Water supply network system and control method, device and storage medium thereof

Abstract

The application belongs to the field of automatic control, and aims to provide a water supply network system, a control method and device thereof and a storage medium, the method comprising: acquiring attribute information of a water diversion channel and a regulating pool in the water supply network system, flow information of an upstream and a downstream of a gate corresponding to different gate opening degrees, and water supply relationships between the gates; establishing a control model; monitoring actual opening degrees of the water diversion gates and the water distribution gates, flow and internal water level of the regulating pool; inputting the monitoring data and preset control target values into the control model to obtain control data; and adjusting the opening degrees of the gates according to the control data. The application analyzes each item of data in the water supply network system to establish a control model, and then collects multi-point real-time monitoring data to calculate how to control and adjust the gates through the model, thereby saving a large amount of time compared with the prior art, having high calculation and execution efficiency, and being able to realize fast response when facing risks, thereby providing better protection for water supply.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water supply control, in particular to a water supply network system and a control method, device and storage medium thereof. BACKGROUND

[0002] The open channel water supply project adopted by the existing water supply network has a certain degree of automatic control ability of channel water supply. However, the existing water supply network still has many problems in the joint scheduling control system of the water supply channel in the multi-water area and multi-channel pool. With the development needs, the control object is diversified, the target constraint is multi-element, and the multi-dimensional channel water distribution and water distribution scheduling are faced. The existing water supply control is easy to cause control deviation and error. To realize distributed multi-point linkage control, there is a problem that it is difficult to realize the water supply and water distribution and water distribution of the complex water supply network. The water level fluctuation caused by the water channel lacks the design of the adjusting component, causing the problem of insufficient buffer space. Moreover, the existing open channel water supply channel structure does not support the complex water supply-water diversion target. It is impossible to realize the overall control of water flow in the channel system including the main channel and the branch channel. Not only can it not inhibit the degree of water flow fluctuation amplitude, but also can cause the loss of artificial channel lining, and cause the shortage of water supply guarantee rate of the water receiving area. At the same time, the channel water distribution device lacks guidance in construction and operation. The structure of the complex water supply is difficult to realize efficient water flow back stabilization, and lacks the setting of the control effect based on the actual demand, causing insufficient applicability. At the same time, the current control algorithm does not process the complex action between devices, especially the mutual restriction of the water power process of the channel formed by the opening and closing control of the gate, which interferes with the control decision. Moreover, the control process lacks an immediate correction mechanism for deviation. The control error in the joint control process of the gate will form accumulation and superposition, and the subsequent operation will continuously affect the control of the non-steady-state system, causing deviation in the establishment of the steady state. The current analysis control generally takes a long time, has low efficiency and poor stability, and cannot timely respond to the water demand of the water receiving area. When facing complex risks, due to the delay in scheduling, there are also other risk hidden dangers. SUMMARY

[0003] Therefore, the embodiments of the present application provide a water supply network system control method to solve the problems of long analysis time, low efficiency and poor stability of the existing water supply control.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0005] The embodiment of the application provides a water supply network system control method, the water supply network system comprises a water supply channel, a plurality of water diversion channels, a plurality of water diversion gates and a regulating pool corresponding to the number of water diversion channels, a plurality of water distribution gates and a plurality of water distribution outlets, the water supply channel is connected with the plurality of water diversion channels, the water diversion channel is connected with the water diversion end of the regulating pool through the water diversion gate, and the water outlet end of the regulating pool is connected through the water distribution gate and the plurality of water distribution outlets, and the control method comprises:

[0006] Attribute information of the water diversion channel and the regulating pool in the water supply network system, flow information of upstream and downstream of different gate openings of the water diversion gate and the water distribution gate, and water supply relationship between the water diversion gate and the water distribution gate are acquired.

[0007] A control model is established according to the attribute information, the flow information and the water supply relationship.

[0008] Actual openings, flow rates of the water diversion gate and the water distribution gate and an inner water level of the regulating pool are monitored to obtain monitoring data.

[0009] The monitoring data and a preset control target value are input into the control model to obtain control data.

[0010] The openings of the water diversion gate and the water distribution gate are adjusted according to the control data.

[0011] Optionally, the control model is established according to the attribute information, the flow information and the water supply relationship, and the control model comprises:

[0012] A water dynamic model is established according to the flow information and the attribute information.

[0013] A state space model is constructed by optimizing the water dynamic model based on preset steady state information.

[0014] The state space model is decoupled and analyzed according to the water supply relationship to obtain the control model.

[0015] Optionally, the state space model is constructed by optimizing the water dynamic model based on preset steady state information, and the state space model comprises:

[0016] Equations in the water dynamic model are discretely converted.

[0017] The converted equations are linearized based on preset steady state information.

[0018] The state space model is generated according to the linearized equations.

[0019] Optionally, the state space model is decoupled and analyzed according to the water supply relationship to obtain the control model, and the control model comprises:

[0020] decoupling the opening of each gate and the flow upstream and downstream according to the water supply relationship and the state space model, to obtain a first correlation between the flow and the gate opening;

[0021] extracting water level data of the regulation pool corresponding to different gate openings from the attribute information;

[0022] correlation analysis of the water level data and the flow data, to obtain a second correlation between the flow and the water level;

[0023] establishing a control model according to the first correlation and the second correlation.

[0024] Optionally, the monitoring data includes gate opening data, flow data and water level data, the actual opening of the diversion gate and the diversion gate, the flow and the water level in the regulation pool are monitored to obtain monitoring data, including:

[0025] acquiring a preset monitoring period;

[0026] acquiring the opening data of the diversion gate and the diversion gate, the flow data upstream and downstream of each gate and the water level data of the regulation pool according to the preset monitoring period.

[0027] Optionally, the method further includes:

[0028] comparing the water level data and the flow data with the preset control target value to obtain deviation data;

[0029] judging whether the deviation data is greater than a preset deviation value;

[0030] when the deviation data is less than or equal to the preset deviation value, returning to the step of monitoring the actual opening of the diversion gate and the diversion gate, the flow and the water level in the regulation pool;

[0031] when the deviation data is greater than the preset deviation value, denoising the water level data and the flow data to obtain updated monitoring data, and executing the step of inputting the monitoring data and the preset control target value into the control model based on the updated monitoring data.

[0032] Optionally, before adjusting the opening of the diversion gate and the diversion gate according to the control data, the method includes:

[0033] constructing a prediction model according to the water supply transmission information, the state space model and the water power model;

[0034] input the control data into the prediction model to predict the water level data and the flow data after the opening degree is adjusted, and obtain a prediction result;

[0035] determine whether a difference between the prediction result and a preset control target value is greater than a preset threshold value;

[0036] if the difference is greater than the preset threshold value, adjust model parameters of the control model, and return to the step of inputting the monitoring data and the preset control target value into the control model to obtain the control data until the difference is less than or equal to the preset threshold value.

