Water conservancy project water delivery amount adjusting method and system based on artificial intelligence

Abstract

The invention relates to the technical field of water conservancy projects, and discloses a water conservancy project water delivery amount adjustment method and system based on artificial intelligence, and the method comprises the steps: obtaining multi-source real-time data in a water conservancy project, extracting local features in input data based on a CNN convolutional neural network, and processing the long-term dependence of a time sequence through an LSTM neural network, thereby achieving the adjustment of the water delivery amount of the water conservancy project. Paying attention to water delivery variables by using an Attention mechanism, and inputting the initial multi-source real-time data into the demand prediction model for prediction to obtain a water delivery demand curve; and according to the water delivery demand curve, an objective function is set as the minimum energy consumption and the maximum supply and demand matching degree through a PPO reinforcement learning algorithm, and a water delivery control instruction is obtained by simulating different control actions. The accuracy of water delivery demand prediction is remarkably improved, and the relation between complex factors and water delivery demands in a water conservancy project can be captured more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of water conservancy projects, and in particular to an artificial intelligence-based water delivery regulation method and system for water conservancy projects. Background Art

[0002] Traditionally, water flow regulation in hydraulic projects has relied primarily on manual experience and simple automated equipment. This approach has numerous drawbacks. Limited by individual experience and knowledge, manual operations struggle to accurately and accurately respond to complex and changing hydraulic environments in real time. In the face of extreme weather conditions like sudden rainfall and drought, rapid and effective water flow regulation decisions cannot be made, leading to water waste or insufficient supply. Simple automated equipment operates solely according to pre-set, fixed rules and is unable to adapt to the complex multi-factor coupling of hydraulic projects. Summary of the Invention

[0003] The purpose of the present invention is to solve the above problems and to design a water delivery regulation method and system for water conservancy projects based on artificial intelligence.

[0004] To achieve the above-mentioned purpose, the technical solution of the present invention is as follows: further, in the above-mentioned artificial intelligence-based water conservancy project water delivery adjustment method, the water conservancy project water delivery adjustment method includes the following steps: Acquiring multi-source real-time data from a water conservancy project, and performing data preprocessing on the multi-source real-time data to obtain initial multi-source real-time data; The CNN convolutional neural network extracts local features from the input data, the LSTM neural network processes the long-term dependencies of the time series, and the attention mechanism is used to focus on the water delivery variables, resulting in a CNN-LSTM-Attention demand forecasting model. Inputting the initial multi-source real-time data into the CNN-LSTM-Attention demand forecasting model for forecasting to obtain a water delivery demand curve; According to the water delivery demand curve, the objective function is set to minimize energy consumption and maximize supply-demand matching through the PPO reinforcement learning algorithm. By simulating different control actions, water delivery control instructions are obtained, and the gate opening and the start and stop status of the pump station are adjusted according to the water delivery control instructions.

[0005] Furthermore, in the above-mentioned artificial intelligence-based water delivery regulation method for a water conservancy project, the step of obtaining multi-source real-time data from the water conservancy project and performing data preprocessing on the multi-source real-time data to obtain initial multi-source real-time data includes: Obtain multi-source real-time data on water conservancy projects, including at least rainfall, evaporation, reservoir water levels, water pipeline pressure, and downstream water demand; Combining the Z-score method and the IQR method to perform outlier detection on the multi-source real-time data, and using a linear interpolation method to fill in missing values, to obtain first multi-source real-time data; Mapping the first multi-source real-time data to the interval [0, 1] using a Min-Max normalization method, and uniformly converting the collected data in different formats into numerical data to obtain second multi-source real-time data; The second multi-source real-time data is time-synchronized based on the time of the data center server, and the data is spatially aligned based on the geographic information of the water conservancy project and the location coordinates of each monitoring point to obtain the initial multi-source real-time data.

[0006] Furthermore, in the aforementioned artificial intelligence-based water delivery regulation method for a water conservancy project, the CNN-based convolutional neural network extracts local features from the input data, the LSTM neural network processes the long-term dependencies of the time series, and the attention mechanism is used to focus on the water delivery variables, thereby obtaining a CNN-LSTM-Attention demand forecasting model, including: The first convolution layer of the CNN convolutional neural network uses 64 convolution kernels of size (3,1) to extract local features from the input multi-source time series data; The second convolution layer uses 128 convolution kernels of different sizes to further extract complex local features; The third convolutional layer uses 256 convolution kernels of different sizes to capture local information. The stride of the convolutional layer is set to 1 and the padding method is the same.

