A method and system for automatic control of gates under branched river channels

By building a split river gate opening model and an automated control system, the problem of inaccurate gate operation under traditional manual control is solved, precise automatic scheduling and optimization of water resources is achieved, and water resource utilization efficiency and engineering stability are improved.

CN118735232BActive Publication Date: 2024-11-12SICHUAN XINGHAI DIGITAL INNOVATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411229228.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-12
Estimated Expiration
2044-09-03

AI Technical Summary

Technical Problem

The traditional sub-segment river gate control relies on manual operation, resulting in inaccurate operation, slow response speed and large human resources losses, and the inability to effectively dispatch the supply and demand of water resources in downstream rivers, affecting life, production and ecological environment.

Method used

Build a split river gate opening model, use real-time monitoring data and historical data to calibrate the parameters, and use the gate control system to automatically adjust the gate opening to achieve accurate adjustment and prediction of water flow and optimize water resource allocation.

Benefits of technology

It realizes precise automated control of water resources in split rivers, reduces labor costs, and improves water resource utilization efficiency and project operation stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118735232B_ABST
    Figure CN118735232B_ABST
Patent Text Reader

Abstract

The invention discloses an automatic control method and system for a gate under a branched river channel, and relates to the technical field of water conservancy engineering. The invention constructs a branched river channel gate opening model by combining the characteristics of the branched river channel gate, uses historical data sets to fit model-related parameters, combines real-time hydrological monitoring data, gate monitoring data and scheduling plans, calculates and predicts the gate opening value and flow data of each branched river channel, and then adjusts the gate to a height corresponding to the predicted opening value through a gate control system; and through real-time monitoring and collection of the flow data of each branched river channel after scheduling, and feeds back to the model, the branched river channel gate opening model is optimized and updated, and finally accurate automatic control of water resource scheduling of the branched river channel gate is achieved and labor costs are reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of water conservancy engineering, and in particular to a method and system for automatically controlling a gate under a branched river channel. Background Art

[0002] When water resources are dispatched at the head of the irrigation area, there are many bifurcated river channels. Bifurcated river channels refer to diversion structures set up in rivers or channels. The diversion and regulation of water flow are controlled by gates to meet different irrigation, water supply, flood control and environmental protection needs.

[0003] Traditional branch river gate control relies on manual control. Operators adjust the opening and closing of the gates based on historical experience and on-site water level conditions. This method has problems such as inaccurate operation, slow response speed and large loss of human resources. It is also prone to unreasonable scheduling, resulting in a mismatch between water supply and demand in downstream rivers, affecting people's life, production and the ecological environment.

[0004] With the development of automation technology, automated gate control systems have emerged on the main branches of some rivers. Sensors, data acquisition systems, control algorithms and other technical means are used to achieve precise automated control of gates, achieve accurate diversion and regulation of water flow, ensure effective use of water resources and safe and stable project operation. However, there is currently a lack of technical means for automated control of gates in branched rivers. Summary of the invention

[0005] In order to solve the above-mentioned deficiencies in the prior art, the present invention provides a method for automatically controlling a gate under a branched river channel, the method comprising the following steps:

[0006] S1. Obtain real-time monitoring information of the upstream and downstream rivers of the gate and gate monitoring information, obtain the total flow of the upstream river before the gate and the branch flow of each branch river after the gate based on the real-time monitoring information, and obtain the gate opening data based on the gate monitoring information;

[0007] S2. Extracting a training data set for the model based on historical monitoring data of the river, basic river data and gate data, and preprocessing the data in the training data set;

[0008] S3. Based on the total flow of the upstream river channel before the gate, the branch flow of each branch river channel after the gate and the gate opening data, a branch river channel gate opening model is established, and based on the training data set after data preprocessing, the branch river channel gate opening model is calibrated;

[0009] S4. Real-time monitoring and acquisition of water flow in the upstream river, using the branched river gate opening model to calculate the predicted water flow of each branched river behind the gate;

[0010] S5. Based on the scheduling plan of the downstream river, obtain the water flow range of each branch river after the gate, and determine whether the predicted water flow of each branch river is within the corresponding water flow range. If so, return to step S4, if not, proceed to step S6;

[0011] S6. Based on the scheduling plan, the planned water discharge of each branched river channel is obtained, the water flow of the upstream river channel and the planned water discharge of each branched river channel are input into the branched river channel gate opening model for processing, the calculated opening of the gate is obtained, and the gate opening value is adjusted to the calculated opening through the gate control system;

[0012] S7. When the gate opening value is adjusted to the calculated opening and the drainage flow of each branched river channel after the gate is stable, obtain the real-time drainage flow of each branched river channel, and calculate the difference between the real-time drainage flow and the planned drainage flow;

[0013] S8. Determine whether the difference is greater than a first set value. If so, update the branch channel gate opening model. If not, return to step S4.

