Chlorination method and apparatus for water supply network

Abstract

The application provides a water supply network chlorination method and device, which is applied to a water supply network intelligent chlorination system based on digital twinning and microbial risk early warning, and relates to the technical field of drinking water treatment. By establishing a digital twinning model and real-time microbial activity monitoring, the defects of traditional chlorination technology, such as lag, extensive and neglect of biological safety, are overcome. Based on real-time data driving the digital twinning model, advanced rolling prediction of the residual chlorine concentration at the end of the pipe network is realized, so that the control is changed from passive response to active intervention. The optimal chlorination amount is reversely solved by taking the continuous compliance of the predicted residual chlorine at all end points as a constraint, so that precise addition is realized and global excess is avoided. According to the microbial activity data, the control target is dynamically switched, and a double safety barrier of chemistry and biology is established. Periodic closed-loop execution ensures that the system is self-adaptive to the working condition change. While significantly improving the reliability of end water quality, the drug consumption and disinfection by-product risk are reduced, and the unity of safety and economy is realized.

Description

Technical Field

[0001] This invention relates to the field of drinking water treatment technology, and in particular to a method and apparatus for chlorinating a water supply network. Background Technology

[0002] Chlorine disinfection is a crucial step in ensuring the safety of municipal water supply and preventing the spread of waterborne diseases. Its core function is to maintain continuous disinfection capabilities during pipeline transportation, inhibit microbial regeneration, and ensure water quality at the point of contact. To achieve effective control of residual chlorine in the pipeline network, the industry has developed a series of technologies.

[0003] Initially, the commonly used control model was a static, experience-based approach based on the water plant outlet. This involved adding chlorine at a fixed ratio or setting a fixed residual chlorine target value according to the outflow of water from the plant. This method was crude and often resulted in excessively high residual chlorine levels at nearby users in order to ensure water quality at the distant end of the pipe network. This also led to the growth of disinfection byproducts and a complete lack of awareness of changes within the pipe network, resulting in severely delayed control actions.

[0004] To improve upon the above approach, a feedback control mode with intermediate monitoring points has emerged, adjusting the chlorination dosage based on the residual chlorine values ​​at several measured points in the pipeline network. However, this method suffers from limited monitoring point coverage, high costs, and is essentially still a "remedial measure," exhibiting time delays and failing to achieve preventative control.

[0005] With technological advancements, intelligent control technologies based on hydraulic models, water quality models, or mechanistic models have emerged, enabling feedforward control by predicting changes in residual chlorine levels in the pipe network. However, these models often rely on complex algorithms (such as LSTM neural networks) or sophisticated hydraulic calculations, requiring high levels of data, calibration, and computing power, resulting in significant implementation complexity. Furthermore, they generally lack online monitoring and linkage of direct microbiological indicators such as ATP and total bacterial count, posing a safety hazard of "residual chlorine levels meeting standards but microorganisms still remaining active." In addition, most technologies still focus on optimization within water plants or at a single end point, failing to deeply coordinate water plant chlorination with pipe network scheduling to form a complete intelligent control chain.

[0006] Furthermore, the secondary chlorination technology used in long-distance pipelines faces challenges such as difficulty in coordinating the timing and dosage of chlorination, and an increased total amount of disinfection byproducts.

[0007] In summary, existing technologies are evolving from static control to dynamic prediction, but they still generally face core challenges such as the contradiction between control accuracy and coverage, the disconnect between chemical indicators and biological safety, and insufficient local optimization and global coordination. Therefore, there is a need for an intelligent chlorination method that can directly target the water quality safety at the end of the pipe network, integrate hydraulic dynamic prediction and microbial risk early warning, and achieve coordinated operation across the entire pipe network. Summary of the Invention

[0008] The purpose of this invention is to provide a method and apparatus for chlorinating water supply networks. By establishing a digital twin model and real-time microbial activity monitoring, it overcomes the shortcomings of traditional chlorination technologies, such as being slow, inefficient, and neglecting biosafety. Based on a real-time data-driven digital twin model, it achieves advanced rolling prediction of residual chlorine concentration at the end of the network, transforming control from passive response to active intervention. By using the continuous achievement of residual chlorine standards at all end points as a constraint, it solves the optimal chlorination dosage in reverse, achieving precise dosing and avoiding global over-chlorination. It dynamically switches control targets based on microbial activity data, establishing a dual safety barrier of chemical and biological components. Periodic closed-loop execution ensures the system adapts to changes in operating conditions. While significantly improving the reliability of water quality assurance at the end points, it reduces the risks of chemical consumption and disinfection byproducts, achieving a balance between safety and economy.

[0009] In a first aspect, the present invention provides a method for chlorinating a water supply network, applied to an intelligent chlorination system for a water supply network based on digital twins and microbial risk early warning. The method includes: performing the following steps in a preset cycle:

[0010] Acquire real-time data from the water supply network; the real-time data includes: real-time hydraulic data, real-time water quality data, and real-time microbial activity data;

[0011] A digital twin model based on real-time data and constructed from basic data of the water supply network is used to predict the distribution of residual chlorine concentration at the end monitoring points of the water supply network within a preset time period. The digital twin model is coupled with a dynamic residual chlorine decay model, and the dynamic decay coefficient of the dynamic residual chlorine decay model is dynamically determined by water temperature, total organic carbon concentration, flow velocity and biofilm activity status on the pipe wall.

[0012] The microbial risk status is determined based on real-time microbial activity data, and the dynamic residual chlorine control target at the terminal monitoring point is determined based on the judgment results.

[0013] With the constraint that the predicted residual chlorine concentration at the terminal monitoring point meets its corresponding dynamic residual chlorine control target, the optimal chlorination dosage for the treated water is solved by an optimization algorithm.

[0014] Based on the optimal chlorination dosage for the treated water, control commands are generated for the chlorination device, and the device is controlled to perform chlorine dosing.

[0015] In some preferred embodiments of the present invention, the real-time hydraulic data includes at least one of the following: instantaneous flow rate of water effluent from the water plant, effluent pressure from the water plant, real-time pressure of key nodes, flow rate of key nodes, opening degree of key valves, start-stop status of pumping stations, and operating frequency of pumping stations; wherein, key nodes include at least one of the following: pumping stations, pressure zone boundaries, and large water users; and key valves include at least one of the following: zone isolation valves, pressure regulating valves, and flow distribution valves.

