Intelligent regulation and control method and system for urban drainage pipe network based on digital twinning

Abstract

The invention discloses an urban drainage pipe network intelligent regulation and control method and system based on digital twinning, and relates to the technical field of urban drainage pipe network regulation and control, and the method comprises the steps: constructing an online calibration digital twinning body based on a hydrodynamic principle and a data assimilation algorithm according to basic physical information and real-time past monitoring data, and carrying out the online calibration of the digital twinning body; then hydraulic simulation is carried out according to real-time past monitoring data and past weather forecast data, and a risk early warning model is constructed; acquiring current real-time monitoring data and current weather forecast data, and inputting the current real-time monitoring data and the current weather forecast data into the risk early warning model to obtain risk early warning information; determining the abnormal state type of the current urban drainage network according to the real-time past monitoring data and the online calibration digital twin; and performing intelligent regulation and control on the urban drainage pipe network according to the abnormal state type and the risk early warning information. According to the invention, abnormal diagnosis of the urban drainage pipe network, predictive early warning of waterlogging risk and global optimization regulation and control of the urban drainage pipe network are realized, and intelligent management of the drainage pipe network is embodied.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of urban drainage pipe network regulation and control, and particularly relates to an urban drainage pipe network intelligent regulation and control method and system based on digital twinning. BACKGROUND

[0002] The urban drainage pipe network is a key infrastructure for ensuring urban public safety. Traditional drainage pipe network management mainly relies on manual inspection, historical data analysis and static hydraulic model simulation, which has the following obvious disadvantages: Hysteresis: It is impossible to real-time perceive the real running state of the pipe network, and the discovery and response to abnormal conditions such as siltation and overload are seriously delayed.

[0003] Lack of foresight: The static model cannot effectively integrate real-time data and weather forecasts, and cannot accurately predict and actively warn of impending waterlogging risks.

[0004] Regulation and control are mainly based on local rules or manual experience, and lack of coordinated scheduling strategies from the perspective of overall optimization of the entire system, resulting in low regulation and control efficiency, and even exacerbating the risk of waterlogging in the local area.

[0005] Digital twinning technology provides a solution to the above problems. However, related applications are mostly limited to simple data mapping level, and the core model is static, which cannot realize continuous, automatic and high-fidelity synchronization with the physical entity, resulting in insufficient credibility of analysis and decision-making based thereon.

[0006] Therefore, there is an urgent need for an urban drainage pipe network intelligent regulation and control method and system based on digital twinning that can truly reflect the dynamic changes of the physical pipe network. SUMMARY

[0007] The present application aims to provide an urban drainage pipe network intelligent regulation and control method and system based on digital twinning, which solves the problems of hysteresis, lack of foresight and estimation of traditional regulation and control methods, and realizes urban drainage pipe network anomaly diagnosis, waterlogging risk predictability warning and control of urban drainage pipe network global optimization regulation and control.

[0008] To achieve the above-mentioned purpose, the present application provides an urban drainage pipe network intelligent regulation and control method based on digital twinning, comprising the following steps: S1, obtaining the basic physical information of the urban drainage pipe network, the real-time past monitoring data of the Internet of Things sensors in the urban drainage pipe network and the past weather forecast data; the basic physical data includes basic geographic information, pipe network attribute information and pipe network facility information; the real-time past monitoring data includes water level and flow; S2, constructing an online calibration digital twin according to the basic physical information and the real-time past monitoring data; S3, data cleaning and denoising are performed on the water level and flow rate respectively to obtain real-time past monitoring sequence data corresponding to the water level and flow rate; S4, a data assimilation algorithm is used to fuse the real-time past monitoring sequence data with the static hydraulic module, and an online calibration digital twin is constructed through calibration; S5, based on the online calibration digital twin, hydraulic simulation is performed according to real-time past monitoring data and past weather forecast data to construct a risk warning model; S6, current real-time monitoring data and current weather forecast data are obtained, and the current real-time monitoring data and the current weather forecast data are input into the risk warning model to obtain risk warning information; S7, according to the real-time past monitoring data and the online calibration digital twin, the abnormal state type of the current urban drainage pipe network is determined; S8, the urban drainage pipe network is intelligently regulated and controlled according to the abnormal state type and the risk warning information.