[0037] The embodiment of the present application also provides a water supply network system control device, the water supply network system comprising: at least one adjusting pool, a water supply end of the adjusting pool being connected with a water diversion channel, a water outlet end of the adjusting pool being provided with a plurality of water distribution outlets, the water diversion channel being provided with a water diversion gate, and the water distribution outlets being provided with water distribution gates, the device comprising:

[0038] an acquisition module, used for acquiring attribute information of the water diversion channel and the adjusting pool in the water supply network system, flow information of upstream and downstream of different gate opening degrees of the water diversion gate and the water distribution gate, and a water supply relationship between the water diversion gate and the water distribution gate;

[0039] an establishment module, used for establishing a control model according to the attribute information, the flow information and the water supply relationship;

[0040] a monitoring module, used for monitoring actual opening degrees of the water diversion gate and the water distribution gate, flow and an internal water level of the adjusting pool, and obtaining monitoring data;

[0041] a calculation module, used for inputting the monitoring data and a preset control target value into the control model to obtain control data;

[0042] an adjustment control module, used for adjusting opening degrees of the water diversion gate and the water distribution gate according to the control data.

[0043] The embodiment of the present application also provides a water supply network system, comprising:

[0044] a water supply channel, a plurality of water diversion channels, water diversion gates and adjusting pools corresponding to the number of the water diversion channels, a plurality of water distribution gates and a plurality of water distribution outlets, the water supply channel being connected with the plurality of water diversion channels, the water diversion channels being connected with the water supply end of the adjusting pool through the water diversion gates, and the water outlet end of the adjusting pool being connected with the water distribution gates and the plurality of water distribution outlets through the water distribution gates;

[0045] The system further comprises a memory and a processor, which are in communication connection with each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the water supply network system control method.

[0046] The application also provides a computer readable storage medium storing computer instructions for causing a computer to execute the water supply network system control method.

[0047] The application has the following advantages:

[0048] The application provides a water supply network system control method, which comprises the following steps: obtaining attribute information of a water diversion channel and a regulating pool in a water supply network system, flow information of an upstream and a downstream of a water diversion gate and a water distribution gate corresponding to different gate opening degrees of the water diversion gate and the water distribution gate, and a water supply relationship between the water diversion gate and the water distribution gate; establishing a control model according to the attribute information, the flow information and the water supply relationship; monitoring actual opening degrees of the water diversion gate and the water distribution gate, flow and an inner water level of the regulating pool to obtain monitoring data; inputting the monitoring data and a preset control target value into the control model to obtain control data; and adjusting the opening degrees of the gates according to the control data. The application analyzes each item of data in the water supply network system to establish a control model, and then collects real-time monitoring data at multiple points to calculate how to control and adjust the gates through the model, thereby saving a large amount of time compared with the prior art, having high calculation and execution efficiency, and being able to realize rapid response when facing risks, thereby providing better protection for water supply. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the specific embodiments of the application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can also be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0050] Figure 1 The flowchart of the water supply network system control method in the embodiments of the application;

[0051] Figure 2 The flowchart of establishing the control model in the embodiments of the application;

[0052] Figure 3 The flowchart of constructing the state space model in the embodiments of the application;

[0053] Figure 4 The flowchart of decoupling analysis on the state space model in the embodiments of the application;

[0054] Figure 5 This is a flowchart illustrating the monitoring of the actual opening degree, flow rate, and water level in the regulating pool of the water intake gate and the water diversion gate according to an embodiment of the present invention.

[0055] Figure 6 This is a flowchart illustrating the deviation analysis according to an embodiment of the present invention;

[0056] Figure 7 This is a diagram of the self-disturbance rejection algorithm structure according to an embodiment of the present invention;

[0057] Figure 8 This is a flowchart illustrating prediction based on control data according to an embodiment of the present invention;

[0058] Figure 9 This is a schematic diagram of the structure of the water supply network system control device in an embodiment of the present invention;

[0059] Figure 10 This is a schematic diagram of the water supply network system in an embodiment of the present invention. Detailed Implementation

[0060] 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, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] According to an embodiment of the present invention, a method for controlling a water supply network system is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0062] This embodiment provides a water supply network system control method, which can be used in scenarios involving the joint automatic control of water inlets and outlets in complex water supply networks, such as... Figure 1 As shown, the water supply network system includes: a water supply channel, multiple water intake channels, water intake gates and a regulating reservoir corresponding to the number of water intake channels, multiple water distribution gates, and multiple water distribution outlets. The water supply channel is connected to the multiple water intake channels. The water intake channels are connected to the water intake end of the regulating reservoir through the water intake gates. The water outlet end of the regulating reservoir is connected to the water distribution gates and multiple water distribution outlets. The control method of the water supply network system includes the following steps:

[0063] Step S1: Obtain the attribute information of the water intake channel and regulating reservoir in the water supply network system, the flow information upstream and downstream of the intake gate and the diversion gate corresponding to different gate openings, and the water supply relationship between the intake gate and the diversion gate. Specifically, since the opening of the intake gate and the diversion gate both affect the water level in the regulating reservoir, achieving linkage control and meeting water supply requirements, obtaining the above information facilitates subsequent analysis.

[0064] Step S2: Establish a control model based on attribute information, flow rate information, and water supply relationship. Specifically, a control model is established by analyzing the relationship between upstream and downstream water level and flow rate caused by gate opening. This facilitates rapid calculation of gate control data through the model, improving control efficiency.

[0065] Step S3: Monitor the actual opening degree of the intake gate and diversion gate, the flow rate, and the water level in the regulating reservoir to obtain monitoring data. Specifically, data is collected in real time through various sensors installed within the water supply system.

[0066] Step S4: Input the monitoring data and preset control target values ​​into the control model to obtain control data. Specifically, taking a water distribution point as an example, when the water distribution volume of a certain water distribution point deviates from the water supply target in the preset control target value, if the monitored value is higher than the water supply target, the opening of the corresponding water distribution gate is reduced; conversely, the opening of the water distribution gate needs to be increased until the water distribution volume monitoring value of that water distribution point reaches the water supply target. When the overall water distribution volume is lower than the water demand target in the preset control target value, the opening of the intake gate can be increased, and the inflow rate of the water distribution gate can be increased accordingly. When the water distribution volume is higher than the water demand setting, the opening of the water distribution gate is reduced, and the opening of the intake gate is reduced according to the actual monitoring situation. By inputting the monitoring data and preset control target values ​​into the control model, the control data of the intake gate and the water distribution gate can be obtained quickly and accurately, which facilitates subsequent adjustment of the gate opening based on this data.

[0067] Step S5: Adjust the opening of the intake gate and the diversion gate according to the control data.

[0068] Through the above steps S1 to S5, the water supply network system control method provided by this embodiment of the invention analyzes various data in the water supply network system to establish a control model, and then collects real-time monitoring data from multiple points to calculate how to control and adjust the gates through the model. Compared with existing analysis, it saves a lot of time, has high calculation and execution efficiency, and can achieve rapid response when facing risks, thus providing better protection for water supply.

[0069] Specifically, in one embodiment, a step of calculating the capacity of the regulating pool according to demand is provided, which specifically includes the following process:

[0070] By obtaining the water supply flow rate of the water diversion channel under the water resource management plan, the water distribution flow rate of each branch point, and the corresponding number of water uses and duration, the capacity of the regulating reservoir is determined, and the principle of maintaining the available water supply and the energy dissipation function are comprehensively considered.

[0071] The changes in water consumption curves over time periods, with a daily cycle, in the water resource management plan reveal the degree of fluctuation in water supply: In the formula: The coefficient for the change in water volume during water diversion. The total water volume during the period of maximum daily flow. Total water volume during the average daily period

[0072] The maximum hourly flow Using the contingency plan as known data, we obtain the current number of water-receiving areas N and the corresponding maximum standard of water supply guarantee q, and apply the hourly variation coefficient. The required flow rate at the water intake and distribution point is obtained under the condition of guaranteed water supply. In the formula: n is the number of time periods per day. If the calculation method is used hourly, then n=24 is selected.

