Hydraulic Experimental Method and System for Drainage Pipe Networks Based on Dynamic Coupling of Two Branches

Abstract

The application discloses a drainage pipe network hydraulics experimental method and system based on double-branch dynamic coupling, belongs to the technical field of water conservancy projects, and comprises the following steps: a double-branch double-gradient dynamic coupling simulation device is built, four types of visual simulation experiments such as pipe network intersection flow state analysis are carried out, and data are collected; after the data are preprocessed, a critical blockage flow prediction model is established, a four-dimensional model is constructed in combination with historical data of a city drainage pipe network to train and iterate the four-dimensional model; field data are collected in real time to input the model for prediction, and the pipe network is controlled in real time according to the results and the model is continuously updated. The system comprises experimental simulation, model establishment, model training and comprehensive control modules. The application realizes multi-parameter dynamic collaborative control, constructs a multi-dimensional accurate measurement system, has the advantages of modularity and water cycle, realizes prediction control integration, provides an active prevention and control means for safe operation of the drainage pipe network, and is suitable for visual research on the hydraulic characteristics of the pipe network.

Description

Technical Field

[0001] This invention belongs to the technical field of experimental equipment for sustainable urban drainage networks, specifically relating to a modular experimental platform for studying the hydraulic characteristics of urban underground drainage networks. It is particularly suitable for analyzing the flow regime at the network junctions, simulating pipe blockage, testing the drainage capacity of reverse slopes, and visualizing the process of urban flooding under multi-parameter coupling conditions. Background Technology

[0002] Urban drainage networks are vital underground lifelines for cities, characterized by large flow fluctuations, complex conditions, and poor water quality. The installation environment for equipment is also challenging. However, monitoring urban drainage networks is of paramount importance. It provides fundamental data for addressing urban flooding, testing the drainage capacity of uphill pipes, detecting pipe damage, and preventing network blockages. It can also monitor key enterprises for illegal discharges, providing evidence for relevant departments. Furthermore, it allows for the study of urban sewage flow rates, understanding network operation, and providing data support for the renovation, improvement, and construction of drainage networks.

[0003] With the rapid development of urbanization, modern urban drainage pipe networks are becoming increasingly large-scale and complex. Existing rainwater drainage pipe systems generally only discharge rainwater into nearby water bodies. However, when rainfall is excessive, continuing to discharge rainwater into these water bodies can lead to excessive water volume, easily causing flooding. Furthermore, these systems can also cause backflow of water from these bodies into the city, resulting in even more severe urban flooding. Moreover, existing drainage systems rely on manholes for drainage. When the water volume is too high, the drainage speed of the manhole covers is slower than the rate of rainfall, causing rainwater to accumulate in the city and resulting in short-term flooding. Additionally, during periods of heavy rainfall, timely warnings and automatic control are lacking, leading to significant economic losses. Therefore, the lack of effective methods for preventing overflow in drainage pipes poses a serious threat to daily safety and health, and to sustainable social development.

[0004] This invention aims to provide a hydraulic experimental method and system for drainage pipe networks based on dynamic coupling of two branches, to conduct research on urban flood control, drainage capacity testing of reverse slope pipes, and monitoring of pipe damage and pipe network blockage, thereby achieving safe operation control of drainage pipes to prevent overflow. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention proposes an intelligent experimental device with multi-parameter dynamic coupling, high-precision flow field analysis, and water resource recycling capabilities, mainly solving the following technical problems: (1) Real-time coordinated control of multiple parameters such as pipe slope, flow rate and pipe diameter. (2) Construct a multi-dimensional and multi-physical quantity synchronous measurement system for pipeline network nodes (3) Develop modular rapid reconfiguration pipeline components (4) Establish an efficient recycling and purification mechanism for experimental water.

[0006] To address the aforementioned problems and technical deficiencies, this invention employs the following technical solution: a hydraulic experimental method and system for drainage pipe networks based on dynamic coupling of two branches, comprising: S1. Construct a dual-branch dual-gradient dynamic coupling simulation device, and use the dual-branch dual-gradient dynamic coupling simulation device to conduct visual simulation experiments under multi-parameter coupling conditions, and collect simulation experimental data; the dual-branch dual-gradient dynamic coupling simulation device includes a dual-gradient water supply unit, an intelligent inspection well group, and a water circulation and purification unit; the visual simulation experiments include pipe network intersection flow pattern analysis, pipe blockage simulation, reverse slope drainage capacity test, and waterlogging overflow process simulation; S2. Preprocess and extract features from the simulated experimental data to obtain a simulated experimental data feature set, and establish a critical congestion flow prediction model based on the simulated experimental data feature set. S3. Obtain historical data of the urban drainage network, and test and train the critical blockage flow prediction model based on the historical data of the urban drainage network to obtain the trained critical blockage flow prediction model. S4. Collect real-time field data of the urban drainage network, input the field data into the trained critical blockage flow prediction model for calculation and prediction, obtain the prediction result of the urban drainage network, and implement real-time control of the urban drainage network based on the prediction result.

