimated siltation rate and the preset rate threshold.

[0108] In some embodiments, the emergency monitoring and management platform can determine whether a candidate pipeline area located on the dredging path in the pipeline area meets preset conditions based on the estimated siltation rate; in response to the candidate pipeline area meeting the preset conditions, the candidate pipeline area is identified as a new work point; and through the emergency monitoring object platform, the automated dredging equipment is controlled to travel along the dredging path to the new work point to carry out dredging operations.

[0109] For more information on dredging paths and paths to be dredged, please refer to step 280 and its related description. Adding a new work point is similar to adding a dredging work point; for more information, please refer to the description of dredging work points. For more information on automated dredging equipment, please refer to... Figure 1 And its related descriptions.

[0110] Candidate pipe areas refer to pipe areas that are not included in the work point sequence and are yet to be selected. In some embodiments, candidate pipe areas may be adjacent pipe areas to pipe areas that have been dredged. For more information on adjacent pipe areas, please refer to step 220 and its related description. For more information on the work point sequence, please refer to step 280 and its related description.

[0111] Preset conditions refer to the conditions under which a candidate pipeline area becomes a new work site. In some embodiments, the preset condition may be that the estimated siltation rate of the pipeline in the candidate pipeline area is greater than a preset rate threshold.

[0112] In some embodiments, the emergency monitoring and management platform can determine the estimated siltation rate of pipelines in candidate pipeline areas using image processing models based on pipeline image data of the candidate pipeline areas. If the estimated siltation rate of a pipeline in a candidate pipeline area meets preset conditions, the emergency monitoring and management platform can designate the candidate pipeline area as a new work site. For the process of determining the estimated siltation rate of pipelines in a candidate pipeline area, please refer to the above and related descriptions.

[0113] In some embodiments, the emergency monitoring and management platform can control automated dredging equipment to move from the current dredging point (i.e., the point where dredging has been completed) along the dredging path to the next dredging point via the emergency monitoring object platform. The next dredging point can be the closest dredging point to the current dredging point or a newly added point. For the process of controlling automated dredging equipment to move along the dredging path to a newly added point for dredging operations via the emergency monitoring object platform, please refer to step 290 above and its related description.

[0114] The embodiments in this specification determine whether to identify pipeline areas located on the path to be dredged as new work points based on the estimated siltation rate and a preset rate threshold. This allows for the priority deployment of dredging work points in high-risk pipeline areas, reducing the maintenance cost of the drainage network and improving dredging efficiency.

[0115] The embodiments in this specification estimate the siltation rate using pipeline image data, solving the problem that traditional pipeline maintenance methods cannot predict siltation risks, realizing a shift from "passive response" to "proactive predictive maintenance," and reducing the possibility of sewage overflow caused by severe pipeline blockage.

[0116] The embodiments described in this manual assess the risk of siltation by collecting flow data and sonar detection data, and automatically complete the dredging of pipeline areas. This constructs a monitoring and management system that progresses from "passive discovery" to "active early warning" and then to "intelligent dredging." It solves the problems of disconnected workflows, delayed response, and heavy reliance on manual experience in traditional pipeline maintenance. Through data-driven decision-making, it greatly improves the systematization, intelligence, and overall operation and maintenance efficiency of drainage pipeline management.

[0117] Figure 3 This is an exemplary schematic diagram illustrating the determination of a target detection area according to some embodiments of this specification.

[0118] In some embodiments, such as Figure 3 As shown, for N (N is a positive integer greater than 1) abnormal pipeline areas 320 (such as abnormal pipeline area 1, abnormal pipeline area 2, ..., abnormal pipeline area N), the emergency monitoring and management platform can filter the abnormal pipeline areas 320 based on the rainfall 311 within a preset time period, the catering sewage discharge 312 and construction sewage discharge 313 upstream of the abnormal pipeline areas, and through preset screening conditions 310; based on the filtered abnormal pipeline areas 330, an abnormal water flow area sequence 340 is determined; based on the abnormal water flow area sequence 340, a target detection area 370 is determined.