[0073] Combining the reaction time, the required equalization tank volume under insufficient water supply conditions can be obtained: .

[0074] Accordingly, the maximum flow rate will be determined from the water diversion channel. The continuous output is used for error calculation to ensure the highest guarantee rate and obtain the maximum water diversion volume. : .

[0075] Average water supply in combined water use plan To calculate the excess water supply, the required storage capacity of the regulating tank is determined by adjusting the water supply flow rate difference when there is excessive water inflow. .

[0076] The capacity of the equalization tank is obtained by calculating the combined difference: .

[0077] Of this, 10% is the additional regulating volume, which is used to meet the maximum water distribution and maximum water use requirements, while also helping to form the water flow at the water inlet.

[0078] In addition, a graphical method can be used to conduct a detailed analysis of the volume calculation of the water diversion and regulating reservoir in the water supply network of this invention. By plotting the flow curves for each time period under the water use plan and water supply error, the cumulative water volume difference is obtained, and a reasonable regulating reservoir capacity is obtained by applying statistical concepts. When the proposed capacity value conforms to a normal distribution N(μ, σ²) and has homogeneity of variance, the expected value μ is selected as the final volume value after a t-test. When the distribution of the values ​​does not conform to a normal distribution, further non-parametric tests are conducted, including but not limited to: Wilcoxon test, KS test, Kruskal-Wallis test, Jonckheere-Terpstra test, McNemar test, etc. Then, statistical methods are applied to the processed water volume difference data to obtain the expected value of the final volume.

[0079] Based on the above capacity calculations, the dimensions of the equalization tank are designed according to the influencing factors of its shape, ensuring that the equalization tank not only has the function of secondary regulation and storage but also the function of stabilizing water flow. The process is as follows:

[0080] By analyzing from the perspective of energy dissipation, the appropriate design operating water depth is determined: .

[0081] In the formula: The total head of the water diversion channel above the water intake point. Assuming average water diversion flow and water distribution Unit width flow rate obtained under the condition of flatness Here, is the flow velocity coefficient (defined as 0.85 in this invention, taking into account current advancements), and g is the acceleration due to gravity. The water depth is due to the leap.

[0082] The formula for calculating the depth of the energy dissipation pool is derived as follows: In the formula: The flooding coefficient is 1.05, which is taken in accordance with relevant standards and similar studies. The downstream water depth; The conjugate of the post-jump water depth is used to obtain the water depth S required for the energy dissipation function.

[0083] Based on the determined water depth, and considering the impact of water inrush during gate opening and closing, the extra height of the regulating reservoir is designed. This design supplements the extra height of the regulating reservoir from the perspectives of flow rate, downstream normal water level mode, equal capacity mode, and control capacity mode, to accommodate additional extra height requirements under specific operating conditions.

[0084]

[0085] In the formula: i is the average longitudinal slope of the regulating pool, L is the length of the regulating pool, R is the maximum run-up of the regulating pool, and e is the maximum wind resistance height. The sum of the water depth and freeboard is used as the design depth of the regulating pool.

[0086] Determining the pool length L here requires iterative calculation. The formula for calculating L is: .

[0087] Will simultaneously satisfy The value of L is used as the final pool length. Based on the pool capacity, pool length, and pool depth, the width B of the pool is determined, thus initially obtaining the pool capacity and corresponding size and shape.

[0088] Specifically, in one embodiment, a mathematical model verification process for constructing the regulating pool project is provided, and the specific process is as follows:

[0089] Using mainstream hydrodynamic simulation software, including but not limited to MIKE HYDRORIVER, FLUENT, and FLOW-3D, the changing trends of hydrodynamics in the regulating reservoir during operation are effectively simulated. First, the governing equations of a one-dimensional hydrodynamic model of the regulating reservoir in the water supply network are established:

[0090]

[0091] In the formula: x is the distance coordinate, t is the time coordinate, A is the cross-sectional area of ​​the equalization tank, Q is the flow rate, h is the water depth, q is the side inflow rate, C is the roughness coefficient of the tank bottom, and R is the hydraulic radius.

[0092] The coordinated application of water diversion channels, water supply networks, and regulating reservoirs in this invention incorporates a hydrodynamic module, including but not limited to: conventional 4-point difference schemes, 6-point Abbott-Ionescu schemes, and implicit finite difference schemes. This paper uses the 6-point Abbott-Ionescu scheme as an example to illustrate its application, solution, and calculation. A continuity equation is used between two flow points, and a momentum equation is used between two water point points to maintain computational stability at relatively high Courant numbers.

[0093] The momentum equation used in this invention: .

[0094] The continuity equation used in this invention: .

[0095] In the formula: the superscript represents t, the subscript represents x, and it is assumed that the time step is uniform by Δt, while the spatial step is non-uniform. , , All The function, and with time n, Q and The magnitude of Q changes with time. These are parameters used to describe the difference form. Where: , , .

[0096] To increase the stability of the model, the Courant-Friedrich Levy (CFL) number of this invention is defined as follows:

[0097]

[0098] In the formula: is the total water depth, and are the components of the flow velocity in the x and y directions, respectively; are the characteristic lengths in the x and y directions, respectively; and is the time interval. Ensure that the time interval set in the model makes the CFL number less than 1 to guarantee the quality of the simulation output from the regulating pool model.

[0099] Finally, using the aforementioned hydrodynamic model, the operational response was simulated, and any deficiencies were corrected and addressed to ultimately determine the design dimensions of the equalization tank. This process aims to eliminate potential adverse factors by simulating the evolution of the equalization tank after its construction.

[0100] Specifically, in one embodiment, a design process for a water intake gate is provided, which includes the following:

[0101] First, define the sensitivity index of the water distribution point:

[0102] In the formula: As a sensitivity indicator for the water diversion point, The magnitude of the change in flow rate at the water diversion point. The adjustment pool tax amount represents the range of change.

[0103] Introducing the disturbance caused by the operation of the gate, analyzing the characteristic parameters, it was found that the opening degree and its amplitude of the gate at different locations play the most important role in the water level change of the regulating pool. Definition:

[0104] ;

[0105] In the formula: , These are the hydraulic sensitivity indicators upstream and downstream of gate i, which are related to the water level in the regulating pool and the water distribution at the corresponding branch outlet, respectively. This represents the range of water level change in front of the sluice gate. The magnitude of the change in flow rate after the gate. This represents the range of change in the gate opening, reflecting the degree to which the gate controls the water flow upstream and downstream.

[0106] The relationship data is fitted to further serve as a verification curve for the relationship between the change in water distribution at the water outlet and the rate of change in the water level in the regulating pool. This can be achieved through methods including but not limited to linear fitting and least squares curve fitting, thereby obtaining the relationship between the change in water distribution at the water outlet and the change in the water level in the regulating pool.

