A water gate control system for a reservoir

By using the method of combining genetic program modules with integrated measurement and control gates during flood discharge in the reservoir, the parameters are adjusted in real time to generate accurate flow through the tillage, which solves the problem of timeliness and accuracy of flood discharge warnings in the existing technology, and reduces the water level The sensitivity of the , improves the fitting accuracy and generalization ability.

CN118732512BActive Publication Date: 2024-12-03SHAOYANG WATER CONSERVANCY & HYDRO POWER RECONNAISSANCE & DESIGN INST
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411235399.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-12-03
Estimated Expiration
2044-09-04

AI Technical Summary

Technical Problem

It is difficult to accurately determine the gate opening and flow rate of the gate during the flood discharge of the reservoir in the prior art, resulting in insufficient timeliness and accuracy of flood discharge warnings, and is highly sensitive to changes in water levels in front of the gate and water levels behind the gate.

Method used

The genetic program module is used to combine it with the integrated measurement and control gate. Through normalized calculation formulas and hydraulic formulas, parameters are adjusted in real time to generate accurate flow through the tide, and early warning and control are carried out in combination with the Internet of Things cloud platform.

Benefits of technology

It realizes the rapid and accurate generation of real-time pass-through flow when the gate collects data is large, which enhances the timeliness and accuracy of flood discharge warnings, reduces the sensitivity to water level, and improves the schema of the optimal objective function. Combination accuracy and generalization ability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118732512B_ABST
    Figure CN118732512B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of water conservancy equipment, and provides a water gate control system for a reservoir, including a measurement and control integrated gate, a model unit, a calculation unit and an early warning unit; the measurement and control integrated gate has a telemetry function of gate opening, water level before the gate and water level after the gate; the model unit is equipped with a genetic program, and the gate opening, water level before the gate and water level after the gate or the corresponding hydraulic coefficient in the historical data are normalized and the measured gate flow is used for iterative genetic program to obtain an optimal objective function; the calculation unit obtains the real-time gate flow of the reservoir through the collected value and the optimal objective function; the early warning unit determines that the real-time gate flow exceeds the upper limit value, then controls the measurement and control integrated gate to reduce the opening, and issues an early warning. The present invention realizes the rapid and accurate generation of real-time gate flow, realizes the timely and accurate adjustment of the gate opening, and enhances the timeliness and accuracy of reservoir flood discharge early warning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of water conservancy equipment, and in particular to a sluice control system for a reservoir. Background Art

[0002] In the process of flood prevention and disaster reduction, reservoirs need to regulate flood flow through gate-type flood discharge to reduce the occurrence of flood disasters downstream, help balance the water level of the reservoir, and avoid dam safety problems caused by excessively high water levels in the reservoir. This regulation mechanism is crucial to protecting the safety of downstream areas, especially when natural disasters such as heavy rains occur.

[0003] However, the traditional hydraulic empirical formula is currently used to determine the flow rate through the reservoir gate during flood discharge. It is necessary to manually correct the parameters in the formula regularly based on the measured water conditions data, which has poor flexibility. In addition, due to the nonlinear relationship between the water level before the gate, the water level after the gate, the gate opening and the flow rate through the gate, it is difficult to obtain the accurate relationship formula through a simple data fitting method.

[0004] For example, the patent with application number 202110929190.5 discloses that the integrated measurement and control gate calculates the target opening by adopting RBF (Radial Basis Function) neural network. However, during the flood discharge process, due to the powerful nonlinear mapping ability of the RBF neural network, it is highly sensitive to the training parameters and has weak generalization ability. During the flood discharge process, the water levels before and after the gate collected by the integrated measurement and control gate as training parameters fluctuate greatly and cannot accurately reflect their actual levels. Therefore, the target opening obtained by the method disclosed in this patent cannot be applied to the flood discharge process of the reservoir gate.