[0014] The present invention is achieved through the following technical solutions:

[0015] Construct a branched river gate opening model: first obtain the real-time monitoring information of the river upstream and downstream of the gate and the gate monitoring information, and build the water level-flow relationship of the monitored river through the real-time monitoring information, and then obtain the total upstream flow before the gate and the flow of each branched river after the gate. Through the gate monitoring information, obtain the gate opening data; construct the branched river gate opening model based on the total upstream flow before the gate, the branch flow of each branched river after the gate, and the gate opening data.

[0016] Parameter calibration of the branched river gate opening model: Based on the historical monitoring data of the monitored river, the basic data of the river and the gate data, the training data set of the model is extracted and preprocessed. The preprocessing specifically includes missing value processing, data conversion and abnormal data processing. The parameters of the branched river opening model are calibrated using the preprocessed training data set.

[0017] The branched river gate opening model is applied: the inflow of the upstream river is obtained, and the predicted water flow of each branched river behind the gate is calculated through the branched river gate opening model; then the scheduling plan of the downstream river behind the gate is obtained, and the water demand flow range of each branched river behind the gate is obtained through the scheduling plan, and it is judged whether the predicted water flow calculated by the branched river gate opening model is within the corresponding water demand flow range. If so, return to step S4 and continue monitoring without adjusting the gate opening; if not, it is necessary to obtain the planned water discharge flow of each branched river behind the gate through the scheduling plan, input the inflow of the upstream river and the planned water discharge flow of each branched river behind the gate into the branched river gate opening model for processing, obtain the calculated opening of the gate, and then adjust the gate opening value to the calculated opening through the gate control system.

[0018] Optimize the branch channel gate opening model: after the gate control system completes gate adjustment and the outflow of each branch channel behind the gate is stable, obtain the real-time outflow of each branch channel, calculate the difference between the real-time outflow of each branch channel and the planned outflow, and determine whether the difference is greater than the first set value. If so, update the branch channel gate opening model. If not, return to step S4 and continue monitoring without optimization and updating.

[0019] As an optional technical solution, the step S2 is specifically as follows:

[0020] S21. Based on the gate data, obtain gate opening historical data;

[0021] S22. Extract the time window set and the corresponding gate opening value in the gate opening historical data whose gate opening value has not changed and whose duration is greater than the second set value, and add them to the training data set;

[0022] S23. Obtain the upstream river flow data set, each branch river flow data set, the water level data set before the gate, and the width of each gate hole of the gate in each time window in the time window set, and add them to the training data set;

[0023] S24. Preprocessing the data in the training data set, including missing value processing, data conversion processing and abnormal data processing.

[0024] As an optional technical solution, the step S24 is specifically as follows:

[0025] The missing value processing of the preprocessing operation includes: if there is a null value in the upstream river flow data set or the branch river flow data set in the training data set, then delete all data in the corresponding time window and the corresponding gate opening value; if there is a null value in the water level data set before the gate, then do nothing;

[0026] The data conversion processing of the preprocessing operation includes: calculating the mean value and standard deviation of the upstream river flow data set, each branch river flow data set and the water level data set before the gate in each time window in the time window set, and replacing the original data set with the mean value and standard deviation of each data set;

[0027] The abnormal data processing of the preprocessing operation includes: after the data in the training data set is processed by data conversion, if there is a data set whose standard deviation exceeds a third set value, deleting all data in the corresponding time window and the corresponding gate opening value.