[0016] In some preferred embodiments of the present invention, real-time water quality data and real-time microbial activity data are acquired based on preset sensors; wherein, the sensors include: a first-line residual chlorine sensor, a turbidity sensor and a pH meter deployed at the water plant outlet; a second-line residual chlorine sensor, an online microbial early warning sensor, an ATP fluorescence detector and a flow cytometer deployed at key feature points; the key feature points include at least one of the following: the location farthest from the water plant in the water supply network, the location with the highest terrain in the water supply network and the location with the longest water age in the water supply network.

[0017] In some preferred embodiments of the present invention, the dynamic residual chlorine decay model is constrained based on the following formula:

[0018] ;

[0019] in, This is the dynamic attenuation coefficient; Let be the residual chlorine concentration at time t; This represents the initial residual chlorine concentration at the water plant outlet.

[0020] In some preferred embodiments of the present invention, the dynamic attenuation coefficient is constrained based on the following formula:

[0021] ;

[0022] in, This is the dynamic attenuation coefficient; The reference attenuation constant at 20℃; [T] represents the temperature correction factor; [T] represents the real-time water temperature; [TOC] represents the total organic carbon concentration; [U] represents the flow rate; and [Biofilm] represents the biofilm activity state on the pipe wall. This is the first weighting coefficient; This is the second weighting coefficient; This is a random item.

[0023] In some preferred embodiments of the present invention, the biofilm activity state of the tube wall is dynamically calibrated based on feedback information at multiple time scales, including:

[0024] Based on historical pipeline maintenance data and seasonal water temperature variation patterns, a baseline prediction of the biofilm activity status on the pipe wall is generated.

[0025] The value of biofilm activity status and its growth parameters in the tube wall are dynamically corrected based on the comparison between real-time microbial activity monitoring data of key feature points and baseline predictions of corresponding areas.

[0026] In some preferred embodiments of the present invention, the optimal chlorination dosage for treated water is calculated using the following formula:

[0027] ;

[0028] ; ;

[0029] ;

[0030] in, The optimal chlorination dosage for treated water; For the i-th terminal node in the future prediction time domain within Predicted residual chlorine at any given time; The target residual chlorine concentration; As a weight for energy saving; This is the minimum effective value; These are preset standard safety limits; This is a preset safety margin; The preset warning conditions indicate whether a microbial warning is triggered.

[0031] In some preferred embodiments of the present invention, the control commands of the chlorination device are constrained by the following formula:

[0032] ;

[0033] ;

[0034] in, To control the amount of chlorine added corresponding to the control command; The first control parameter characterizes the proportional gain; The second control parameter represents the ratio of proportional gain to integral time. The third control parameter represents the product of the proportional gain and the derivative time. This is the chlorination setpoint; This is the feedback value from the online residual chlorine sensor at the water plant outlet; It is a feedforward quantity for predicting information based on a digital twin model.

[0035] In some preferred embodiments of the present invention, the first control parameter, the second control parameter, and the third control parameter are all adaptively switched based on the operating condition zone to which the real-time influent flow belongs.

[0036] Secondly, the present invention provides a chlorination device for a water supply network, applicable to an intelligent chlorination system for a water supply network based on digital twins and microbial risk early warning. The device includes the following modules that are executed on a rolling basis according to a preset cycle:

[0037] The real-time data acquisition module is used to acquire real-time data from the water supply network; the real-time data includes: real-time hydraulic data, real-time water quality data, and real-time microbial activity data.

[0038] The residual chlorine prediction module is used to drive a digital twin model based on the basic data of the water supply network, which is used to predict the distribution of residual chlorine concentration at the end monitoring points in the water supply network within a preset time period. The digital twin model is coupled with a dynamic residual chlorine decay model. The dynamic decay coefficient of the dynamic residual chlorine decay model is dynamically determined by water temperature, total organic carbon concentration, flow velocity and biofilm activity status on the pipe wall.

[0039] The control target determination module is used to determine the microbial risk status based on real-time microbial activity data and determine the dynamic residual chlorine control target at the terminal monitoring point based on the judgment result.

[0040] The chlorination dosage determination module is used to solve the optimal chlorination dosage for treated water by means of an optimization algorithm, which takes the predicted residual chlorine concentration at the terminal monitoring point as a constraint that the corresponding dynamic residual chlorine control target is met.

[0041] The instruction determination module is used to generate control instructions for the chlorination device based on the optimal chlorination dosage for the treated water, and to control the chlorination device to perform chlorine dosing.

[0042] This invention brings the following beneficial effects:

[0043] This invention provides a method and apparatus for chlorinating a water supply network, applied to an intelligent chlorination system for a water supply network based on digital twins and microbial risk early warning. The method includes: executing the following steps in a preset cycle: acquiring real-time data of the water supply network; wherein, the real-time data includes: real-time hydraulic data, real-time water quality data, and real-time microbial activity data; driving a digital twin model constructed based on the basic data of the water supply network based on the real-time data, to predict the distribution of residual chlorine concentration at the end monitoring points of the water supply network within a preset time period; wherein, the digital twin model is coupled with a dynamic residual chlorine decay model, and the dynamic decay of the dynamic residual chlorine decay model... The coefficients are dynamically determined by water temperature, total organic carbon concentration, flow velocity, and the activity state of the biofilm on the pipe wall. The microbial risk status is judged based on real-time microbial activity data, and the dynamic residual chlorine control target at the terminal monitoring point is determined based on the judgment results. With the predicted residual chlorine concentration at the terminal monitoring point meeting its corresponding dynamic residual chlorine control target as a constraint, the optimal chlorination dosage for the treated water is solved through an optimization algorithm. Based on the optimal chlorination dosage for the treated water, control instructions for the chlorination device are generated, and the chlorination device is controlled to perform chlorine dosing. By establishing a digital twin model and real-time microbial activity monitoring, the shortcomings of traditional chlorination technology, such as lag, extensiveness, and neglect of biosafety, are overcome. Based on a real-time data-driven digital twin model, the system enables proactive rolling prediction of residual chlorine concentration at the end of the pipe network, transforming control from a passive response to active intervention. By using the continuous achievement of residual chlorine standards at all end points as a constraint, the optimal chlorination dosage is solved in reverse, achieving precise dosing and avoiding global overdose. Dynamic switching of control targets based on microbial activity data establishes a dual safety barrier of chemical and biological components. Periodic closed-loop execution ensures the system adapts to changes in operating conditions. While significantly improving the reliability of water quality assurance at the end points, the system reduces chemical consumption and disinfection byproduct risks, achieving a balance between safety and economy. Attached Figure Description