[0005] Therefore, how to utilize the remote sensing function of the integrated measurement and control gate for the gate opening, water level before the gate, and water level after the gate to determine the accurate flow rate through the integrated measurement and control gate, so as to issue early warnings in a timely and accurate manner during the flood discharge process and adjust the gate opening in a timely and accurate manner is a technical problem that needs to be solved. Summary of the invention

[0006] To this end, the present invention provides a sluice control system for a reservoir, which obtains real-time flow through the sluice through a genetic program, ensuring that even if the water levels before and after the sluice collected by the sluice during the flood discharge process as training parameters change greatly and are not accurate enough, the genetic program can quickly adjust the parameters without making a lot of modifications to the algorithm itself, thereby achieving rapid and accurate generation of real-time flow through the sluice, timely and accurate adjustment of the gate opening, and enhancing the timeliness and accuracy of reservoir flood discharge warning.

[0007] To achieve the above object, the present invention proposes a water gate control system for a reservoir, comprising a measurement and control integrated gate and a genetic program module;

[0008] The integrated measurement and control gate has the remote measurement function of gate opening, water level before the gate and water level after the gate. The water level before the gate is the water level in front of the reservoir dam where the gate is installed.

[0009] The genetic program module communicates with the integrated measurement and control gate, and includes a model unit, a calculation unit and an early warning unit;

[0010] The model unit is equipped with a genetic program, and the gate opening, the water level before the gate, and the water level after the gate in the historical data are normalized and used as neurons of the input layer of the genetic program respectively, and the measured gate flow for flood discharge, or the hydraulic coefficient corresponding to the measured gate flow, is used as the neuron of the output layer of the genetic program, and the genetic program calculates to obtain the optimal objective function;

[0011] The calculation unit inputs the gate opening, water level before the gate and water level after the gate collected in real time into the optimal objective function of the model unit to obtain the real-time gate flow rate of the reservoir for flood discharge;

[0012] When the early warning unit determines that the real-time gate flow rate exceeds the upper limit value, the integrated measurement and control gate is controlled to reduce the opening degree and a warning instruction is issued;

[0013] The normalized calculation formula of the model unit is:

[0014] ;

[0015] And / or, the normalized calculation formula of the model unit is:

[0016] ;

[0017] Wherein, Z is the normalized output value, X is the normalized input value, is the average value of the normalized input value, and S is the standard value of the normalized input value;

[0018] The standard value S is the pre-sluice design water level for the pre-sluice water level, the post-sluice design water level for the post-sluice water level, and the gate opening is the water depth under the pre-sluice design water level.

[0019] In particular, the sensitivity of the genetic program to the water levels before and after the gate is further reduced through the normalized calculation formula.

[0020] Furthermore, the model unit also normalizes the measured gate flow rate, wherein the standard value S for the gate flow rate is the design flow rate of the gate.

[0021] Furthermore, the genetic program module is mounted on the IoT cloud platform and also includes a big data unit;

[0022] The model unit obtains the gate opening, water level before the gate, water level after the gate and measured flow rate from at least 1000 historical data in the big database stored in the big data unit for iterative training of the genetic program, thereby obtaining the optimal objective function.

[0023] Furthermore, the early warning unit obtains the downstream waterway data recorded by the IoT cloud platform, and issues an early warning level instruction based on the comprehensive setting of the real-time lock flow and the downstream waterway data.

[0024] Furthermore, the early warning unit is equipped with a calculation formula for predicting the flood discharge height of the downstream waterway, specifically:

[0025] ;

[0026] Wherein, A is the predicted flood discharge height of the downstream waterway, Q is the real-time gate flow, W is the design width of the downstream waterway, and L is the real-time water level of the downstream waterway;

[0027] The early warning unit determines the early warning level instruction to be issued according to the level interval of the predicted downstream waterway flood discharge height;

[0028] The early warning unit obtains the rainfall data of the downstream waterway recorded by the Internet of Things cloud platform, and if the rainfall data exceeds the upper limit of rainfall, the early warning level instruction is increased by one level.

[0029] Further, the early warning unit includes a gate control subunit;

[0030] When it is determined that the real-time gate flow exceeds the upper limit value, the gate control subunit inputs the difference between the set opening and the actual gate opening into the control algorithm to obtain an adjustment value for reducing the opening of the integrated measurement and control gate.