[0028] As an optional technical solution, the expression of the branched river gate opening model is:

[0029]

[0030]

[0031]

[0032] Where: The upstream river is divided into river channel 1 and river channel 2 after bifurcation, Indicates the opening value of each gate hole of gate 1 corresponding to river channel 1, in meters; N indicates the number of gate holes of gate 1; Indicates the width of each gate hole of gate 1, in meters; Indicates the opening value of each gate hole of gate 2 of river channel 2, in meters; M indicates the number of gate holes of gate 2; Indicates the width of each gate hole of gate 2, in meters; The coefficient is the diversion ratio of each branch channel when the gate is fully open; is the correction function, and Perform parameter fitting through the training data set and obtain the optimal parameters using the least squares method; Indicates the water level before the gate; It represents the total flow of the upstream river; represents the flow rate of river channel 1, Indicates the flow rate of river 2.

[0033] As an optional technical solution, step S6 is specifically as follows:

[0034] S61. Pre-configure the relevant parameters of the automatic gate in the gate control system, including the maximum number of simultaneous gates, the time interval between adjacent gates, the gate opening sequence and the gate closing sequence;

[0035] S62. When the gate control system receives a gate opening instruction, the gate movement command event is started, wherein the gate opening instruction includes the calculated opening value of each gate hole of the gate;

[0036] S63. The gate control system obtains the current opening value of each gate hole of the gate, generates the gates that need to be adjusted and the execution time based on the received gate opening instructions and the relevant parameters of the automatic gate movement, and forms a gate execution instruction set;

[0037] S64. Based on the gate execution instruction set, the gate hoist on each gate hole is controlled in sequence to adjust the gate to the calculated opening value, and the execution result of each instruction set is fed back;

[0038] S65. The gate control system receives feedback of the execution result of each instruction set, calculates the error value between the actual gate opening value and the corresponding calculated opening value, and determines whether the error value is lower than the fourth set value. If so, the execution of the instruction ends. If not, a warning alarm is issued;

[0039] S66. Determine whether the gate execution instruction set has been executed. If so, the gate operation command event ends. If not, execute step S64.

[0040] As an optional technical solution, step S8 is specifically as follows:

[0041] Obtaining the current opening value of the gate, the water level in front of the gate, the flow rate of the upstream river channel and the flow rate of each branch river channel as a set of first data sets;

[0042] The data in the first data set is input into the branching river gate opening model to calculate the correction function The value of f 1;

[0043] Based on the training data set after data preprocessing, the correction function is calculated The value of f 2. Calculation f 1 and f 2 to obtain a calculation result, and based on the calculation result, the correction function In and Parameters to adjust.

[0044] In order to solve the above-mentioned deficiencies in the prior art, the present invention also provides an automatic control system for gates under branched river channels, the system comprising:

[0045] A monitoring unit, used to obtain real-time monitoring information of the upstream and downstream rivers of the gate and gate monitoring information, obtain the total flow of the upstream river before the gate and the branch flow of each branch river after the gate based on the real-time monitoring information, and obtain the gate opening data based on the gate monitoring information;

[0046] A training unit, used for extracting a training data set of a model based on historical monitoring data of a monitored river, basic river data and gate data, and preprocessing data in the training data set;

[0047] An opening model unit is used to establish a branched river channel gate opening model based on the total flow of the upstream river channel before the gate, the branched flow of each branched river channel after the gate and the opening data of the gate, and to calibrate the parameters of the branched river channel gate opening model based on the training data set after data preprocessing;

[0048] A prediction unit, used for real-time monitoring and obtaining the water flow of the upstream river channel, and calculating the predicted water flow of each branch river channel behind the gate by using the branch river channel gate opening model;

[0049] A judgment unit, for obtaining the required water flow range of each branched river channel behind the gate based on the scheduling plan of the downstream river channel, and judging whether the predicted water flow of each branched river channel is within the corresponding required water flow range, if so, returning to the prediction unit, if not, entering the gate adjustment unit;

[0050] A gate adjustment unit, for obtaining a planned water discharge flow of each branched river channel based on the scheduling plan, inputting the water flow of the upstream river channel and the planned water discharge flow of each branched river channel into the branched river channel gate opening model for processing, obtaining a calculated opening of the gate, and adjusting the gate opening value to the calculated opening through the gate control system;

[0051] The optimization calculation unit is used to obtain the real-time drainage flow of each branched river channel when the gate opening value is adjusted to the calculated opening and the drainage flow of each branched river channel behind the gate is stable, and calculate the difference between the real-time drainage flow and the planned drainage flow;

[0052] The optimization updating unit is used to determine whether the difference is greater than a first set value. If so, the branch channel gate opening model is updated; if not, the prediction unit is returned.