[0044] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0045] Figure 1 A schematic diagram of a smart chlorination system for water supply networks based on digital twins and microbial risk early warning, provided for an embodiment of the present invention;

[0046] Figure 2 A flowchart of a chlorination method for a water supply network is provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of a chlorination device for a water supply network provided in an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0049] Icons: 310 - Real-time data acquisition module; 320 - Residual chlorine prediction module; 330 - Control target determination module; 340 - Chlorine dosage determination module; 350 - Instruction determination module; 400 - Memory; 401 - Processor; 402 - Bus; 403 - Communication interface. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0051] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0052] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0053] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of this invention is in use. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention. In addition, the terms "first," "second," "third," etc., are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0054] Furthermore, terms such as "horizontal," "vertical," and "sag" do not imply that components must be absolutely horizontal or suspended, but rather that they can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal relative to "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0055] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0056] The following detailed description of some embodiments of the present invention is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0057] Example 1

[0058] This invention provides a chlorination method for water supply networks, applied to an intelligent chlorination system for water supply networks based on digital twins and microbial risk early warning. See [link to relevant documentation]. Figure 1 The diagram shown is a schematic of an intelligent chlorination system for water supply networks based on digital twins and microbial risk early warning, provided by an embodiment of the present invention. The system adopts a three-layer architecture design, from bottom to top: multi-source information perception layer, digital twin and intelligent decision-making layer, and execution and control layer.

[0059] The multi-source information perception layer, acting as the system's "sensory nerves," is responsible for collecting various types of data from the physical pipeline network in real time, and its output forms the basis for upper-level decision-making. This layer consists of basic data units, real-time hydraulic data units, and real-time water quality sensing units. Among them, the basic data units store the inherent attribute data of the water supply network that does not change frequently over time, forming the system's static archive and serving as the spatial and physical foundation for constructing the digital twin model.

[0060] The digital twin and intelligent decision-making layer is the "intelligent brain" of the system. It constructs a dynamic digital twin in virtual space that is synchronized and interactively mapped with the physical pipeline network in real time, and performs simulation, prediction and optimization decisions on this basis.

[0061] The execution and control layer is the "limbs" and "peripheral nerves" of the system, responsible for accurately translating decision-making instructions into control actions of physical devices.

[0062] These three layers work together to form a closed-loop control system of "continuous perception - dynamic prediction - intelligent decision-making - precise execution". For example... Figure 1 As shown, the data flow converges upward from the bottom perception layer to the decision layer, and the instructions generated by the decision layer are then transmitted downward to the execution layer, acting on the physical pipeline network to form a complete intelligent control closed loop.

[0063] See Figure 2The flowchart shown in this embodiment of the invention provides a method for chlorinating a water supply network. The method includes: performing the following steps in a preset cycle:

[0064] Step S102: Obtain real-time data of the water supply network; wherein, the real-time data includes: real-time hydraulic data, real-time water quality data and real-time microbial activity data.

[0065] Specifically, corresponding Figure 1 The "Multi-Source Information Sensing Layer" is the core of the system. This layer is the data foundation for precise control, aiming to capture the operational status of the water supply network in a comprehensive and real-time manner. First, the system relies on its static archive—the basic data unit. This unit stores the inherent attribute data of the network system necessary for building the digital twin model, including: 1) Topology: the connection relationship map between nodes (water plants, pumping stations, users, monitoring points) and pipelines in the network; 2) Pipe material and diameter: the material (e.g., cast iron, steel, PVC, cement) and internal diameter of each pipe; 3) Pipe roughness: coefficients determined based on pipe material and service life (e.g., the Hayzen-Williams coefficient), used to calculate pipe friction loss; 4) Geographic information: the geographic coordinates (GIS data) of pipelines, nodes, and user points, used for spatial positioning and visualization. This static data forms the "genetic map" for model construction. Based on this static foundation, the sensing layer, through integrated sensors and monitoring systems, simultaneously collects three types of dynamic data: hydraulic, water quality, and microbial activity data, thus providing comprehensive and timely input for building and driving a high-fidelity digital twin. By constructing a comprehensive information sensing network that integrates static "genetic maps" with dynamic real-time data, the system not only possesses the foundation for describing the physical structure of the pipeline network but also can capture its operational pulses in real time. This solves the pain points of traditional control modes, such as weak model foundations, single data dimensions, and slow updates, providing a solid and complete data foundation for achieving accurate and forward-looking predictions and closed-loop control.

[0066] Furthermore, in some preferred embodiments of the present invention, the real-time hydraulic data includes at least one of the following: instantaneous flow rate of water effluent from the water plant, effluent pressure from the water plant, real-time pressure of key nodes, flow rate of key nodes, opening degree of key valves, start / stop status of pumping stations, and operating frequency of pumping stations; wherein, key nodes include at least one of the following: pumping stations, pressure zone boundaries, and large water users; and key valves include at least one of the following: zone isolation valves, pressure regulating valves, and flow distribution valves.

[0067] Specifically, these data are Figure 1The core content of the "real-time hydraulic data unit" in the perception layer collectively characterizes the "pulsation" of water flow in the pipe network and its human-mandated scheduling status. Water treatment plant effluent data serves as the source boundary conditions for model calculations; pressure and flow at key nodes reflect the distribution and losses within the pipe network; while valve opening and pump station status (start / stop, frequency) directly reflect human or automatic scheduling interventions, belonging to the system's "control variables." Collecting this comprehensive hydraulic condition data, especially the status information of controllable equipment, is to combine it with static foundation data to accurately construct and drive the digital twin hydraulic model, enabling it to realistically reflect the transient flow field and water age distribution of the physical pipe network. Based on the static pipe network topology, by acquiring comprehensive real-time hydraulic conditions, including the status of controllable equipment, the digital twin model can perform accurate hydraulic balance calculations, simulating the actual flow field and water age distribution. This provides crucial, dynamic hydraulic boundary conditions for the accurate prediction of subsequent residual chlorine decay, overcoming the prediction distortion problems caused by ambiguous, static, or missing boundary conditions in traditional models.