[0007] Furthermore, in the aforementioned artificial intelligence-based water delivery regulation method for a water conservancy project, the CNN-based convolutional neural network extracts local features from the input data, the LSTM neural network processes the long-term dependencies of the time series, and the attention mechanism is used to focus on the water delivery variables, thereby obtaining a CNN-LSTM-Attention demand forecasting model, including: The first LSTM layer of the LSTM neural network receives the local feature data output by the CNN convolutional neural network and converts it into a time series data format; The second LSTM layer is used to further process the output of the first LSTM layer to enhance the model's ability to capture long-term dependencies in time series. The dropout rate of the LSTM layer is set to 0.2, and the return sequence is set to True.

[0008] Furthermore, in the aforementioned artificial intelligence-based water delivery regulation method for a water conservancy project, the CNN-based convolutional neural network extracts local features from the input data, the LSTM neural network processes the long-term dependencies of the time series, and the attention mechanism is used to focus on the water delivery variables, thereby obtaining a CNN-LSTM-Attention demand forecasting model, including: The hidden state output by the LSTM neural network is used as the query, key, and value. The attention score is obtained by calculating the dot product of the query and the key and dividing it by the scaling factor. Use the Softmax function to normalize the attention scores to obtain the attention weight of each input element; Finally, the Value is weighted and summed according to the attention weight, and the importance between the water supply demand and each input variable is automatically learned through the Attention mechanism.

[0009] Furthermore, in the above-mentioned artificial intelligence-based water delivery regulation method for a water conservancy project, the objective function is set to minimize energy consumption and maximize supply-demand matching through the PPO reinforcement learning algorithm according to the water delivery demand curve, and the water delivery control instruction is obtained by simulating different control actions, including: Define the state space and state space, and establish the state transfer equation according to the physical model of the water conservancy project and the dynamic characteristics of the water delivery system; Design an objective function that gives positive rewards when energy consumption decreases and the supply-demand match improves; and gives negative rewards when energy consumption increases or the supply-demand match decreases.

[0010] Furthermore, in the above-mentioned artificial intelligence-based water delivery regulation method for a water conservancy project, the objective function is set to minimize energy consumption and maximize supply-demand matching through the PPO reinforcement learning algorithm according to the water delivery demand curve, and water delivery control instructions are obtained by simulating different control actions, which also includes: The PPO reinforcement learning algorithm is used to simulate different control actions in the state space, and the reward value of each action is calculated based on the state transition equation and reward function; The control action that minimizes the objective function is selected as the optimal water delivery control instruction.

[0011] Furthermore, in a water conservancy project water delivery regulation system based on artificial intelligence, the water conservancy project water delivery regulation system includes the following modules: A real-time data acquisition module is used to acquire multi-source real-time data in a water conservancy project, and perform data preprocessing on the multi-source real-time data to obtain initial multi-source real-time data; The forecasting model building module is used to extract local features from input data based on the CNN convolutional neural network, process the long-term dependencies of time series through the LSTM neural network, and use the Attention mechanism to focus on water delivery variables to obtain the CNN-LSTM-Attention demand forecasting model; A water transmission demand prediction module is used to input the initial multi-source real-time data into the CNN-LSTM-Attention demand prediction model to perform prediction and obtain a water transmission demand curve; The water delivery control and adjustment module is used to set the objective function as minimizing energy consumption and maximizing supply-demand matching according to the water delivery demand curve through the PPO reinforcement learning algorithm, obtain water delivery control instructions by simulating different control actions, and adjust the gate opening and the start and stop status of the pump station according to the water delivery control instructions.

[0012] Furthermore, in an artificial intelligence-based water conservancy project water delivery regulation system, the water delivery control and regulation module includes the following submodules: Definition submodule, used to define the state space and state space, and establish the state transfer equation according to the physical model of the water conservancy project and the dynamic characteristics of the water delivery system; The judgment submodule is used to design the objective function. It gives positive rewards when energy consumption decreases and the supply-demand matching degree improves; it gives negative rewards when energy consumption increases or the supply-demand matching degree decreases.

