A method and system for dynamic prediction of weir flow rate

Abstract

This invention discloses a method and system for dynamically predicting the flow rate of a weir or sluice gate, comprising: acquiring and processing real-time data from various stations; predicting the future inundation outflow coefficient using an inundation outflow coefficient prediction model, wherein the inputs to the inundation outflow coefficient prediction model include the upstream water level, the downstream water level, and the trend changes of various parameters at each time step, and the output of the inundation outflow coefficient prediction model is the inundation outflow coefficient at a future time; the inundation outflow coefficient prediction model employs a machine learning model; and, based on the inundation outflow coefficient at a future time output by the inundation outflow coefficient prediction model, calculating the predicted flow rate of the weir or sluice gate using the weir flow formula and outputting the result. This invention enables dynamic prediction of the flow rate of a weir or sluice gate, improving the prediction accuracy of the flow rate.

Description

Technical Field

[0001] This invention relates to a method for predicting the flow rate of a weir or sluice gate, and more particularly to a method and system for dynamically predicting the flow rate of a weir or sluice gate. Background Technology

[0002] In water conservancy projects, overflow dams and sluice gates are often constructed to control and regulate flow, taking into account the comprehensive requirements of flood control, irrigation, and power generation. In hydraulics, a wet structure with overflowing water at its top is called a weir. The flow of water over a weir, when not controlled by a gate, is called weir flow. Therefore, weir flow refers to the phenomenon of a continuous and smooth drop in water surface when the water flows over a spillway structure. The flow phenomena of water over the top of an overflow dam, bridge openings, and the inlet of a pressureless tunnel are all examples of weir flow. When the flow of water over a weir is controlled by a gate, it is called gate outflow, or simply orifice flow. Gate outflow is closely related to weir flow; when the gate opening height exceeds a certain value, the bottom edge of the gate no longer constrains the upper edge of the water flow, and gate outflow transforms into weir flow.

[0003] In plain areas, the flow state of weirs and sluices is generally submerged outflow, so the submerged outflow formula is used for weir and sluice flow calculations. When using this formula to calculate flow rate, fixed parameters are employed. This value is suitable for steady flow, but in reality, water flow conditions are complex, so using a fixed parameter is necessary. This will reduce the accuracy of the calculation results and result in a large discrepancy between the actual measured flow rate and the calculated value. Summary of the Invention

[0004] Purpose of the invention: To address the above problems, this invention proposes a method and system for dynamic prediction of flow rate through weirs and sluices, which can realize dynamic prediction of flow rate through weirs and sluices and improve the prediction accuracy of flow rate through weirs and sluices.

[0005] Technical Solution: The technical solution adopted in this invention is a dynamic prediction method for the flow rate of a weir or sluice gate, comprising: acquiring and processing real-time data from each station; predicting the future inundation outflow coefficient based on the processed real-time data using an inundation outflow coefficient prediction model, wherein the inputs of the inundation outflow coefficient prediction model include the upstream water level, the downstream water level, and the trend changes of each parameter at each time step, and the output of the inundation outflow coefficient prediction model is the inundation outflow coefficient at a future time; the inundation outflow coefficient prediction model employs a machine learning model; and calculating the predicted flow rate of the weir or sluice gate using the weir flow formula based on the inundation outflow coefficient at a future time output by the inundation outflow coefficient prediction model, and then outputting the predicted flow rate of the weir or sluice gate.

[0006] As a preferred embodiment of the dynamic prediction method for weir and sluice gate flow rate, real-time data from each station is acquired, including the time series of the upstream water level, downstream water level, and weir and sluice gate flow rate. Processing the real-time data from each station includes: calculating the trend changes of each parameter at each time step based on the real-time data from each station, including the rate of change of the upstream water level over time, the rate of change of the downstream water level over time, the rate of change of the difference between the upstream and downstream water levels over time, and the rate of change of the weir and sluice gate flow rate over time.

[0007] As a preferred embodiment of the dynamic prediction method for the flow rate of the weir and sluice gate, the prediction model for the inundation outflow coefficient adopts a BP neural network model or an RNN neural network model.