[0009] Preferably, the basic physical data includes basic geographic information, pipe network attribute information and pipe network facility information; and the real-time past monitoring data includes water level and flow rate.

[0010] Preferably, the specific content of constructing the online calibration digital twin according to the basic physical information and the real-time past monitoring data in S4 includes: a static hydraulic module is constructed based on the principle of hydrodynamics according to the basic geographic information, the pipe network attribute information and the pipe network facility information; data cleaning and denoising are performed on the water level and flow rate respectively to obtain real-time past monitoring sequence data corresponding to the water level and flow rate; a data assimilation algorithm is used to fuse the real-time past monitoring sequence data with the static hydraulic module, and an online calibration digital twin is constructed through calibration.

[0011] Preferably, the specific content of constructing the online calibration digital twin according to the basic physical information and the real-time past monitoring data in S4 includes: a state vector is defined; the state vector includes the water level and flow rate of the urban drainage pipe network; the state vector is taken as an initial condition, and the static hydraulic module is run to obtain a predicted state vector; the real-time past monitoring sequence data is compared with the predicted state vector, the predicted state vector is corrected by calculating a Kalman gain matrix to obtain an optimal state vector, and an online calibration digital twin is obtained.

[0012] Preferably, the specific content of constructing the risk early warning model based on the online calibration digital twin in S5, according to the real-time past monitoring data and past meteorological forecast data, includes: According to the past meteorological forecast data and the online calibration digital twin, performing hydraulic simulation to obtain simulation results; Performing key risk index extraction on the simulation results and risk early warning evaluation to obtain comprehensive evaluation results; According to the comprehensive evaluation results, generating risk early warning information and obtaining a risk early warning model.

[0013] Preferably, the specific content of performing key risk index extraction on the simulation results and risk early warning evaluation to obtain comprehensive evaluation results includes: Extracting key risk indexes in the simulation results; the key risk indexes include: a flooded water depth index, a flooded area index and a flooded time index; Defining a key risk index comprehensive evaluation standard; Obtaining a flooded water depth value, configuring a flooded water depth emphasis conversion coefficient to the flooded water depth value according to the flooded water depth emphasis requirement in the key risk index comprehensive, to obtain a flooded water depth evaluation result; Obtaining a flooded area value, configuring a flooded area emphasis conversion coefficient to the flooded area value according to the flooded area emphasis requirement in the key risk index comprehensive, to obtain a flooded area evaluation result; Obtaining a flooded time value, configuring a flooded time emphasis conversion coefficient to the flooded time value according to the flooded time emphasis requirement in the key risk index comprehensive, to obtain a flooded time evaluation result; Configuring weight coefficients to the flooded water depth evaluation result, the flooded area evaluation result and the flooded time evaluation result respectively, to obtain a comprehensive evaluation value, i.e. a comprehensive evaluation result.

[0014] Preferably, the specific content of generating risk early warning information according to the comprehensive evaluation results and obtaining a risk early warning model includes: If the comprehensive evaluation value is higher than the key risk index comprehensive evaluation standard, it is high risk, and a red warning is generated; If the comprehensive evaluation value meets the key risk index comprehensive evaluation standard, it is medium risk, and a yellow warning is generated; If the comprehensive evaluation value is lower than the key risk index comprehensive evaluation standard, it is low risk, and a blue warning is generated.

[0015] Preferably, the expression of the comprehensive evaluation value is: ; Wherein, H is the comprehensive evaluation value, α is the flooded water depth weight coefficient, a is the flooded water depth emphasis conversion coefficient,D is a submerged water depth value, β is a submerged area weight coefficient, b is a submerged area emphasis conversion coefficient, A is a submerged area value, γ is a submerged time weight coefficient, c is a submerged time emphasis conversion coefficient, T is a submerged time value.