[0068] Furthermore, in some preferred embodiments of the present invention, real-time water quality data and real-time microbial activity data are acquired based on preset sensors; wherein, the sensors include: a first-line residual chlorine sensor, a turbidity sensor and a pH meter deployed at the water plant outlet; a second-line residual chlorine sensor, an online microbial early warning sensor, an ATP fluorescence detector and a flow cytometer deployed at key feature points; the key feature points include at least one of the following: the location farthest from the water plant in the water supply network, the location with the highest elevation in the water supply network and the location with the longest water age in the water supply network.

[0069] Specifically, corresponding to Figure 1 The composition and deployment strategy of the "real-time water quality sensing unit" in the sensing layer. A baseline sensor (first line) is deployed at the water plant outlet to calibrate the starting point of control. More strategically, a sensor cluster (second line) is deployed at key characteristic points identified through hydraulic model simulation analysis (such as the most unfavorable points, those with the furthest distance, highest elevation, and longest water age). This cluster includes online residual chlorine sensors and online microbial early warning sensors (such as ATP fluorescence detectors or flow cytometers). This deployment method aims to directly monitor the disinfection effect (residual chlorine) and biological activity (microorganisms) in the most vulnerable areas of the pipe network. Through precise direct monitoring at "points," combined with model extrapolation to the "area," an optimal balance between monitoring costs and overall coverage benefits is achieved. By directly monitoring microbial activity at the terminal characteristic points that best represent the overall risk of the pipe network, biosafety indicators are incorporated into the real-time control closed loop for the first time. This allows for the timely detection of potential risks such as "residual chlorine levels meeting standards but microbial levels exceeding standards," achieving a fundamental leap from simple chemical indicator control to dual chemical and biological safety assurance.

[0070] Step S104: Based on real-time data, a digital twin model is constructed based on the basic data of the water supply network to predict the distribution of residual chlorine concentration at the end monitoring points in the water supply network within a preset time period. The digital twin model is coupled with a dynamic residual chlorine decay model. The dynamic decay coefficient of the dynamic residual chlorine decay model is dynamically determined by water temperature, total organic carbon concentration, flow rate and biofilm activity status on the pipe wall.

[0071] Specifically, corresponding to Figure 1 The core computational process of the "Digital Twin and Intelligent Decision-Making Layer" is as follows. This layer receives full data from the perception layer. First, the system constructs an initial digital twin spatial skeleton based on the static archive (pipeline topology, pipe material and diameter, roughness, and geographic information) provided by the "basic data unit" of the perception layer. Subsequently, real-time hydraulic, water quality, and microbiological data are used to drive the model to perform rolling simulation predictions. Figure 1 As shown, the core of this process is the dynamic hydraulic-water quality model. The dynamic hydraulic model, based on static network topology, pipe diameter, elevation, and other data, along with real-time SCADA hydraulic data, calculates and predicts the distribution of flow velocity, flow rate, pressure, and hydraulic residence time (water age) in all pipe segments of the entire network in real time by solving the network's hydraulic balance equations. Building upon this, the dynamic water quality model (i.e., the dynamic residual chlorine decay model), based on the flow field provided by the dynamic hydraulic model, specifically simulates the transport and decay process of residual chlorine in the network. This model abandons the traditional approach of using a fixed decay coefficient; its core parameter—the decay coefficient—is defined as a dynamic value jointly determined by multiple environmental and operational variables (water temperature, TOC, flow velocity) and pipe wall ecological variables (biofilm activity), thus more realistically simulating the spatiotemporal consumption process of residual chlorine in actual complex network structures. By constructing the model framework from static basic data and using a multi-factor-driven dynamic decay coefficient for real-time water quality calculations, the accuracy, adaptability, and reliability of the residual chlorine concentration prediction model are significantly improved. This transforms the prediction of future water quality at the tap from a rough estimate based on experience to a reliable forecast based on mechanisms and data, providing a scientific basis for subsequent optimization decisions and solving the problem that static or simple models cannot respond to complex real-world changes.

[0072] Furthermore, in some preferred embodiments of the present invention, the dynamic residual chlorine decay model is constrained based on the following formula: ;in, This is the dynamic attenuation coefficient; Let be the residual chlorine concentration at time t; This represents the initial residual chlorine concentration at the water plant outlet.

[0073] Specifically, this formula constitutes Figure 1 The mathematical foundation of the dynamic water quality model characterizes the fundamental law of exponential decay of residual chlorine concentration over time. The innovation of this system lies not in the formula itself, but in its core parameters. Defined as a dynamic variable rather than a constant in the traditional sense, this allows classical models to integrate and respond to real-time multi-source information. Within the framework of the general decay model, by dynamizing the core decay coefficient, classical models are given new vitality, enabling them to be compatible with and integrate multi-source real-time information, and providing a flexible mathematical foundation for building high-precision, adaptive prediction models.

[0074] Furthermore, in some preferred embodiments of the present invention, the dynamic attenuation coefficient is constrained based on the following formula: ;in, This is the dynamic attenuation coefficient; The reference attenuation constant at 20℃; [T] represents the temperature correction factor; [T] represents the real-time water temperature; [TOC] represents the total organic carbon concentration; [U] represents the flow rate; and [Biofilm] represents the biofilm activity state on the pipe wall. This is the first weighting coefficient; This is the second weighting coefficient; This is a random item.

[0075] Specifically, the dynamic attenuation coefficient decomposes the total attenuation into three mechanistically defined contribution components and a random term: the first part Characterizing the temperature dependence of bulk chemical reactions in water; Part Two Characterizing the chemical reactions in the pipe wall, the intensity of which is positively correlated with the reactant concentration [TOC] and negatively correlated with the water flow scouring velocity U; Part Three It innovatively introduces a state variable [Biofilm] to characterize the ecological activity of the tube wall microorganisms, directly quantifying the consumption of residual chlorine by the biofilm. It characterizes factors that he did not consider. By embedding the key biological factor of pipe wall biofilm activity into the residual chlorine decay mechanism model in a quantifiable manner, the model prediction can simultaneously respond to changes in physical, chemical, and biological processes, greatly improving the accuracy and reliability of predictions in complex real-world pipe networks.

