Ecological infiltration and intelligent diversion coordinated management method of sponge city drainage pipeline

Abstract

This invention discloses a sponge city drainage pipeline management method based on ecological infiltration and coordinated intelligent diversion, belonging to the field of intelligent and water conservancy synergy technology. This method acquires dynamic data of the entire sponge city drainage network, performs feature fusion and extraction on the data through an ecological network collaborative analytical model, obtains a multi-dimensional collaborative parameter set, inputs this multi-dimensional collaborative parameter set into a dynamic diversion decision model, and combines it with a preset runoff control target threshold to generate network diversion control commands and ecological infiltration facility control commands, achieving coordinated dynamic management and control of network runoff and ecological infiltration. This invention uses an analytical model that couples unsaturated soil seepage theory with the hydraulic laws of the network, extracts multi-dimensional collaborative parameters using an attention mechanism, and then generates precise commands through multi-objective optimization and a condition-adaptive decision model. This enables the linkage of multiple actuators to achieve dynamic adaptation of network ecological facilities, taking into account runoff reduction, pollution removal, and energy consumption optimization, breaking through the limitations of traditional static management.

Description

Technical Field

[0001] This invention relates to the field of intelligent and water conservancy synergy technology, specifically to a sponge city drainage pipeline management method with ecological infiltration synergy and intelligent diversion. Background Technology

[0002] With the continuous advancement of urbanization, the proportion of impervious urban areas has increased significantly. Traditional drainage systems rely excessively on centralized drainage structures, leading to a surge in rainwater runoff, imbalance in the hydrological cycle, and increased risks of urban flooding and water pollution. There is an urgent need for efficient rainwater management technologies to achieve the dual goals of flood control and ecological protection.

[0003] Chinese patent (publication number: CN118260892A) discloses a comprehensive stormwater management design method combining low-impact development (LID) with urban drainage pipelines. This invention aims to reduce the environmental impact of urbanization by simulating natural hydrological processes, while simultaneously improving the efficiency and sustainability of urban drainage systems. Through ingenious design, this invention can divert stormwater runoff of varying intensities into dedicated LID facilities and site water retention facilities, achieving both flood relief and environmental benefits. The specific design process includes coordinating the elevation of side ditches (collection wells) and LID facility drainage pipe outlets, inspecting and designing retention ponds, and controlling inflow and outflow. This invention can balance environmental benefits and flood reduction effects, providing a comprehensive stormwater management solution. However, this method mainly relies on static design logic of elevation adaptation and facility combination, failing to achieve dynamic perception and coordinated control of pipeline runoff and the status of ecological infiltration facilities. It is difficult to cope with complex and variable rainfall conditions and lacks deep data fusion and intelligent decision-making mechanisms, resulting in limited control accuracy and adaptability.

[0004] To address the structural modeling deficiencies in existing patents and the need for dynamic regulation, Chinese patent (publication number: CN116950197A) proposes a distributed hierarchical interception and diversion control method and system for urban drainage networks. This method includes establishing two main pipelines and water storage facilities. The water storage facilities are used to store polluted water sources and low-pollution or even unpolluted water sources, respectively. The two main pipelines are connected to the polluted water source storage facilities and the low-pollution water source storage facilities, respectively. Branch pipelines are also established. Branch pipelines with significantly higher levels of water pollution are differentiated according to the water source and installed on the corresponding main pipelines. Branch pipelines with less significant water pollution are connected to both main pipelines. By simultaneously using a hierarchical interception and diversion control system to control the opening and closing of electric valves in the branch pipelines, drainage efficiency can be improved, thus preventing urban flooding. Furthermore, it allows for more effective classification of urban drainage, saving time and effort while also making more efficient use of water resources. This scheme focuses on tiered interception within the pipeline network, without establishing a deep collaborative mechanism with ecological infiltration facilities. It lacks consideration of core state parameters of ecological facilities such as soil infiltration characteristics, and the decision-making logic revolves only around flow rate and water quality, without taking into account the multi-objective optimization needs such as energy consumption control. Therefore, it cannot achieve the optimal comprehensive efficiency at the system level of the pipeline network ecological facilities.

[0005] Therefore, there is an urgent need for a sponge city drainage pipeline management method that integrates ecological infiltration and intelligent diversion, which can deeply couple the hydraulic characteristics of the pipeline network with the ecological infiltration law, and realize dynamic collaborative control of sponge city drainage pipeline management through intelligent models, so as to solve the bottleneck of existing technologies. Summary of the Invention

[0006] Based on the above-mentioned technical problems, this application discloses a sponge city drainage pipeline management method with ecological infiltration and collaborative intelligent diversion, which specifically includes: acquiring dynamic data of the entire scenario of the sponge city drainage network, wherein the dynamic data includes a first core data and a second core data, wherein the first core data is real-time runoff characteristic data of the pipeline node; and the second core data is ecological infiltration facility status data.