[0053] One or more technical solutions provided by the present invention have at least the following technical effects or advantages:

[0054] The present invention constructs a branched river gate opening model by combining the characteristics of the branched river gate, uses historical data sets to fit model-related parameters, combines real-time hydrological monitoring data, gate monitoring data and scheduling plans, calculates and predicts the gate opening value and the flow data of each branched river, and then adjusts the gate to the height corresponding to the predicted opening value through the gate control system; and through real-time monitoring and collection of the flow data of each branched river after scheduling, feeds back to the model, realizes the optimization and updating of the branched river gate opening model, and finally realizes precise automated control of water resource scheduling of branched river gates and reduces labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation on the embodiments of the present invention;

[0056] Figure 1 It is a schematic flow chart of an automatic control method for a gate under a bifurcated river channel in the present invention;

[0057] Figure 2 It is a schematic diagram of a branched river gate layout in the present invention;

[0058] Figure 3 The invention is a schematic diagram of the composition of an automatic control system for a gate under a branched river channel. DETAILED DESCRIPTION

[0059] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0060] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those within the scope of this description. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0061] Embodiment 1

[0062] Please refer to Figure 1 and Figure 2 , Figure 1 It is a schematic diagram of a flow chart of an automatic control method for a gate under a branched river channel in the present invention. Figure 2 This is a schematic diagram of a branched river gate layout in the present invention. It should be noted that: Figure 2 1-6 represent gate holes. The method comprises the following steps:

[0063] S1. Obtain real-time monitoring information of the upstream and downstream rivers of the gate and gate monitoring information, obtain the total flow of the upstream river before the gate and the branch flow of each branch river after the gate based on the real-time monitoring information, and obtain the gate opening data based on the gate monitoring information;

[0064] S2. Extracting a training data set for the model based on historical monitoring data of the river, basic river data and gate data, and preprocessing the data in the training data set;

[0065] S3. Based on the total flow of the upstream river channel before the gate, the branch flow of each branch river channel after the gate and the gate opening data, a branch river channel gate opening model is established, and based on the training data set after data preprocessing, the branch river channel gate opening model is calibrated;

[0066] S4. Real-time monitoring and acquisition of water flow in the upstream river, using the branched river gate opening model to calculate the predicted water flow of each branched river behind the gate;

[0067] S5. Based on the scheduling plan of the downstream river, obtain the water flow range of each branch river after the gate, and determine whether the predicted water flow of each branch river is within the corresponding water flow range. If so, return to step S4, if not, proceed to step S6;

[0068] S6. Based on the scheduling plan, the planned water discharge of each branched river channel is obtained, the water flow of the upstream river channel and the planned water discharge of each branched river channel are input into the branched river channel gate opening model for processing, the calculated opening of the gate is obtained, and the gate opening value is adjusted to the calculated opening through the gate control system;

[0069] S7. When the gate opening value is adjusted to the calculated opening and the drainage flow of each branched river channel after the gate is stable, obtain the real-time drainage flow of each branched river channel, and calculate the difference between the real-time drainage flow and the planned drainage flow;

[0070] S8. Determine whether the difference is greater than a first set value. If so, update the branch channel gate opening model. If not, return to step S4.

[0071] The specific embodiments of the present invention are as follows:

[0072] Constructing a gate opening model for a bifurcated river channel: obtaining real-time monitoring information of the river channel upstream and downstream of the gate, constructing the water level-flow relationship of the monitored river channel, and then obtaining the total flow of the upstream river channel before the gate and the diversion flow of each bifurcated river channel after the gate. In this embodiment, the real-time monitoring information mainly includes real-time river channel water level elevation data, and also includes basic information of the river channel (mainly riverbed elevation data and river channel width data). Based on the gate monitoring information, the gate opening data is obtained. Based on the total flow of the upstream river channel before the gate, the diversion flow of each bifurcated river channel after the gate, and the gate opening data, a bifurcated river channel gate opening model is constructed.

[0073] The monitoring equipment for real-time monitoring information acquisition is aimed at the standard river section. By obtaining the water level and flow relationship of the standard river section and combining the historical water level and flow data with the on-site flow measurement, the water level and flow relationship is fitted to meet the following formula:

[0074]

[0075] In the formula, Q represents the flow rate of the river, h is the river water level elevation data, and A and B are the parameters of the formula.