[0008] Furthermore, the training method for the flood outflow coefficient prediction model includes the following steps:

[0009] (21) Obtain real-time data from each station, including the water level Z at the sluice gate. u Water level Z downstream of the sluice gate d The time series of the outflow Q of the weir and sluice gate were used; based on the data from each station, the inundation outflow coefficient was calculated using the weir flow formula. The time series; based on data from each station, the trend changes of each parameter at each time step are calculated, including the rate of change of the water level above the sluice gate over time. Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time with the weir gate

[0010] (22) Adjust the water level Z at the sluice gate u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir gate The corresponding flooding outflow coefficient at a later time. Packaged into a dataset for training machine learning models.

[0011] The weir flow formula is:

[0012]

[0013] Where Q is the predicted flow rate of the weir / sluice gate. Where B is the flood discharge coefficient, and H is the total opening width of the gate. S The water depth above the sluice gate is Z. u The water level at the sluice gate, Z dLet g be the water level below the sluice gate, and g be the acceleration due to gravity.

[0014] This invention proposes a dynamic prediction system for the flow rate of a weir or sluice gate, which includes a data processing module, a flood outflow coefficient prediction model module, and a weir or sluice gate flow rate prediction module.

[0015] The data processing module is used to acquire and process real-time data from each site.

[0016] The inundation outflow coefficient prediction model module is used to: predict the future inundation outflow coefficient based on the processed real-time data of each station. The input of the inundation outflow coefficient prediction model includes the upstream water level, downstream water level, and the trend changes of each parameter at each time step. The output of the inundation outflow coefficient prediction model is the inundation outflow coefficient at a future time. The inundation outflow coefficient prediction model adopts a machine learning model.

[0017] The weir and sluice gate flow prediction module is used to calculate and output the predicted flow rate of the weir and sluice gate based on the inundation outflow coefficient output by the inundation outflow coefficient prediction model at a certain future moment, using the weir flow formula.

[0018] As a preferred embodiment of the dynamic prediction system for weir and sluice gate flow rate, real-time data from each station is acquired, including the time series of the upstream water level, downstream water level, and weir and sluice gate flow rate. Processing the real-time data from each station includes: calculating the trend changes of each parameter at each time step based on the real-time data from each station, including the rate of change of the upstream water level over time, the rate of change of the downstream water level over time, the rate of change of the difference between the upstream and downstream water levels over time, and the rate of change of the weir and sluice gate flow rate over time.

[0019] This invention proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the dynamic prediction method for the flow rate of the weir gate.

[0020] This invention proposes a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the dynamic prediction method for the flow rate of a weir gate.

[0021] This invention proposes a computer program product, including a computer program and / or instructions, which, when executed by a processor, implement the aforementioned method for dynamically predicting the flow rate of a weir or sluice gate.

[0022] Beneficial Effects: Compared with existing technologies, this invention has the following advantages: This invention simulates and predicts the submerged outflow coefficient in the weir flow formula based on dynamically changing time series trends. By predicting the submerged outflow coefficient in real time, it considers the influence of unsteady flow on the submerged outflow coefficient in the weir flow formula, thereby improving the prediction accuracy of the weir and sluice gate flow rate. This invention uses a BP neural network model from machine learning, combined with real-time changing upstream and downstream water levels and flow rates, to predict the submerged outflow coefficient, which can further improve the prediction accuracy of the weir and sluice gate flow rate. Comparing existing static methods and the dynamic prediction method described in this invention, it can be seen that the correlation coefficient R between the prediction results and the measured values ​​of the weir and sluice gate flow rate is significantly higher. 2 This represents a significant improvement, with the relative error of the data decreasing from 5.52% to 3.04%. Attached Figure Description

[0023] Figure 1 This is a simplified schematic diagram of a weir / sluice gate;

[0024] Figure 2 This is the interface for training data in a neural network model.