[0007] The first core data and the second core data are fused and extracted by the ecological pipeline network collaborative analysis model to obtain a multi-dimensional collaborative parameter set. The ecological pipeline network collaborative analysis model is constructed based on the coupling of the unsaturated soil seepage theory and the hydraulic transmission law of the pipeline network.

[0008] The multi-dimensional collaborative parameter set is input into the dynamic diversion decision model, and combined with the preset runoff control target threshold, intelligent diversion command parameters are generated. The dynamic diversion decision model is constructed based on a multi-objective optimization algorithm and a real-time operating condition adaptive adjustment mechanism.

[0009] Based on the intelligent diversion command parameters, pipeline diversion control commands and ecological infiltration facility regulation commands are generated;

[0010] By using an edge computing gateway, control commands are sent to the intelligent diversion valves of the drainage network, the drainage pumps of the ecological infiltration facilities, and the infiltration layer dredging devices, respectively, to achieve coordinated dynamic control of network runoff and ecological infiltration.

[0011] Preferably, the first core data includes runoff flow. Pollutant concentration Water flow velocity and runoff temperature The data is collected synchronously using a distributed ultrasonic flow meter, an optical water quality sensor, an electromagnetic flow meter, and a temperature sensor; the second core data includes the water content of the permeable layer. Degree of pore blockage Soil permeability coefficient and facility water storage capacity The data is collected by a time domain reflectometer, an ultrasonic tomography scanner, a seepage sensor, and a liquid level sensor. Both types of data carry GPS timestamps, ensuring high synchronization accuracy.

[0012] Preferably, the construction of the ecological pipeline network collaborative analysis model includes a seepage hydraulic coupling module and a feature fusion module, which achieves data fusion and extraction of a multi-dimensional collaborative parameter set through coupling formulas: ,in, For the first A multidimensional collaborative parameter, , , These are the coupling weight coefficients. For the hydraulic gradient of ecological infiltration facilities, The cross-sectional area of ​​the pipeline network, For pipeline roughness, As the reference runoff temperature, The attenuation coefficient is determined by the effect of temperature.

[0013] Preferably, the seepage hydraulic coupling module constructs the seepage equation based on the unsaturated soil seepage theory: ,in, , , They are respectively , , Soil permeability coefficient in the direction of direction, For time, The total head is used; simultaneously, the pipe flow equation is constructed by combining the hydraulic transmission law of the pipe network: ,in, The lateral inflow rate per unit length of the pipeline network is represented by two types of equations, which are used to achieve dynamic coupling between ecological infiltration and pipeline hydraulics.

[0014] Preferably, the feature fusion module of the ecological pipeline network collaborative analysis model employs an attention mechanism to enhance the weight of key data, and calculates the attention weight using the following formula: ,in, For the first Significance score of class data , For the first Feature values ​​of class data , This is the rating coefficient. The total number of data types is represented by the multiplication of the attention weight and coupling weight coefficients, which are then used in the calculation of the multidimensional collaborative parameter set.

[0015] Preferably, the multi-objective optimization algorithm of the dynamic diversion decision model aims to maximize runoff emission reduction rate, maximize pollutant removal rate, and minimize facility energy consumption, and constructs the objective function as follows: ,in, These are decision variables, including diversion ratios and facility operating parameters. , These are the inflow and outflow rates of the pipeline network, respectively. These are the influent pollutant concentration and the effluent pollutant concentration, respectively. Energy consumption for facility operation For maximum allowable energy consumption, , , The target weight coefficient.

[0016] Preferably, the real-time adaptive adjustment mechanism of the dynamic diversion decision model is implemented through operating condition identification coefficients: ,in, Design flow rate for pipeline network, The soil saturation water content, This is the weighting coefficient for the operating conditions.

[0017] Preferably, the preset runoff control target threshold is set based on pipeline network safety operation standards, the carrying capacity of ecological infiltration facilities, and environmental emission requirements, specifically including pipeline network safe flow threshold. Maximum water storage threshold for ecological infiltration facilities Pollutant emission concentration thresholds .

[0018] Preferably, the intelligent traffic splitting command parameters include a traffic splitting ratio. Diverter valve opening Drainage pump operating frequency and the start interval of the dredging device The diversion ratio Calculated using the following formula: ,in To adjust the time step, V represents the current water storage capacity of the ecological infiltration facility, serving as a safety factor.

[0019] Preferably, the edge computing gateway uses the lightweight IoT communication MQTT protocol to transmit control commands, and the commands include command type identifier, parameter values, execution time and check code; the intelligent diversion valve is an electric regulating ball valve, and the permeation layer unblocking device uses a high-pressure pulse flushing method.