[0007] Preferably, the dual-branch dual-gradient dynamic coupling simulation device in S1 further includes a water tank, a first branch pipe, a second branch pipe, and a circulating water pipe. The first branch pipe and the second branch pipe are respectively connected to the two output ports of the water tank, and Coriolis mass flow meters and electric regulating valves are installed at the connection points of the first branch pipe and the second branch pipe with the water tank. The second branch pipeline is equipped with and connected to a reverse slope test node inspection well and a junction node inspection well; Two junction manholes are installed and connected on the first branch pipeline, and the reverse slope test node manhole is connected to the junction manhole on the first branch pipeline through a branch pipe; The tail ends of the first branch pipeline and the second branch pipeline are fixedly connected to and communicate with a junction node inspection well. The output end of the junction node inspection well is connected to the multi-functional purification room. The output end of the multi-functional purification room is connected to the circulating water pipeline. A centrifugal pump is fixedly installed and connected to the output end of the circulating water pipeline. The output end of the centrifugal pump flows through the input port of the water tank. A rotating motor is fixedly installed on the multifunctional purification chamber, and a filter plate is fixedly installed inside the multifunctional purification chamber. The drive end of the rotating motor extends into the multifunctional purification chamber and is fixedly installed with an electric telescopic rod. An arc-shaped push plate is fixedly installed at the bottom end of the electric telescopic rod, and the arc-shaped push plate abuts against the top surface of the filter plate. The filter plate includes a circular filter plate and a filter ring with a U-shaped cross-section; A hexagonal column block is fixedly installed on the arc-shaped push plate. The electric telescopic rod is provided with a regular hexagonal sliding groove that matches the hexagonal column block. A buffer spring is fixedly installed on the hexagonal column block, and the other end of the buffer spring is fixedly connected to the electric telescopic rod.

[0008] Preferably, the water tank is a double-layered 304 stainless steel water tank, and the height difference between the upper chamber and the lower chamber is 345~355mm. The water tank is equipped with a PID temperature controller and an ultrasonic water level gauge. The PID temperature controller operates within a temperature range of 5~40℃. Both output ports of the water tank are equipped with honeycomb rectifiers. Both output ports of the water tank are connected to the upper chamber, and the input port of the water tank is connected to the lower chamber. The upper chamber is connected to the lower chamber. The lower chamber is equipped with a three-stage filtration system, which includes: a primary cyclone sand separator, a secondary ceramic membrane filter, and a tertiary ultraviolet sterilization module.

[0009] As a preferred embodiment, the pipeline confluence flow analysis described in S1 uses a three-dimensional ADV flow meter and a micro differential pressure sensor array in the inspection well of the confluence node, combined with laser-induced fluorescence (LIF) technology and high-speed imaging, to capture the three-dimensional velocity, pressure distribution and flow field dynamics of water flow in real time, analyze complex flow states such as stagnation, deflection and shearing in the confluence area, and provide data support for pipeline silt reduction and optimization. The pipeline blockage simulation involves dropping 1-20mm particles into the inspection well at the reverse slope node to simulate blockage, while simultaneously monitoring abnormal flow fluctuations and pressure changes. High-speed cameras record the blockage accumulation process, and the impact mechanism of blockage on flow capacity and pressure imbalance is analyzed. The reverse slope drainage capacity test utilizes a hydraulic slope adjustment device to adjust the pipe slope, monitors the flow rate attenuation using a Coriolis flow meter, and combines a fiber optic strain sensor and an ADV flow meter to evaluate the pipe stress distribution and hydraulic performance under reverse slope conditions, revealing the influence law of slope on drainage efficiency. The waterlogging and overflow simulation experiment simulates heavy rainfall inflow through a dual-gradient water supply unit, and intelligent inspection well groups monitor water level changes in real time. Combined with flow rate, velocity and pressure data, it quantifies the critical conditions for waterlogging formation and overflow risk, providing a basis for urban flood control and drainage design.

[0010] Preferably, the first branch pipeline is divided into a basic section pipeline and a replaceable section pipeline; the pipe material selection for the replaceable section pipeline includes UPVC smooth pipe, cast iron threaded pipe, or 3D printed bionic pipe; a hydraulic slope adjuster is installed on the second branch pipeline, with a slope adjustment range of -5% to +5% and a minimum adjustment step of 0.1%; a fiber optic strain sensor is installed on the second branch pipeline for pipe stress monitoring; a rotatable guide plate is rotatably installed inside the inspection well of the reverse slope test node, and a particulate matter dispensing device is installed at the bottom of the inspection well of the reverse slope test node; the inspection well of the confluence node is made of 10mm thick plexiglass, and a three-dimensional ADV flow meter and a micro-differential pressure sensor array are installed inside the inspection well of the confluence node; a laser-induced fluorescence observation window is installed on the top of the inspection well of the confluence node.

[0011] Preferably, the process of establishing the critical congestion flow prediction model in S2 includes: preprocessing the simulation experimental data to remove abnormal data, performing statistical analysis on the preprocessed data to obtain characteristic parameters, using dimensional indices to perform flow data analysis on the characteristic parameters, combining the control results to obtain flow prediction results, and then establishing the critical congestion flow prediction model.

[0012] Preferably, the process of testing and training the critical congestion flow prediction model in S3 includes: S3.1 Classify each group of data in the historical data of urban drainage pipe network according to its address and collection time. Each group of data includes the collected data and the control results. S3.2 Establish a three-dimensional model of the urban drainage network, associate each group of classified historical data with the three-dimensional model according to its address, and sort them according to the collection time to construct a four-dimensional model of the urban drainage network. S3.3 Input the collected data from the four-dimensional model into the critical congestion flow prediction model to obtain the predictive control result. Compare the predictive control result with the corresponding actual control result and determine whether to perform iterative training on the model based on the comparison result.

[0013] Preferably, the process of comparing the predictive control results with the actual control results described in S3.3 includes: A preset correct threshold is set, and the percentage of predictive control results that match actual control results is calculated out of all correct predictive control results. This percentage is then compared with the preset correct threshold. If the correct percentage is greater than the correct threshold, the critical congestion flow prediction model is deemed to meet the usage requirements. If the correct percentage is less than the correct threshold, the critical congestion flow prediction model is deemed unsuitable for use, and iterative training is performed on it.