[0013] Furthermore, in an artificial intelligence-based water conservancy project water delivery regulation system, the water delivery control and regulation module includes the following submodules: The simulation submodule is used to simulate different control actions in the state space through the PPO reinforcement learning algorithm and calculate the reward value of each action according to the state transition equation and reward function; The selection submodule is used to select the control action that minimizes the objective function as the optimal water delivery control instruction.

[0014] Its beneficial effects are as follows: by acquiring multi-source real-time data from water conservancy projects, the multi-source real-time data is preprocessed to obtain initial multi-source real-time data; based on the CNN convolutional neural network, local features in the input data are extracted, the long-term dependencies of the time series are processed through the LSTM neural network, and the attention mechanism is used to focus on water transmission variables to obtain a CNN-LSTM-Attention demand prediction model; the initial multi-source real-time data is input into the CNN-LSTM-Attention demand prediction model for prediction to obtain a water transmission demand curve; based on the water transmission demand curve, the objective function is set to minimize energy consumption and maximize supply and demand matching through the PPO reinforcement learning algorithm, water transmission control instructions are obtained by simulating different control actions, and the gate opening and pump station start and stop status are adjusted according to the water transmission control instructions. 1. Compared with a single model or traditional prediction method, the accuracy of water transmission demand prediction is significantly improved, and the relationship between complex factors in water conservancy projects and water transmission demand can be more accurately captured, providing a reliable prediction basis for water transmission control, and reducing the irrational allocation of water resources due to prediction bias. 2. It can comprehensively assess the impact of various operations on energy consumption and supply-demand matching, thereby generating optimal water transfer control instructions. Compared to traditional water transfer control methods, this solution can dynamically adjust gate openings and pump station start and stop states based on real-time data and forecast results. While meeting downstream water demand, it effectively reduces energy consumption, achieves efficient use of water resources, optimizes water project operating costs, and improves the economic benefits of water conservancy projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Various other advantages and benefits will become apparent to those skilled in the art by reading the following detailed description of the preferred embodiment.The accompanying drawings are only for the purpose of illustrating the preferred embodiment and are not to be considered as limiting the present invention.

[0016] Figure 1 This is a schematic diagram of a first embodiment of a method for regulating water delivery of a water conservancy project based on artificial intelligence in an embodiment of the present invention; Figure 2 Schematic diagram of a second embodiment of a method for regulating water delivery of a water conservancy project based on artificial intelligence in an embodiment of the present invention; Figure 3 This is a schematic diagram of a first embodiment of an artificial intelligence-based water delivery regulation system for a water conservancy project in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a," "an," "said," and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the stated features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0019] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1 As shown, a water delivery adjustment method for a water conservancy project based on artificial intelligence includes the following steps: Step 101: Acquire multi-source real-time data from a water conservancy project, perform data preprocessing on the multi-source real-time data, and obtain initial multi-source real-time data; Specifically, in this embodiment, multi-source real-time data in water conservancy projects is obtained, including at least rainfall, evaporation, reservoir water level, water pipeline pressure, and downstream water demand; The Z-score method and the IQR method are combined to detect outliers in multi-source real-time data, and the missing values ​​are filled using the linear interpolation method to obtain the first multi-source real-time data; The first multi-source real-time data is mapped to the interval [0, 1] using the Min-Max normalization method, and the collected data in different formats are uniformly converted into numerical data to obtain the second multi-source real-time data; Based on the time of the data center server, the second multi-source real-time data is time-synchronized, and the data is spatially aligned according to the geographic information of the water conservancy project and the location coordinates of each monitoring point to obtain the initial multi-source real-time data.

[0020] Specifically: (1) Multi-source real-time data collection; Data acquisition equipment and installation: Rainfall: A tipping bucket rain gauge is installed in an open, unobstructed area within the water conservancy project basin to ensure accurate collection of natural rainfall data. The sensor collects rainfall data once per minute and transmits the data in real time to the data center server via a 4G wireless communication module.

[0021] Evaporation: An E601B evaporator is installed in a flat, well-ventilated observation area that complies with national meteorological observation standards. Evaporation data is recorded hourly and transmitted to a data center using an NB-IoT wireless communication module.