[0020] Compared with the prior art, the technical solution of this application has the following technical effects:

[0021] This invention couples the theory of unsaturated soil seepage with the hydraulic laws of the pipe network through an ecological pipe network collaborative analysis model, and strengthens the weight of key data by combining the attention mechanism, accurately extracting multi-dimensional collaborative parameters, breaking the limitations of data fragmentation in traditional management, making runoff regulation and ecological infiltration more compatible, improving the comprehensive efficiency of the sponge city drainage system from the source, and realizing deep collaborative management and control of pipe network and ecological facilities.

[0022] This invention possesses adaptive intelligent decision-making capabilities based on operating conditions. The dynamic diversion decision model is based on a multi-objective optimization algorithm. It switches operating modes in real time through operating condition identification coefficients to balance the needs of runoff reduction, pollutant removal, and energy consumption control. It can adapt to different rainfall scenarios without human intervention, significantly improving the intelligence level and operational stability of drainage pipeline management.

[0023] This invention constructs a closed-loop control system for the entire process, from dual-core data acquisition and feature fusion analysis to intelligent command generation and linkage with the execution mechanism. It relies on the edge computing gateway to achieve efficient transmission of control commands and synchronously regulate diversion valves, drainage pumps and dredging devices, effectively solving problems such as blockage of infiltration facilities and imbalance of runoff distribution, and ensuring long-term stable operation of the system.

[0024] This invention enhances the precision and versatility of regulation. Through coupled formulas and multi-module collaborative calculations, it achieves refined parameter analysis and precise command issuance, adapting to sponge city projects with different pipe materials, soil types, and facility layouts. It does not require significant modifications to existing pipe networks, has low promotion and application costs, and provides flexible and efficient management technology support for sponge city construction.

[0025] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the preferred embodiments of this application are described in detail below with reference to the accompanying drawings.

[0026] The above and other objects, advantages and features of this application will become more apparent to those skilled in the art from the following detailed description of specific embodiments of this application in conjunction with the accompanying drawings. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0028] Based on the description of the figures and their corresponding technical content in the document, the titles of the figures are as follows:

[0029] Figure 1 A schematic diagram of the overall process of the sponge city drainage pipeline management method based on ecological infiltration and intelligent diversion;

[0030] Figure 2 Ecological pipeline network collaborative analysis model architecture diagram;

[0031] Figure 3 Dynamic triage decision-making model architecture diagram;

[0032] Figure 4 Schematic diagram of the time-series evolution curve of runoff reduction rate and water storage capacity of ecological infiltration facilities;

[0033] Figure 5 : Schematic diagram of dynamic control curve with a 24-hour start-up interval;

[0034] Figure 6 : Schematic diagram of the iterative convergence curve of the objective function value and constraint satisfaction of the dynamic diversion decision model;

[0035] Figure 7 Schematic diagram of the spectrum distribution of the multidimensional collaborative parameter set. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. In the following description, specific details such as specific configurations and components are provided merely to help fully understand the embodiments of this application. Therefore, those skilled in the art should understand that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. In addition, for clarity and brevity, descriptions of known functions and structures are omitted in the embodiments.

[0037] It should be understood that the phrase "an embodiment" or "this embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "an embodiment" or "this embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0038] Furthermore, reference numerals and / or letters may be repeated in different examples within this application. Such repetition is for the purpose of simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or settings discussed.

[0039] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" in this article describes another type of relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " in this article generally indicates that the related objects before and after it are in an "or" relationship.

[0040] In this article, the term "at least one" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, "at least one of A and B" can mean: A exists alone, A and B exist simultaneously, or B exists alone.

[0041] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion.

[0042] Example 1

[0043] This embodiment mainly describes a sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion, such as... Figure 1 As shown, this specifically includes: acquiring dynamic data of the entire scenario of the sponge city drainage network, wherein the dynamic data includes a first core data and a second core data, wherein the first core data is real-time runoff characteristic data of the network nodes; and the second core data is ecological infiltration facility status data.

[0044] The first core data and the second core data are fused and extracted by the ecological pipeline network collaborative analysis model to obtain a multi-dimensional collaborative parameter set. The ecological pipeline network collaborative analysis model is constructed based on the coupling of the unsaturated soil seepage theory and the hydraulic transmission law of the pipeline network.

[0045] The multi-dimensional collaborative parameter set is input into the dynamic diversion decision model, and combined with the preset runoff control target threshold, intelligent diversion command parameters are generated. The dynamic diversion decision model is constructed based on a multi-objective optimization algorithm and a real-time operating condition adaptive adjustment mechanism.

[0046] Based on the intelligent diversion command parameters, a pipe network diversion control command and an ecological infiltration facility regulation command are generated. The control commands are then sent to the intelligent diversion valve of the drainage pipe network, the drainage pump of the ecological infiltration facility, and the infiltration layer dredging device through the edge computing gateway, so as to realize the coordinated dynamic management and control of pipe network runoff and ecological infiltration.