[0014] Preferably, S4 further includes adding real-time collected on-site data of the urban drainage network and the corresponding prediction results to the four-dimensional model of the urban drainage network, and updating the critical blockage flow prediction model based on the updated data in the four-dimensional model every preset period.

[0015] A comprehensive hydraulic experimental system for urban drainage pipe networks based on dynamic coupling of two branches includes: The experimental simulation module is used to build a dual-branch dual-gradient dynamic coupling simulation device, and to conduct visual simulation experiments under multi-parameter coupling conditions using the dual-branch dual-gradient dynamic coupling simulation device. The model building module is used to preprocess the simulation experimental data, extract features, obtain the simulation experimental data feature set, and build a critical congestion flow prediction model based on the simulation experimental data feature set. The model training module is used to acquire historical data of urban drainage pipe networks, test and train the critical blockage flow prediction model, and obtain the trained critical blockage flow prediction model. The integrated control module is used to collect data from the urban drainage network in real time, calculate and predict the critical blockage flow rate using the trained model, obtain the prediction results of the urban drainage network, and perform real-time control of the urban drainage network.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention constructs a dual-branch, dual-gradient dynamic coupling simulation device to conduct visual simulation experiments, acquire simulation data, establish a critical blockage flow prediction model based on the simulation data, test and train the critical blockage flow prediction model by combining it with historical data of the urban drainage network, and then use the trained critical blockage flow prediction model to predict the real-time collected urban drainage network data. Based on the prediction results, the urban drainage network is controlled in real time to avoid economic losses caused by the inability to provide timely early warning and automatic control, thereby achieving safe operation control of urban drainage pipelines to prevent overflow.

[0017] 1. Outstanding multi-parameter dynamic collaborative control capability: This scheme achieves real-time collaborative control of multiple parameters such as pipeline slope (-5% to +5%), flow rate, pipe diameter and pipe material through a dual-branch dual-gradient dynamic coupling simulation device. It solves the pain point of existing technologies being unable to simultaneously simulate complex working conditions. It can accurately reproduce the actual operating scenarios of multi-factor coupling in urban drainage pipe networks, and provide a more realistic experimental basis for hydraulic characteristic research.

[0018] 2. The multidimensional data measurement system is accurate and comprehensive. Relying on the three-dimensional ADV flow meter and micro differential pressure sensor array mounted on the intelligent inspection well group, combined with laser-induced fluorescence (LIF) technology and high-speed imaging, a multidimensional and multi-physical quantity synchronous measurement system has been constructed. It can capture key data such as three-dimensional velocity, pressure distribution and flow field dynamics of water flow in real time. Compared with traditional measurement methods, the data dimensions are richer and the analytical accuracy is higher, providing reliable data support for pipeline network flow analysis and performance evaluation.

[0019] 3. Modular design and efficient resource recycling: The modular design allows for rapid reconfiguration of pipe components, enabling flexible replacement of different pipe materials such as UPVC smooth pipes and cast iron threaded pipes to meet diverse experimental needs. At the same time, a three-stage filtration + circulating water supply system is built to achieve efficient purification and circulation of experimental water, which not only reduces experimental costs but also solves the problems of high material consumption and insufficient flexibility in existing experimental devices, thus improving the economy and environmental friendliness of experiments.

[0020] 4. Integrated prediction and control ensures safe operation: By fusing simulation data with historical data from urban drainage networks, a critical blockage flow prediction model is constructed. Combined with continuous iterative optimization using a four-dimensional model, this model can predict risks such as network blockage and flooding in real time, thereby achieving dynamic regulation of the drainage network. Compared to existing technologies that lack effective early warning and automatic control, this solution can proactively avoid safety hazards such as overflows, providing a proactive prevention and control measure for the safe operation of urban drainage networks. Attached Figure Description

[0021] In the attached diagram: Figure 1 This is a three-dimensional structural diagram of an embodiment of the present invention; Figure 2 This is a schematic diagram of the visualization simulation experiment architecture of the present invention; Figure 3 This is a schematic diagram of the device structure system according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the device structure and connection relationship according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the partial structural connection relationship of the multifunctional cleanroom of the device according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the reverse slope structure of the simulation device according to an embodiment of the present invention; Figure 7 This is a schematic diagram of simulated pipeline siltation according to an embodiment of the present invention; Figure 8 This is a schematic diagram of the comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches, as proposed in this invention.

[0022] In the diagram: 1. Water tank; 2. First branch pipeline; 3. Second branch pipeline; 4. Upside-down slope test node inspection well; 5. Intersection node inspection well; 6. Electric regulating valve; 7. Coriolis mass flow meter; 8. Centrifugal pump; 9. Circulating water pipeline; 11. Multifunctional purification chamber; 12. Rotary motor; 13. Filter plate; 14. Electric telescopic rod; 15. Arc-shaped push plate; 151. Hexagonal column block; 152. Buffer spring. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. Generally, the components of the embodiments of the present invention described and shown in the accompanying drawings can be arranged and designed in various different configurations.