[0119] A preset time period refers to a pre-defined current or future time range. For example, a preset time period could be 9:00 AM to 9:00 PM on the current day or a future day. In some embodiments, the preset time period is located before the abnormal water overflow time. For more information on abnormal water overflow times, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0120] Rainfall refers to the depth of water accumulation within a 320-meter catchment area of ​​the abnormal pipeline within a preset time period. For example, the rainfall within the 320-meter catchment area of ​​the abnormal pipeline within 24 hours is 35 mm. In some embodiments, the emergency monitoring service platform can obtain minute-level or hourly rainfall data released by urban meteorological monitoring stations through the meteorological department's API (Application Programming Interface) and send it to the emergency monitoring management platform.

[0121] Food service wastewater discharge refers to the total amount of wastewater and / or solid waste (e.g., kitchen waste) generated by food service establishments upstream of the abnormal pipeline area 320 during their operations within a preset time period. For example, if the food service wastewater discharge upstream of the abnormal pipeline area 320 is 240 m³ within 24 hours. 3 (i.e. 0.003 m) 3 / s). In some embodiments, the emergency monitoring and management platform can obtain the amount of sewage discharged by catering establishments through flow meters deployed at the sewage outlets of catering establishments.

[0122] Construction wastewater discharge refers to the total amount of wastewater and / or solid waste (e.g., construction debris, slag) generated by construction activities such as building construction, municipal construction, and demolition projects upstream of the abnormal pipeline area 320 within a preset time period. For example, if the construction wastewater discharge upstream of the abnormal pipeline area 320 is 100 m³ within 24 hours. 3 (i.e., 0.001 m) 3 / s). In some embodiments, the emergency monitoring and management platform can obtain the construction sewage discharge volume through flow meters deployed at the construction sewage outlet.

[0123] Preset screening conditions refer to the conditions set in advance for screening abnormal pipeline areas. In some embodiments, the preset screening condition 310 may be the sum of normalized rainfall, catering sewage discharge, and construction sewage discharge within a preset time period, which must be less than a preset flow threshold. The preset flow threshold can be set based on experience or by the system.

[0124] In some embodiments, the emergency monitoring and management platform can convert rainfall into runoff (m³) using a hydrological model. 3 / s). Runoff flow can be expressed as formula (2):

[0125] (2)

[0126] in, For runoff flow, The runoff coefficient, Rainfall intensity (m / s) The catchment area (m²) of the abnormal pipeline area 2 The runoff coefficient can be determined by the surface type; for example, the runoff coefficient for asphalt pavement is 0.9. The catchment area of ​​the anomalous pipeline area 320 can be obtained from a GIS database.

[0127] In some embodiments, in response to the sum of normalized rainfall, catering wastewater discharge, and construction wastewater discharge corresponding to the abnormal pipeline area 320 within a preset time period, which meets the preset screening condition 310, the emergency monitoring and management platform can identify the abnormal pipeline area 320 as the screened abnormal pipeline area 330. For more information on abnormal pipeline areas, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0128] An abnormal flow area sequence refers to a numerical sequence consisting of at least one abnormal flow area. In some embodiments, the abnormal flow area may be the flow area at the time of the abnormal flow.

[0129] In some embodiments, the emergency monitoring and management platform can determine the abnormal water flow areas corresponding to multiple screened abnormal pipe areas 330 at the same abnormal water flow time as an abnormal water flow area sequence 340. In some embodiments, the emergency monitoring and management platform can determine the abnormal water flow areas of a screened abnormal pipe area 330 at multiple abnormal water flow times as an abnormal water flow area sequence 340 for that screened abnormal pipe area 330. For more information on abnormal water flow times and water flow areas, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0130] In some embodiments, in response to the abnormal water flow area sequence 340 including the same abnormal water flow time, the abnormal water flow areas corresponding to multiple filtered abnormal pipe regions 330, and an abnormal water flow area in the abnormal water flow area sequence 340 being significantly smaller than a water flow area threshold (e.g., less than 60% of the water flow area threshold), the emergency monitoring and management platform can obtain the abnormal pipe region corresponding to the abnormal water flow area and determine the abnormal pipe region and the adjacent pipe region located upstream of the abnormal pipe region as the target detection area 370. In some embodiments, the emergency monitoring and management platform can directly determine the abnormal pipe region corresponding to the abnormal water flow area as the target detection area 370.