[0047] Furthermore, the first core data collection is carried out at key nodes of the pipeline network, including the intersection of the main pipeline network, the node where the branch road connects to the main pipeline, and the node where the ecological infiltration facility connects. A total of 32 data collection units are deployed. Each unit integrates a distributed ultrasonic flow meter, an optical water quality sensor, an electromagnetic flow meter, and a temperature sensor. The sensors are installed in the pipeline well, parallel to the pipeline axis, with the sampling direction facing the water flow direction to ensure the accuracy of data collection.

[0048] The second core data collection is carried out in ecological infiltration facilities such as rain gardens, permeable pavement strips and underground infiltration tanks. 28 status monitoring units are deployed according to the principle of layering and zoning. Among them, time domain reflectometers are deployed with one detection point every 30cm along the depth of the infiltration layer, ultrasonic tomography scanners are installed in the middle of the side wall of the facility, seepage sensors are deployed in the drainage layer at the bottom of the facility, and liquid level sensors are installed on the top of the inner wall of the underground infiltration tank.

[0049] An edge computing gateway is deployed in the pipeline control center to establish a main communication link with the data acquisition unit and actuators via wired fiber optics. At the same time, a wireless IoT backup link is provided. The actuators include 16 intelligent diversion valves for drainage pipelines, installed in the connecting pipe sections of the ecological infiltration facilities and the pipeline network, 8 drainage pumps for ecological infiltration facilities, deployed at the bottom of the underground infiltration tank, and 12 infiltration layer dredging devices, corresponding to rain gardens and permeable pavement strips.

[0050] In the ecological pipeline network collaborative analysis model, the coupling weight coefficient =0.4、 =0.35、 =0.25, reference runoff temperature Set according to the local average annual surface runoff temperature; temperature effect attenuation coefficient. Adjusted dynamically according to the season, summer =0.04 ,winter =0.06 Pipeline cross-sectional area The roughness of the pipeline network is determined based on the design drawings of the corresponding pipe section. Designated according to pipe type, concrete pipe =0.013, HDPE pipe ;

[0051] Target weight coefficients of dynamic diversion decision model , , ,satisfy Working condition weighting coefficient Pipeline design flow rate Calculated based on the intensity of a 50-year return period rainstorm in the local area; soil saturation moisture content Based on on-site soil sampling tests, the sandy soil... =0.32, silty soil =0.41;

[0052] Pipeline safe flow threshold Set at 80% of the maximum allowable flow capacity of the pipeline network; maximum water storage threshold for ecological infiltration facilities. The effective volume of the facility is 85%; pollutant emission concentration threshold. The control limits for surface runoff pollutants shall be implemented in accordance with GB / T51347-2019 "Evaluation Standard for Sponge City Construction".

[0053] Furthermore, the first core data collection: runoff flow. Pollutant concentration Water flow velocity Runoff temperature (T) is synchronously collected by corresponding sensors at a preset frequency. The collected data is then appended with a GPS timestamp in real time to ensure data synchronization across different nodes. After outliers are removed by the sensor's built-in preprocessing module, the collected data is transmitted to the edge computing gateway.

[0054] Second core data acquisition: Water content of the permeable layer Degree of pore blockage Soil permeability coefficient and facility water storage capacity The data was collected according to the principle of zoned sampling, including the water content of the permeable layer. Samples were collected every 5 minutes to measure the degree of pore blockage. Soil permeability coefficient was collected once every hour. Collected once daily, facility water storage capacity Real-time data collection, with timestamps added to the collected data to maintain time synchronization accuracy with the primary core data;

[0055] Furthermore, the construction of the ecological pipeline network collaborative analysis model includes a seepage hydraulic coupling module and a feature fusion module, such as... Figure 2 As shown, the seepage hydraulic coupling module calculates the seepage equation based on the unsaturated soil seepage theory, combined with the collected water content of the permeable layer. Soil permeability coefficient ,calculate , , Soil permeability coefficient in the direction , , Then, the total head can be calculated. Spatial distribution and rate of change over time Meanwhile, the pipe flow equations constructed based on the hydraulic transmission laws of the pipe network, combined with runoff flow rate... Pipeline cross-sectional area Calculate the lateral inflow rate per unit length of pipeline network based on the data. By simultaneously solving the seepage equation and the pipe flow equation, the dynamic coupling of ecological infiltration and pipe network hydraulics is achieved;

[0056] The feature fusion module uses an attention mechanism to calculate the saliency scores of various data types. Among them, the rating coefficient , Set according to data type (corresponding to runoff flow and facility storage capacity) =0.7、 =0.3, the corresponding values ​​for the remaining data =0.6、 =0.4), based on Calculate attention weights Combine it with the coupling weight coefficient , , After multiplying, substitute into the coupling formula: A multidimensional collaborative parameter set containing 8 parameters was extracted. The parameters correspond to core dimensions such as the coupling strength of pipeline ecological facilities, runoff transmission efficiency, and permeability adaptability.