[0076] The river water level elevation data is obtained in real time through monitoring equipment, and is substituted into the above-mentioned fitted water level-flow relationship equation to obtain the real-time flow data of the upstream and downstream rivers.

[0077] Parameter calibration of the gate opening model of the bifurcated river channel: Based on the historical monitoring data of the monitored river channel, the basic river channel data and the gate data, the training data set of the model is extracted and the data preprocessing is performed.

[0078] In this embodiment, the specific steps of extracting the training data set include:

[0079] S21. Based on the gate data, obtain gate opening historical data;

[0080] S22. Extract the time window set and the corresponding gate opening value in the gate opening historical data whose gate opening value has not changed and whose duration is greater than the second set value, and add them to the training data set;

[0081] S23. Obtain the upstream river flow data set, each branch river flow data set, the water level data set before the gate, and the width of each gate hole of the gate in each time window in the time window set, and add them to the training data set;

[0082] S24. Preprocessing the data in the training data set, including missing value processing, data conversion processing and abnormal data processing.

[0083] Among them, the gate data includes the historical gate opening data. When the gate is activated, the data will be saved once. The saved data contains two important fields, namely the gate opening value and the timestamp. Extract the two timestamps of adjacent data (adjacent gate opening values). If the time difference between the two timestamps (that is, the time when the gate opening value has not changed) is greater than the second set value, obtain the time window formed between the two timestamps and the corresponding gate opening value and add it to the training data set.

[0084] The upstream river flow data set, each branch river flow data set, the water level data set before the gate, and the width of each gate hole of the gate in each time window in the time window set are obtained, and added to the training data set; the data in the training data set are preprocessed, including missing value processing, data conversion processing, and abnormal data processing. In this embodiment, specifically:

[0085] The missing value processing of the preprocessing operation includes: if there is a null value in the upstream river flow data set or the branch river flow data set in the training data set, then delete all data in the corresponding time window and the corresponding gate opening value; if there is a null value in the water level data set before the gate, then do nothing;

[0086] The data conversion processing of the preprocessing operation includes: calculating the mean value and standard deviation of the upstream river flow data set, each branch river flow data set and the water level data set before the gate in each time window in the time window set, and replacing the original data set with the mean value and standard deviation of each data set;

[0087] Specifically, the calculation formula for the average value of the upstream river flow data set, each branch river flow data set, and the water level data set before the gate is as follows:

[0088]

[0089] The standard deviation is calculated as follows:

[0090]

[0091] It should be noted that the calculation formulas for the mean and standard deviation are common mathematical formulas, so they are not explained in detail. The mean is the sum of all data divided by the number of data points, which represents the average size of the data set; the standard deviation is the square root of the variance, which represents the degree of dispersion of the data points.

[0092] The abnormal data processing of the preprocessing operation includes: after the data in the training data set is processed by data conversion, if there is a data set whose standard deviation exceeds a third set value, deleting all data in the corresponding time window and the corresponding gate opening value.

[0093] Based on the training data set after data preprocessing, the parameters of the branched river gate opening model are calibrated. In this embodiment, it is specifically performed as follows:

[0094] The expression of the branch channel gate opening model is:

[0095]

[0096]

[0097]

[0098] Where: The upstream river is divided into river channel 1 and river channel 2 after bifurcation, Indicates the opening value of each gate hole of gate 1 corresponding to river channel 1, in meters; N indicates the number of gate holes of gate 1; Indicates the width of each gate hole of gate 1, in meters; Indicates the opening value of each gate hole of gate 2 of river channel 2, in meters; M indicates the number of gate holes of gate 2; Indicates the width of each gate hole of gate 2, in meters; The coefficient is the diversion ratio of each branch channel when the gate is fully open; is the correction function, and Perform parameter fitting through the training data set and obtain the optimal parameters using the least squares method; Indicates the water level before the gate; It represents the total flow of the upstream river; represents the flow rate of river channel 1, Indicates the flow rate of river 2.

[0099] Among them, the coefficient Calibration is performed through historical data, specifically finding the flow ratio of each branched river channel when the gate is fully open and taking the average value; Parameter and is the physical quantity of the gate; correction function In and Parameter fitting is performed through the training data set, and the optimal parameters are found using the least squares method, and the objective function is to minimize the residual sum of squares.