[0022] Reservoir water level: A radar water level meter is installed at a suitable location upstream of the reservoir dam to avoid being affected by factors such as water flow disturbances and aquatic plants. Reservoir water level is collected every 10 minutes and the data is sent to the data center via a 4G communication module.

[0023] Water pipeline pressure: A pressure transmitter is installed in a straight section of the water pipeline, away from valves, elbows, and other components that could interfere with pressure measurement. The pressure transmitter collects pipeline pressure data once per second and transmits the data to a data center via 4G wireless communication.

[0024] Downstream water demand: This forecast combines real-time user demand reporting data with historical water demand data. Users submit real-time water demand reports through a dedicated water conservancy project water demand reporting system, which updates user demand reporting data hourly. Historical water demand data forecasts are based on downstream user water use records from the past three years and are updated daily at dawn using an ARIMA (Asynchronous Recognition and Integrated Molecular Analyses) algorithm to generate water demand forecasts for the next period.

[0025] Data collection frequency and communication method: Each sensor and data source collects data at the specified frequency and transmits the data to the data center server in real time via 4G or NB-IoT wireless communication modules to ensure real-time and reliable data. The data center server has a dedicated database to store and manage the collected multi-source data.

[0026] (2) Data preprocessing; Data cleaning: Outlier Detection: We use a combination of the Z-score and IQR methods to detect outliers in the collected data. The Z-score method determines outliers by calculating the standard deviation of a data point from the mean, with data points exceeding ±3 standard deviations from the mean considered outliers. The IQR method calculates the interquartile range (IQR = Q3 - Q1), with data points less than Q1 - 1.5 IQR or greater than Q3 + 1.5 IQR considered outliers. Detected outliers are filled with the mean or median of the data at adjacent time points, depending on the time series characteristics of the data.

[0027] Missing value processing: For missing data in the short term (data missing within a few minutes), linear interpolation is used to fill in the missing data; for missing data in the long term (data missing for more than one hour), regression prediction is performed based on historical data and relevant influencing factors (rainfall, downstream water demand, etc.).

[0028] Data conversion: Normalization Method: Based on the data characteristics and model requirements, a combination of Min-Max normalization and Z-score normalization was used to normalize the data. For data with distinct ranges, such as rainfall, evaporation, and reservoir water levels, Min-Max normalization was used to map the data to the [0, 1] interval. For data such as water pipeline pressure and downstream water demand, Z-score normalization was used to ensure zero mean and unit variance, as the mean and standard deviation significantly influence the data distribution.

[0029] Data format conversion: Convert the collected data in different formats (text format, numerical format, etc.) into numerical data to facilitate subsequent model input and processing.

[0030] Data Integration: Time synchronization: Data collected by various sensors and data sources is synchronized using the data center server time as the benchmark, ensuring that all data has the same timestamp. Data with a time deviation exceeding a certain threshold (1 minute) is deemed invalid and cleaned.

[0031] Spatial alignment: Based on the geographic information of the water conservancy project and the location coordinates of each monitoring point, multi-source data is spatially aligned, and the monitoring data at different locations are associated with the water delivery system structure of the water conservancy project to facilitate subsequent model analysis and control instruction generation.

[0032] Step 102: Extract local features from the input data based on the CNN convolutional neural network, process the long-term dependencies of the time series through the LSTM neural network, and use the Attention mechanism to focus on the water delivery variables to obtain the CNN-LSTM-Attention demand forecasting model; Specifically, in this embodiment, the first convolution layer of the CNN convolutional neural network uses 64 convolution kernels of size (3, 1) to extract local features from the input multi-source time series data; The second convolution layer uses 128 convolution kernels of different sizes to further extract complex local features; The third convolutional layer uses 256 convolution kernels of different sizes to capture local information. The stride of the convolutional layer is set to 1 and the padding method is the same.

[0033] The first LSTM layer of the LSTM neural network receives the local feature data output by the CNN convolutional neural network and converts it into a time series data format; The second LSTM layer is used to further process the output of the first LSTM layer to enhance the model's ability to capture long-term dependencies in time series. The dropout rate of the LSTM layer is set to 0.2, and the return sequence is set to True.