[0107] Considering the flow capacity at different opening degrees during gate linkage control, an arc-shaped gate is designed. Formulas that can be used in this process include, but are not limited to, traditional gate flow calculation formulas and Henry's formula. A specific example is used here to illustrate the design of the arc-shaped gate: free outflow and submerged outflow are used. The water supply from the intake gate is considered as free outflow, simplified to the gate sill being at the same level as the regulating pool, resulting in the flow through the intake channel:

[0108]

[0109] Treating the water intake and diversion at the sluice gate at the water diversion point as submerged outflow, and continuing to make the assumptions of a bottom sill height of 0 and submerged outflow from an approximately flat-bottomed channel, the outflow formula is as follows:

[0110]

[0111] In the formula: To regulate the water depth of the pool, Let e ​​be the head of the water flow at the diversion point, b be the gate opening, and R be the radius of the arc-shaped gate. , For the corresponding free outflow and submerged outflow flow coefficients.

[0112] This allows for the accurate design of the gate's device configuration and its opening and closing operation mode.

[0113] Specifically, in one embodiment, step S2 described above is as follows: Figure 2 As shown, the specific steps include the following:

[0114] Step S21: Establish a hydrodynamic model based on flow and attribute information. Specifically, attribute information includes the dimensions, water capacity, cross-sectional area, flow area, and flow rate of the water supply channel, diversion channel, and regulating reservoir. A prototype model of the water diversion, distribution, and supply channel structure is established using digital twin technology. Existing 3D hydrodynamic models, including but not limited to MIKE21, Hydro Qual, and Fluent, can be used. Based on the continuity equation, momentum equation, and energy equation, the channel attribute information and corresponding system functions from this step are added to improve the model's form and function verification mechanism. The overall design layout and the accuracy of real-time monitoring and control during operation are simulated and verified, accurately reflecting the simulated operation of the initial channel structure in virtual space. The simulation process can refer to the simulation of the regulating reservoir and gates mentioned above, further introducing the implicit Preissmann four-point spatiotemporal eccentricity method to discretize the St. Venant equations and solving them using the pursuit method. Equation discretization format:

[0115]

[0116] In the formula: ; ; ; ; ; ; ; ; ;

[0117] Step S22: Optimize the hydrodynamic model based on preset steady-state information to construct a state-space model. Specifically, the flow equations can be used as boundary conditions for the St. Venant equations. The Preissmann implicit difference scheme is used to perform incremental linearization of the St. Venant equations at the steady point to construct the state-space model of the entire channel. The coupling relationship between the channel and the pool is implicitly contained within the model.

[0118] Step S23: Decouple the state-space model based on the water supply relationship to obtain the control model. Specifically,

[0119] Specifically, in one embodiment, step S22 described above is as follows: Figure 3 As shown, the specific steps include the following:

[0120] Step S221: Discretize the equations in the hydrodynamic model.

[0121] Step S222: Linearize the transformed equations based on preset steady-state information.

[0122] Step S223: Generate a state-space model based on the linearized equations.

[0123] Specifically, the transformation is performed using the St. Venant equations, which include two sub-equations: the continuity equation and the momentum equation. The continuity and momentum equations are discretized separately, and incremental linearization is applied at the steady-state operating point. The continuity equation is then transformed using the Pressimann four-point eccentric scheme as follows:

[0124]

[0125] In the formula: A is the cross-sectional area of ​​the water passage, where Let be the flow area at node j, Δt represent the time step, Δx represent the spatial step, Q represent the flow rate, and θ represent the angle between the tangent at the lower edge of the arc-shaped gate and the horizontal direction. For the side inflow or outflow per unit length of the channel pool, assume .

[0126] Then, if we set the steady-state operating point of the canal pool to be e, then we have:

[0127] ,

[0128] In the formula: Abbreviated as , and These are the channel equilibrium point traffic. and water level Small deviations.

[0129] Assume nodes again Flow area for Further incremental linearization expression:

[0130]

[0131] An improved transformation of the momentum equation is proposed, employing the Pressimann four-point eccentric scheme to discretize the time-domain momentum equation and incrementally linearizing it at the steady-state operating point. For the existing momentum equation:

[0132] In the formula: The radius is the hydraulic radius.

[0133] Description of the current flow through the gate:

[0134] In the formula: denoted by , which includes the lateral contraction coefficient, submergence coefficient, and flow coefficient; b is the gate's overflow width; h is the water depth of the regulating pool; and e is the gate opening degree.

[0135] Then, based on the aforementioned inner and outer boundary conditions, the fundamental equations for calculating unsteady flow are formed:

[0136]

[0137] ,

[0138] Specifically, the actual channel status can be used as the monitoring expectation, and the ability to stabilize water flow in a short period of time can be used as the control expectation. Then, the simulation results are combined with the expectation to form a feedback of deviation. The deviation from the expectation is continuously fed back and adjusted, and the simulation continues to improve the spatial model. At the same time, the channel operation and maintenance mode is verified by prototype test in combination with the actual situation. The layout of subsequent monitoring points and the rationality of the operation of water diversion, water distribution and water supply channels are obtained. Finally, the overall structural composition and control operation mode are determined.

[0139] By establishing a state-space model, the accuracy of the monitoring point placement and its ability to reflect the overall water flow status through limited monitoring data can be verified. The model also verifies operational status and the control effect under combined gate opening and closing. Verification is achieved through a combination of digital twin model simulation and prototype testing, further validating the current structure. Before the final implementation of the monitoring point layout, the accuracy of water level and flow rate measurements is verified using the constructed hydrodynamic model and model tests. Based on the monitoring station types determined in the preliminary device structure scheme, the state-space model is used to verify, through controlled variables, whether it can accurately reflect the current overall system status under different water levels, flow rates, and conditions, and whether the entire system can achieve coordination and integration.

[0140] During the verification process, if the simulation results deviate from the expected measurement accuracy and control effect, adjustments need to be made. These adjustments may include: optimizing and selecting monitoring station types, relocating monitoring stations, and adjusting the position and structure of control devices. After completing one stage of adjustments based on the current model simulation feedback, the next stage of simulation is implemented, with continuous feedback and adjustments. This process continues until the positions of the monitoring stations in the state-space model accurately represent the actual working conditions and can handle and connect different working conditions and channel states.

[0141] Specifically, in one embodiment, step S23 described above is as follows: Figure 4 As shown, the specific steps include the following:

[0142] Step S231: Decouple the opening degree of each gate and the upstream and downstream flow rates according to the water supply relationship and state space model to obtain the first correlation between flow rate and gate opening degree.

[0143] Step S232: Extract the water level data of the regulating pool corresponding to different gate openings from the attribute information.

[0144] Step S233: Perform correlation analysis on water level data and flow rate data to obtain a second correlation between flow rate and water level.

[0145] Step S234: Establish a control model based on the first and second associations.

[0146] Specifically, the relationship between water level and flow rate changes in the upstream and downstream of the channel system caused by gate opening or closure is analyzed through decoupled calculations. Due to the complex mutual influence between gate operation and water flow disturbance, the relationship and degree of influence of gate group control on the water distribution at the diversion point and the water level in the regulating pool can be obtained by combining the water flow-gate sensitivity index, thus forming a control model.

[0147] For a single gate, decoupling needs to be performed from both flow rate and water level perspectives, with the decoupling calculations primarily focused on the upstream and downstream sides of the gate. Furthermore, two modes of disturbance propagation, transmission, and superposition are considered: one along the upstream-to-downstream direction and the other along the downstream-to-upstream direction. It is assumed that the coupling effect will not affect the water supply source of the water diversion channel or the receiving area corresponding to each branch gate. The downstream of the diversion gate is taken as the starting point, and the upstream of the branch gate as the boundary of the impact. The effects of fluctuating head loss and hydraulic disturbances between branch gates during disturbance transmission are ignored. This simplifies and centrally addresses the mutual influences and interferences between actuators during control operations.