[0100] Applying the gate opening model of the bifurcated river channel: S4. Real-time monitoring and obtaining the water flow of the upstream river channel, and using the bifurcated river channel gate opening model to calculate the predicted water flow of each bifurcated river channel behind the gate;

[0101] S5. Based on the scheduling plan of the downstream river, obtain the water flow range of each branch river after the gate, and determine whether the predicted water flow of each branch river is within the corresponding water flow range. If so, return to step S4, if not, proceed to step S6;

[0102] S6. Based on the scheduling plan, the planned outflow of each branched river channel is obtained, the inflow of the upstream river channel and the planned outflow of each branched river channel are input into the branched river channel gate opening model for processing, the calculated opening of the gate is obtained, and the gate opening value is adjusted to the calculated opening through the gate control system.

[0103] In this embodiment, the inflow flow of the upstream river channel and the planned outflow flow of each branch river channel are input into the branch river channel gate opening model for processing, and the calculated opening of the gate is obtained, which includes the following steps:

[0104] S61. Pre-configure the relevant parameters of the automatic gate in the gate control system, including the maximum number of simultaneous gates, the time interval between adjacent gates, the gate opening sequence and the gate closing sequence;

[0105] S62. When the gate control system receives a gate opening instruction, the gate movement command event is started, wherein the gate opening instruction includes the calculated opening value of each gate hole of the gate;

[0106] S63. The gate control system obtains the current opening value of each gate hole of the gate, generates the gates that need to be adjusted and the execution time based on the received gate opening instructions and the relevant parameters of the automatic gate movement, and forms a gate execution instruction set;

[0107] S64. Based on the gate execution instruction set, the gate hoist on each gate hole is controlled in sequence to adjust the gate to the calculated opening value, and the execution result of each instruction set is fed back;

[0108] S65. The gate control system receives feedback of the execution result of each instruction set, calculates the error value between the actual gate opening value and the corresponding calculated opening value, and determines whether the error value is lower than the fourth set value. If so, the execution of the instruction ends. If not, a warning alarm is issued;

[0109] S66. Determine whether the gate execution instruction set has been executed. If so, the gate operation command event ends. If not, execute step S64.

[0110] Optimizing the gate opening model of the bifurcated river channel: S7. When the gate opening value is adjusted to the calculated opening and the drainage flow of each bifurcated river channel behind the gate is stable, obtaining the real-time drainage flow of each bifurcated river channel, and calculating the difference between the real-time drainage flow and the planned drainage flow;

[0111] S8. Determine whether the difference is greater than a first set value. If so, update the branch channel gate opening model. If not, return to step S4.

[0112] In this embodiment, if the difference is greater than the first set value, updating the branch channel gate opening model includes the following steps:

[0113] Obtaining the current opening value of the gate, the water level in front of the gate, the flow rate of the upstream river channel and the flow rate of each branch river channel as a set of first data sets;

[0114] The data in the first data set is input into the branching river gate opening model to calculate the correction function The value of f 1;

[0115] Based on the training data set after data preprocessing, the correction function is calculated The value of f 2. Calculation f 1 and f 2 to obtain a calculation result, and based on the calculation result, the correction function In and Parameters to adjust.

[0116] Among them, and The adjustment range of the parameters cannot exceed the preset value.

[0117] Embodiment 2

[0118] Please refer to Figure 3 , Figure 3 The figure is a schematic diagram of the automatic control system for the gate under the branched river in the present invention, which comprises:

[0119] A monitoring unit, used to obtain real-time monitoring information of the upstream and downstream rivers of the gate and gate monitoring information, obtain the total flow of the upstream river before the gate and the branch flow of each branch river after the gate based on the real-time monitoring information, and obtain the gate opening data based on the gate monitoring information;

[0120] A training unit, used for extracting a training data set of a model based on historical monitoring data of a monitored river, basic river data and gate data, and preprocessing data in the training data set;

[0121] An opening model unit is used to establish a branched river channel gate opening model based on the total flow of the upstream river channel before the gate, the branched flow of each branched river channel after the gate and the opening data of the gate, and to calibrate the parameters of the branched river channel gate opening model based on the training data set after data preprocessing;

[0122] A prediction unit, used for real-time monitoring and obtaining the water flow of the upstream river channel, and calculating the predicted water flow of each branch river channel behind the gate by using the branch river channel gate opening model;