[0031] Furthermore, the control algorithm is a PID control algorithm, and the gate control subunit sets corresponding proportional gain, integral gain and differential gain according to the warning level instruction.

[0032] Furthermore, the genetic program module also includes a hydraulic coefficient calculation unit;

[0033] The hydraulic coefficient calculation unit is used to obtain the relationship between the hydraulic coefficient, the gate flow rate, and the water level before the gate according to the gate flow rate calculation formula of hydraulics;

[0034] The model unit uses the hydraulic coefficient as the neuron of the output layer of the genetic program to obtain the optimal objective function with the gate opening, the water level before the gate and the water level after the gate as independent variables and the hydraulic coefficient as the dependent variable;

[0035] The calculation unit inputs the gate opening, water level before the gate and water level after the gate collected in real time into the optimal objective function of the model unit to obtain a predicted hydraulic coefficient, and substitutes the predicted hydraulic coefficient into the gate flow calculation formula to obtain the predicted gate flow.

[0036] In particular, by combining the hydraulic formula for calculating the flow rate through the sluice hole, the fitting accuracy and generalization ability of the optimal objective function obtained by genetic programming are further enhanced.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] 1. The real-time flow rate through the gate is obtained through the genetic program, which ensures that even if the water levels before and after the gate collected by the gate during the flood discharge process as training parameters change greatly and are not accurate enough, the genetic program can quickly adjust the parameters without making a lot of modifications to the algorithm itself. Therefore, the real-time flow rate through the gate is generated quickly and accurately, and the gate opening is adjusted in a timely and accurate manner, which enhances the timeliness and accuracy of the reservoir flood discharge warning.

[0039] 2. Through the normalized calculation formula, the sensitivity of the genetic program to the water level before and after the gate is further reduced.

[0040] 3. By combining the hydraulic formula for calculating the flow rate through the gate hole, the fitting accuracy and generalization ability of the optimal objective function obtained by genetic programming are further enhanced.

[0041] 4. By setting the control algorithm according to the warning level instructions, the adjustment speed of the gate opening can be flexibly controlled during flood discharge. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A schematic diagram of the general structure of a water gate control system according to an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of the general flow of a water gate control system according to an embodiment of the present invention;

[0044] Figure 3 A detailed flow chart of a water gate control system according to an embodiment of the present invention;

[0045] Figure 4 It is a detailed structural schematic diagram of a water gate control system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0048] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0049] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0050] like Figures 1 to 4 As shown, this embodiment proposes a water gate control system for a reservoir, including a measurement and control integrated gate and a genetic program (GP) module; the measurement and control integrated gate has a remote sensing function of gate opening, water level before the gate and water level after the gate, and the water level before the gate is the water level in front of the reservoir dam where the gate is provided; the genetic program module communicates with the measurement and control integrated gate, and includes a model unit, a calculation unit and an early warning unit;

[0051] The model unit is equipped with a genetic program, and the gate opening, water level before the gate, and water level after the gate in the historical data are normalized and used as neurons of the input layer of the genetic program respectively, and the measured through-gate flow for flood discharge, or the hydraulic coefficient corresponding to the measured through-gate flow is used as the neuron of the output layer of the genetic program, and the genetic program calculates to obtain the optimal objective function; the calculation unit inputs the gate opening, water level before the gate, and water level after the gate collected in real time into the optimal objective function of the model unit to obtain the real-time through-gate flow of the reservoir for flood discharge; the early warning unit determines that the real-time through-gate flow exceeds the upper limit value, then controls the integrated measurement and control gate to reduce the opening, and issues an early warning.

[0052] It should be noted that the integrated measurement and control gate described in this embodiment is an automated metering device that integrates measurement, real-time monitoring, and intelligent regulation. It is the basic support for the informatization of irrigation areas. It can automatically correspond to the optimal objective function formula of the corresponding genetic program according to the requirements of the reservoir specifications and the flow state of the flood discharge, and then calculate the flow through the gate and control the gate flow. It is equipped with upper-level monitoring software to realize the distribution and regulation of reservoir flood discharge, improve the informatization, intelligence, and remote management level of reservoir flood discharge, and make the reservoir flood discharge "visible, transmittable, controllable, and measurable."