[0016] Preferably, the specific content of determining the abnormal state type of the current urban drainage pipe network in S7 according to the current real-time monitoring data and the online calibration digital twin includes: preset water level threshold and flow threshold; the current real-time monitoring data includes: current water level and current flow; based on the current water level and the current flow, the online calibration digital twin simulation is carried out to obtain the simulated water level and the simulated flow; the current water level and the simulated water level are compared, if the current water level is higher than the simulated water level, and the difference between the water level and the simulated water level is higher than the water level threshold, the urban drainage pipe network is in the abnormal state of pipe deposition; the current flow and the simulated flow are compared, if the current flow is higher than the simulated flow, and higher than the flow threshold, the urban drainage pipe network is in the abnormal state of pipe overload.

[0017] The application also provides an urban drainage pipe network intelligent regulation and control system based on digital twin, comprising: a data acquisition module for acquiring basic physical information of the urban drainage pipe network, real-time past monitoring data and past weather forecast data of Internet of Things sensors in the urban drainage pipe network; the basic physical data includes: basic geographic information, pipe network attribute information and pipe network facility information; the real-time past monitoring data includes: water level and flow; a module construction module for constructing a static water power module based on the basic geographic information, the pipe network attribute information and the pipe network facility information according to the principle of water dynamics; a sequence data acquisition module for respectively performing data cleaning processing and denoising processing on the water level and the flow to obtain real-time past monitoring sequence data corresponding to the water level and the flow; a twin construction module for adopting a data assimilation algorithm to fuse the real-time past monitoring sequence data with the static water power module, and constructing an online calibration digital twin through calibration; a model construction module for constructing a risk warning model based on the online calibration digital twin according to the real-time past monitoring data and the past weather forecast data, and performing water simulation; a risk prediction module configured to obtain current real-time monitoring data and current weather forecast data, and input the current real-time monitoring data and the current weather forecast data into a risk early warning model to obtain risk early warning information; a state determination module configured to determine an abnormal state type of the current urban drainage pipe network according to the real-time past monitoring data and the online calibration digital twin; an intelligent regulation and control module configured to intelligently regulate and control the urban drainage pipe network according to the abnormal state type and the risk early warning information.

[0018] In summary, the present application provides an urban drainage pipe network intelligent regulation and control method and system based on digital twinning, which has the following beneficial effects compared with the traditional technology: the data assimilation algorithm is used to fuse the real-time past monitoring sequence data and the static hydraulic module, the online calibration digital twin constructed by calibration is always synchronized with the urban drainage pipe network, and a reliable data basis is provided; based on the online calibration digital twin, the risk early warning model is constructed according to the real-time past monitoring data and the past weather forecast data, which realizes the transition from passive response to active early warning, and saves valuable time for emergency response; the abnormal state type of the current urban drainage pipe network is determined through the real-time past monitoring data and the online calibration digital twin, which can automatically and accurately locate deep abnormalities such as pipe clogging and pipe overload, and guide precise operation and maintenance; the urban drainage pipe network is intelligently regulated and controlled according to the risk early warning model and the determined abnormal state type of the current urban drainage pipe network, which solves the problems of lag, lack of predictability and estimation of the traditional regulation and control method, realizes the abnormal diagnosis of the urban drainage pipe network, the predictability early warning of waterlogging risk and the overall optimization regulation and control of the urban drainage pipe network, and embodies the integrity, full-process intelligentization and automation of the drainage pipe network management.

[0019] The technical solutions of the present application will be further described in detail below with the aid of the accompanying drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a flowchart of an urban drainage pipe network intelligent regulation and control method based on digital twinning; Figure 2 is a module schematic diagram of an urban drainage pipe network intelligent regulation and control system based on digital twinning. DETAILED DESCRIPTION

[0021] The technical method of the present application will be further described below with the aid of the accompanying drawings and examples. It should be noted that: unless otherwise specifically stated, the relative arrangement, numerical expression and values of the components and steps set forth in these examples do not limit the scope of the present application.

[0022] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way limiting to the scope of the application or its applications or uses.

[0023] Techniques, systems, and devices known to those of ordinary skill in the relevant art can not be discussed in detail, but should be considered part of the specification.

[0024] In all of the examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not limiting. Thus, other examples of the exemplary embodiments can have different values.