[0025] Figure 3 This is a comparison chart of the correlation between the calculated flow rate and the measured flow rate in this embodiment. Detailed Implementation

[0026] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0027] Example 1

[0028] A simplified schematic diagram of a weir and sluice gate is shown below. Figure 1 As shown, the bottom elevation Z0 is the elevation of the bottom of the weir, and the water level Z above the weir is... u Z represents the water depth upstream of the weir and the water level downstream of the weir. d The depth of water downstream of the weir is H0, and the depth of water above the sill above the weir is Z, which represents the water level above the weir. u Subtract the bottom elevation Z0 of the gate, and the water depth H above the gate sill. S The water level Z downstream of the sluice gate d Subtracting the gate bottom elevation Z0, the weir-gate flow rate Q is the submerged outflow from upstream to downstream. In actual production applications, considering the ease of data observation, the submerged outflow is generally calculated using the weir flow formula (submerged outflow), as follows:

[0029]

[0030] in: The submerged outflow coefficient is typically a fixed constant between 1.0 and 1.18; B is the total opening width of the gate, in meters per meter (m); H S Z represents the water depth above the sluice gate threshold, in meters (m). uZ represents the upstream water level of the sluice gate, in meters per second (m). d This refers to the water level downstream of the sluice gate, in meters per second (m).

[0031] This invention uses dynamically changing time series trends to simulate and predict the submerged outflow coefficient in the weir flow formula. Taking measured data from a certain station as an example, the dynamic prediction method for weir and sluice gate flow rate described in this invention includes the following steps:

[0032] (1) Acquire and process data, including the water level Z above the sluice gate. u Water level Z downstream of the sluice gate d The time series of the flow rate Q of the weir and sluice gate.

[0033] Given the total gate opening width B = 80m, the gate bottom elevation Z0 = -3m, and g = 9.8m / s², we can determine the values ​​of g and g. 2 Obtain detailed daily, hourly, or more specific data for each station, including time t and water level Z above the sluice gate. u Water level Z downstream of the sluice gate d The flow rate Q of the weir / sluice gate;

[0034] (2) According to the water level Z at the sluice gate u Water level Z below the sluice gate d The time series of the flow rate Q through the weir and sluice gate is used to calculate the submerged outflow coefficient using the weir flow formula. The time series data is shown in Table 1.

[0035] Table 1. Collected Data and Calculated Submerged Outflow Coefficient

[0036]

[0037]

[0038] (3) According to the water level Z at the sluice gate u Water level Z below the sluice gate d The time series of the flow rate Q at the weir and sluice gate was used to calculate the trend change at each time step, including the rate of change of the water level above the gate over time. Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time with the weir gate Data excerpts are shown in Table 2.

[0039] Table 2 Calculation Input Elements Table

[0040]

[0041]

[0042] (4) Adjust the water level Z at the sluice gate uWater level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir gate The corresponding flooding outflow coefficient for the next time step The data is packaged into a dataset, and a machine learning model is trained using this dataset. After training, a flood outflow coefficient prediction model is obtained. The upstream water level Z... u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir gate The flood outflow coefficient at the next time step is used as the input to the machine learning model and as the output of the machine learning model.

[0043] The machine learning model can be a backpropagation (BP) neural network or an RNN neural network (using time-series data as input). Any other machine learning model capable of learning from data can replace the aforementioned neural network models.

[0044] This embodiment uses a BP neural network model. The "Automatic Training Network and Parameters" function can obtain the simulation results. You can click again as needed to continue training based on these results. The interface is as follows: Figure 2 As shown.

[0045] Those skilled in the art can foresee that, and can also use the flood outflow coefficient data at a future time step to train the BP neural network model, so that the BP neural network model outputs the flood outflow coefficient at a future time as the predicted flood outflow coefficient.

[0046] (5) The real-time collected water level Z at the gate u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir gate The flood outflow coefficient prediction model outputs the flood outflow coefficient for the next time step, i.e., the predicted flood outflow coefficient.

[0047] (6) The obtained predicted flood outflow coefficient By substituting the formula for the predicted flow rate Q of the weir and sluice gate, the flow rate of the weir and sluice gate at future times can be calculated.