[0131] In some embodiments, for one of the selected abnormal pipe regions 330, if the mean of the abnormal water flow area in the abnormal water flow area sequence 340 corresponding to the selected abnormal pipe region 330 is significantly less than the water flow area threshold (e.g., less than 60% of the water flow area threshold), the emergency monitoring and management platform can identify the selected abnormal pipe region 330 and / or the adjacent pipe region upstream of the selected abnormal pipe region 330 as the target detection region 370. In some embodiments, the emergency monitoring and management platform can directly identify the selected abnormal pipe region 330 as the target detection region 370. For more information on the water flow area threshold, adjacent pipe regions, and target detection regions, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0132] In some embodiments, such as Figure 3 As shown, the emergency monitoring and management platform can determine flow fluctuation information 350 based on historical rainfall 351, historical catering sewage discharge 352, and historical construction sewage discharge 353; based on the flow fluctuation information 350, it can determine whether there are false anomalies in the abnormal water flow area sequence 340; in response to the existence of false anomalies, it can remove the false anomalies from the abnormal water flow area sequence 340 and generate an updated abnormal water flow area sequence 360; based on the updated abnormal water flow area sequence 360, it can determine the target detection area 370.

[0133] Historical rainfall (351), historical restaurant wastewater discharge (352), and historical construction wastewater discharge (353) are similar to rainfall, restaurant wastewater discharge, and construction wastewater discharge; more details can be found above and in related descriptions. In some embodiments, the emergency monitoring and management platform can obtain historical data from the database, and based on this historical data, obtain historical rainfall (351), historical restaurant wastewater discharge (352), and historical construction wastewater discharge (353).

[0134] Flow fluctuation information refers to the flow fluctuations or patterns in a pipeline area under conditions where the pipeline's drainage capacity is normal (e.g., no siltation or damage) and external environmental factors exist (e.g., rainfall, restaurant wastewater, construction wastewater). In some embodiments, the flow fluctuation information 350 may be the fluctuations or patterns of the water-passing area sequence in the pipeline area within a preset time period. For more information on water-passing area sequences, please refer to [link to relevant documentation]. Figure 2 And its related description. For more information about preset time periods, please refer to the above and its related description.

[0135] In some embodiments, the emergency monitoring and management platform can construct a fluctuation information database based on historical rainfall 351, historical catering wastewater discharge 352, and historical construction wastewater discharge 353, and determine flow fluctuation information 350 by retrieving the fluctuation information database. The emergency monitoring and management platform can obtain historical rainfall 351, historical catering wastewater discharge 352, and historical construction wastewater discharge 353 for multiple historical time periods based on historical data, and construct multiple reference fluctuation vectors based on these data. Each reference fluctuation vector has a corresponding fluctuation label. The fluctuation label can be historical flow fluctuation information for the corresponding historical time period of the reference fluctuation vector, and can be manually labeled based on historical data. Historical flow fluctuation information is similar to flow fluctuation information 350; for more details, please refer to the flow fluctuation information and its related description. The emergency monitoring and management platform can store multiple reference fluctuation vectors and their corresponding fluctuation labels in the fluctuation information database.

[0136] In some embodiments, the emergency monitoring and management platform can construct a target vector based on rainfall 311 within a preset time period, catering wastewater discharge 312 upstream of the abnormal pipeline area, and construction wastewater discharge 313. The calculation unit of the emergency monitoring and management platform can calculate the similarity (e.g., cosine similarity, Euclidean distance) between the target vector and multiple reference fluctuation vectors, and determine the fluctuation label of the reference fluctuation vector with the highest similarity as flow fluctuation information 350. In some embodiments, multiple historical time periods can be the same as the preset time period. For example, multiple historical time periods can be 24 hours of each day for the past 30 days.

[0137] False anomalies refer to surface anomalies in water flow area caused by other factors (e.g., measurement errors). For example, during the dry season, the water flow area of ​​a pipeline area might be 50 m². 2 After entering the flood season, due to increased rainfall, the water flow area in the pipeline area became 80 m². 2 Judging an "abnormal increase" solely based on numerical changes may be a misjudgment.

[0138] In some embodiments, the emergency monitoring and management platform can obtain a fitting function for the flow fluctuation information 350 by fitting a model. The fitting model can include linear regression models (e.g., least squares method), nonlinear fitting (e.g., exponential fitting, polynomial fitting), time series models (e.g., autoregressive integral moving average model, moving average, exponential smoothing), etc. The emergency monitoring and management platform can determine the predicted sequence corresponding to the abnormal water flow area sequence 340 through the fitting function; that is, the predicted values ​​in the predicted sequence correspond one-to-one with the abnormal water flow areas in the abnormal water flow area sequence 340.