[0025] Unless otherwise defined, technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0026] The present application provides a digital twin-based intelligent control method for urban drainage pipe network, as shown in Figure 1 The method comprises the following steps: Step S1, obtaining the basic physical information of the urban drainage pipe network, the real-time past monitoring data of the Internet of Things sensor in the urban drainage pipe network, and the past meteorological forecast data. The basic physical data includes basic geographic information, pipe network attribute information, and pipe network facility information; the real-time past monitoring data includes water level and flow.

[0027] Step S2, based on the principle of hydrodynamics, constructing a static hydraulic module according to the basic geographic information, the pipe network attribute information, and the pipe network facility information. The one-dimensional simulation of the drainage pipe network mainly uses the principle of hydrodynamics described by the Saint-Venant equation set. The Saint-Venant equation set contains two partial differential equations, which are based on the law of conservation of mass and the law of conservation of momentum in physics, respectively. The expression of the Saint-Venant equation set is: ; Wherein, A is the cross-sectional area of the water, Q is the flow, t is the time, x is the distance along the flow direction, g is the acceleration of gravity, h is the water depth, S f is the friction slope.

[0028] Step S3, respectively performing data cleaning processing and denoising processing on the water level and the flow to obtain real-time past monitoring sequence data corresponding to the water level and the flow.

[0029] Step S4, using a data assimilation algorithm to fuse the real-time past monitoring sequence data with the static hydraulic module, and constructing an online calibration digital twin through calibration. Specifically, the specific content of step S4 includes: Step S401, defining a state vector. The state vector includes the water level and the flow of the urban drainage pipe network.

[0030] Step S402, running the static hydraulic module with the state vector as the initial condition to obtain a predicted state vector.

[0031] Step S403, comparing the real-time past monitoring sequence data with the predicted state vector, correcting the predicted state vector by calculating the Kalman gain matrix to obtain an optimal state vector, and obtaining an online calibration digital twin.

[0032] The present application uses the ensemble Kalman filter data assimilation algorithm to realize the transformation of the digital twin from static and display to intelligent core capable of autonomous learning, continuous calibration and high-fidelity reflection of reality, solves the problem of disconnection between the static hydraulic module and the data, and constitutes the decisive difference of the present application from only data visualization or fixed model simulation. The online calibration digital twin constructed deeply integrates data, model and physical world, and creates an intelligent agent capable of synchronous perception, deep cognition, scientific prediction, intelligent decision and autonomous evolution.

[0033] Step S5, based on the online calibration digital twin, performing hydraulic simulation according to real-time past monitoring data and past weather forecast data to construct a risk warning model.

[0034] Further, the specific content of step S5 includes: Step S501, performing hydraulic simulation according to past weather forecast data and the online calibration digital twin to obtain simulation results.

[0035] Step S502, extracting key risk indicators from the simulation results and performing risk warning evaluation to obtain a comprehensive evaluation result. The specific content of step S502 includes: Extracting key risk indicators from the simulation results. The key risk indicators include: submergence water depth indicator, submergence area indicator and submergence time indicator.

[0036] Defining the comprehensive evaluation standard of the key risk indicators.

[0037] Obtaining the submergence water depth value, configuring a submergence water depth emphasis conversion coefficient to the submergence water depth value according to the submergence water depth emphasis requirement in the key risk indicator comprehensive, and obtaining a submergence water depth evaluation result.

[0038] Obtaining the submergence area value, configuring a submergence area emphasis conversion coefficient to the submergence area value according to the submergence area emphasis requirement in the key risk indicator comprehensive, and obtaining a submergence area evaluation result.

[0039] Obtaining the submergence time value, configuring a submergence time emphasis conversion coefficient to the submergence time value according to the submergence time emphasis requirement in the key risk indicator comprehensive, and obtaining a submergence time evaluation result.

[0040] The evaluation result of the submerged water depth, the evaluation result of the submerged area and the evaluation result of the submerged time are respectively configured with a weight coefficient to obtain a comprehensive evaluation value, that is, a comprehensive evaluation result. ; Among them, H is the comprehensive evaluation value, α is the submerged water depth weight coefficient, a is the submerged water depth emphasis conversion coefficient, D is the submerged water depth value, β is the submerged area weight coefficient, b is the submerged area emphasis conversion coefficient, A is the submerged area value, γ is the submerged time weight coefficient, c is the submerged time emphasis conversion coefficient, T is the submerged time value.