[0057] Furthermore, such as Figure 3As shown, operating condition identification uses runoff flow rate from a multi-dimensional collaborative parameter set. Water content of the permeable layer Substitute into the formula for the working condition identification coefficient: ,when When the value is greater than 1.2, the dynamic diversion decision model switches to the rainstorm emergency mode; when the value is less than or equal to 0.8... When ≤1.2, switch to normal collaboration mode; when When the concentration is less than 0.8, switch to water conservation mode;

[0058] Multi-objective optimization decision-making: Based on the current operating mode, with the objectives of maximizing runoff emission reduction rate, maximizing pollutant removal rate, and minimizing facility energy consumption, the following is substituted into the objective function: The decision variables are solved using a multi-objective optimization algorithm. To obtain the diversion ratio Diverter valve opening Drainage pump operating frequency and the start interval of the dredging device Intelligent traffic splitting command parameters, including the splitting ratio. Through the formula: The adjustment time step was calculated. =5min, safety factor =0.9;

[0059] The edge computing gateway generates pipeline diversion control commands and ecological infiltration facility regulation commands based on intelligent diversion command parameters. The commands include command type identifiers, such as diversion valve regulation and dredging device start-up, parameter values, such as valve opening degree of 60% and pump operating frequency of 30Hz, execution time, and check code commands. The commands are sent to the corresponding actuators via the MQTT protocol. During the transmission process, the check code is used to verify the integrity of the commands.

[0060] The intelligent diversion valve adjusts its valve core position according to the opening command, achieving precise allocation of pipeline runoff to the ecological infiltration facility; the drainage pump adjusts its output power according to the operating frequency command, controlling the water storage volume within the ecological infiltration facility; the infiltration layer unblocking device periodically removes blockages from the pores of the infiltration layer using high-pressure pulse flushing according to the start interval command, ensuring stable infiltration performance. After the actuator completes its action, it transmits a status feedback signal to the edge computing gateway, forming a closed-loop control.

[0061] Furthermore, the emergency mode for heavy rain ( >1.2), when encountering heavy rain and a surge in pipe network runoff, the model prioritizes ensuring the pipe network's drainage capacity, and the intelligent diversion command parameter is set as follows: diversion ratio. =0.3, only 30% of the runoff enters the ecological infiltration facility, and the diversion valve opening is... =40%, Drainage pump operating frequency =50Hz (full load operation), dredging device start-up interval =1h (shortening the interval to ensure unobstructed infiltration channels), by reducing the total amount of runoff entering the ecological facilities and accelerating the drainage speed of the facilities, water accumulation in the pipe network and overflow of the facilities are avoided;

[0062] Standard collaborative mode (0.8≤ (≤1.2), under normal rainfall or runoff conditions, the model balances runoff emission reduction and ecological infiltration efficiency. Diversion ratio =0.7 (70% of runoff enters the ecological infiltration facility), diversion valve opening =70%, Drainage pump operating frequency =25Hz, dredging device start-up interval =6h. By fully utilizing the infiltration and purification functions of ecological infiltration facilities, runoff reduction and pollutant removal are achieved, while controlling facility energy consumption;

[0063] Water conservation and conservation model ( <0.8), under conditions of little or no rain, the model prioritizes increasing the water storage capacity of ecological infiltration facilities to provide water for greening irrigation and groundwater recharge. Diversion ratio =1.0 (all runoff enters the ecological infiltration facility), diversion valve opening =100%, the drainage pump stops running. =0Hz), dredging device start interval =24h. By maximizing the water storage capacity of ecological facilities, water resources can be recycled.

[0064] This embodiment achieves coordinated dynamic management and control of the drainage network and ecological infiltration facilities in sponge cities through the above steps, effectively improving runoff reduction efficiency, pollutant removal effect and facility operation stability, and can provide a replicable implementation reference for sponge city projects with different climates and different network conditions.

[0065] Example 2, based on Example 1, to comprehensively verify the practical application effect of the sponge city drainage pipeline management method of ecological infiltration and intelligent diversion of the present invention, a sponge city renovation project in an old urban area in a temperate monsoon climate zone was selected as the verification scenario. The pipeline network covers an area of ​​5 km², with 12 rain gardens, 8 permeable pavement strips and 6 underground infiltration tanks constructed. The verification period is 12 months, covering different rainfall conditions in spring, summer, autumn and winter. The method of the present invention is used for dynamic management throughout the process. Through multi-dimensional data collection and analysis, the runoff control effect, facility coordination efficiency and operational stability of the method are systematically evaluated.