[0076] Furthermore, in some preferred embodiments of the present invention, the biofilm activity status of the pipe wall is dynamically calibrated based on feedback information at multiple time scales, including: generating a baseline prediction of the biofilm activity status of the pipe wall based on historical pipeline maintenance operation data and seasonal water temperature change patterns; and dynamically correcting the value of the biofilm activity status of the pipe wall and its growth parameters based on the comparison results of real-time microbial activity monitoring data of key feature points and the baseline prediction of the corresponding area.

[0077] Specifically, this is the core calibration mechanism that transforms the [Biofilm] state variables from static parameters into a "living" digital image, reflecting... Figure 1The system leverages the self-evolutionary capability of its model. First, it generates a "baseline prediction" of biofilm activity based on historical pipeline cleaning and scraping records (long-term reset signals) and seasonal water temperature variations (medium-term growth trends). More importantly, the system uses real-time data from online microbial sensors (such as ATP analyzers) in the sensing layer to validate and correct this baseline: if the measured activity remains consistently lower than the prediction, the [Biofilm] value for that region is lowered; if the measured value spikes abnormally, far exceeding the baseline prediction, the [Biofilm] value is immediately and significantly increased. This forms a self-evolutionary mechanism. Figure 1 The diagram illustrates a self-learning and self-calibration closed loop: "baseline prediction (historical data + water temperature) → real-time biosignal verification → dynamic correction of model parameters." By integrating long-term, medium-term, and short-term multi-scale information for dynamic learning and calibration of biofilm status, the model can learn the characteristics of the pipeline network, respond to seasonal patterns, and keenly capture abnormal events. This makes the residual chlorine prediction model an intelligent agent that can "breathe" and "evolve" along with the actual pipeline network ecosystem, fundamentally improving prediction accuracy.

[0078] Step S106: Determine the microbial risk status based on real-time microbial activity data, and determine the dynamic residual chlorine control target for the terminal monitoring point based on the determination result.

[0079] Specifically, corresponding to Figure 1 The "Microbial Risk Identification Module" is a core decision-making component connecting microbial risk early warning and chlorination control actions. For example... Figure 1 As shown in the flowchart, this module analyzes real-time microbial activity data (such as ATP values) uploaded by the sensing layer and compares it with preset safety thresholds. If the data is normal, the system is in "normal optimization mode," and the residual chlorine control target at the terminal level adopts the standard safety limit. If the data exceeds the threshold, it is determined that there is a risk of microbial regeneration, and the system immediately switches to "early warning mode." At this time, the lower limit of the residual chlorine control target at the terminal level is automatically increased by a safety margin, aiming to proactively suppress risks by strengthening disinfection. This realizes the automatic dynamic switching of control strategies based on biosafety signals, enabling the system not only to maintain the normal disinfection level but also to proactively respond to sudden microbial risks, nipping potential water quality safety problems in the bud and greatly enhancing the initiative and reliability of biosafety assurance in the water supply system.

[0080] Step S108: With the predicted residual chlorine concentration at the terminal monitoring points meeting their corresponding dynamic residual chlorine control targets as constraints, the optimal chlorination dosage for the treated water is solved using an optimization algorithm.

[0081] Specifically, corresponding to Figure 1 The core computational process of the "Intelligent Optimization Algorithm Module" in the text. For example... Figure 1As shown, this module receives the future residual chlorine prediction results from the dynamic hydraulic-water quality model and the risk status signal from the microbial risk identification module. Its core optimization idea is to ensure that the predicted residual chlorine at all terminal points is not lower than the dynamic control target within a future period (prediction time domain), which is an inviolable "hard constraint." Under this premise, the goal is to find a chlorination dosage for the treated water that minimizes the total chlorination amount and keeps the terminal residual chlorine close to the ideal target value. This is a typical constrained optimization problem, usually solved using a model predictive control (MPC) framework. This method overturns the traditional forward control logic centered on the water plant outlet and pioneers a reverse optimization control approach centered on the safety of all terminal points. It eliminates the global over-chlorination caused by ensuring terminal water quality at the source, achieving a balance between safety and economy while absolutely guaranteeing the safety of the water quality at the most unfavorable point.

[0082] Furthermore, in some preferred embodiments of the present invention, the optimal chlorination dosage for the treated water is calculated using the following formula: ; ; ; ;in, The optimal chlorination dosage for treated water; For the i-th terminal node in the future prediction time domain within Predicted residual chlorine at any given time; The target residual chlorine concentration; As a weight for energy saving; This is the minimum effective value; These are preset standard safety limits; This is a preset safety margin; The preset warning conditions indicate whether a microbial warning is triggered.

[0083] Specifically, the objective function aims to minimize two terms: first, the sum of deviations between the predicted residual chlorine at all endpoints and the ideal target at all future times (to ensure water quality accuracy); and second, the total chlorination amount. This itself (saves on drug consumption). The constraint mandates that the predicted residual chlorine at all terminal points must not fall below the effective minimum limit at any future moment. .and The value depends on the risk flag bit. Dynamic switching: Under normal circumstances Under warning, it is This clearly demonstrates how the output of the microbial risk identification module directly alters the constraints of the optimization problem, enabling the entire decision-making process to possess risk-adaptive capabilities. By unifying the three objectives of "last-mile protection," "risk early warning and response," and "economic optimization" within a single optimization framework through a rigorous mathematical model, the intelligent decision-making process transforms from experience-based judgment into calculable and verifiable scientific optimization, ensuring the optimality, consistency, and transparency of the control strategy.

[0084] Step S110: Based on the optimal chlorination dosage for the treated water, generate control instructions for the chlorination device and control the chlorination device to perform chlorine dosing.