[0139] For an abnormal water flow area in the abnormal water flow area sequence 340, the emergency monitoring and management platform can calculate the difference between the abnormal water flow area and its corresponding predicted value, and determine whether the difference is less than a deviation threshold. It is known that there are two scenarios: the difference between the abnormal water flow area and its corresponding predicted value is less than the deviation threshold, and the difference is greater than or equal to the deviation threshold. In response to the case where the difference between the abnormal water flow area and its corresponding predicted value is less than the deviation threshold, the emergency monitoring and management platform can identify the abnormal water flow area corresponding to this difference as a pseudo-abnormal water flow area, remove this pseudo-abnormal water flow area from the abnormal water flow area sequence 340, and generate an updated abnormal water flow area sequence 360. The deviation threshold can be set based on experience or by the system.

[0140] The process of determining the target detection area 370 based on the updated abnormal water flow area sequence 360 ​​is similar to the process of determining the target detection area 370 based on the abnormal water flow area sequence 340. For more details, please refer to the above and related descriptions.

[0141] The embodiments in this specification are based on flow fluctuation information to remove pseudo-abnormal flow areas in abnormal flow area sequences, thereby reducing the possibility of misjudgment and improving the efficiency of dredging operations.

[0142] The embodiments in this specification analyze abnormal flow in abnormal pipeline areas based on external environmental data such as rainfall, catering sewage discharge, and construction sewage discharge. They further consider the impact of external environmental factors such as rainstorms and sewage peaks on pipeline drainage capacity, reduce the cost of ineffective dredging operations caused by false alarms, and significantly improve the accuracy and reliability of drainage capacity early warning.

[0143] Figure 4 This is an exemplary schematic diagram of a siltation model shown according to some embodiments of this specification.

[0144] In some embodiments, such as Figure 4 As shown, the emergency monitoring and management platform can determine the detection density 420 of the pipeline in the circumferential direction in the target detection area based on the change range of the abnormal water flow area sequence 340 relative to the normal water flow area sequence 410; through the emergency monitoring object platform, the robot is controlled to detect the target detection area based on the detection density 420 and collect sonar detection data 430; through the siltation model 450, the sonar detection data 430 and pipeline features 440 of multiple circumferential points in the target detection area are processed to generate the estimated siltation thickness 451 and siltation type 452 of the target detection area.

[0145] A normal flow area sequence refers to a numerical sequence consisting of at least one normal flow area. A normal flow area refers to the flow area of ​​a pipeline region under normal hydrological conditions and without abnormal events (e.g., floods, blockages, pipeline structural damage, etc.). Normal hydrological conditions refer to the state in which hydrological elements (e.g., precipitation, water level, flow rate, evaporation, etc.) exhibit periodic, predictable natural fluctuations, unaffected by extreme events (e.g., floods, droughts, geological disasters, etc.) or abnormal human interference (e.g., engineering failures, violations of regulations, etc.). In some embodiments, the determination of the normal flow area sequence 410 is similar to the determination of flow fluctuation information; for more details, please refer to [link to relevant documentation]. Figure 3 And related descriptions. In some embodiments, the emergency monitoring and management platform can obtain the normal water flow area sequence 410 from the database.

[0146] The variation range of the abnormal water flow area sequence 340 relative to the normal water flow area sequence 410 refers to the degree of deviation of the abnormal water flow area sequence 340 from the normal water flow area sequence 410. In some embodiments, the emergency monitoring and management platform can obtain abnormal fitting curves and normal fitting curves respectively based on the abnormal water flow area sequence 340 and the normal water flow area sequence 410 through fitting models. The fitting model may include linear regression models (e.g., least squares method), nonlinear fitting (e.g., exponential fitting, polynomial fitting), time series models (e.g., autoregressive integral moving average model, moving average, exponential smoothing), etc. The emergency monitoring and management platform can determine the variation range of the abnormal water flow area sequence 340 relative to the normal water flow area sequence 410 based on the mean square error, root mean square error, mean absolute error, coefficient of determination, maximum deviation, etc. of the abnormal fitting curve and the normal fitting curve. For more information on abnormal water flow area sequences, please refer to [link to relevant documentation]. Figure 3 And its related descriptions.

[0147] The detection density in the circumferential direction of a pipeline refers to the number of echo points collected by a sonar sensor around a 360-degree cross-section of the pipeline when scanning inside the pipeline. For example, the detection density in the circumferential direction of a pipeline 420 could be 128 echo points / circumference or 512 echo points / circumference.