[0041] Step S503, according to the comprehensive evaluation result, generate risk warning information, and obtain a risk warning model.

[0042] Further, the specific content of step S503 includes: If the comprehensive evaluation value is higher than the comprehensive evaluation standard of the key risk index, it is high risk, and a red warning is generated.

[0043] If the comprehensive evaluation value meets the comprehensive evaluation standard of the key risk index, it is medium risk, and a yellow warning is generated.

[0044] If the comprehensive evaluation value is lower than the comprehensive evaluation standard of the key risk index, it is low risk, and a blue warning is generated.

[0045] The risk warning model constructed by the present application not only sends an alarm signal, but also can convert data assets and advanced models into actual productivity and safety protection, giving managers the eyes to foresee the future and the brain to make scientific decisions, and ultimately achieving the comprehensive goal of protecting people's life and property safety, improving urban operation efficiency and optimizing fiscal expenditure.

[0046] Step S6, acquire current real-time monitoring data and current weather forecast data, and input the current real-time monitoring data and the current weather forecast data into the risk warning model to obtain risk warning information.

[0047] Step S7, according to real-time past monitoring data and online calibration digital twin, determine the abnormal state type of the current urban drainage pipe network.

[0048] Further, the specific content of step S7 includes: Step S701, presetting a water level threshold and a flow threshold. The current real-time monitoring data includes a current water level and a current flow.

[0049] Step S702, based on the current water level and the current flow, performing online calibration of a digital twin simulation to obtain a simulated water level and a simulated flow.

[0050] Step S703, comparing the current water level with the simulated water level, if the current water level is higher than the simulated water level, and the difference between the water level and the simulated water level is higher than the water level threshold, the urban drainage pipe network is in an abnormal state of pipe sedimentation.

[0051] Step S704, comparing the current flow with the simulated flow, if the current flow is higher than the simulated flow, and higher than the flow threshold, the urban drainage pipe network is in an abnormal state of pipe overload.

[0052] The present application realizes precise operation and maintenance by determining the abnormal state type of the current urban drainage pipe network from problem discovery to problem positioning. Moreover, different types of abnormalities have different risk levels and disposal urgency, and the determination of the abnormal state type of the current urban drainage pipe network realizes the optimization of resource allocation, improves the precision, initiative and efficiency of operation and maintenance, and completely changes the traditional mode of relying on manual experience and extensive management. It is the core embodiment of the true wisdom of the intelligent drainage system.

[0053] Step S8, intelligently regulating and controlling the urban drainage pipe network according to the abnormal state type and risk warning information.

[0054] The present application realizes precise matching of regulation and control strategy and specific problems by intelligently regulating and controlling the urban drainage pipe network according to the abnormal state type and risk warning information, avoids blind operation, realizes precise operation and maintenance from the whole system, and can adjust the strategy in real time according to the real-time state and warning, has strong adaptability, and based on the model and algorithm, the decision-making process changes from experience to data and model driving, which is more objective and reliable. The present application changes the drainage pipe network from a static infrastructure that needs manual intervention into an intelligent system that can perceive, analyze, decide and optimize itself.

[0055] The present application provides an intelligent regulation and control system for urban drainage pipe network based on digital twin, as shown in Figure 2 , comprising: A data acquisition module is configured to acquire basic physical information of the urban drainage pipe network, real-time past monitoring data of Internet of Things sensors in the urban drainage pipe network, and past meteorological forecast data. The basic physical data includes basic geographic information, pipe network attribute information and pipe network facility information; the real-time past monitoring data includes water level and flow.

[0056] A module construction module is configured to construct a static hydraulic module based on a water dynamics principle, according to basic geographic information, pipe network attribute information and pipe network facility information.

[0057] A sequence data acquisition module is configured to perform data cleaning processing and denoising processing on the water level and the flow, respectively, to obtain real-time past monitoring sequence data corresponding to the water level and the flow.