[0123] A judgment unit, for obtaining the required water flow range of each branched river channel behind the gate based on the scheduling plan of the downstream river channel, and judging whether the predicted water flow of each branched river channel is within the corresponding required water flow range, if so, returning to the prediction unit, if not, entering the gate adjustment unit;

[0124] A gate adjustment unit, for obtaining a planned water discharge flow of each branched river channel based on the scheduling plan, inputting the water flow of the upstream river channel and the planned water discharge flow of each branched river channel into the branched river channel gate opening model for processing, obtaining a calculated opening of the gate, and adjusting the gate opening value to the calculated opening through the gate control system;

[0125] The optimization calculation unit is used to obtain the real-time drainage flow of each branched river channel when the gate opening value is adjusted to the calculated opening and the drainage flow of each branched river channel behind the gate is stable, and calculate the difference between the real-time drainage flow and the planned drainage flow;

[0126] The optimization updating unit is used to determine whether the difference is greater than a first set value. If so, the branch channel gate opening model is updated; if not, the prediction unit is returned.

[0127] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0128] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for automatic control of gates under bifurcated river channels, characterized in that: The method comprises the following steps: S1. Obtain real-time monitoring information of the upstream and downstream rivers of the gate and gate monitoring information, obtain the total flow of the upstream river before the gate and the branch flow of each branch river after the gate based on the real-time monitoring information, and obtain the gate opening data based on the gate monitoring information; S2. Extracting a training data set for the model based on historical monitoring data of the river, basic river data and gate data, and preprocessing the data in the training data set; S3. Based on the total flow of the upstream river channel before the gate, the branch flow of each branch river channel after the gate and the gate opening data, a branch river channel gate opening model is established, and based on the training data set after data preprocessing, the branch river channel gate opening model is calibrated; The expression of the branch channel gate opening model is: Where: The upstream river is divided into river channel 1 and river channel 2 after bifurcation, Indicates the opening value of each gate hole of gate 1 corresponding to river channel 1, in meters; N indicates the number of gate holes of gate 1; Indicates the width of each gate hole of gate 1, in meters; Indicates the opening value of each gate hole of gate 2 of river channel 2, in meters; M indicates the number of gate holes of gate 2; Indicates the width of each gate hole of gate 2, in meters; The coefficient is the diversion ratio of each branch channel when the gate is fully open; is the correction function, and Perform parameter fitting through the training data set and obtain the optimal parameters using the least squares method; Indicates the water level before the gate; It represents the total flow of the upstream river; represents the flow rate of river channel 1, represents the flow rate of river channel 2; S4. Real-time monitoring and acquisition of water flow in the upstream river, using the branched river gate opening model to calculate the predicted water flow of each branched river behind the gate; S5. Based on the scheduling plan of the downstream river, obtain the water flow range of each branch river after the gate, and determine whether the predicted water flow of each branch river is within the corresponding water flow range. If so, return to step S4, if not, proceed to step S6; S6. Based on the scheduling plan, the planned water discharge of each branched river channel is obtained, the water flow of the upstream river channel and the planned water discharge of each branched river channel are input into the branched river channel gate opening model for processing, the calculated opening of the gate is obtained, and the gate opening value is adjusted to the calculated opening through the gate control system; S7. When the gate opening value is adjusted to the calculated opening and the drainage flow of each branched river channel after the gate is stable, obtain the real-time drainage flow of each branched river channel, and calculate the difference between the real-time drainage flow and the planned drainage flow; S8. Determine whether the difference is greater than a first set value. If so, update the branch channel gate opening model. If not, return to step S4.

2. The method for automatic control of gates under a branched river according to claim 1, characterized in that: Step S2 is specifically as follows: S21. Based on the gate data, obtain gate opening historical data; S22. Extract the time window set and the corresponding gate opening value in the gate opening historical data whose gate opening value has not changed and whose duration is greater than the second set value, and add them to the training data set; S23. Obtain the upstream river flow data set, each branch river flow data set, the water level data set before the gate, and the width of each gate hole of the gate in each time window in the time window set, and add them to the training data set; S24. Perform preprocessing operations on the data in the training data set, including missing value processing, data conversion processing and abnormal data processing.