[0053] The integrated gate of measurement and control described in this embodiment includes an electric gate water measurement monitoring box, upstream and downstream radar / ultrasonic water level gauges and a host monitoring computer of the management department equipped with a genetic program module. The electric gate water measurement monitoring box is composed of a gate measurement and control instrument, a power supply, a low-voltage electrical appliance, a lightning protection and communication equipment. The gate measurement and control instrument can detect the gate opening, and is externally connected to the upstream and downstream radar / ultrasonic water level gauges and the host monitoring computer of the management department via a communication network.

[0054] The integrated measurement and control gate described in this embodiment can easily realize large-scale management of the entire reservoir, channel, and river basin. Therefore, in view of the fact that the integrated measurement and control gate has the dual functions of measurement and control compared with the traditional gate, the research on the adaptability of the hydraulic characteristics of the gate needs to comprehensively consider aspects such as accurate measurement, safe operation, and easy maintenance. On the one hand, from the perspective of hydraulics, on the basis of ensuring the stability of the upstream and downstream water levels, strive for higher water level and flow calculation accuracy; on the other hand, it is necessary to strengthen its adaptability research, reasonably arrange the use scenarios of different equipment, reduce maintenance costs, and maximize its functions and benefits.

[0055] It should be noted that the mechanism model is widely used in the calculation method of the flow rate through the traditional gate, that is, only the corresponding hydraulic theory is used to calculate the flow rate. However, this method does not have time correlation, and when the flow state through the gate in the project does not meet the empirical formula assumption, it will greatly affect the accuracy. Soft sensor technology belongs to control theory, which can also be called state observation technology, including soft sensor modeling method, engineering implementation technology of real-time calculation of the model and model self-correction technology, among which the soft sensor modeling method is the core of this technology. The soft sensor modeling method adopted in this embodiment is mainly based on data. This type of method regards the research object as a black box and uses genetic programs to perform mathematical regression to establish a model. Its advantage is that it does not require an in-depth understanding of the internal laws of the research object (gate opening, water level before the gate and water level after the gate), and has a wide range of applicability. The soft sensor model of this embodiment combines the advantages of the two modeling technologies, can take into account the physical meaning and time correlation, improves the nonlinear approximation ability of the model, and is suitable for hydraulic processes with strong nonlinear and time-varying characteristics.

[0056] It should be noted that the genetic program used in this embodiment is specifically applied to the integrated gate for measurement and control of weir flow state.

[0057] As a specific implementation, the normalized calculation formula of the model unit is:

[0058] ;

[0059] Wherein, Z is the normalized output value, X is the normalized input value, and S is the standard value of the normalized input value; the standard value S is the pre-sluice design water level for the pre-sluice water level, the post-sluice design water level for the post-sluice water level, and the water depth under the pre-sluice design water level for the gate opening.

[0060] As another specific implementation, the normalized calculation formula of the model unit is:

[0061] ;

[0062] Wherein, Z is the normalized output value, X is the normalized input value, is the average value of the normalized input value, S is the standard value of the normalized input value; the standard value S is the pre-sluice design water level for the pre-sluice water level, the post-sluice design water level for the post-sluice water level, and the water depth under the pre-sluice design water level for the gate opening.

[0063] It can be understood that normalization is a means to reduce the impact of internal offsets of training parameters on genetic programs. The first normalized calculation formula mentioned above is used when the difference between the maximum and minimum values ​​of the training parameter is less than 1 meter. It is specifically applied to a group of data collected within 5 minutes by the integrated measurement and control gate when the early warning unit determines that the fluctuation of rainfall changes is small. Therefore, the first normalized calculation formula can better retain the trend of training parameters with small fluctuations. The second normalized calculation formula mentioned above is used when the difference between the maximum and minimum values ​​of the training parameter is greater than 1 meter. It is specifically applied when the early warning unit determines that the fluctuation of rainfall changes is large, or when the interval between multiple data collected within 5 minutes by the integrated measurement and control gate is greater than 1 minute. Therefore, the second normalized calculation formula can further reduce the impact of data fluctuations on the genetic program to obtain data trends.