[0085] Specifically, corresponding to Figure 1 The function of the "execution and control layer" is the final step in translating the system's intelligent decisions into physical actions. For example... Figure 1 As shown, the optimal chlorination rate for the treated water is set as a control command and sent to the chlorination execution equipment in the water plant. This layer needs to overcome interference such as process lag and flow fluctuations to accurately and stably control the residual chlorine in the treated water near the set value, thus completing the entire process from virtual decision-making to physical control. The control command of the chlorination device is used to drive the chlorination equipment so that the actual residual chlorine concentration Cfeedback(t) at the water plant outlet accurately and stably reaches the target set value Cset determined by the optimal chlorination rate Dplant for the treated water. This set value Cset can be calculated based on parameters such as Dplant and the real-time influent flow rate of the water plant, or obtained by looking up a preset mapping table. This embodiment of the invention completes a closed loop from "virtual space optimization decision-making" to "precise execution in the physical world," ensuring that the theoretically optimal value calculated by optimization can be faithfully reflected in actual production, which is the key to realizing the implementation of intelligent control of the entire system.

[0086] Furthermore, in some preferred embodiments of the present invention, the control commands of the chlorination device are constrained by the following formula: ; ;in, To control the amount of chlorine added corresponding to the control command; The first control parameter characterizes the proportional gain; The second control parameter represents the ratio of proportional gain to integral time. The third control parameter represents the product of the proportional gain and the derivative time. This is the chlorination setpoint; This is the feedback value from the online residual chlorine sensor at the water plant outlet; It is a feedforward quantity for predicting information based on a digital twin model.

[0087] Specifically, corresponding to Figure 1In the execution layer, the "adaptive PID controller" employs a feedforward-feedback composite PID algorithm to control the chlorination device. The feedback component eliminates the deviation e(t) between the setpoint and measured values, while the feedforward component FF(t) predicts upcoming flow and water quality changes based on a digital twin model, adjusting the control output in advance to address foreseeable disturbances and thus more effectively achieve the optimal chlorination decision. Traditional PID feedback control... Used to eliminate set value (i.e., the target residual chlorine corresponding to the optimal chlorination dosage) and the measured feedback value Deviation between A feedforward term FF(t) has been added, derived from the prediction of impending measurable disturbances (such as planned large-scale flow changes) by the digital twin and intelligent decision-making layer. Figure 1 As shown, feedforward control can act in advance, greatly reducing the impact of these disturbances on the control effect, and complementing feedback control. By combining the stability of feedback control with the advance compensation capability of feedforward control, the response speed, anti-interference capability, and control accuracy of the control system are significantly improved. It can effectively cope with common flow and water quality shocks in the water supply process, ensure the stability and reliability of residual chlorine in the treated water, and provide solid execution-level support for ensuring water quality at the end point of distribution.

[0088] Furthermore, in some preferred embodiments of the present invention, the first control parameter, the second control parameter, and the third control parameter are all adaptively switched based on the operating condition zone to which the real-time influent flow belongs.

[0089] Specifically, the dynamic characteristics of a water supply system (such as lag time and gain) vary significantly with flow rate. Fixed PID parameters cannot achieve optimal control performance across all flow rates. Therefore, as... Figure 1 The associated system design involves the controller dividing the real-time inflow rate into different operating condition zones, such as low, medium, and high flow rates, and pre-setting a set of optimized PID parameters for each zone. , , When changes in flow rate cause a switch in operating conditions, the controller automatically calls the corresponding parameter group to maintain optimal control quality at all times. See Table 1, which provides a table corresponding to PID parameters under different operating conditions, as shown in this embodiment of the invention.

[0090] Table 1

[0091]

[0092] It enables the controller parameters to adapt to operating conditions, ensuring that the control system maintains the best control quality of fast, stable and overshoot-free operation, regardless of whether the water usage is in a low-water or high-water period. This improves the control performance and robustness under all operating conditions and ensures the accuracy and stability of the chlorine dosing process.

[0093] This invention provides a chlorination method for water supply networks, applied to an intelligent chlorination system for water supply networks based on digital twins and microbial risk early warning. The method includes: executing the following steps on a rolling basis according to a preset cycle: acquiring real-time data of the water supply network; wherein, the real-time data includes: real-time hydraulic data, real-time water quality data, and real-time microbial activity data; driving a digital twin model constructed based on the basic data of the water supply network based on the real-time data, to predict the residual chlorine concentration distribution at the end monitoring points of the water supply network within a preset time period; wherein, the digital twin model is coupled with a dynamic residual chlorine decay model, and the dynamic decay coefficient of the dynamic residual chlorine decay model... The system dynamically determines the residual chlorine dosage based on water temperature, total organic carbon concentration, flow rate, and the biofilm activity status on the pipe wall. It assesses the microbial risk status based on real-time microbial activity data and determines the dynamic residual chlorine control target for the terminal monitoring points. With the predicted residual chlorine concentration at each terminal monitoring point meeting its corresponding dynamic residual chlorine control target as a constraint, an optimization algorithm is used to solve for the optimal chlorination dosage for the treated water. Based on the optimal chlorination dosage, control commands are generated for the chlorination device, and the device is controlled to perform chlorine dosing. By establishing a digital twin model and real-time microbial activity monitoring, the system overcomes the shortcomings of traditional chlorination technologies, such as being slow, inefficient, and neglecting biosafety. Based on a real-time data-driven digital twin model, the system enables proactive rolling prediction of residual chlorine concentration at the end of the pipe network, transforming control from a passive response to active intervention. By using the continuous achievement of residual chlorine standards at all end points as a constraint, the optimal chlorination dosage is solved in reverse, achieving precise dosing and avoiding global overdose. Dynamic switching of control targets based on microbial activity data establishes a dual safety barrier of chemical and biological components. Periodic closed-loop execution ensures the system adapts to changes in operating conditions. While significantly improving the reliability of water quality assurance at the end points, the system reduces chemical consumption and disinfection byproduct risks, achieving a balance between safety and economy.