[0034] The hidden state output by the LSTM neural network is used as the query, key, and value. The attention score is obtained by calculating the dot product of the query and the key and dividing it by the scaling factor. Use the Softmax function to normalize the attention scores to obtain the attention weight of each input element; Finally, the Value is weighted and summed according to the attention weight, and the importance between the water supply demand and each input variable is automatically learned through the Attention mechanism.

[0035] Specifically: (1) CNN convolutional neural network; Network structure: CNN convolutional neural network consists of 3 layers of convolutional layers and 3 layers of maximum pooling layers alternating.

[0036] The first convolutional layer uses 64 convolution kernels of size (3, 1) to extract local features from the input multi-source time series data. The convolution kernel has a sliding window size of 3 in the time dimension and 1 in the feature dimension to capture local correlations in the data over time. ReLU is used as the activation function to introduce nonlinearity and enhance the model's expressiveness.

[0037] The first maximum pooling layer: The pooling kernel size is (2,1), which downsamples the data output by the convolutional layer to reduce the data dimension, reduce the computational complexity of the model, and avoid overfitting.

[0038] The second convolutional layer uses 128 convolution kernels of size (5, 1) to further extract more complex local features. Larger convolution kernels can capture local information over a longer time range. The activation function also uses ReLU.

[0039] The second maximum pooling layer: The pooling kernel size is (2,1), and the data output by the second convolutional layer is downsampled.

[0040] The third convolutional layer uses 256 convolution kernels of size (7, 1) to capture richer local information. Increasing the number of convolution kernels improves the model's ability to extract different features. The activation function is ReLU.

[0041] The third maximum pooling layer: The pooling kernel size is (2,1), and the data output by the third convolutional layer is downsampled to obtain the final local feature representation.

[0042] Parameter settings: The step size of the convolution layer is set to 1 to ensure that the local features of the data can be fully extracted; the padding method is same, so that the time dimension of the data remains unchanged after the convolution operation, which facilitates subsequent pooling operations and connection with the LSTM neural network.

[0043] (2) LSTM neural network; Network structure: The LSTM neural network consists of two hidden layers, each containing 128 neurons.

[0044] The first LSTM layer receives local feature data output by the CNN convolutional neural network and converts it into a time series data format, allowing the LSTM neural network to process long-term dependencies in the time series. LSTM neurons control the flow of information through forget gates, input gates, and output gates, effectively capturing data dependencies in long time series.

[0045] The second LSTM layer further processes the output of the first LSTM layer to enhance the model's ability to capture long-term dependencies in time series. Both LSTM layers use a bidirectional LSTM structure to simultaneously consider past and future time series information, improving the model's forecasting accuracy.

[0046] Parameter settings: The dropout rate of the LSTM layer is set to 0.2 to prevent overfitting; the return sequence is set to True so that the output of the LSTM layer is passed to the Attention mechanism for processing.

[0047] (3) Attention mechanism; Attention type: Scaled Dot-Product Attention is used. This type of attention can efficiently calculate the correlation between elements in the input sequence, thereby paying attention to the water delivery variable.

[0048] Operational process: The hidden state output by the LSTM neural network is used as the query, key, and value. An attention score is calculated by calculating the dot product of the query and key and dividing it by a scaling factor (√d_k, where d_k is the dimension of the key). The attention score is then normalized using the Softmax function to obtain the attention weight for each input element. Finally, the value is weighted and summed according to the attention weight to obtain the final output. Through the attention mechanism, the model can automatically learn the importance between water demand and various input variables (such as rainfall, reservoir water level, and downstream water demand), thereby paying more attention to variables that have a greater impact on water demand.

[0049] (4) Model integration; The local features extracted by the CNN convolutional neural network are input into the LSTM neural network to process long-term dependencies in the time series. The attention mechanism then focuses on the water supply variables, ultimately resulting in a CNN-LSTM-Attention demand forecasting model. The model outputs the predicted water supply demand for a period of time.

[0050] Step 103: Input the initial multi-source real-time data into the CNN-LSTM-Attention demand forecasting model to perform forecasting and obtain a water delivery demand curve; Specifically, in this embodiment: (1) Data input format; The preprocessed multi-source real-time data is organized into a multidimensional array in time series, with the dimensions [number of samples, time step, number of features]. The number of samples is determined by the size of the training data, the time step is the length of the time window input to the model (the past 24 hours of time data), and the number of features is the feature dimensions of the collected multi-source data (including rainfall, evaporation, reservoir water level, water pipeline pressure, and downstream water demand).