[0064] It should be noted that the above-mentioned normalized input value is any one of the water level before the gate, the water level after the gate and the gate opening, that is, this embodiment preferably uses the same normalized calculation formula for the three collected values. At the same time, for different situations of the three collected values, the above-mentioned two normalized calculation formulas can also be used respectively. For example, the water level before the gate and the water level after the gate use the first normalized calculation formula, and the gate opening uses the second normalized calculation formula.

[0065] In particular, the sensitivity of the genetic program to the water levels before and after the gate is further reduced through the normalized calculation formula.

[0066] Furthermore, the model unit also normalizes the measured gate flow rate using one of the above-mentioned normalized calculation formulas, wherein the standard value S for the gate flow rate is the design flow rate of the gate.

[0067] Furthermore, the genetic program module is mounted on the Internet of Things cloud platform and also includes a big data unit; the model unit obtains the gate opening, water level before the gate, water level after the gate and measured flow rate from at least 1,000 historical data in the big database stored in the big data unit for iterative training of the genetic program, thereby obtaining the optimal objective function.

[0068] Furthermore, the early warning unit obtains the downstream waterway data recorded by the IoT cloud platform, and comprehensively sets the early warning level to be issued based on the real-time flow rate through the lock and the downstream waterway data.

[0069] Furthermore, the early warning unit is equipped with a calculation formula for predicting the flood discharge height of the downstream waterway, specifically:

[0070] ;

[0071] In the formula, A is the predicted flood discharge height of the downstream waterway, Q is the real-time gate flow, W is the design width of the downstream waterway, and L is the real-time water level of the downstream waterway; the early warning unit determines the warning level to be issued according to the level interval of the predicted flood discharge height of the downstream waterway.

[0072] Furthermore, the early warning unit obtains the rainfall data of the downstream waterway recorded by the Internet of Things cloud platform, and if the rainfall data exceeds the upper limit of rainfall, the issued early warning level is increased.

[0073] Furthermore, the genetic program module also includes a hydraulic coefficient calculation unit; the hydraulic coefficient calculation unit is used to obtain the relationship between the hydraulic coefficient and the gate flow rate and the water level before the gate according to the hydraulic gate flow rate calculation formula; the model unit uses the hydraulic coefficient as the neuron of the output layer of the genetic program to obtain the optimal objective function with the gate opening, the water level before the gate and the water level after the gate as independent variables and the hydraulic coefficient as the dependent variable; the calculation unit inputs the gate opening, the water level before the gate and the water level after the gate collected in real time into the optimal objective function of the model unit to obtain the predicted hydraulic coefficient, and substitutes the predicted hydraulic coefficient into the gate flow rate calculation formula to obtain the predicted gate flow rate.

[0074] Furthermore, the calculation formula for the gate flow rate (hydraulic solution) of the gate hole is:

[0075] ;

[0076] In the formula, Q is the flow rate through the gate, σ is the flooding coefficient, μ is the flow coefficient, b is the gate bottom width, e is the gate opening, g is the gravitational acceleration, and H is the water level in front of the gate; the genetic program module uses the product of the flooding coefficient and the flow coefficient as the hydraulic coefficient.

[0077] It should be noted that, for the regulating gate, the gate bottom width b is fixed, and the hydraulic coefficient is a function of the gate opening, the water level before the gate, and the water level after the gate.

[0078] In particular, by combining the hydraulic formula for calculating the flow rate through the sluice hole, the fitting accuracy and generalization ability of the optimal objective function obtained by genetic programming are further enhanced.

[0079] In this embodiment, Figure 3 As shown in FIG. 1 , in the genetic programming, the gate opening, the water level before the gate and the water level after the gate in the historical big data are used as the input training sample set X, and the corresponding measured flow through the gate is used as the output sample set Y. The genetic programming process is to find the expression of the optimal objective function with the input training sample set X as the independent variable through evolution, so that the fitting error of the training sample set X to the output sample set Y is minimized.