[0024] Example 1 like Figure 1 , Figure 3 , Figure 4 and Figure 5 As shown, this scheme, based on a dual-branch dynamic coupling drainage network hydraulic comprehensive experimental device, consists of a water tank 1, a first branch pipeline 2, a second branch pipeline 3, a circulating water pipeline 9, and supporting functional components, forming a closed-loop collaborative experimental flow path system: the water tank 1 serves as the core of water supply, with its two output ports connected to the first branch pipeline 2 and the second branch pipeline 3 respectively, and each connection is equipped with a Coriolis mass flow meter 7 and an electric regulating valve 6 to achieve accurate flow measurement and real-time control; the second branch pipeline 3 is connected in series with the reverse slope experimental node inspection well 4 and the confluence node inspection well 5, the first branch pipeline 2 is connected to the two confluence node inspection wells 5, and the reverse slope experimental node inspection well 4 is interconnected with the confluence node inspection well 5 of the first branch pipeline 2 through a branch pipe, constructing a multi-node coupled pipeline network simulation structure; the tail ends of the two branch pipelines are connected to a confluence node inspection well 5, the output end of which is connected to a multi-functional purification chamber 11, and the purified water flows back to the water tank 1 through the circulating water pipeline 9 and the centrifugal pump 8, completing the closed-loop circulation of experimental water.

[0025] The multi-functional purification chamber 11 has a built-in core purification component: a rotating motor 12 is fixed at the top of the chamber, and a filter plate 13 composed of a circular filter plate and a U-shaped filter ring is installed inside. The drive end of the rotating motor 12 extends into the chamber and is connected to an electric telescopic rod 14. An arc-shaped push plate 15 is installed at the bottom of the telescopic rod, and the arc-shaped push plate 15 cooperates with the regular hexagonal sliding groove of the telescopic rod through a hexagonal column block 151, supplemented by a buffer spring 152 to achieve elastic fit. When the blockage generated in the experiment flows into the multi-functional purification chamber 11, the filter plate 13 can quickly intercept solid impurities. If too much blockage accumulates on the surface of the filter plate and affects the water flow, the rotating motor 12 and the electric telescopic rod 14 are started. The arc-shaped push plate 15 rotates under elastic compression, and its arc-shaped convex surface pushes the blockage along the water flow direction, causing the impurities to slide into the U-shaped filter ring along the convex surface, efficiently clearing the filter plate and ensuring the continuous smooth flow of the water circulation system.

[0026] Among them, the multi-functional cleanroom 11 has the following advantages over existing technologies: Building a foundation for multi-condition simulation: Through the combined design of dual-branch pipelines and multiple inspection wells, the key structures such as the intersection nodes and reverse slope sections of the urban drainage network are accurately reproduced, providing a realistic physical simulation scenario for core experiments such as pipeline intersection flow analysis, pipeline blockage simulation, and reverse slope drainage capacity testing.

[0027] Achieving precise control of experimental parameters: The linkage between the Coriolis mass flow meter 7 and the electric regulating valve 6 can monitor and adjust the branch flow in real time. In conjunction with the hydraulic slope changing mechanism of the second branch, it can meet the needs of coordinated control of key parameters such as flow rate and slope in multi-parameter coupled experiments.

[0028] Ensuring experimental continuity and stability: The filtration and automatic unclogging functions of the multi-functional purification chamber 11 not only achieve the purification and circulation of experimental water, avoiding the accumulation of impurities that affect experimental accuracy, but also prevent the filter plate 13 from becoming clogged and causing experimental interruption through the active unclogging design of the arc-shaped push plate 15, ensuring the stable conduct of long-term continuous experiments.

[0029] Supporting the integrity of data acquisition: Sensors (such as flow meters, pressure sensors, etc.) that are matched with the inspection wells and pipelines at each node can comprehensively collect data such as flow rate, pressure, and flow velocity under different operating conditions based on the flow path structure of this device, providing complete experimental data support for subsequent model building.

[0030] High flow control accuracy: The combination of Coriolis mass flow meter 7 and electric regulating valve 6 enables real-time flow measurement and closed-loop control, solving the problems of lagging and large error in flow control of traditional experimental devices and ensuring the accuracy of experimental parameters.

[0031] Water recycling is efficient, environmentally friendly, and sustainable: The three-stage filtration and automatic unclogging design of the multi-functional purification chamber 11 not only enables the reuse of experimental water and reduces water consumption, but also avoids frequent disassembly and cleaning of filter plates through the active unclogging mechanism, thus improving experimental efficiency; the U-shaped filter ring design facilitates the centralized treatment of impurities and further optimizes the ease of operation.

[0032] Strong component synergy: Each component forms a closed-loop system of "water supply-regulation-simulation-purification-recirculation". From parameter regulation to experimental simulation and system maintenance, automation and collaboration are achieved, reducing manual intervention, which not only reduces the complexity of operation, but also avoids the impact of human error on experimental results, and improves the repeatability and reliability of the experiment.

[0033] The water outlet pipe is pumped through the water circulation pipe 9 to the stainless steel water tank 1 by the centrifugal pump 8 for repeated experiments. The experimental process includes: A dual-branch, dual-gradient dynamic coupling simulation device was constructed, and a visual simulation experiment was conducted under multi-parameter coupling conditions using the dual-branch, dual-gradient dynamic coupling simulation device to obtain simulation experimental data. The dual-branch dual-gradient dynamic coupling simulation device includes a dual-gradient water supply unit, a dual-branch experimental system, an intelligent inspection well group, and a water circulation and purification unit. like Figure 8 As shown, the visualization experiment simulation is conducted under multi-parameter coupling conditions to perform flow regime analysis at pipe network intersections, pipe blockage simulation, reverse slope drainage capacity testing, and simulation of waterlogging and overflow processes.

[0034] The visualization experiment is as follows: During the pipeline confluence flow analysis experiment, the three-dimensional ADV velocimeter in the inspection well 5 at the confluence node measures the three-dimensional velocity of the water flow, the micro-differential pressure sensor array measures the pressure difference, the laser-induced fluorescence (LIF) observation window and the 532nm pulsed laser work together to make the tracer particles emit light, the high-speed camera records the images, and the water flow velocity, flow direction and other information are obtained by algorithm analysis and then transmitted. The data is transmitted to the acquisition system to help analyze the water flow conditions in the pipeline confluence area.