[0051] (2) Model training process; Dataset Partitioning: Historical data is divided into training, validation, and test sets, with the training set accounting for 70%, the validation set for 20%, and the test set for 10%. The training set is used for model parameter learning, the validation set for hyperparameter adjustment and overfitting detection, and the test set for evaluating the final model performance.

[0052] Optimizer selection: The Adam optimizer is used, which combines the momentum method and the adaptive learning rate method. It can automatically adjust the learning rate during training, improving the training efficiency and convergence speed of the model.

[0053] Loss function definition: The loss function uses the mean square error (MSE) to measure the difference between the model prediction value and the actual water demand value.

[0054] Training Process: The model is iteratively trained using the training set. The loss function is calculated for each iteration, and the model parameters are updated using the backpropagation algorithm. During training, the model performance is regularly evaluated using the validation set. Hyperparameters (such as the learning rate, number of convolution kernels, and number of LSTM neurons) are adjusted based on the validation set loss to avoid overfitting and improve the model's generalization ability. Training is terminated when the loss values ​​on the training and validation sets no longer decrease significantly, resulting in the optimal model parameters.

[0055] (3) Model prediction; The preprocessed initial multi-source real-time data is input into the trained CNN-LSTM-Attention demand forecasting model according to the input format. The model outputs the predicted water supply demand value for a period of time in the future. These predicted values ​​are connected to obtain the water supply demand curve.

[0056] Step 104: According to the water delivery demand curve, the objective function is set to minimize energy consumption and maximize the supply-demand matching through the PPO reinforcement learning algorithm. By simulating different control actions, the water delivery control instruction is obtained, and the gate opening and the start and stop status of the pump station are adjusted according to the water delivery control instruction.

[0057] Specifically, in this embodiment, the state space and the state space are defined, and the state transition equation is established based on the physical model of the water conservancy project and the dynamic characteristics of the water delivery system; Design an objective function that gives positive rewards when energy consumption decreases and the supply-demand match improves; and gives negative rewards when energy consumption increases or the supply-demand match decreases.

[0058] The PPO reinforcement learning algorithm is used to simulate different control actions in the state space, and the reward value of each action is calculated based on the state transition equation and reward function; The control action that minimizes the objective function is selected as the optimal water delivery control instruction.

[0059] Specifically: (1) PPO reinforcement learning algorithm; Objective Function Setting: The objective function is a weighted sum of minimizing energy consumption and maximizing supply-demand matching. Adjusting the weight coefficients can balance the importance of energy consumption and supply-demand matching. Energy consumption primarily includes the electrical energy consumed by the pumping station and the mechanical energy consumed by gate adjustment. Supply-demand matching is measured by calculating the degree of match between actual water delivery and predicted water demand. The inverse of the root mean square error (RMSE) is used as the indicator of supply-demand matching: supply-demand matching = 1 / RMSE.

[0060] State space definition: The state space includes real-time data such as the current reservoir water level, pipeline pressure, downstream water demand, gate opening, pump station start and stop status, and other information, as well as the predicted value of the water demand curve. The dimensions of the state vector are determined by the actual hydraulic system parameters.

[0061] Action Space Definition: Control actions include gate opening and pump station start / stop status. The gate opening range is 0-100%, adjustable in 1% increments. The pump station start / stop status is 0 or 1, with 0 indicating pump station stop and 1 indicating pump station start.

[0062] State transition equations: Based on the physical model of the hydraulic project and the dynamic characteristics of the water delivery system, state transition equations are established to describe the changes in state space after a control action is executed. The state transition equations take into account factors such as the continuity equation for water flow, the energy equation, and the control characteristics of the pumping station and gates.

[0063] Reward function definition: The reward function is designed based on the objective function. When energy consumption decreases and the supply-demand match improves, positive rewards are given; when energy consumption increases or the supply-demand match decreases, negative rewards are given.