[0080] Specifically, Figure 3 As shown, the coding elements of the genetic program are arithmetic operators {+, -, ×,} and inverse trigonometric functions {sin, cos, arctg, arcctg}. The genetic program is represented in the form of a binary tree, that is, each chromosome in the binary tree represents a coding element. The genetic program decodes and evaluates the chromosomes, analyzes the functional formulas represented by multiple chromosomes, and sorts them according to the objective function. Then, through the genetic operations of selection, crossover, and mutation, the parent population evolves in the optimal direction to generate a new child population. The evolution is repeated in this way, and the fitness of individuals in various populations is calculated until the number of iterations reaches a preset value, or the objective function value of the best individual reaches or exceeds the preset accuracy, the operation is terminated, and the objective function of the best individual is used as the optimal objective function.

[0081] In a specific application of this embodiment, some of the training parameters are shown in the following table:

[0082]

[0083] By using the above data as the training parameters of the genetic program, we can obtain the optimal objective function, for example: y=arcctg(cos(x1 / (x1+x2+0.0001))+0.0001)×cos(x1+x2+x3+0.0001)), where y is the hydraulic coefficient, and x1, x2 and x3 are respectively the water level before the gate, the water level after the gate and the gate opening. The gate opening, water level before the gate and water level after the gate collected in real time are respectively input into the above optimal objective function to obtain the real-time gate flow of the reservoir for flood discharge, and the real-time gate flow is compared with the measured real-time gate flow, or the real-time gate flow and the measured real-time gate flow are substituted into the error function to calculate the average error. It can be seen that the average error of the genetic program is 2%, the average error of the BP neural network method is 8%, and the average error calculated only by the hydraulic method is 30%.

[0084] Specifically, the mathematical model of the genetic program and the solution method thereof are implemented by Python programming, and the model operation results are evaluated based on the measured gate flow rate and the error formula of the gate flow rate obtained by solution.

[0085] Furthermore, the early warning unit includes a gate control subunit; when it is determined that the real-time gate flow exceeds the upper limit value, the gate control subunit inputs the difference between the set opening and the actual gate opening into the control algorithm to obtain an adjustment value for reducing the opening of the integrated measurement and control gate.

[0086] Furthermore, the control algorithm is a PID (Proportional Integral Derivative) algorithm, and the gate control subunit sets corresponding proportional gain, integral gain and differential gain according to the warning level instruction.

[0087] In a specific application of this embodiment, the warning level instructions are divided into very dangerous, relatively dangerous, generally dangerous, less dangerous and not dangerous, corresponding to level 5 to level 1. In level 5 and level 4, the proportional gain is set to be greater than the integral gain and the differential gain to make a faster adjustment. In level 3 and level 2, the integral gain is set to be greater than the proportional gain and the differential gain to make a medium-speed and relatively stable adjustment. In level 1, the proportional gain is set to 0, and only the integral gain and the differential gain are performed to achieve a slow and stable adjustment.

[0088] Furthermore, if Figure 4 As shown, the system further includes a feedback module mounted on a mobile terminal. The mobile terminal is a mobile device such as a host computer or a mobile phone.

[0089] Furthermore, the adjustment value of the opening is also subject to the constraints of the channel operation downstream of the gate, the constraints including: branch channel water distribution flow constraint, the actual water distribution flow does not exceed 0.8 times its design flow; branch channel water distribution time is less than the maximum allowable total water distribution time determined by the irrigation forecast calculation of the Internet of Things cloud platform; water volume balance constraint of upper and lower channel water supply; and continuity constraint of upper and lower channel water supply.

[0090] Furthermore, the adjustment value of the opening is also limited by the amount of irrigation water in the irrigation area planned to be mobilized by the Internet of Things cloud platform. Specifically, the amount of irrigation water in the irrigation area directly affects crop yield. By predicting the water demand of crops throughout their life cycle, the optimal water demand and irrigation time for crop growth can be obtained, and crops can be replenished with water scientifically, accurately and timely according to their growth needs. The irrigation water consumption and the maximum acceptable flood discharge of each typical field in the irrigation area can be predicted in combination with the crop planting structure. According to the maximum acceptable flood discharge and appropriate flood discharge of the irrigation area, the adjustment value of the opening of the integrated measurement and control gate and the duration of the execution of the adjustment value can be scientifically controlled to achieve water demand prediction for the entire irrigation area.