[0148] In some embodiments, it is known that there are two scenarios: the variation amplitude of the abnormal water-flow area sequence 340 relative to the normal water-flow area sequence 410 is greater than a preset amplitude threshold, and the variation amplitude of the abnormal water-flow area sequence 340 relative to the normal water-flow area sequence 410 is less than or equal to the preset amplitude threshold. In response to the variation amplitude of the abnormal water-flow area sequence 340 relative to the normal water-flow area sequence 410 being greater than the preset amplitude threshold, the emergency monitoring and management platform can determine the detection density 420 of the pipeline circumferential direction in the target detection area as high-density detection (e.g., 512 data points / circumference); in response to the variation amplitude of the abnormal water-flow area sequence 340 relative to the normal water-flow area sequence 410 being less than or equal to the preset amplitude threshold, the emergency monitoring and management platform can determine the detection density 420 of the pipeline circumferential direction in the target detection area as low-density detection (e.g., 128 data points / circumference). The preset amplitude threshold can be set based on experience or by the system.

[0149] In some embodiments, the emergency monitoring management platform can send guidance instructions to the emergency monitoring target platform via an emergency monitoring sensor network platform. The guidance instructions may include a detection density 420 in the circumferential direction of the pipeline. The emergency monitoring target platform sends the guidance instructions to the robot via a wireless network. Based on the detection density 420 in the circumferential direction of the pipeline in the guidance instructions, the robot configures the operating mode of the sonar sensor (e.g., the number of data points collected per rotation). The sonar sensor, based on the configured operating mode, detects the target detection area and collects sonar detection data 430. For more information on robots and sonar sensors, please refer to [link to relevant documentation]. Figure 1 And related descriptions. For more information on target detection areas and sonar detection data, please refer to... Figure 2 And its related descriptions.

[0150] In some embodiments, the input to the siltation model 450 is sonar detection data 430 from multiple circumferential points and pipe features 440, and the output is the estimated siltation thickness 451 and siltation type 452 of the target detection area. In some embodiments, the siltation model 450 is a machine learning model. The siltation model 450 may include convolutional neural networks (CNN), recurrent neural networks (RNN), etc.

[0151] In some embodiments, multiple circumferential points refer to multiple echo points distributed along the circumference of the pipe. In other embodiments, multiple circumferential points refer to multiple locations along the circumference of the pipe and multiple echo points distributed along the circumference of the pipe. For more information on echo points, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0152] In some embodiments, the siltation model 450 can be obtained through training based on at least one set of second training samples and their corresponding second labels. In some embodiments, the second training samples can be constructed based on historical data, which can be obtained from a database. The second training samples may include sonar detection data of at least one set of sample circumferential points in the sample pipe region and sample pipe features, and the second label may be the siltation thickness and siltation type of the sample pipe region. In some embodiments, the second label may be determined and labeled based on historical data of the sample pipe region. For example, under conditions similar to sample pipe features, the emergency monitoring and management platform can label the historical siltation thickness and historical siltation type of the sample pipe region as siltation thickness and siltation type.

[0153] During training, the second training sample is input into the initial congested model. A loss function is constructed based on the output of the initial congested model and the second label. The parameters of the initial congested model are iteratively updated (e.g., using gradient descent) based on the loss function until preset training conditions are met. Training then ends, and the trained congested model is obtained and used as congested model 450. The preset training conditions may include, but are not limited to, loss function convergence and reaching a threshold training period.

[0154] In some embodiments, the emergency monitoring and management platform can standardize and / or encode the sonar detection data 430 and pipeline features 440 of multiple circumferential points, and use the standardized and / or encoded sonar detection data and pipeline features of multiple circumferential points as input to the siltation model 450.

[0155] For more information on sonar detection data, pipe characteristics, target detection area, estimated silt thickness, and silt type, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0156] In some embodiments, the emergency monitoring and management platform can determine the dredging accuracy rate 460 based on the estimated siltation thickness 451 and siltation type 452; determine the associated pipeline area 470 corresponding to the target detection area based on the dredging accuracy rate 460; and control the robot to detect the associated pipeline area 470 through the emergency monitoring object platform.