[0148] By employing decoupling computation, this study addresses the complex situation where the combined control of canal gates becomes complicated due to the overlapping and interactive influences between them. By analyzing the coupling relationships in the operation control of water intake and diversion, a decoupling element is introduced to reduce the mutual influence of hydrodynamic disturbances generated during the operation of each gate on water flow and gate control disturbances. Furthermore, the study eliminates the effects of these complex disturbances during the development of control methods, thereby facilitating the implementation of the control process. Decoupling methods that can be used here include, but are not limited to, feedback decoupling, complex vector decoupling, categorical decoupling, decoupling depth networks, and decoupling using adapter patterns. This study uses an improved dynamic enhanced coordinated decoupling control algorithm as an example to illustrate its application in the control of water intake, diversion, and supply, demonstrating the application of decoupling computation in the combined gate control of a water supply canal system.

[0149] a. A decoupled control algorithm is used for each individual gate. The control variables are divided into gate opening output decoupling and flow output decoupling. By combining the control variables, the gate opening and flow are decoupled from the upstream and downstream directions of the channel.

[0150] b. To decouple the gates at the diversion point from the upstream direction, the current gate operation is transmitted to the upstream intake gate to accelerate the time required for the flow rate through the regulating pool and corresponding channels to change, thereby preventing the control operation, especially the flow disturbance generated by the control, from propagating upstream towards the water intake.

[0151] c. To decouple the water intake gates of the water diversion channel downstream, a portion of the current operation of the water intake gate is transmitted to the downstream diversion gate to prevent the propagation of control disturbances downstream, thereby isolating the impact of the opening and closing of the water intake gates on subsequent water diversion and supply.

[0152] d. Integrate flow output decoupling and gate opening output decoupling into practical applications. Use flow control as an indirect decoupling mechanism and the actual gate as the control structure. For this purpose, use a flow controller to convert flow output into gate opening output. This not only effectively isolates the coupling transmitted downstream, but also speeds up the response of the control system to disturbances.

[0153] 5. A decoupled calculation-based control process is established. When the flow rate in the water diversion channel changes, causing the water level in the regulating reservoir to deviate from the target value, the water level error is fed back into the control system to obtain the flow error for the water diversion channel. This error is then added to the output flow rate obtained from the decoupled calculation upstream and fed back into the control model. The control model calculates the adjustment value for the opening of the water diversion gate and controls the gate's actuator. By maintaining a stable water level in the regulating reservoir, fluctuations in the flow rate leading to the water distribution point are mitigated, preventing upstream flow changes from propagating downstream. The coupling effect of the control system is also considered, thus preventing the transmission and superposition of disturbances. Furthermore, when the flow rate at the water distribution point deviates from the set value, the gate opening can be adjusted in coordination with the decoupled output, avoiding complex hydrodynamic disturbances and effects during the combined operation of gate groups at different locations.

[0154] Specifically, the decoupling calculation control algorithm here addresses the decoupling of the gate opening output, specifically the decoupling of the diversion gate from the water distribution gate to the water intake gate at the water intake channel:

[0155]

[0156] Decoupling of the intake gate from the diversion gate:

[0157]

[0158] Decoupling of traffic output:

[0159]

[0160] In the formula: Let be the opening degree of the i-th gate among the i-th water distribution outlets. Let i be the water distribution volume of the i-th gate's water distribution outlet. The value of k represents the deviation between the water level at the sluice gate i and the corresponding water supply target setting, where k represents the time period. , These represent the proportional coefficient and integral coefficient of the i-th water outlet in the model algorithm, respectively, and the subscript 0 represents the coefficient of the water intake gate at the water intake channel; , These are the gate opening and the decoupling parameters for decoupling the flow output, respectively.

[0161] Decoupling parameters are determined through simulation. Initial operating conditions for each component are set based on hydrodynamic simulation, and the simulation time and step size are specified (e.g., 24 hours simulation, 3-minute step size). During the simulation, relevant control coefficients and decoupling parameters are continuously adjusted. The values ​​of the decoupling parameters are constantly corrected based on the water level error process curve. The decoupling effect in the upstream and downstream directions of flow output and gate output is analyzed. Furthermore, the manner and extent of the gate control's influence on water level and flow are analyzed. Combined with the fluctuation amplitude of water level and flow, a system stability judgment is made under the decoupling effect, ensuring balanced system stability and response speed.

[0162] Based on the coupling effect between gate controls and the coordinated application of corresponding flow decoupling and gate opening decoupling, algorithms for water intake, distribution, and supply control are derived, generating a control model. This facilitates the subsequent determination of feedback control links in the control model based on preset control target values, forming the control process: Monitoring the water distribution volume at the water inlet and the water level in the regulating reservoir is implemented. When the water distribution volume at the water inlet deviates from the preset control target value, or the water level in the regulating reservoir deviates from the steady-state range, the deviations of the water level and water distribution volume from the set values ​​are used as inputs to the control terminal. For the water level deviation in the regulating reservoir, the corresponding flow change ΔQ in the water intake channel is calculated. The decoupling flow is calculated through the decoupling controller, and this decoupling flow, along with the feedback flow, is input to the flow controller in the control terminal. The flow controller then outputs the gate opening change ΔG. In this process, all controllable conditions are converted into control information for the opening of each gate, corresponding to the upstream regulating reservoir water level control and the downstream water inlet flow control. From both upward and downward directions, with opening decoupling as the objective, the final control data is obtained.

[0163] Specifically, in one embodiment, the monitoring data in step S3 above includes gate opening data, flow rate data, and water level data, such as... Figure 5As shown, the specific steps include the following:

[0164] Step S31: Obtain the preset monitoring cycle.

[0165] Step S32: Collect the opening data of the water intake gate and the water diversion gate, the flow data upstream and downstream of each gate, and the water level data of the regulating pool according to the preset monitoring cycle.

[0166] Specifically, by setting a monitoring cycle, data can be collected periodically, and the monitoring cycle time can be changed according to time or accuracy requirements, providing greater flexibility.

[0167] Specifically, in one embodiment, the water supply network system consists of multiple water intake channels connected to the water supply channels, drawing water from the water supply channels; at the same time, each water outlet is also connected to the next level of water supply channels for water supply, thus forming a complex water supply network system with multi-stage regulating pools.

[0168] Specifically, in one embodiment, step S3 described above is as follows: Figure 6 As shown, the specific steps also include the following:

[0169] Step S331: Compare the water level data and flow rate data with the preset control target value to obtain the deviation data.

[0170] Step S332: Determine whether the deviation data is greater than the preset deviation value.

[0171] Step S333: When the deviation data is less than or equal to the preset deviation value, return to the step of monitoring the actual opening degree, flow rate, and water level in the regulating reservoir of the intake and diversion gates. Specifically, if the current water supply situation is consistent with the target, there is no need to control the gates until a large error occurs that requires adjustment through control, at which point the subsequent steps will be executed.