[0091] It should be noted that the reservoir sluice control system formed by the IoT cloud platform and the integrated measurement and control gate in this embodiment is realized by data collection and real-time monitoring of the integrated measurement and control gate. This system integrates functions such as remote control of the gate, accurate flow generation, video monitoring, report generation and export. It not only provides accurate data support for water volume scheduling and quota management for irrigation district management units, but also is a smart means to promote smart flood discharge and smart irrigation, and is also an important part of the informatization of irrigation districts and reservoirs.

[0092] Multi-factor three-dimensional perception is the basis for building a smart flood discharge management system. Through a comprehensive three-dimensional perception system, comprehensive and reliable data information is provided for the realization of smart flood discharge management. By strengthening the linkage application of satellite, UAV remote sensing and ground monitoring, a three-dimensional monitoring network of air-space-ground network integrating rainfall, flow through the sluice gate, water level, water quality, images and video is established to create a multi-factor and multi-level information chain of water conditions, rainfall conditions, dangerous conditions and disaster conditions, breaking the limitations of single-factor perception and providing support for the implementation of flood discharge and command decision-making.

[0093] Determining accurate key indicators such as flow through the sluice and gate opening is the key to implementing the three-in-one monitoring measures of "human defense + physical defense + technical defense". Building a new generation of early warning general model platform based on cloud technology is a key link in effectively strengthening the dynamic monitoring and supervision of reservoir flood discharge behavior.

[0094] Specifically, the detailed structure of the water gate control system described in this embodiment is as follows Figure 4As shown, the hardware system of the integrated gate for measurement and control includes a PLC (programmable logic controller) host, a PLC analog expansion module, a servo drive, a servo motor, a reducer, a DC switching power supply, a touch screen, an intermediate relay, etc. As a control terminal, the IoT cloud platform is the core communication component of the entire system. It uses GPRS / 3G / 4G as a communication method and has high stability and system response speed. The PLC host is connected to the RJ45 network port of the IoT control terminal via a network cable, receives control instructions, executes the gate start and stop action, and the servo drive, servo motor and reducer work together to control the gate opening. The PLC analog expansion module is used to receive channel water level signals and gate opening signals. The DC switching power supply provides working power for each module of the system.

[0095] Therefore, in this embodiment, the real-time gate flow is obtained through the genetic program, which ensures that even if the water level before the gate and the water level after the gate collected by the gate during the flood discharge process as training parameters change greatly and are not accurate enough, the genetic program can quickly adjust the parameters without making a lot of modifications to the algorithm itself, thereby achieving the rapid and accurate generation of real-time gate flow, achieving timely and accurate adjustment of the gate opening, and enhancing the timeliness and accuracy of reservoir flood discharge warning. Through the normalized calculation formula, the sensitivity of the genetic program to the water level before the gate and the water level after the gate is further reduced. By combining the hydraulic gate hole gate flow calculation formula, the fitting accuracy and generalization ability of the optimal objective function obtained by the genetic program are further enhanced.