[0157] Dredging accuracy is used to evaluate how well the output of siltation model 450 matches actual siltation data (e.g., actual siltation thickness, actual siltation type). For example, dredging accuracy 460 can be expressed as a percentage.

[0158] In some embodiments, the robot can upload the actual silt thickness and actual silt type collected after completing the dredging operation to the emergency monitoring object platform. The emergency monitoring object platform then uploads this information to the emergency monitoring management platform via the emergency monitoring sensor network platform. The emergency monitoring management platform can determine the dredging accuracy rate 460 based on the estimated silt thickness 451, silt type 452, actual silt thickness, and actual silt type output by the silt model 450. For example, the dredging accuracy rate 460 can be characterized as:

[0159] ,

[0160] This is a penalty factor used to punitively lower the dredging accuracy rate 460. When the siltation type 452 output by the siltation model 450 does not match the actual siltation type, the emergency monitoring and management platform can use the penalty factor. The accuracy rate of dredging was reduced by 460%. It can be set based on experience or by the system.

[0161] Associated pipe regions refer to other pipe regions that are associated with the target detection region. In some embodiments, associated pipe regions 470 may include one or more pipe regions upstream of the target detection region and / or one or more pipe regions downstream of the target detection region.

[0162] In some embodiments, it is known that the dredging accuracy rate of 460 is within a preset range. a %, b Within %], and the dredging accuracy rate of 460 is within the preset range. a %, b There are two scenarios besides %]. If the dredging accuracy rate of 460% is within the preset range, the emergency monitoring and management platform can determine that the output of the siltation model 450 is accurate; if the dredging accuracy rate of 460% is less than %... a The emergency monitoring and management platform can identify one or more pipeline areas downstream of the target detection area as associated pipeline areas of the target detection area 470; in response to the dredging accuracy rate 460 greater than b The emergency monitoring and management platform can identify one or more pipeline areas upstream of the target detection area as associated pipeline areas of the target detection area. a %, b The percentage can be set based on experience or by the system. In some embodiments, a % can be set to a negative value. b % can be set to a positive value. For example, a % can be set to -20%. b % can be set to 20%.

[0163] The detection of associated pipeline areas is similar to that of target detection areas; for more information, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0164] The embodiments described in this specification establish a feedback correction closed loop by evaluating the accuracy of the siltation model output, thereby improving siltation efficiency. Simultaneously, based on the accuracy of the siltation model output, these embodiments can intelligently trace and locate overlooked pipeline areas, enhancing the depth and accuracy of pipeline network problem investigation.

[0165] The embodiments in this specification adjust the detection density of sonar data based on the variation range of abnormal water flow area sequences relative to normal water flow area sequences, thereby improving the detection efficiency of the target detection area. Simultaneously, based on sonar detection data from multiple circumferential points and pipe characteristics, and utilizing a trained siltation model, the embodiments in this specification predict siltation thickness and type. This allows for a more accurate prediction of siltation conditions in the target detection area, reducing the manpower costs and resource waste required for manual assessment.

[0166] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

Claims

1. A drainage pipe network siltation treatment system based on an Internet of Things (IoT) big data model, characterized in that, This includes an emergency monitoring and management platform and an emergency monitoring object platform, wherein the emergency monitoring and management platform is configured as follows: By deploying acquisition devices in the drainage pipe network, flow data of the pipe area is collected, and the flow data uploaded by the acquisition devices is obtained; Based on the flow data of the pipeline area, a sequence of water-passing areas of multiple adjacent pipeline areas is determined; Based on the water flow area sequence of the multiple adjacent pipe regions, the abnormal pipe region and the abnormal water flow time are determined. Based on the abnormal pipeline area and the abnormal water flow time, the target detection area and target detection time are determined; The determination of the target detection area includes: Based on the rainfall within a preset time period, the amount of sewage discharged from catering establishments and construction sites upstream of the abnormal pipeline area, the abnormal pipeline area is screened through preset screening conditions, wherein the preset time period is before the abnormal water flow time. Based on the screened abnormal pipe areas, a sequence of abnormal water flow areas was determined; Based on the abnormal water flow area sequence, the target detection area is determined; The emergency monitoring platform controls a robot to perform sonar detection on the target detection area during the target detection time and collect sonar detection data. The robot is equipped with a sonar sensor. Based on the sonar detection data and pipeline characteristics, the estimated siltation thickness and siltation type of the target detection area are generated; Based on the estimated silt thickness, the silt type, and the pipe characteristics, the silt risk is determined; Based on the aforementioned siltation risk, the dredging path and dredging parameters are automatically generated; The emergency monitoring platform controls automated dredging equipment to travel along the dredging path to the dredging work site and performs dredging operations based on the dredging parameters.