[0035] During the pipeline blockage simulation experiment, the particle dispensing device at the bottom of the inspection well at the reverse slope test node, according to the set experimental plan, dispenses solid blockage materials of different diameters (1~20mm) into the pipeline. Meanwhile, a Coriolis mass flow meter 7 installed on the pipeline monitors flow changes. If the pipeline shows signs of blockage or partial blockage, such as... Figure 7As shown, flow data may fluctuate abnormally, and the data is transmitted to the data acquisition and control system in real time. Simultaneously, pressure sensors inside the manhole monitor pressure changes; if pipe blockage causes pressure increases, the pressure data is transmitted to the data acquisition and control system. Furthermore, a high-speed camera captures images of the inside of the pipe and manhole, recording the movement trajectory of the blockage, its accumulation process, and changes in water flow. This video data is transmitted to the data acquisition and control system for analyzing the obstruction of water flow and the patterns of pressure and flow changes within the pipe.

[0036] During the reverse slope drainage capacity test, the hydraulic slope adjustment device of branch II adjusts the pipe slope to the set reverse slope state (adjustment range -5% to +5%, minimum adjustment step 0.1%). A Coriolis mass flow meter 7 monitors the flow data in the reverse slope pipe in real time, recording the flow rate changes under different reverse slope gradients and transmitting the data to the data acquisition and control system. A fiber optic strain sensor monitors the pipe stress changes in real time. Because the stress state of the pipe changes during reverse slope drainage, the stress data will change accordingly and is transmitted to the data acquisition and control system for analyzing the mechanical response of the pipe structure under reverse slope drainage conditions. A three-dimensional ADV flow meter in the inspection well of the reverse slope test node measures the water flow velocity, and a micro-differential pressure sensor array measures the pressure difference, monitoring the water flow motion state and pressure distribution changes under reverse slope conditions. All data are transmitted to the data acquisition and control system, and the reverse slope drainage capacity can be evaluated by combining these data.

[0037] During the experimental simulation of urban flooding and overflow, the dual-gradient water supply unit increased the water supply according to the experimental settings to simulate flooding caused by heavy rainfall. Water level sensors in the intelligent inspection well group monitored water level changes in the wells in real time. When the water level rose close to or reached the preset flooding and overflow threshold, the data was rapidly transmitted to the data acquisition and control system. Based on this data, the formation mechanism, development process, and impact on the surrounding environment of urban flooding and overflow were analyzed, providing a basis for the optimized design of urban drainage networks and urban flooding prevention.

[0038] The simulation experimental data is preprocessed and features are extracted to obtain a feature set of the simulation experimental data. A critical congestion flow prediction model is then established based on the feature set of the simulation experimental data. The process of establishing the critical blockage flow prediction model is as follows: preprocessing the simulation experimental data, extracting abnormal data, performing statistical analysis, statistically analyzing the characteristic parameters of the experimental data, using dimensional indices to analyze the flow data of the characteristic parameters, and combining the control results to obtain the flow prediction results, thus establishing the critical blockage flow prediction model.

[0039] Historical data of urban drainage pipe network is obtained, and the critical blockage flow prediction model is tested and trained to obtain the trained critical blockage flow prediction model. The process of testing and training the critical congestion flow prediction model is as follows: Each set of data in the historical data of the urban drainage network is classified according to its location and collection time. Each set of data includes the collected data and the control results. A three-dimensional model of the urban drainage network is established. Each set of data from the historical data of the urban drainage network is added to the three-dimensional model of the urban drainage network according to its location. The data is sorted according to the collection time to establish a four-dimensional model of the urban drainage network. The collected data from the four-dimensional model of the urban drainage network is input into the critical blockage flow prediction model to obtain the predicted control results. The predicted control results are compared with the actual control results, and the comparison results determine whether to iteratively train the critical blockage flow prediction model.

[0040] Comparing and judging the predicted control results with the actual control results includes: Preset a correct threshold, determine the proportion of correct predictive control results that are the same as actual control results among all predictive control results, and compare the correct proportion with the correct threshold. If the correct percentage is greater than the correct threshold, then the critical congestion flow prediction model is deemed to meet the usage requirements. If the correct percentage is less than the correct threshold, the critical congestion flow prediction model is deemed unsuitable for use and requires iterative training.

[0041] Data from the urban drainage network is collected in real time, and the trained critical blockage flow prediction model is used to calculate and predict the urban drainage network to obtain the prediction results and control the urban drainage network in real time.

[0042] After receiving real-time urban drainage network data, the collected urban drainage network data and urban drainage network prediction results will be added to the urban drainage network four-dimensional model. Every preset period, the critical blockage flow prediction model will be updated based on the updated data in the urban drainage network four-dimensional model.

[0043] Example 2 like Figure 2 As shown, a dual-branch dual-gradient dynamic coupling simulation device was built. The dual-branch dual-gradient dynamic coupling simulation device was used to conduct a visual simulation experiment under multi-parameter coupling conditions and obtain simulation experiment data. like Figure 6 As shown, the dual-branch dual-gradient dynamic coupling simulation device includes a dual-gradient water supply unit, a dual-branch experimental system, an intelligent inspection well group, and a water circulation and purification unit. Visualized experimental simulations are used to analyze the flow patterns at pipe network junctions, simulate pipe blockages, test reverse slope drainage capacity, and simulate waterlogging and overflow processes under multi-parameter coupling conditions.