[0094] Example 2

[0095] Based on the above embodiments, this invention provides a chlorination device for water supply networks, see [link to relevant documentation]. Figure 3 The schematic diagram shown in this embodiment of the invention provides a chlorination device for a water supply network, which is applied to an intelligent chlorination system for a water supply network based on digital twins and microbial risk early warning. The device includes the following modules that are executed in a rolling manner according to a preset cycle:

[0096] The real-time data acquisition module 310 is used to acquire real-time data of the water supply network; wherein, the real-time data includes: real-time hydraulic data, real-time water quality data and real-time microbial activity data;

[0097] The residual chlorine prediction module 320 is used to drive a digital twin model based on the basic data of the water supply network based on real-time data, so as to predict the distribution of residual chlorine concentration at the end monitoring points in the water supply network within a preset time period. The digital twin model is coupled with a dynamic residual chlorine decay model. The dynamic decay coefficient of the dynamic residual chlorine decay model is dynamically determined by water temperature, total organic carbon concentration, flow rate and biofilm activity status on the pipe wall.

[0098] The control target determination module 330 is used to determine the microbial risk status based on real-time microbial activity data and determine the dynamic residual chlorine control target at the terminal monitoring point based on the judgment result.

[0099] The chlorination dosage determination module 340 is used to solve the optimal chlorination dosage for the treated water by means of an optimization algorithm, with the constraint that the predicted residual chlorine concentration at the terminal monitoring point meets its corresponding dynamic residual chlorine control target.

[0100] The instruction determination module 350 is used to generate control instructions for the chlorination device based on the optimal chlorination dosage for the treated water, and to control the chlorination device to perform chlorine dosing.

[0101] Furthermore, in some preferred embodiments of the present invention, the real-time hydraulic data includes at least one of the following: instantaneous flow rate of water effluent from the water plant, effluent pressure from the water plant, real-time pressure of key nodes, flow rate of key nodes, opening degree of key valves, start / stop status of pumping stations, and operating frequency of pumping stations; wherein, key nodes include at least one of the following: pumping stations, pressure zone boundaries, and large water users; and key valves include at least one of the following: zone isolation valves, pressure regulating valves, and flow distribution valves.

[0102] Furthermore, in some preferred embodiments of the present invention, real-time water quality data and real-time microbial activity data are acquired based on preset sensors; wherein, the sensors include: a first-line residual chlorine sensor, a turbidity sensor and a pH meter deployed at the water plant outlet; a second-line residual chlorine sensor, an online microbial early warning sensor, an ATP fluorescence detector and a flow cytometer deployed at key feature points; the key feature points include at least one of the following: the location farthest from the water plant in the water supply network, the location with the highest elevation in the water supply network and the location with the longest water age in the water supply network.

[0103] Furthermore, in some preferred embodiments of the present invention, the residual chlorine prediction module 320 is used to constrain the dynamic residual chlorine decay model based on the following formula: ;in, This is the dynamic attenuation coefficient; Let be the residual chlorine concentration at time t; This represents the initial residual chlorine concentration at the water plant outlet.

[0104] Furthermore, in some preferred embodiments of the present invention, the residual chlorine prediction module 320 is used to constrain the dynamic decay coefficient based on the following formula: ;in, This is the dynamic attenuation coefficient; The reference attenuation constant at 20℃; [T] represents the temperature correction factor; [T] represents the real-time water temperature; [TOC] represents the total organic carbon concentration; [U] represents the flow rate; and [Biofilm] represents the biofilm activity state on the pipe wall. This is the first weighting coefficient; This is the second weighting coefficient; This is a random item.

[0105] Furthermore, in some preferred embodiments of the present invention, the residual chlorine prediction module 320 is used to generate a baseline prediction of the biofilm activity status of the pipe wall based on historical pipeline maintenance operation data and seasonal water temperature change patterns; and to dynamically correct the value of the biofilm activity status of the pipe wall and its growth parameters based on the comparison results of real-time microbial activity monitoring data of key feature points and the baseline prediction of the corresponding area.

[0106] Furthermore, in some preferred embodiments of the present invention, the chlorination dosage determination module 340 is used to calculate the optimal chlorination dosage for the treated water using the following formula: ; ; ; ;in, The optimal chlorination dosage for treated water; For the i-th terminal node in the future prediction time domain within Predicted residual chlorine at any given time; The target residual chlorine concentration; As a weight for energy saving; This is the minimum effective value; These are preset standard safety limits; This is a preset safety margin; The preset warning conditions indicate whether a microbial warning is triggered.

[0107] Furthermore, in some preferred embodiments of the present invention, the instruction determination module 350 is used to constrain the control instructions of the chlorination device using the following formula: ; ;in, To control the amount of chlorine added corresponding to the control command; The first control parameter characterizes the proportional gain; The second control parameter represents the ratio of proportional gain to integral time. The third control parameter represents the product of the proportional gain and the derivative time. This is the chlorination setpoint; This is the feedback value from the online residual chlorine sensor at the water plant outlet; It is a feedforward quantity for predicting information based on a digital twin model.

[0108] Furthermore, in some preferred embodiments of the present invention, the instruction determination module 350 is used to adaptively switch the first control parameter, the second control parameter, and the third control parameter based on the operating condition zone to which the real-time influent flow belongs.

[0109] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the water supply network chlorination device described above can be referred to the corresponding process in the aforementioned embodiments of the water supply network chlorination method, and will not be repeated here.

[0110] Example 3

[0111] This invention also provides an electronic device for operating a chlorination method in a water supply network; see [link to related documentation]. Figure 4 The schematic diagram of an electronic device provided in the embodiment of the present invention shown includes a memory 400 and a processor 401. The memory 400 is used to store one or more computer instructions, which are executed by the processor 401 to implement the above-mentioned chlorination method for water supply networks.

[0112] Furthermore, Figure 4 The electronic device shown also includes a bus 402 and a communication interface 403. The processor 401, the communication interface 403 and the memory 400 are connected via the bus 402.