[0066] In the early stages of verification, the entire system was calibrated and data acquisition equipment was deployed. Data was collected simultaneously at 32 key nodes in the pipeline network and 28 monitoring points of the ecological infiltration facilities. All sensors underwent three-level precision calibration, with data synchronization accuracy ≤1ms, ensuring the authenticity and reliability of the collected data. During the verification process, four core indicators were monitored: runoff reduction rate, pollutant removal rate, facility energy consumption, and control response time. At the same time, the changes in pipeline network operation status and ecological infiltration facility parameters under different rainfall intensities were recorded. A total of 1.28 million valid data points were collected and used for effect analysis after preprocessing.

[0067] To visually demonstrate the core performance advantages of the method of this invention, statistical analysis was performed on key indicator data during the verification period, resulting in the statistical results of the core performance indicators shown in Table 1. In the table, RRR (Runoff Reduction Rate) is the runoff reduction rate, PRR (Pollutant Removal Rate) is the pollutant removal rate, E (Energy Consumption) is the average daily energy consumption per unit area of ​​the facility, RT (Response Time) is the control response time, and CV (Coefficient of Variation) is the coefficient of variation, reflecting the stability of the data. The data in the table show that under different rainfall intensity levels, this method… The invention's method achieves an average RRR of 78.6%, with the highest reaching 85.3% under moderate rain conditions, 72.8% under light rain conditions, and maintaining a high level of 77.7% under heavy rain conditions. Furthermore, the CV value is only 3.2%, demonstrating excellent runoff regulation stability. The average PRR values ​​for the three main pollutants—COD, TN, and TP—are 76.2%, 68.5%, and 82.3%, respectively, with CV values ​​all below 5%, indicating stable and efficient pollutant removal. The average daily energy consumption per unit area of ​​the facility is only 0.86 kWh / 100 m², with minimal energy consumption fluctuations under different operating conditions (CV = 4.1%). The average regulation response time is 42 ms, with the fastest response time being only 28 ms, fully meeting the requirements for real-time control.

[0068] Table 1 Statistical Results of Core Performance Indicators

[0069] Rainfall Intensity Level RRR (%) - Mean ± SD RRR-CV (%) PRR-COD (%) - Mean ± SD PRR-TN (%) - Mean ± SD PRR-TP (%) - Mean ± SD E (kWh / 100m²) - Mean ± SD E-CV (%) RT (ms) - mean ± SD RT-CV (%) Light rain (<10mm / d) 72.8±2.1 2.9 71.5±3.2 63.2±2.8 78.6±2.5 0.72±0.03 4.2 38±5 13.2 Moderate rain (10-25 mm / d) 77.7±2.6 2.8 80.1±2.7 72.3±3.1 86.7±2.3 0.85±0.04 4.7 43±6 14.0 Heavy rain (25-50 mm / day) 77.7±2.6 3.3 75.8±3.0 67.9±2.9 81.5±2.7 0.98±0.05 5.1 47±7 14.9 Heavy rain (>50mm / d) 70.2±3.1 4.4 67.3±3.5 61.1±3.3 76.8±3.0 1.12±0.06 5.4 53±8 15.1 Overall mean 78.6±3.0 3.2 76.2±3.3 68.5±3.2 82.3±2.8 0.86±0.04 4.1 42±7 14.3

[0070] In verifying the dynamic characteristics of runoff regulation, data from a continuous 30-day period of frequent moderate rainfall were selected to analyze the temporal relationship between runoff regulation rate (RRR) and the water storage capacity of ecological infiltration facilities. Figure 4As shown in the figure, this graph contains two curves. The upper curve is the time-series evolution curve of RRR (Regular Rate of Retention), and the lower curve is the time-series evolution curve of the average water storage capacity of the ecological infiltration facility. The horizontal axis represents the number of monitoring days (1-30 days), the left vertical axis represents RRR (%), and the right vertical axis represents water storage capacity (m³). It can be clearly seen from the graph that the RRR time-series curve generally remains in the high range of 80%-88%, with only slight decreases on days 12 and 25 due to a sudden increase in short-term rainfall intensity, dropping to 76.3% and 77.1% respectively. However, it quickly recovered to over 80% within 1 hour, demonstrating the rapid regulation capability of the method of this invention. The water storage curve of the ecological infiltration facility and the RRR curve showed a significant synergistic change trend. The water storage was maintained between 60% and 80% of the effective volume. When the water storage approached the 80% threshold, the RRR increased accordingly. When the water storage was below 60%, the RRR decreased slightly, verifying the synergistic control effect of pipeline runoff and ecological infiltration facilities. The Pearson correlation coefficient between the two reached 0.87, indicating good synergy.