[0044] The dual-gradient water supply unit uses a double-layer 304 stainless steel water tank 1 (total volume 2.5m³). The height difference between the upper water tank 1 and the lower water tank 1 is 350±5mm, and the upper water tank 1 and the lower water tank 1 form a stable head difference of ≥300mm. Equipped with a PID temperature control system (operating range 5-40℃, control accuracy ±0.3℃) and an ultrasonic water level gauge (resolution 0.5mm). A honeycomb rectifier (pore diameter Φ10mm, length-to-diameter ratio 6:1) is installed at the outlet to ensure initial laminar flow conditions.

[0045] The dual-branch experimental system uses a DN50 pipe with a total length of 8.6m. The basic section of branch I2 includes a slope-compatible replaceable pipe module and a manhole set equipped with multiple physical quantity sensors. It is equipped with an electric regulating valve 6 (CV value 0-650, response time ≤1s) and a Coriolis mass flow meter 7 (accuracy class 0.2). The replaceable section uses three optional pipe materials: UPVC smooth pipe (roughness height ks=0.06mm), cast iron threaded pipe (ks=0.15mm), and 3D printed bionic pipe (ks can be programmed). The pipe diameter of branch II3 (variable slope branch) of the dual-branch test system is DN40, the total length is 7.2m, and it is equipped with a hydraulic variable slope mechanism. Branch II3 includes a hydraulic continuous slope changing pipeline module and an intelligent inspection well with an integrated pellet delivery device. The slope adjustment range is -5% to +5%, the minimum adjustment step is 0.1%, and the dynamic response time is ≤3s; integrated fiber optic strain sensors (50cm spacing) are used for pipe stress monitoring.

[0046] The intelligent inspection well group includes the intersection node inspection well 5 and the reverse slope test node inspection well 4, which realizes the time synchronization of multi-source heterogeneous data (deviation ≤1ms). The intersection node inspection well 5 is made of 10mm thick aviation-grade organic glass with an inner diameter of Φ600mm. It is equipped with a three-dimensional ADV flow meter (sampling rate 200Hz), a micro differential pressure sensor array (16-point arrangement), and a laser-induced fluorescence (LIF) observation window on the top, which is used in conjunction with a 532nm pulsed laser for flow field tracing. The reverse slope test node inspection well 4 has a built-in rotatable guide plate (angle adjustable from 0-180°, driven by a stepper motor, angular resolution 0.1°), and a particulate matter dispensing device is installed at the bottom to simulate solid blockages with a diameter of Φ1-20mm.

[0047] The data acquisition and control system uses the NicDAQ-9188XT chassis and integrates the following modules: 4-channel synchronous analog input (24-bit ADC, ±10V range); digital I / O module (32 channels, 1MHz sampling rate); fieldbus communication module (supports PROFINET / EtherCAT); and dedicated control software with the following functions: Multi-device collaborative control (synchronization accuracy of valve-pump-slope changing mechanism ≤10ms); Real-time flow field reconstruction (velocity field refresh rate ≥30fps based on PIV algorithm). Batch processing of experimental data (automatic generation of ISO5800 standard reports).

[0048] The water circulation purification unit adopts a three-stage filtration system, which keeps the turbidity ≤5NTU. It includes: a first-stage cyclone sand separator (removal rate ≥95% of particles >50μm); a second-stage ceramic membrane filter (filtration accuracy 1μm); and a third-stage ultraviolet sterilization module (wavelength 254nm, radiation intensity 80μW / cm²). It is equipped with 8 variable frequency centrifugal pumps (power 1.5kW, flow rate 0-30m³ / h adjustable).

[0049] For example, set the slope of branch road II to -4%, replace the pipe section with cast iron pipe with ks=0.12mm, set the guide plate of inspection well V to 55°, and release Φ15mm spherical particles; The flow rate of branch II is increased in a stepwise manner (5→15L / s, step size 2L / s), the pressure difference between the inlet and outlet of pipeline 5 is collected simultaneously, the water level fluctuation of manhole V is monitored, and the particle movement trajectory is recorded by an HSV camera.

[0050] The inner surface roughness of the replaceable pipe module along the slope exhibits a gradient change, with the roughness ratio of adjacent pipe sections ≥1:1.5, and the pipe sections are connected by pneumatic locking quick-installation flanges.

[0051] The simulation experimental data is preprocessed and features are extracted to obtain a feature set of the simulation experimental data. A critical congestion flow prediction model is then established based on the feature set of the simulation experimental data. The process of establishing the critical blockage flow prediction model is as follows: preprocessing the simulation experimental data, extracting abnormal data, performing statistical analysis, statistically analyzing the characteristic parameters of the experimental data, using dimensional indices to analyze the flow data of the characteristic parameters, and combining the control results to obtain the flow prediction results, thus establishing the critical blockage flow prediction model.

[0052] Historical data of urban drainage pipe network is obtained, and the critical blockage flow prediction model is tested and trained to obtain the trained critical blockage flow prediction model. The process of testing and training the critical congestion flow prediction model is as follows: Each set of data in the historical data of the urban drainage network is classified according to its location and collection time. Each set of data includes the collected data and the control results. A three-dimensional model of the urban drainage network is established. Each set of data from the historical data of the urban drainage network is added to the three-dimensional model of the urban drainage network according to its location. The data is sorted according to the collection time to establish a four-dimensional model of the urban drainage network. The collected data from the four-dimensional model of the urban drainage network is input into the critical blockage flow prediction model to obtain the predicted control results. The predicted control results are compared with the actual control results, and the comparison results determine whether to iteratively train the critical blockage flow prediction model.