[0058] A twin construction module is configured to fuse the real-time past monitoring sequence data and the static hydraulic module by using a data assimilation algorithm, to construct an online calibration digital twin through calibration.

[0059] A model construction module is configured to construct a risk early warning model by performing hydraulic simulation based on the online calibration digital twin, according to real-time past monitoring data and past weather forecast data.

[0060] A risk prediction module is configured to obtain current real-time monitoring data and current weather forecast data, and input the current real-time monitoring data and the current weather forecast data into the risk early warning model to obtain risk early warning information.

[0061] A state determination module is configured to determine an abnormal state type of the current urban drainage pipe network according to the real-time past monitoring data and the online calibration digital twin.

[0062] An intelligent regulation and control module is configured to intelligently regulate and control the urban drainage pipe network according to the abnormal state type and the risk early warning information.

[0063] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application but not to limit it, although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that: it can still modify or equivalently replace the technical solutions of the present application, and these modifications or equivalent replacements cannot make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. A digital-twin-based intelligent regulation and control method for urban drainage networks, characterized in that, The method comprises the following steps: S1, acquiring basic physical information of a city drainage pipe network, real-time past monitoring data of Internet of Things sensors in the city drainage pipe network, and past meteorological forecast data; The basic physical data comprises basic geographic information, pipe network attribute information, and pipe network facility information; the real-time past monitoring data comprises water level and flow rate; S2, based on the principle of water dynamics, a static water power module is constructed according to the basic geographic information, the pipe network attribute information, and the pipe network facility information; S3, data cleaning processing and denoising processing are respectively performed on the water level and the flow rate to obtain real-time past monitoring sequence data corresponding to the water level and the flow rate; S4, a data assimilation algorithm is used to fuse the real-time past monitoring sequence data and the static water power module, and an online calibration digital twin is constructed through calibration; S5, based on the online calibration digital twin, water simulation is performed according to the real-time past monitoring data and the past meteorological forecast data, and a risk early warning model is constructed; S6, current real-time monitoring data and current meteorological forecast data are acquired, and the current real-time monitoring data and the current meteorological forecast data are input into the risk early warning model to obtain risk early warning information; S7, according to the real-time past monitoring data and the online calibration digital twin, the abnormal state type of the current city drainage pipe network is determined; S8, the city drainage pipe network is intelligently regulated and controlled according to the abnormal state type and the risk early warning information.

2. The urban drainage network intelligent regulation and control method based on digital twinning according to claim 1, characterized in that, In S4, the specific content of using the data assimilation algorithm to fuse the real-time past monitoring sequence data and the static water power module, and constructing the online calibration digital twin through calibration comprises: a state vector is defined; the state vector comprises the water level and the flow rate of the city drainage pipe network; the state vector is taken as an initial condition, and the static water power module is run to obtain a predicted state vector; the real-time past monitoring sequence data is compared with the predicted state vector, the predicted state vector is corrected through calculation of a Kalman gain matrix to obtain an optimal state vector, and an online calibration digital twin is obtained.

3. The urban drainage network intelligent regulation and control method based on digital twinning according to claim 1, characterized in that, In S5, the specific content of performing water simulation based on the online calibration digital twin according to the real-time past monitoring data and the past meteorological forecast data, and constructing a risk early warning model comprises: water simulation is performed according to the past meteorological forecast data and the online calibration digital twin to obtain simulation results; key risk indicators in the simulation results are extracted, and risk early warning evaluation is performed to obtain comprehensive evaluation results; risk early warning information is generated according to the comprehensive evaluation results, and a risk early warning model is obtained.