3. The method for automatic control of gates under a branched river according to claim 2, characterized in that: Step S24 is specifically as follows: The missing value processing of the preprocessing operation includes: if there is a null value in the upstream river flow data set or the branch river flow data set in the training data set, then delete all data in the corresponding time window and the corresponding gate opening value; if there is a null value in the water level data set before the gate, then do nothing; The data conversion processing of the preprocessing operation includes: calculating the mean value and standard deviation of the upstream river flow data set, each branch river flow data set and the water level data set before the gate in each time window in the time window set, and replacing the original data set with the mean value and standard deviation of each data set; The abnormal data processing of the preprocessing operation includes: after the data in the training data set is processed by data conversion, if there is a data set whose standard deviation exceeds a third set value, deleting all data in the corresponding time window and the corresponding gate opening value.

4. The method for automatic control of gates under a branched river according to claim 1, characterized in that: Step S6 is specifically as follows: S61. Pre-configure the relevant parameters of the automatic gate in the gate control system, including the maximum number of simultaneous gates, the time interval between adjacent gates, the gate opening sequence and the gate closing sequence; S62. When the gate control system receives a gate opening instruction, the gate movement command event is started, wherein the gate opening instruction includes the calculated opening value of each gate hole of the gate; S63. The gate control system obtains the current opening value of each gate hole of the gate, generates the gates that need to be adjusted and the execution time based on the received gate opening instructions and the relevant parameters of the automatic gate movement, and forms a gate execution instruction set; S64. Based on the gate execution instruction set, the gate hoist on each gate hole is controlled in sequence to adjust the gate to the calculated opening value, and the execution result of each instruction set is fed back; S65. The gate control system receives feedback of the execution result of each instruction set, calculates the error value between the actual gate opening value and the corresponding calculated opening value, and determines whether the error value is lower than the fourth set value. If so, the execution of the instruction ends. If not, a warning alarm is issued; S66. Determine whether the gate execution instruction set has been executed. If so, the gate operation command event ends. If not, execute step S64.

5. The method for automatic control of gates under a branched river according to claim 1, characterized in that: Step S8 is specifically as follows: Obtaining the current opening value of the gate, the water level in front of the gate, the flow rate of the upstream river channel and the flow rate of each branch river channel as a set of first data sets; The data in the first data set is input into the branching river gate opening model to calculate the correction function The value of f 1; Based on the training data set after data preprocessing, the correction function is calculated The value of f 2. Calculation f 1 and f 2 to obtain a calculation result, and based on the calculation result, the correction function In and Parameters to adjust.

6. An automatic control system for gates under a bifurcated river channel, implemented by an automatic control method for gates under a bifurcated river channel as claimed in claim 1, characterized in that: The system comprises: A monitoring unit, used to obtain real-time monitoring information of the upstream and downstream rivers of the gate and gate monitoring information, obtain the total flow of the upstream river before the gate and the branch flow of each branch river after the gate based on the real-time monitoring information, and obtain the gate opening data based on the gate monitoring information; A training unit, used for extracting a training data set of a model based on historical monitoring data of a monitored river, basic river data and gate data, and preprocessing data in the training data set; An opening model unit is used to establish a branched river channel gate opening model based on the total flow of the upstream river channel before the gate, the branched flow of each branched river channel after the gate and the opening data of the gate, and to calibrate the parameters of the branched river channel gate opening model based on the training data set after data preprocessing; A prediction unit, used for real-time monitoring and obtaining the water flow of the upstream river channel, and calculating the predicted water flow of each branch river channel behind the gate by using the branch river channel gate opening model; A judgment unit, for obtaining the required water flow range of each branched river channel behind the gate based on the scheduling plan of the downstream river channel, and judging whether the predicted water flow of each branched river channel is within the corresponding required water flow range, if so, returning to the prediction unit, if not, entering the gate adjustment unit; A gate adjustment unit, for obtaining a planned water discharge flow of each branched river channel based on the scheduling plan, inputting the water flow of the upstream river channel and the planned water discharge flow of each branched river channel into the branched river channel gate opening model for processing, obtaining a calculated opening of the gate, and adjusting the gate opening value to the calculated opening through the gate control system; The optimization calculation unit is used to obtain the real-time drainage flow of each branched river channel when the gate opening value is adjusted to the calculated opening and the drainage flow of each branched river channel behind the gate is stable, and calculate the difference between the real-time drainage flow and the planned drainage flow; The optimization updating unit is used to determine whether the difference is greater than a first set value. If so, the branch channel gate opening model is updated; if not, the prediction unit is returned.