2. The sewer network clogging treatment system according to claim 1, characterized by, The emergency monitoring and management platform is also configured as follows: Based on historical rainfall, historical restaurant wastewater discharge, and historical construction wastewater discharge, flow fluctuation information is determined. Based on the flow fluctuation information, determine whether there are any pseudo-abnormal flow areas in the abnormal flow area sequence; In response to the presence of the pseudo-abnormal water area, the pseudo-abnormal water area is removed from the abnormal water area sequence to generate an updated abnormal water area sequence. The target detection area is determined based on the updated abnormal water flow area sequence.

3. The sewer network clogging treatment system according to claim 1, wherein The emergency monitoring and management platform is also configured as follows: The emergency monitoring platform controls the robot to collect dredging data from the actual dredging process. Based on the dredging data, adjust the dredging parameters; The emergency monitoring platform controls the automated dredging equipment to perform the dredging operation based on the adjusted dredging parameters.

4. The sewer network clogging treatment system according to claim 3, characterized by, The emergency monitoring and management platform is also configured as follows: The pipeline image data of the pipeline area is acquired using an image acquisition device; Based on the pipeline image data, the estimated siltation rate of the pipeline in the pipeline area is determined; Based on the estimated siltation rate, the dredging operation is carried out on the pipes in the pipe area. 5.A sewer network clogging processing method based on an Internet of Things large model, characterized by, The method is executed by the emergency monitoring and management platform, and the method includes: By using acquisition devices deployed in the drainage pipe network, flow data of the pipe area is collected, and the flow data uploaded by the acquisition devices is obtained; Based on the flow data of the pipeline area, a sequence of water passage areas of multiple adjacent pipeline areas is determined; Based on the water flow area sequence of the multiple adjacent pipe regions, the abnormal pipe region and the abnormal water flow time are determined. Based on the abnormal pipeline area and the abnormal water flow time, the target detection area and target detection time are determined; the determination of the target detection area includes: Based on the rainfall within a preset time period, the amount of sewage discharged from catering establishments and construction sites upstream of the abnormal pipeline area, the abnormal pipeline area is screened through preset screening conditions, wherein the preset time period is before the abnormal water flow time. Based on the screened abnormal pipe areas, a sequence of abnormal water flow areas was determined; Based on the abnormal water flow area sequence, the target detection area is determined; The emergency monitoring platform controls a robot to perform sonar detection on the target detection area during the target detection time and collect sonar detection data. The robot is equipped with sonar sensors. Based on the sonar detection data and pipeline characteristics, the estimated siltation thickness and siltation type of the target detection area are generated; Based on the estimated silt thickness, the silt type, and the pipe characteristics, the silt risk is determined; Based on the aforementioned siltation risk, the dredging path and dredging parameters are automatically generated; The emergency monitoring platform controls automated dredging equipment to travel along the dredging path to the dredging work site and performs dredging operations based on the dredging parameters.

6. The drainage pipe network siltation treatment method as described in claim 5, characterized in that, include: Based on historical rainfall, historical restaurant wastewater discharge, and historical construction wastewater discharge, flow fluctuation information is determined. Based on the flow fluctuation information, determine whether there are any pseudo-abnormal flow areas in the abnormal flow area sequence; In response to the presence of the pseudo-abnormal water area, the pseudo-abnormal water area is removed from the abnormal water area sequence to generate an updated abnormal water area sequence. The target detection area is determined based on the updated abnormal water flow area sequence.

7. The drainage pipe network siltation treatment method as described in claim 5, characterized in that, include: The emergency monitoring platform controls the robot to collect dredging data from the actual dredging process. Based on the dredging data, adjust the dredging parameters; The emergency monitoring platform controls the automated dredging equipment to perform the dredging operation based on the adjusted dredging parameters.

8. The drainage pipe network siltation treatment method as described in claim 7, characterized in that, include: The pipeline image data of the pipeline area is acquired using an image acquisition device; Based on the pipeline image data, the estimated siltation rate of the pipeline in the pipeline area is determined; Based on the estimated siltation rate, the dredging operation is carried out on the pipes in the pipe area.

Images