4. The urban drainage network intelligent regulation and control method based on digital twinning according to claim 3, characterized in that, The specific content of extracting key risk indicators from the simulation results and performing risk early warning evaluation to obtain comprehensive evaluation results comprises: key risk indicators in the simulation results are extracted; the key risk indicators comprise a submerged water depth indicator, a submerged area indicator, and a submerged time indicator; a key risk indicator comprehensive evaluation standard is defined; a submerged water depth value is acquired, a submerged water depth emphasis conversion coefficient is configured to the submerged water depth value according to a submerged water depth emphasis requirement in the key risk indicator comprehensive evaluation to obtain a submerged water depth evaluation result; a submerged area value is acquired, a submerged area emphasis conversion coefficient is configured to the submerged area value according to a submerged area emphasis requirement in the key risk indicator comprehensive evaluation to obtain a submerged area evaluation result; The submergence time value is obtained, a submergence time emphasis conversion coefficient is configured to the submergence time value according to the submergence time emphasis requirement in the key risk indicator synthesis, and a submergence time evaluation result is obtained; The submergence depth evaluation result, the submergence area evaluation result and the submergence time evaluation result are respectively configured with weight coefficients, and a comprehensive evaluation value, that is, a comprehensive evaluation result, is obtained.

5. The urban drainage network intelligent regulation and control method based on digital twinning according to claim 4, characterized in that, According to the comprehensive evaluation result, risk early warning information is generated, and the specific content of the risk early warning model includes: If the comprehensive evaluation value is higher than the key risk indicator comprehensive evaluation standard, it is high risk, and a red warning is generated; If the comprehensive evaluation value meets the key risk indicator comprehensive evaluation standard, it is medium risk, and a yellow warning is generated; If the comprehensive evaluation value is lower than the key risk indicator comprehensive evaluation standard, it is low risk, and a blue warning is generated.

6. The urban drainage network intelligent regulation and control method based on digital twinning according to claim 4, characterized in that, The expression of the comprehensive evaluation value is: ； wherein, H is a comprehensive evaluation value, α is a submerged water depth weight coefficient, a is a submerged water depth emphasis conversion coefficient, D is a submerged water depth value, β is a submerged area weight coefficient, b is a submerged area emphasis conversion coefficient, A is a submerged area value, γ is a submerged time weight coefficient, c is a submerged time emphasis conversion coefficient, T is a submerged time value.

7. The urban drainage network intelligent regulation and control method based on digital twinning according to claim 3, characterized in that, In S7, the specific content of determining the abnormal state type of the current urban drainage pipe network according to the current real-time monitoring data and the online calibration digital twin includes: Pre-set water level threshold and flow threshold; the current real-time monitoring data includes: current water level and current flow; Based on the current water level and the current flow, the online calibration digital twin simulation is performed to obtain the simulated water level and the simulated flow; The current water level and the simulated water level are compared, if the current water level is higher than the simulated water level, and the difference between the water level and the simulated water level is higher than the water level threshold, the urban drainage pipe network is in the abnormal state of pipe deposition; The current flow and the simulated flow are compared, if the current flow is higher than the simulated flow, and higher than the flow threshold, the urban drainage pipe network is in the abnormal state of pipe overload.

8. A digital-twin-based intelligent regulation and control system for urban drainage networks, characterized in that, It includes: A data acquisition module for acquiring basic physical information of the urban drainage pipe network, real-time past monitoring data and past meteorological forecast data of the Internet of Things sensor in the urban drainage pipe network; The basic physical data includes: basic geographic information, pipe network attribute information and pipe network facility information; the real-time past monitoring data includes: water level and flow; A module construction module for constructing a static hydraulic module based on the principle of hydrodynamics according to the basic geographic information, the pipe network attribute information and the pipe network facility information; A sequence data acquisition module for performing data cleaning and denoising processing on the water level and the flow respectively to obtain real-time past monitoring sequence data corresponding to the water level and the flow; A twin construction module for fusing the real-time past monitoring sequence data with the static hydraulic module by using a data assimilation algorithm to construct an online calibration digital twin through calibration; A model construction module for constructing a risk early warning model based on the online calibration digital twin according to the real-time past monitoring data and the past meteorological forecast data; A risk prediction module for acquiring current real-time monitoring data and current meteorological forecast data, and inputting the current real-time monitoring data and the current meteorological forecast data into the risk early warning model to obtain risk early warning information; A state determination module for determining the abnormal state type of the current urban drainage pipe network according to the real-time past monitoring data and the online calibration digital twin; An intelligent control module for intelligently controlling the urban drainage pipe network according to the abnormal state type and the risk early warning information.

Images