[0053] Comparing and judging the predicted control results with the actual control results includes: Preset a correct threshold, determine the proportion of correct predictive control results that are the same as actual control results among all predictive control results, and compare the correct proportion with the correct threshold. If the correct percentage is greater than the correct threshold, then the critical congestion flow prediction model is deemed to meet the usage requirements. If the correct percentage is less than the correct threshold, the critical congestion flow prediction model is deemed unsuitable for use and requires iterative training.

[0054] Data from the urban drainage network is collected in real time, and the trained critical blockage flow prediction model is used to calculate and predict the urban drainage network to obtain the prediction results and control the urban drainage network in real time.

[0055] After receiving real-time urban drainage network data, the collected urban drainage network data and urban drainage network prediction results will be added to the urban drainage network four-dimensional model. Every preset period, the critical blockage flow prediction model will be updated based on the updated data in the urban drainage network four-dimensional model.

[0056] Example 3 A comprehensive hydraulic experimental system for urban drainage pipe networks based on dynamic coupling of two branches includes: The experimental simulation module is used to build a dual-branch dual-gradient dynamic coupling simulation device, and to conduct visual simulation experiments under multi-parameter coupling conditions using the dual-branch dual-gradient dynamic coupling simulation device. The model building module is used to preprocess the simulation experimental data, extract features, obtain the simulation experimental data feature set, and build a critical congestion flow prediction model based on the simulation experimental data feature set. The model training module is used to acquire historical data of urban drainage pipe networks, test and train the critical blockage flow prediction model, and obtain the trained critical blockage flow prediction model. The integrated control module is used to collect data from the urban drainage network in real time, calculate and predict the critical blockage flow prediction model after training, obtain the prediction results of the urban drainage network, and perform real-time control of the urban drainage network. The real-time alarm module is used to set multiple alarm thresholds based on different drainage conditions of the urban drainage network. When the data collected in real time in the urban drainage network exceeds the alarm threshold in the critical blockage flow prediction model and cannot be effectively controlled, an alarm will be pushed to the administrator.

[0057] The embodiments described above are merely preferred embodiments of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications, improvements, and substitutions without departing from the concept of the present invention, and these all fall within the protection scope of the present invention.

Claims

1. A comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches, characterized in that, include: S1. Construct a dual-branch dual-gradient dynamic coupling simulation device, and use the dual-branch dual-gradient dynamic coupling simulation device to conduct visual simulation experiments under multi-parameter coupling conditions, and collect simulation experimental data; the dual-branch dual-gradient dynamic coupling simulation device includes a dual-gradient water supply unit, an intelligent inspection well group, and a water circulation and purification unit; the visual simulation experiments include pipe network intersection flow pattern analysis, pipe blockage simulation, reverse slope drainage capacity test, and waterlogging overflow process simulation; S2. Preprocess and extract features from the simulated experimental data to obtain a simulated experimental data feature set, and establish a critical congestion flow prediction model based on the simulated experimental data feature set. S3. Obtain historical data of the urban drainage network, and test and train the critical blockage flow prediction model based on the historical data of the urban drainage network to obtain the trained critical blockage flow prediction model. S4. Collect real-time field data of the urban drainage network, input the field data into the trained critical blockage flow prediction model for calculation and prediction, obtain the prediction result of the urban drainage network, and implement real-time control of the urban drainage network based on the prediction result.

2. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches as described in claim 1, characterized in that, The dual-branch dual-gradient dynamic coupling simulation device described in S1 also includes a water tank (1), a first branch pipeline (2), a second branch pipeline (3), and a circulating water pipeline (9). The first branch pipe (2) and the second branch pipe (3) are respectively connected to the two output ports of the water tank (1). Coriolis mass flow meter (7) and electric regulating valve (6) are installed at the connection between the first branch pipe (2) and the second branch pipe (3) and the water tank (1). The second branch pipeline (3) is equipped with and connected to a reverse slope test node inspection well (4) and a junction node inspection well (5); Two junction manholes (5) are installed and connected on the first branch pipeline (2), and the reverse slope test node manhole (4) is connected to the junction manhole (5) on the first branch pipeline (2) through a branch pipe; The tail ends of the first branch pipeline (2) and the second branch pipeline (3) are fixedly connected to and communicate with a junction inspection well (5). The output end of the junction inspection well (5) is connected to the multi-functional purification chamber (11). The output end of the multi-functional purification chamber (11) is connected to the circulating water pipeline (9). The output end of the circulating water pipeline (9) is fixedly installed and connected to a centrifugal pump (8). The output end of the centrifugal pump (8) flows through the input port of the water tank (1). A rotating motor (12) is fixedly installed on the multifunctional purification chamber (11), and a filter plate (13) is fixedly installed inside the multifunctional purification chamber (11). The drive end of the rotating motor (12) extends into the multifunctional purification chamber (11) and is fixedly installed with an electric telescopic rod (14). An arc-shaped push plate (15) is fixedly installed at the bottom end of the electric telescopic rod (14), and the arc-shaped push plate (15) abuts against the top surface of the filter plate (13). The filter plate (13) includes a circular filter plate and a filter ring with a U-shaped cross-section; A hexagonal column block (151) is fixedly installed on the arc-shaped push plate (15). The electric telescopic rod (14) is provided with a regular hexagonal groove that matches the hexagonal column block (151). A buffer spring (152) is fixedly installed on the hexagonal column block (151). The other end of the buffer spring (152) is fixedly connected to the electric telescopic rod (14).

3. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches as described in claim 2, characterized in that, The water tank (1) is a double-layer 304 stainless steel water tank, and the height difference between the upper chamber and the lower chamber is 345~355mm. The water tank (1) is equipped with a PID temperature controller and an ultrasonic water level gauge. The working temperature range of the PID temperature controller is 5~40℃. Both output ports of the water tank (1) are equipped with honeycomb rectifiers. Both output ports of the water tank (1) are connected to the upper chamber. The input port of the water tank (1) is connected to the lower chamber. The upper chamber is connected to the lower chamber. The lower chamber is equipped with a three-stage filtration system, which includes a primary cyclone sand separator, a secondary ceramic membrane filter, and a tertiary ultraviolet sterilization module.

4. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches as described in claim 1, characterized in that, The pipeline confluence flow analysis described in S1 uses a three-dimensional ADV flow meter and a micro differential pressure sensor array in the manhole of the confluence node, combined with laser-induced fluorescence (LIF) technology and high-speed imaging, to capture the three-dimensional velocity, pressure distribution and flow field dynamics of water flow in real time, and analyze complex flow states such as stagnation, deflection and shear in the confluence area, providing data support for pipeline silt reduction and optimization. The pipeline blockage simulation involves dropping 1-20mm particles into the inspection well at the reverse slope node to simulate blockage, while simultaneously monitoring abnormal flow fluctuations and pressure changes. High-speed cameras record the blockage accumulation process, and the impact mechanism of blockage on flow capacity and pressure imbalance is analyzed. The reverse slope drainage capacity test utilizes a hydraulic slope adjustment device to adjust the pipe slope, monitors the flow rate attenuation using a Coriolis flow meter, and combines a fiber optic strain sensor and an ADV flow meter to evaluate the pipe stress distribution and hydraulic performance under reverse slope conditions, revealing the influence law of slope on drainage efficiency. The waterlogging and overflow simulation experiment simulates heavy rainfall inflow through a dual-gradient water supply unit, and intelligent inspection well groups monitor water level changes in real time. Combined with flow rate, velocity and pressure data, it quantifies the critical conditions for waterlogging formation and overflow risk, providing a basis for urban flood control and drainage design.

5. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches according to claim 2, characterized in that, The first branch pipeline (2) is divided into a basic section pipeline and a replaceable section pipeline; the pipe material selection of the replaceable section pipeline includes UPVC smooth pipe, cast iron threaded pipe or 3D printed bionic pipe; the second branch pipeline (3) is equipped with a hydraulic slope changer, the slope adjustment range is -5% to +5%, and the minimum adjustment step is 0.1%; the second branch pipeline (3) is equipped with a fiber optic strain sensor for monitoring pipe stress; a rotatable guide plate is rotatably installed in the reverse slope test node inspection well (4), and a particulate matter dispensing device is installed at the bottom of the reverse slope test node inspection well (4); the confluence node inspection well (5) is made of 10mm thick organic glass, and a three-dimensional ADV flow meter and a micro-differential pressure sensor array are installed in the confluence node inspection well (5); a laser-induced fluorescence observation window is installed on the top of the confluence node inspection well (5).

6. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches according to claim 1, characterized in that, The process of establishing the critical congestion flow prediction model described in S2 includes: preprocessing the simulation experimental data to remove abnormal data, performing statistical analysis on the preprocessed data to obtain characteristic parameters, using dimensional indices to perform flow data analysis on the characteristic parameters, combining the control results to obtain flow prediction results, and then establishing the critical congestion flow prediction model.

7. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches as described in claim 1, characterized in that, The process of testing and training the critical congestion flow prediction model in S3 includes: S3.1 Classify each group of data in the historical data of urban drainage pipe network according to its address and collection time. Each group of data includes the collected data and the control results. S3.2 Establish a three-dimensional model of the urban drainage network, associate each group of classified historical data with the three-dimensional model according to its address, and sort them according to the collection time to construct a four-dimensional model of the urban drainage network. S3.3 Input the collected data from the four-dimensional model into the critical congestion flow prediction model to obtain the predictive control result. Compare the predictive control result with the corresponding actual control result and determine whether to perform iterative training on the model based on the comparison result.

8. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches according to claim 1, characterized in that, The process of comparing the predictive control results with the actual control results as described in S3.3 includes: A preset correct threshold is set, and the percentage of predictive control results that match actual control results is calculated out of all correct predictive control results. This percentage is then compared with the preset correct threshold. If the correct percentage is greater than the correct threshold, the critical congestion flow prediction model is deemed to meet the usage requirements. If the correct percentage is less than the correct threshold, the critical congestion flow prediction model is deemed unsuitable for use, and iterative training is performed on it.

9. The comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches according to claim 1, characterized in that, S4 also includes adding real-time collected on-site data of urban drainage pipe network and corresponding prediction results to the four-dimensional model of urban drainage pipe network, and updating the critical blockage flow prediction model based on the updated data in the four-dimensional model every preset period.

10. A comprehensive hydraulic experimental system for urban drainage pipe networks based on dynamic coupling of two branches, applicable to the comprehensive hydraulic experimental method for drainage pipe networks based on dynamic coupling of two branches as described in any one of claims 1-9, characterized in that, include: The experimental simulation module is used to build a dual-branch dual-gradient dynamic coupling simulation device, and to conduct visual simulation experiments under multi-parameter coupling conditions using the dual-branch dual-gradient dynamic coupling simulation device. The model building module is used to preprocess the simulation experimental data, extract features, obtain the simulation experimental data feature set, and build a critical congestion flow prediction model based on the simulation experimental data feature set. The model training module is used to acquire historical data of urban drainage pipe networks, test and train the critical blockage flow prediction model, and obtain the trained critical blockage flow prediction model. The integrated control module is used to collect data from the urban drainage network in real time, calculate and predict the critical blockage flow rate using the trained model, obtain the prediction results of the urban drainage network, and perform real-time control of the urban drainage network.

Images