[0113] The memory 400 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 403 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 402 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0114] Processor 401 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 401 or by instructions in software form. Processor 401 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 400, and processor 401 reads information from memory 400 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0115] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the above-described water supply network chlorination method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0116] The computer program product of the water supply network chlorination method, apparatus and electronic equipment provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0117] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and / or device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0118] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0119] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for chlorinating a water supply network, characterized in that, The method, applied to an intelligent chlorination system for water supply networks based on digital twins and microbial risk early warning, includes: performing the following steps on a rolling basis according to a preset cycle: Acquire real-time data of the water supply network; wherein, the real-time data includes: real-time hydraulic data, real-time water quality data, and real-time microbial activity data; The digital twin model, driven by the real-time data and constructed based on the basic data of the water supply network, is used to predict the distribution of residual chlorine concentration at the end monitoring points of the water supply network within a preset time period. The digital twin model is coupled with a dynamic residual chlorine decay model, and the dynamic decay coefficient of the dynamic residual chlorine decay model is dynamically determined by water temperature, total organic carbon concentration, flow velocity and biofilm activity status on the pipe wall. The microbial risk status is determined based on the real-time microbial activity data, and the dynamic residual chlorine control target of the terminal monitoring point is determined based on the judgment result. With the constraint that the predicted residual chlorine concentration at the terminal monitoring points all meet the corresponding dynamic residual chlorine control target, the optimal chlorination dosage for the treated water is solved by an optimization algorithm. Based on the optimal chlorination dosage for the treated water, control commands are generated for the chlorination device, and the device is controlled to perform chlorine dosing. The optimal chlorination rate for treated water is determined using the following formula: ； ； ； ； in, The optimal chlorination dosage for the treated water; For the i-th terminal node in the future prediction time domain within Predicted residual chlorine at any given time; The target residual chlorine concentration; As a weight for energy saving; This is the minimum effective value; These are preset standard safety limits; This is a preset safety margin; The preset warning conditions indicate whether a microbial warning is triggered.

2. The chlorination method for water supply networks according to claim 1, characterized in that, The real-time hydraulic data includes at least one of the following: instantaneous flow rate of water effluent from the water plant, effluent pressure from the water plant, real-time pressure of key nodes, flow rate of the key nodes, opening degree of key valves, start / stop status of pumping stations, and operating frequency of the pumping stations; wherein, the key nodes include at least one of the following: pumping stations, pressure zone boundaries, and large water users; and the key valves include at least one of the following: zone isolation valves, pressure regulating valves, and flow distribution valves.

3. The chlorination method for water supply networks according to claim 1, characterized in that, The real-time water quality data and the real-time microbial activity data are acquired based on preset sensors; wherein, the sensors include: a first-line residual chlorine sensor, a turbidity sensor and a pH meter deployed at the water plant outlet; a second-line residual chlorine sensor, an online microbial early warning sensor, an ATP fluorescence detector and a flow cytometer deployed at key feature points; the key feature points include at least one of the following: the location farthest from the water plant in the water supply network, the location with the highest elevation in the water supply network and the location with the longest water age in the water supply network.

4. The chlorination method for water supply networks according to claim 1, characterized in that, The dynamic residual chlorine decay model is constrained by the following formula: ； in, The dynamic attenuation coefficient is mentioned above; Let be the residual chlorine concentration at time t; This represents the initial residual chlorine concentration at the water plant outlet.

5. The chlorination method for water supply networks according to claim 4, characterized in that, The dynamic attenuation coefficient is constrained by the following formula: ； in, The dynamic attenuation coefficient is mentioned above; The reference attenuation constant is at 20℃; [T] is the temperature correction factor; [TOC] is the total organic carbon concentration; [U] is the flow rate; [Biofilm] is the activity state of the biofilm on the pipe wall. This is the first weighting coefficient; This is the second weighting coefficient; This is a random item.

6. The chlorination method for water supply networks according to claim 5, characterized in that, The biofilm activity state of the tube wall is dynamically calibrated based on feedback information at multiple time scales, including: Based on historical pipeline maintenance data and seasonal water temperature variation patterns, a baseline prediction of the biofilm activity status on the pipe wall is generated. The value of the biofilm activity status and its growth parameters in the tube wall are dynamically corrected based on the comparison results between real-time microbial activity monitoring data of key feature points and the baseline prediction of the corresponding area.

7. The chlorination method for water supply networks according to claim 1, characterized in that, The control commands of the chlorination device shall be constrained by the following formula: ； ； in, The amount of chlorine added corresponding to the control command; The first control parameter characterizes the proportional gain; The second control parameter represents the ratio of the proportional gain to the integral time. The third control parameter represents the product of the proportional gain and the derivative time. This is the chlorination setpoint; This is the feedback value from the online residual chlorine sensor at the water plant outlet; This is the feedforward quantity for predicting information based on the digital twin model.

8. The chlorination method for water supply networks according to claim 7, characterized in that, The first control parameter, the second control parameter, and the third control parameter are all adaptively switched based on the operating condition zone to which the real-time influent flow belongs.

9. A chlorination device for a water supply network, characterized in that, An intelligent chlorination system for water supply networks based on digital twins and microbial risk early warning is provided, comprising the following modules that execute on a rolling basis according to a preset cycle: A real-time data acquisition module is used to acquire real-time data of the water supply network; wherein, the real-time data includes: real-time hydraulic data, real-time water quality data, and real-time microbial activity data; The residual chlorine prediction module is used to drive a digital twin model built based on the basic data of the water supply network based on the real-time data, so as to predict the distribution of residual chlorine concentration at the end monitoring points in the water supply network within a preset time period. The digital twin model is coupled with a dynamic residual chlorine decay model, and the dynamic decay coefficient of the dynamic residual chlorine decay model is dynamically determined by water temperature, total organic carbon concentration, flow velocity and biofilm activity state on the pipe wall. The control target determination module is used to determine the microbial risk status based on the real-time microbial activity data, and to determine the dynamic residual chlorine control target of the terminal monitoring point based on the judgment result; The chlorination dosage determination module is used to solve the optimal chlorination dosage for the treated water by means of an optimization algorithm, with the constraint that the predicted residual chlorine concentrations at the terminal monitoring points all meet the corresponding dynamic residual chlorine control targets. The instruction determination module is used to generate control instructions for the chlorination device based on the optimal chlorination dosage for the treated water, and to control the chlorination device to perform chlorine dosing. The chlorination dosage determination module is used to calculate the optimal chlorination dosage for the treated water using the following formula: ; ; ; ;in, The optimal chlorination dosage for the treated water; For the i-th terminal node in the future prediction time domain within Predicted residual chlorine at any given time; The target residual chlorine concentration; As a weight for energy saving; This is the minimum effective value; These are preset standard safety limits; This is a preset safety margin; The preset warning conditions indicate whether a microbial warning is triggered.

Images