[0096] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0097] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A sluice control system for a reservoir, characterized in that: Including measurement and control integrated gate and genetic program module; The integrated measurement and control gate has the remote measurement function of gate opening, water level before the gate and water level after the gate. The water level before the gate is the water level in front of the reservoir dam where the gate is installed. The genetic program module communicates with the integrated measurement and control gate, and includes a model unit, a calculation unit and an early warning unit; The model unit is equipped with a genetic program, and the gate opening, the water level before the gate, and the water level after the gate in the historical data are normalized and used as neurons of the input layer of the genetic program respectively, and the measured gate flow for flood discharge, or the hydraulic coefficient corresponding to the measured gate flow, is used as the neuron of the output layer of the genetic program, and the genetic program calculates to obtain the optimal objective function; The calculation unit inputs the gate opening, water level before the gate and water level after the gate collected in real time into the optimal objective function of the model unit to obtain the real-time gate flow rate of the reservoir for flood discharge; When the early warning unit determines that the real-time gate flow rate exceeds the upper limit value, the integrated measurement and control gate is controlled to reduce the opening degree and a warning instruction is issued; The first calculation formula for normalization of the model unit is: ; And / or, the normalized second calculation formula of the model unit is: ; Wherein, Z is the normalized output value, X is the normalized input value, is the average value of the normalized input value, and S is the standard value of the normalized input value; The standard value S is the design water level before the gate for the water level before the gate, the design water level after the gate for the water level after the gate, and the water depth under the design water level before the gate for the gate opening; The first calculation formula is used for the data collected by the integrated gate within 5 minutes when the difference between the maximum and minimum values ​​of the training parameter is less than 1 meter and the early warning unit determines that the fluctuation of rainfall change is small; The second calculation formula is used when the difference between the maximum and minimum values ​​of the training parameters is greater than 1 meter, the early warning unit determines that the rainfall fluctuation is large, or when the interval between multiple data collected by the integrated measurement and control gate within 5 minutes is greater than 1 minute; The genetic program module is mounted on the IoT cloud platform; When it is determined that the real-time gate flow exceeds the upper limit, the gate control subunit inputs the difference between the set gate opening and the actual gate opening into the control algorithm to obtain an adjustment value for reducing the opening of the integrated measurement and control gate; The adjustment value of the opening is also subject to the constraints of the channel operation downstream of the gate, and the constraints include: branch channel water distribution flow constraint, the actual water distribution flow does not exceed 0.8 times of its design flow, the branch channel water distribution time is less than the maximum allowable total water distribution time determined by the irrigation forecast calculation of the Internet of Things cloud platform, the water volume balance constraint of the upper and lower channels, and the water delivery continuity constraint of the upper and lower channels; The adjustment value of the opening is also subject to the limit of the irrigation water volume of the irrigation area planned to be mobilized by the Internet of Things cloud platform, including: by predicting the water demand of crops throughout their life cycle, obtaining the optimal water demand and irrigation time for crop growth, replenishing water for crops according to their growth needs, and predicting the irrigation water consumption and the maximum acceptable flood discharge of each typical field in the irrigation area in combination with the crop planting structure. According to the maximum acceptable flood discharge of the irrigation area, the adjustment value of the opening of the integrated measurement and control gate and the duration of execution of the adjustment value are controlled.

2. The water gate control system for a reservoir according to claim 1, characterized in that: The model unit also normalizes the measured gate flow rate, wherein the standard value S is the design flow rate of the gate for the gate flow rate.

3. The water gate control system for a reservoir according to claim 1, characterized in that: The genetic program module also includes a large data unit; The model unit obtains the gate opening, water level before the gate, water level after the gate and measured flow rate from at least 1000 historical data in the big database stored in the big data unit for iterative training of the genetic program, thereby obtaining the optimal objective function.

4. The water gate control system for a reservoir according to claim 3, characterized in that: The early warning unit obtains the downstream waterway data recorded by the Internet of Things cloud platform, and issues an early warning level instruction based on the real-time flow rate through the lock and the downstream waterway data.

5. The water gate control system for a reservoir according to claim 4, characterized in that: The control algorithm is a PID control algorithm, and the gate control subunit sets the corresponding proportional gain, integral gain and differential gain according to the warning level instruction.

6. The water gate control system for a reservoir according to any one of claims 1 to 5, characterized in that: The genetic program module also includes a hydraulic coefficient calculation unit; The hydraulic coefficient calculation unit is used to obtain the relationship between the hydraulic coefficient, the gate flow rate, and the water level before the gate according to the gate flow rate calculation formula of hydraulics; The model unit uses the hydraulic coefficient as the neuron of the output layer of the genetic program to obtain the optimal objective function with the gate opening, the water level before the gate and the water level after the gate as independent variables and the hydraulic coefficient as the dependent variable; The calculation unit inputs the gate opening, water level before the gate and water level after the gate collected in real time into the optimal objective function of the model unit to obtain a predicted hydraulic coefficient, and substitutes the predicted hydraulic coefficient into the gate flow calculation formula to obtain the predicted gate flow.