[0071] To analyze the parameter fusion effect of the ecological pipeline network collaborative analysis model, a spectral analysis was performed on the core data of a typical moderate rainy day (daily rainfall of 18 mm), such as... Figure 5 As shown in the figure, this graph contains three spectral curves, corresponding to the spectral distribution of the first core data (runoff flow), the second core data (permeable layer water content), and the multidimensional collaborative parameter set, respectively. The horizontal axis represents frequency (Hz), and the vertical axis represents spectral amplitude (dB). The graph shows that the runoff flow data spectrum is mainly concentrated in the 0.01-0.1Hz frequency band, with three distinct peaks at 0.03Hz, 0.06Hz, and 0.09Hz, corresponding to the periodic fluctuations of runoff. The permeable layer water content data spectrum is concentrated in the 0.005-0.05Hz frequency band, with peaks at 0.02Hz and 0.04Hz. The multidimensional collaborative parameter set spectrum curve is smooth, with peaks concentrated in the 0.02-0.07Hz frequency band, effectively integrating the spectral characteristics of the two types of core data while suppressing high-frequency noise (the spectral amplitude at frequencies > 0.1Hz is reduced by more than 20dB compared to the original data). This demonstrates that the model can effectively extract key features and eliminate interfering information, providing high-quality parameter support for subsequent decision-making.

[0072] The multi-objective optimization performance of the dynamic diversion decision model was verified using iterative convergence curves. A complete control process under heavy rain conditions was selected, such as... Figure 6As shown in the figure, there are two curves: the iterative evolution curve of the objective function value and the iterative evolution curve of the constraint satisfaction. The horizontal axis represents the number of iterations (1-50), the left vertical axis represents the objective function value (dimensionless), and the right vertical axis represents the constraint satisfaction (%). It can be observed from the figure that the objective function value decreases rapidly in the early stage of iteration, from the initial value of 0.62 to 0.85 in the first 10 iterations. After that, the rate of decrease slows down, reaching 0.92 in the 30th iteration and stabilizing. The final convergence value is 0.93, indicating that the model can quickly find the optimal decision solution. The constraint satisfaction curve rises synchronously with the objective function value curve, increasing from 65% to 82% in the first 5 iterations, stabilizing above 98% after the 25th iteration, and finally reaching 99.2%. This proves that the model can fully satisfy multiple constraints such as pipeline safety, facility load-bearing capacity, and energy consumption control during the optimization process, and achieve multi-objective collaborative optimization.

[0073] To evaluate the effectiveness of control commands under different operating conditions, dynamic adjustment data on the opening degree of the intelligent diversion valve, the operating frequency of the drainage pump, and the start-up interval of the permeable layer unblocking device were analyzed. Figure 7 As shown, the graph contains three curves, corresponding to the temporal changes in valve opening (%), pump operating frequency (Hz), and dredging device start-up interval (h). The horizontal axis represents time (0-24h), the left vertical axis represents valve opening (%) and pump operating frequency (Hz), and the right vertical axis represents dredging device start-up interval (h). The graph shows that from 0-6:00 is the rainless period, with valve opening maintained at 100%, pump operating frequency at 0Hz, and dredging device start-up interval at 24h, indicating a water-saving and conservation mode. From 6:00-14:00 is the rainfall period, with... As rainfall increased, the valve opening was gradually adjusted from 100% to 70%, the pump operating frequency increased from 0Hz to 25Hz, and the dredging device activation interval was shortened to 6 hours, switching to the normal coordinated mode. From 2 PM to 6 PM, rainfall surged (hourly rainfall intensity reached 15mm), the valve opening was rapidly adjusted to 40%, the pump operating frequency increased to 50Hz, and the dredging device activation interval was shortened to 1 hour, switching to the rainstorm emergency mode. After 6 PM, rainfall decreased, and all parameters gradually returned to the level of the normal coordinated mode, returning to the water conservation mode after 10 PM. Throughout the entire control process, the parameters of various actuators were adjusted smoothly and responded promptly, highly adapting to changes in operating conditions, verifying the adaptive control capability of the method of this invention.

[0074] Based on the above verification results, the method of this invention achieves efficient collaborative management and control of the drainage network and ecological infiltration facilities of sponge cities through the collaborative operation of the ecological pipeline network collaborative analysis model and the dynamic diversion decision model. It exhibits excellent runoff reduction effect, pollutant removal capacity, energy consumption control level and regulation response speed under different rainfall conditions. All core performance indicators are stable and reliable, fully meeting the actual needs of sponge city construction and possessing broad application value.

[0075] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. For those skilled in the art, the present invention can have various modifications and variations. Any changes, modifications, substitutions, integrations, and parameter changes made to these embodiments within the spirit and principles of the present invention, without departing from the principles and spirit of the present invention, through conventional substitutions or to achieve the same function, fall within the scope of protection of the present invention.