[0048] like Figure 3 The figure shows a comparison of the correlation between calculated and measured flow rates using the static method and this embodiment. The trend line R in the figure... 2 The increase from 0.7939 to 0.9795 demonstrates that the dynamic prediction method for weir and sluice gate flow rate described in this invention provides a better simulation effect between the actual and calculated flow rates. Further data analysis shows that when using the existing static method, the correlation coefficient between the actual and calculated flow rates is 0.89, the relative error is 5.52%, and the root mean square error is 42.88, indicating a level of significant fluctuation around the average. After using the new trend-changing method (dynamic prediction method for weir and sluice gate flow rate), the correlation coefficient between the actual and calculated flow rates increases to 0.99, the relative error decreases to 3.04%, and the data accuracy significantly improves, reflected in a decrease in the root mean square error to 19.14.

[0049] Example 2

[0050] The dynamic prediction system for weir and sluice gate flow rate of the present invention includes a data processing module, a flood outflow coefficient prediction model module, and a weir and sluice gate flow rate prediction module.

[0051] The data processing module is used to acquire and process real-time data from each station. Specifically, it acquires real-time data from each station, including the time series of the upstream water level, downstream water level, and weir / sluice flow rate. Processing the real-time data from each station includes: calculating the trend changes of each parameter at each time step based on the real-time data from each station, including the rate of change of the upstream water level over time, the rate of change of the downstream water level over time, the rate of change of the difference between the upstream and downstream water levels over time, and the rate of change of the weir / sluice flow rate over time.

[0052] The flood outflow coefficient prediction model module adopts a machine learning model architecture. The input of the machine learning model includes the water level Z above the sluice gate. u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time with the weir gate The output of the machine learning model is the flood outflow coefficient for the next time step.

[0053] The water level at the sluice gate Z u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir gate The corresponding flooding outflow coefficient for the next time step The dataset is packaged for training machine learning models. The specific process for acquiring the dataset is as follows: real-time data from each station is obtained, including the water level Z above the sluice gate. u Water level Z downstream of the sluice gate d The time series of the outflow Q of the weir and sluice gate were used; based on the data from each station, the inundation outflow coefficient was calculated using the weir flow formula. The time series; based on data from each station, the trend changes of each parameter at each time step are calculated, including the rate of change of the water level above the sluice gate over time. Rate of change of water level downstream of the sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time with the weir gate

[0054] The weir / sluice gate flow rate prediction module is used to predict the inundation outflow coefficient output by the inundation outflow coefficient prediction model module. Substituting the flow formula back into the weir, we obtain the predicted flow rate Q of the weir, which is the flow rate of the weir at future times.

[0055] Example 3

[0056] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described method for dynamic prediction of flow rate of a weir gate.

[0057] Example 4

[0058] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method for dynamically predicting the flow rate of a weir or sluice gate.

[0059] Example 5

[0060] In one embodiment, a computer program product is provided, including a computer program / instruction that, when executed by a processor, implements the dynamic prediction method for the flow rate of the weir gate.

[0061] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0063] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0064] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

Claims

1. A method for dynamically predicting the flow rate of a weir or sluice gate, characterized in that, include: Acquire and process real-time data from each site; Based on the processed real-time data, the future inundation outflow coefficient is predicted using an inundation outflow coefficient prediction model, including: the real-time collected upstream water level Z. u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir / sluice gate The flood outflow coefficient prediction model outputs the flood outflow coefficient for the next time step, i.e., it predicts the flood outflow coefficient. The inundation outflow coefficient prediction model uses a machine learning model. Based on the inundation outflow coefficient at a future time output by the inundation outflow coefficient prediction model, the predicted flow rate of the weir is calculated using the weir flow formula and then output. The training method for the flood outflow coefficient prediction model includes the following steps: (1) Obtain real-time data from each station, including the water level Z at the sluice gate. u Water level Z downstream of the sluice gate d The time series of the outflow Q of the weir and sluice gate were used; based on the data from each station, the inundation outflow coefficient was calculated using the weir flow formula. Time series of 0; based on data from each station, calculate the trend changes of each parameter at each time step, including the rate of change of the water level above the sluice gate over time. Rate of change of water level downstream of sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time with the weir gate ; (2) Adjust the water level Z at the sluice gate u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir / sluice gate The corresponding inundation outflow coefficient at a later time. 0 is packaged into a dataset for training machine learning models; The weir flow formula is: ， Where Q is the predicted flow rate of the weir / sluice gate. Where B is the flood discharge coefficient, and H is the total opening width of the gate. S The water depth above the sluice gate is Z. u The water level at the sluice gate, Z d Let g be the water level below the sluice gate, and g be the acceleration due to gravity.