[0172] Step S334: When the deviation data is greater than the preset deviation value, the water level data and flow data are denoised to obtain updated monitoring data, and the updated monitoring data is used to input the monitoring data and the preset control target value into the control model.

[0173] Specifically, due to fluctuations in water levels, and because the water level under non-steady-state control is inherently dynamic, changing, and fluctuating, data filtering methods are employed, including but not limited to ADRC (Active Disturbance Rejection Control), amplitude limiting filtering, median filtering, arithmetic mean filtering, recursive average filtering, median average filtering, amplitude limiting average filtering, debouncing filtering, and Kalman filtering.

[0174] Specifically, disturbances generated during monitoring can be handled using Active Disturbance Rejection Regulator (ADRC) as an example. Its components can be divided into three parts: a tracking-differentiator (TD), an extended state observer (ESO), and a state error feedback law (SEFL), forming a... Figure 7 The algorithm structure shown is as follows:

[0175] Where X is the real-time input signal, X1 is the approximate input extracted by the differential tracker, and X2 is the differential signal; e1 and e2 are both error signals; z1, z2, and z3 are the state observation signals of the extended state controller; u0 is the input control gain, u is the controller input, b0 is the feedback compensation factor; mg0 represents large-amplitude, high-load fluctuations; and Y is the relative deviation between the current channel water level and flow rate and the steady state.

[0176] Assuming a specific measurement value is influenced by three main factors—its own characteristics, the gate system at the water diversion point, and the regulating reservoir—the monitoring data from these three monitoring points are described using new state variables.

[0177]

[0178] in: This represents the inertial time constant of the channel gate linkage control; , All of these are constants for the self-adjustment coefficient. This indicates large load fluctuations. By processing the measured data using an active disturbance rejection algorithm, accurate measured water level and flow rate information can be obtained after removing disturbances and noise.

[0179] A mechanism for converting real-time monitoring data acquisition to discrete sampling acquisition is implemented, and the corresponding time path and method are derived. Based on the active disturbance rejection algorithm, a fuzzy sampling data controller based on the parallel compensation principle is developed. Furthermore, periodic sampling conditions are applied to the real-time data collection to form a preprocessing mechanism for water level and flow monitoring. Two data state feedback mechanisms with fuzzy rules are designed for the inputs of water level and flow, as follows:

[0180]

[0181]

[0182] In the formula: , These are the feedback gains of the two rules that need to be designed separately; It is the output vector in the corresponding rule; It refers to the fixed time points (and also fixed time periods) for monitoring data collection. Initial monitoring values Sampling is performed using a zero-order hold and through a piecewise function. It reflects the real-time monitored water level and flow rate information; similarly, it also indicates the water level and flow rate subsystems respectively. The state vector at time t. The total solution of the fuzzy controller is the fuzzy output. Combined with discrete control signals It can be expressed as Furthermore, the weight of the i-th local model is introduced. ,express: This serves as the design of the controller for data acquisition and preprocessing in this invention.

[0183] This method allows us to obtain the output from the zero-order hold (ZOH) under two rules, transforming continuous real-time, initial monitoring into periodic, regularized water level and flow monitoring, resulting in a closed-loop model with a fuzzy sampling data control law.

[0184]

[0185] and its corresponding discretized system model:

[0186]

[0187] In the formula: To control the coefficient matrix of the transfer function, To control the input coefficient matrix, represents the weight of the i-th local model, and h is a constant sampling period. Let be the real-time monitoring value obtained from the j-th sample, and s be the time constant of the fuzzy controller for the acquired data.

[0188] By combining a fuzzy linearization system with fuzzy control of sampled data, the sampling process of water level and flow signals from water diversion, distribution, and supply systems is performed at regular time intervals to acquire real-time monitoring data. This monitoring data, which includes interference and noise, is used as an external input signal W. Then, a regulating system, a corresponding sampler S, and a fuzzy controller K are added. d A zero-order hold H forms a fuzzy system for data acquisition and preprocessing. Based on the external input signal W, it is first converted into a sampling input signal Y suitable for sampling operation control. Then, through the combined use of water level and flow monitoring equipment and the sampler, periodic discrete state values ​​Y are obtained from the continuous real-time changes in water level and flow parameters. d The discrete state values ​​are then further processed by a discrete-time fuzzy controller to form a discrete signal U. d The input is then passed through a zero-order hold to form the control input U, and then through an automatic processing system to obtain the corresponding output Z.

[0189] By adding an active disturbance rejection algorithm and combining discrete monitoring data with fuzzy sampling, the system is unified into real-time state monitoring, evaluation, and deviation processing. The real-time initial monitoring data is used as input to process disturbances and deviations during the monitoring process, thereby obtaining accurate water level information with disturbances and noise removed.

[0190] Specifically, in one embodiment, before performing step S5 as described above, such as Figure 7 As shown, the specific steps include the following:

[0191] Step S41: Construct a prediction model based on water supply transmission information, state-space model, and hydrodynamic model.

[0192] Step S42: Input the control data into the prediction model to predict the water level and flow rate data after adjusting the opening, and obtain the prediction results.

[0193] Step S43: Determine whether the difference between the prediction result and the preset control target value is greater than the preset threshold.

[0194] Step S44: If the difference is greater than the preset threshold, adjust the model parameters of the control model and return to the step of inputting the monitoring data and the preset control target value into the control model to obtain the control data, until the difference is less than or equal to the preset threshold.

[0195] Specifically, by continuously adjusting the control model through predictive models, the accuracy and reliability of the control model can be effectively improved. The process of establishing the predictive model is as follows:

[0196] Deep learning is applied to form a correction mechanism for instability, and a regression model is used to establish a state space. Combined with the application of a hydrodynamic model, a prediction function model is formed. Fuzzy neural networks are used for input hierarchical and classification purposes. Mechanism control and fuzzy neural network-based prediction model control are used to form a transition and connection from principle control to fuzzy control and predictive control, realizing a prediction function based on a state space model.

[0197] First, through supervised learning and the aforementioned state-space model, the equations for water level and flow rate are applied to the gate based on the water flow mass conservation law and the gate outflow formula:

[0198]

[0199] In the formula: For the flow rate through the gate, Let be the gate orifice flow coefficient, u be the gate opening, and b be the gate orifice width. This can be expressed as a matrix solution space:

[0200]

[0201] In the formula: , , , , , .

[0202] To process the disturbance term, let nodes j and j+1 be the nodes before and after the water diversion point, respectively. Let the water flow rate at the water distribution point be denoted as . Then the relationship between water level and flow rate between nodes j and j+1 is as follows:

[0203]

[0204] Furthermore, based on the model transformation matrix, a computational node is used to correspond to the two variables of water level and flow rate, and a gate boundary term is introduced to increase the sparsity of the model transformation matrix. The corresponding details are as follows:

[0205]

[0206] The processed model is transformed into a spatial form and written as a general expression for the system state equations:

[0207]

[0208] In the formula: , , And the matrix , and Depends on the channel steady-state operating point The deviation signal is segmented, and the input control signal is matched according to rules and membership functions. This constructs the state space of the water supply system.

[0209] Based on this, the parameters of the prediction model function are obtained through learning, and then the prediction model is constructed through feedback and adjustment. The prediction problem is solved using a regression model, taking the water level values ​​at multiple points in the control process at the same time in each sample as independent variables and the corresponding gate control indicators as dependent variables. Regression analysis methods that can be used include, but are not limited to: Linear Regression, Logistic Regression, Polynomial Regression, Stepwise Regression, Ridge Regression, Lasso Regression, Elastic Net Regression, etc., forming a near-continuous mapping relationship between independent and dependent variables.