Claims

1. A sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion, characterized in that, include: Acquire dynamic data of the entire scenario of the sponge city drainage network. The dynamic data includes a first core data and a second core data. The first core data is real-time runoff characteristic data of the network nodes; the second core data is status data of ecological infiltration facilities. The first core data and the second core data are fused and extracted by the ecological pipeline network collaborative analysis model to obtain a multi-dimensional collaborative parameter set. The ecological pipeline network collaborative analysis model is constructed based on the coupling of the unsaturated soil seepage theory and the hydraulic transmission law of the pipeline network. The multi-dimensional collaborative parameter set is input into the dynamic diversion decision model, and combined with the preset runoff control target threshold, intelligent diversion command parameters are generated. The dynamic diversion decision model is constructed based on a multi-objective optimization algorithm and a real-time operating condition adaptive adjustment mechanism. Based on the intelligent diversion command parameters, pipeline diversion control commands and ecological infiltration facility regulation commands are generated; By using an edge computing gateway, control commands are sent to the intelligent diversion valves of the drainage network, the drainage pumps of the ecological infiltration facilities, and the infiltration layer dredging devices, respectively, to achieve coordinated dynamic control of network runoff and ecological infiltration.

2. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 1, characterized in that, The first core data includes runoff flow. Pollutant concentration Water flow velocity and runoff temperature The data is collected synchronously using a distributed ultrasonic flow meter, an optical water quality sensor, an electromagnetic flow meter, and a temperature sensor; the second core data includes the water content of the permeable layer. Degree of pore blockage Soil permeability coefficient and facility water storage capacity The data is collected by a time domain reflectometer, an ultrasonic tomography scanner, a seepage sensor, and a liquid level sensor. Both types of data carry GPS timestamps, ensuring high synchronization accuracy.

3. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 1, characterized in that, The construction of the ecological pipeline network collaborative analysis model includes a seepage hydraulic coupling module and a feature fusion module. Data fusion is achieved through coupling formulas to extract a multi-dimensional collaborative parameter set. ,in, For the first A multidimensional collaborative parameter, , , These are the coupling weight coefficients. For the hydraulic gradient of ecological infiltration facilities, The cross-sectional area of ​​the pipeline network, For pipeline roughness, As the reference runoff temperature, The attenuation coefficient is determined by the effect of temperature.

4. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 3, characterized in that, The seepage hydraulic coupling module constructs the seepage equation based on the unsaturated soil seepage theory: ,in, , , They are respectively , , Soil permeability coefficient in the direction of direction, For time, The total head is used; simultaneously, the pipe flow equation is constructed by combining the hydraulic transmission law of the pipe network: ,in, The lateral inflow rate per unit length of the pipeline network is represented by two types of equations, which are used to achieve dynamic coupling between ecological infiltration and pipeline hydraulics.

5. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 3, characterized in that, The feature fusion module of the ecological pipeline network collaborative analysis model uses an attention mechanism to strengthen the weight of key data, and the attention weight is calculated by the following formula: ,in, For the first Significance score of class data , For the first Feature values ​​of class data , This is the rating coefficient. The total number of data types is represented by the multiplication of the attention weight and coupling weight coefficients, which are then used in the calculation of the multidimensional collaborative parameter set.

6. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 1, characterized in that, The multi-objective optimization algorithm of the dynamic diversion decision model aims to maximize runoff emission reduction rate, maximize pollutant removal rate, and minimize facility energy consumption, and constructs the objective function as follows: ,in, These are decision variables, including diversion ratios and facility operating parameters. , These are the inflow and outflow rates of the pipeline network, respectively. These are the influent pollutant concentration and the effluent pollutant concentration, respectively. Energy consumption for facility operation For maximum allowable energy consumption, , , The target weight coefficient.

7. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 5, characterized in that, The real-time adaptive adjustment mechanism of the dynamic diversion decision model is achieved through operating condition identification coefficients: ,in, Design flow rate for pipeline network, The soil saturation water content, This is the weighting coefficient for the operating conditions.

8. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 1, characterized in that, The preset runoff control target threshold is set based on pipeline network safety operation standards, the carrying capacity of ecological infiltration facilities, and environmental emission requirements, specifically including pipeline network safe flow threshold. Maximum water storage threshold for ecological infiltration facilities Pollutant emission concentration thresholds .

9. The sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 1, characterized in that, The intelligent traffic splitting command parameters include the traffic splitting ratio. Diverter valve opening Drainage pump operating frequency and the start interval of the dredging device The diversion ratio Calculated using the following formula: ,in To adjust the time step, V represents the current water storage capacity of the ecological infiltration facility, serving as a safety factor.

10. A sponge city drainage pipeline management method with ecological infiltration and coordinated intelligent diversion according to claim 1, characterized in that, The edge computing gateway uses the lightweight IoT communication MQTT protocol to transmit control commands. The commands include command type identifier, parameter values, execution time, and checksum. The intelligent diversion valve is an electrically adjustable ball valve, and the permeation layer unblocking device uses a high-pressure pulse flushing method.

Images