2. The method for dynamically predicting the flow rate of a weir or sluice gate according to claim 1, characterized in that: Acquire real-time data from each station, including time series of water levels upstream and downstream of the sluice gate and the flow rate through the weir and sluice gate; process the real-time data from each station, including: based on the real-time data from each station, calculate the trend changes of each parameter at each time step, including the rate of change of water level upstream of the sluice gate over time, the rate of change of water level downstream of the sluice gate over time, the rate of change of the difference between water levels upstream and downstream of the sluice gate over time, and the rate of change of flow rate through the weir and sluice gate over time.

3. The method for dynamically predicting the flow rate of a weir or sluice gate according to claim 1, characterized in that: The flood outflow coefficient prediction model adopts either a BP neural network model or an RNN neural network model.

4. A dynamic prediction system for the flow rate of a weir or sluice gate, characterized in that: The system includes a data processing module, a flood outflow coefficient prediction model module, and a weir / sluice gate flow rate prediction module; The data processing module is used to acquire and process real-time data from each site. The inundation outflow coefficient prediction model module is used to: predict future inundation outflow coefficients using the inundation outflow coefficient prediction model, including: using the real-time collected upstream water level Z... u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir / sluice gate The flood outflow coefficient prediction model outputs the flood outflow coefficient for the next time step, i.e., it predicts the flood outflow coefficient. The flood outflow coefficient prediction model uses a machine learning model. The weir and sluice gate flow prediction module is used to calculate and output the predicted flow rate of the weir and sluice gate based on the inundation outflow coefficient output by the inundation outflow coefficient prediction model at a certain future moment, using the weir flow formula. The training method for the flood outflow coefficient prediction model includes the following steps: (1) Obtain real-time data from each station, including the water level Z at the sluice gate. u Water level Z downstream of the sluice gate d The time series of the outflow Q of the weir and sluice gate were used; based on the data from each station, the inundation outflow coefficient was calculated using the weir flow formula. Time series of 0; based on data from each station, calculate the trend changes of each parameter at each time step, including the rate of change of the water level above the sluice gate over time. Rate of change of water level downstream of sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time with the weir gate ; (2) Adjust the water level Z at the sluice gate u Water level Z below the sluice gate d Rate of change of water level above the sluice gate over time Rate of change of water level downstream of sluice gate over time The rate of change of the difference between the water level upstream and downstream of the sluice gate over time. Rate of change of flow rate over time at the weir / sluice gate The corresponding inundation outflow coefficient at a later time. 0 is packaged into a dataset for training machine learning models; The weir flow formula is: ， Where Q is the predicted flow rate of the weir / sluice gate. Where B is the flood discharge coefficient, and H is the total opening width of the gate. S The water depth above the sluice gate is Z. u The water level at the sluice gate, Z d Let g be the water level below the sluice gate, and g be the acceleration due to gravity.

5. The method for dynamically predicting the flow rate of a weir or sluice gate according to claim 4, characterized in that: Acquire real-time data from each station, including time series of water levels upstream and downstream of the sluice gate and the flow rate through the weir and sluice gate; process the real-time data from each station, including: based on the real-time data from each station, calculate the trend changes of each parameter at each time step, including the rate of change of water level upstream of the sluice gate over time, the rate of change of water level downstream of the sluice gate over time, the rate of change of the difference between water levels upstream and downstream of the sluice gate over time, and the rate of change of flow rate through the weir and sluice gate over time.

6. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the dynamic prediction method for the flow rate of the weir gate as described in any one of claims 1 to 3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the dynamic prediction method for the flow rate of the weir and sluice gate as described in any one of claims 1 to 3.

8. A computer program product, comprising a computer program and / or instructions, characterized in that, When the computer program and / or instructions are executed by the processor, they implement the method for dynamic prediction of flow rate of the weir and sluice gate as described in any one of claims 1 to 3.

Images