[0210] The state space of the water supply system is used as the controlled model object, and simulated control is applied to guide gate control. Then, a regression model is used to quantitatively describe the statistical relationship between inputs and outputs in the sample, such as the different water level feedbacks caused by different control operations under similar operating conditions. Further, combined with the adjustment of the state space expression, predictive modeling techniques are formed to study the relationship between water level, flow rate, and the control of various gate openings, as well as the influence of variables under different situations. Testing, feedback, and adjustments are then performed to form regression-predictive analysis, statistical testing, and verification of the significance of specific problems, ultimately leading to practical application.

[0211] Further regression verification was applied to the state-space model to obtain the parameters of the prediction function suitable for this invention. Through simulation, computation, and feedback adjustment, the parameters of the prediction function were verified and finally determined, resulting in a reasonable prediction model. Using water level as input, this model can predict subsequent water level and flow rate trends after control decisions are applied. The inductively derived k+1 time-time prediction model uses a linear combination of basis functions. Using this to represent control input can solve the problem of ambiguous control input and effectively reduce online computation. It can be represented as:

[0212]

[0213] In the formula: Let J represent the control variable, and J represent the number of basis functions. This represents the linear weighting coefficients obtained from basis function optimization calculations. This represents the value of the odd function at a given time point within the sampling period.

[0214] Further details on the construction of the prediction model function:

[0215]

[0216]

[0217] in: A predictive model representing the state of a device system. This represents the prediction model for the opening degree of each gate in the system. Indicates free response output, This indicates a forced response output.

[0218] This invention defines predictive control for water diversion, distribution, and supply as a time-sliding control method that continuously corrects for the predicted water level deviation at control points in subsequent time periods based on the current state of the channel. For example, if the water diversion flow changes at time K, the predicted changes in the control point water level over the next N time periods are calculated. These changes are compared to the set water level values, and the control input is adjusted to correct the model parameters, resulting in a new predicted value. This process is repeated, adjusting the control input or control model parameters based on the measured values ​​of the current time period, ultimately maintaining a constant water level at the control points. The key characteristic of predictive control is its ability to determine current actions based on future changes. During actual operation, the channel's operating state is adjusted in real time according to changes in future water diversion targets. Control decisions for the current time period are made based on predicted future system requirements and anticipated changes in external disturbances.

[0219] The optimal control law of the system is solved using a quadratic optimal regulator design method through an expanded error system containing M-step future information. Error system:

[0220]

[0221] In the formula: The error signal after first-order difference, and the system matrix of the error system. Input matrix Perturbation matrix .

[0222] Suppose that the change in the external disturbance can be predicted M steps in advance, and define:

[0223] , ,

[0224] Then, using predictive modeling, the error system is expanded to include M-step future perturbation information:

[0225]

[0226] In the formula: , ( )

[0227] Based on this, the expression for the control decision guidance is obtained:

[0228]

[0229]

[0230] A fuzzy control mechanism based on prediction functions is employed. The prediction model, combined with intelligent contingency plan generation, and applied to complex water supply systems, enables predictive control in the state space. Building upon fuzzy control, a fuzzy neural network is introduced, treating the classification problem of input states as essentially a regression of each category. From a classification perspective, the inputs are categorized and hierarchically layered, corresponding to reasonable states in the state space under fuzzy control, and outputting discrete linkage control guidelines. This invention uses a loss function to make assumptions about the label distribution, then derives the maximum likelihood formula for all samples using the maximum likelihood method, and finally uses convex optimization (gradient descent) to solve the regression model.

[0231]

[0232] in: This is the predicted value, and n is the number of sample data used in the regression model.

[0233] Furthermore, the system device adjustment system, as the generalized controlled object in this invention, utilizes a decoupling control algorithm based on a fuzzy neural network to obtain the desired and actual output vectors, input vectors, and control vectors. Then, the fuzzy neural network is trained, with the training iterations and initial parameters, including the center and width of the Gaussian function and the weights of the neural network, pre-set. The input signal is then fed into the channels of the FNN. The objective function is solved to determine if the accuracy requirements are met. If the accuracy is unsatisfactory, the fuzzy neural network parameters are readjusted, and the objective function is recalculated. Training ends when all samples meet the accuracy requirements or the number of training iterations reaches the set value.

[0234] This embodiment also provides a water supply network system control device. The water supply network system includes: at least one regulating tank, the water supply end of which is connected to a water intake channel, the water outlet end of which is provided with a plurality of water distribution outlets, a water intake gate provided on the water intake channel, and water distribution gates provided on the water distribution outlets. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0235] This embodiment provides a water supply network system control device, such as... Figure 8 As shown, it includes:

[0236] The acquisition module 101 is used to acquire the attribute information of the water diversion channel and regulating pool in the water supply network system, the flow information of the upstream and downstream of the gate corresponding to different gate openings of the water diversion gate and the water distribution gate, and the water supply relationship between the water diversion gate and the water distribution gate. For details, please refer to the relevant description of step S1 in the above method embodiment, which will not be repeated here.

[0237] Module 102 is used to establish a control model based on attribute information, flow information and water supply relationship. For details, please refer to the relevant description of step S2 in the above method embodiment, which will not be repeated here.

[0238] The monitoring module 103 is used to monitor the actual opening degree, flow rate and water level in the regulating pool of the water intake gate and the water diversion gate, and obtain monitoring data. For details, please refer to the relevant description of step S3 in the above method embodiment, which will not be repeated here.

[0239] The calculation module 104 is used to input the monitoring data and the preset control target value into the control model to obtain control data. For details, please refer to the relevant description of step S4 in the above method embodiment, which will not be repeated here.

[0240] The adjustment control module 105 is used to adjust the opening degree of the water intake gate and the water diversion gate according to the control data. For details, please refer to the relevant description of step S4 in the above method embodiment, which will not be repeated here.

[0241] In this embodiment, the water supply network system control device is presented in the form of a functional unit. Here, a unit refers to an ASIC circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0242] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0243] According to embodiments of the present invention, a water supply network system is also provided, such as... Figure 9 As shown, the water supply network system includes:

[0244] At least one regulating reservoir 1006 is provided. The water supply end of the regulating reservoir 1006 is connected to the water intake channel 1004, and the water outlet end is equipped with several branch outlets 1008. A water intake gate 1005 is installed on the water intake channel 1004, and a branch outlet gate 1007 is installed on each of the branch outlets 1008. Specifically, water flows from the water supply channel 1003 to the water intake channel 1004, passes through the regulating reservoir 1006, and then flows to each branch outlet 1008. A water intake gate 1005 is installed at the outlet of the water intake channel 1004 to control the incoming water volume. By adding the regulating reservoir 1006 to connect each branch outlet 1008, it plays a secondary regulating role and supplements the insufficient control. A branch outlet gate 1007 is installed at the front end of each branch outlet 1008 to regulate the water volume of each branch outlet. Different water supply demands are met by controlling the opening of the gates. When the water level in the regulating reservoir 1006 drops, the intake gate 1005 is opened to increase the water supply to ensure stability. If the water level exceeds a specified value, the intake gate 1005 is closed. Alternatively, to achieve dynamic regulation, the opening degree of the intake gate 1005 can be controlled to regulate the water level in the regulating reservoir 1006 while supplying water. When the water distribution at certain water distribution outlets 1008 deviates from the target water receiving setting, the flow rate at the corresponding water distribution gate 1007 is adjusted to control the flow rate at the water distribution outlet 1008, thereby ensuring that fluctuations in water level and flow rate remain stable within the specified range.

[0245] The system further includes a processor 1001 and a memory 1002, wherein the processor 1001 and the memory 1002 can be connected via a bus or other means. Figure 10 Taking the example of a connection between China and Israel via a bus.

[0246] Processor 1001 may be a central processing unit (CPU). Processor 1001 may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.

[0247] The memory 1002, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the method embodiments of the present invention. The processor 1001 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory 1002, thereby implementing the methods in the above method embodiments.

[0248] The memory 1002 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor 1001, etc. Furthermore, the memory 1002 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory 1002 may optionally include memory remotely located relative to the processor 1001, and these remote memories may be connected to the processor 1001 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0249] One or more modules are stored in memory 1002 and, when executed by processor 1001, perform the methods described in the above method embodiments.

[0250] The system also includes multiple sensors installed at the intake gate, regulating pool, and diversion gate to collect gate opening, flow rate, and water level data.

[0251] The specific details of the above-mentioned water supply network system can be understood by referring to the relevant descriptions and effects in the above method embodiments, and will not be repeated here.

[0252] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0253] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A control method for a water supply network system, characterized in that, The water supply network system includes: a water supply channel, multiple water intake channels, water intake gates and regulating reservoirs corresponding to the number of water intake channels, multiple water distribution gates, and multiple water distribution outlets. The water supply channel is connected to the multiple water intake channels. The water intake channels are connected to the water intake end of the regulating reservoir through the water intake gates. The water outlet end of the regulating reservoir is connected to the multiple water distribution outlets through the water distribution gates. The control method includes: Acquire the attribute information of the water diversion channel and the regulating reservoir in the water supply network system, the flow information of the upstream and downstream of the water diversion gate corresponding to different gate openings of the water diversion gate and the water distribution gate, and the water supply relationship between the water diversion gate and the water distribution gate; the attribute information includes the size information, water capacity information, cross-sectional area, flow area and flow rate of the water supply channel, water diversion channel and regulating reservoir; A control model is established based on the attribute information, the flow rate information, and the water supply relationship; the establishment of the control model based on the attribute information, the flow rate information, and the water supply relationship includes: establishing a hydrodynamic model based on the flow rate information and the attribute information; optimizing the hydrodynamic model based on preset steady-state information to construct a state-space model; and performing decoupling analysis on the state-space model based on the water supply relationship to obtain the control model; The actual opening degree and flow rate of the water intake gate and the water diversion gate, as well as the water level in the regulating pool, are monitored to obtain monitoring data; The monitoring data and the preset control target value are input into the control model to obtain control data; The opening degrees of the water intake gate and the water diversion gate are adjusted according to the control data.

2. The water supply network system control method according to claim 1, characterized in that, The optimization and construction of a state-space model based on preset steady-state information of the hydrodynamic model includes: Discretize the equations in the hydrodynamic model. The transformed equations are linearized based on preset steady-state information; A state-space model is generated based on the linearized equations.

3. The water supply network system control method according to claim 1, characterized in that, The step of decoupling the state-space model based on the water supply relationship to obtain the control model includes: Based on the water supply relationship and the state space model, the opening degree of each gate and the upstream and downstream flow rates are decoupled to obtain the first correlation between the flow rate and the gate opening degree. Extract water level data of the regulating pool corresponding to different gate openings from the attribute information; A correlation analysis was performed on the water level data and flow rate data to obtain a second correlation between flow rate and water level; A control model is established based on the first association and the second association.

4. The water supply network system control method according to claim 1, characterized in that, The monitoring data includes gate opening data, flow rate data, and water level data. The actual opening and flow rate of the intake gate and the diversion gate, as well as the water level in the regulating reservoir, are monitored to obtain the monitoring data, including: Obtain the preset monitoring cycle; According to the preset monitoring cycle, the opening data of the water intake gate and the water diversion gate, the flow data upstream and downstream of each gate, and the water level data of the regulating pool are collected respectively.

5. The water supply network system control method according to claim 4, characterized in that, The method further includes: The water level data and the flow rate data are compared with the preset control target value to obtain the deviation data; Determine whether the deviation data is greater than a preset deviation value; When the deviation data is less than or equal to the preset deviation value, the process returns to the step of monitoring the actual opening degree and flow rate of the water intake gate and the water diversion gate, as well as the water level in the regulating pool. When the deviation data is greater than the preset deviation value, the water level data and the flow rate data are denoised to obtain updated monitoring data, and the step of inputting the monitoring data and the preset control target value into the control model is performed based on the updated monitoring data.

6. The water supply network system control method according to claim 1, characterized in that, Before adjusting the opening of the intake gate and the diversion gate according to the control data, the method includes: A prediction model is constructed based on water supply transmission information, the state-space model, and the hydrodynamic model. The control data is input into the prediction model to predict the water level and flow rate data after the opening degree is adjusted, and the prediction results are obtained. Determine whether the difference between the prediction result and the preset control target value is greater than a preset threshold; If the difference is greater than a preset threshold, the model parameters of the control model are adjusted, and the process of inputting the monitoring data and the preset control target value into the control model to obtain control data is repeated until the difference is less than or equal to the preset threshold.

7. A control device for a water supply network system, the water supply network system comprising: At least one regulating tank, wherein the water supply end of the regulating tank is connected to a water intake channel, and the water outlet end is provided with a plurality of water distribution outlets; a water intake gate is provided on the water intake channel, and a water distribution gate is provided on each water distribution outlet; characterized in that the device comprises: The acquisition module is used to acquire attribute information of water diversion channels and regulating reservoirs in the water supply network system, flow information of upstream and downstream of different gate openings of water diversion gates and water distribution gates, and water supply relationship between the water diversion gates and the water distribution gates; the attribute information includes the size information, water capacity information, cross-sectional area, flow area, and flow rate of the water supply channels, water diversion channels, and regulating reservoirs. A module is established to build a control model based on the attribute information, the flow information, and the water supply relationship. The process of building the control model based on the attribute information, the flow information, and the water supply relationship includes: building a hydrodynamic model based on the flow information and the attribute information; optimizing the hydrodynamic model based on preset steady-state information to construct a state-space model; and performing decoupling analysis on the state-space model based on the water supply relationship to obtain the control model. The monitoring module is used to monitor the actual opening degree and flow rate of the water intake gate and the water diversion gate, as well as the water level in the regulating pool, and to obtain monitoring data. The calculation module is used to input the monitoring data and the preset control target value into the control model to obtain control data; An adjustment control module is used to adjust the opening degree of the water intake gate and the water diversion gate according to the control data.

8. A water supply network system, characterized in that, include: At least one regulating tank, the water supply end of which is connected to a water diversion channel, and the water outlet end is provided with several water distribution outlets. A water diversion gate is provided on the water diversion channel, and a water distribution gate is provided on the water distribution outlets. The system further includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the water supply network system control method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the water supply network system control method according to any one of claims 1-6.

Images