[0064] (2) Simulating different control actions; Different control actions are simulated in the state space through the PPO reinforcement learning algorithm. The reward value of each action is calculated according to the state transition equation and the reward function. The control action that can minimize the objective function (i.e., maximize the reward value) is selected as the optimal water delivery control instruction.

[0065] (3) Adjust gate opening and pump station start and stop status; According to the generated water transfer control instructions, the gate opening and pump station start and stop status are adjusted in real time to achieve precise control of the water transfer volume of the water conservancy project to meet downstream water demand while minimizing energy consumption.

[0066] The proposed method obtains multi-source real-time data from water conservancy projects and preprocesses it to generate initial multi-source real-time data. A CNN convolutional neural network extracts local features from the input data, an LSTM neural network processes long-term dependencies in time series, and an attention mechanism focuses on water transfer variables, resulting in a CNN-LSTM-Attention demand forecasting model. The initial multi-source real-time data is then fed into the CNN-LSTM-Attention demand forecasting model for prediction, generating a water transfer demand curve. Based on the water transfer demand curve, the PPO reinforcement learning algorithm sets the objective function to minimize energy consumption and maximize supply-demand matching. Water transfer control instructions are generated by simulating different control actions, and gate openings and pump station start and stop states are adjusted based on these instructions. Compared to single models or traditional forecasting methods, this method significantly improves the accuracy of water transfer demand forecasting, more accurately capturing the relationship between complex factors in water conservancy projects and water transfer demand, providing a reliable forecasting basis for water transfer control and reducing the irrational allocation of water resources due to forecasting bias. Furthermore, it comprehensively assesses the impact of various operations on energy consumption and supply-demand matching, thereby generating optimal water transfer control instructions. Compared with traditional water transfer control methods, this solution can dynamically adjust the gate opening and pump station start and stop status based on real-time data and prediction results. While meeting downstream water demand, it effectively reduces energy consumption, achieves efficient utilization of water resources and optimizes the operating costs of water conservancy projects, and improves the economic benefits of water conservancy projects.

[0067] See also Figure 2 In an AI-based water flow regulation method for water conservancy projects, the improved NeRF neural radiance field framework is used to align and model the fused point cloud data and drone image data to generate a geographic real-world 3D model. The following steps are included: Step 201: Acquire multi-source real-time data on water conservancy projects, including at least rainfall, evaporation, reservoir water level, water pipeline pressure, and downstream water demand; Step 202: Combine the Z-score method and the IQR method to perform outlier detection on the multi-source real-time data, and use the linear interpolation method to fill in the missing values ​​to obtain the first multi-source real-time data; Step 203: Map the first multi-source real-time data to the interval [0, 1] using the Min-Max normalization method, and uniformly convert the collected data in different formats into numerical data to obtain second multi-source real-time data; Step 204: Based on the time of the data center server, the second multi-source real-time data is time-synchronized, and the data is spatially aligned according to the geographic information of the water conservancy project and the position coordinates of each monitoring point to obtain the initial multi-source real-time data.

[0068] The above is an introduction to the embodiment of the water flow regulation method of a water conservancy project based on artificial intelligence of the present invention. Figure 3 In an artificial intelligence-based water conservancy project water delivery regulation system, the water conservancy project water delivery regulation system includes the following modules: The real-time data acquisition module is used to acquire multi-source real-time data in water conservancy projects, perform data preprocessing on the multi-source real-time data, and obtain initial multi-source real-time data; The forecasting model building module is used to extract local features from input data based on the CNN convolutional neural network, process the long-term dependencies of time series through the LSTM neural network, and use the Attention mechanism to focus on water delivery variables to obtain the CNN-LSTM-Attention demand forecasting model; The water transmission demand prediction module is used to input the initial multi-source real-time data into the CNN-LSTM-Attention demand prediction model to obtain the water transmission demand curve; The water delivery control and regulation module is used to set the objective function as minimizing energy consumption and maximizing supply-demand matching based on the water delivery demand curve through the PPO reinforcement learning algorithm. It obtains water delivery control instructions by simulating different control actions and adjusts the gate opening and the start and stop status of the pump station according to the water delivery control instructions.

[0069] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A water delivery regulation method for a water conservancy project based on artificial intelligence, characterized in that: The water transfer rate regulation method for a water conservancy project comprises the following steps: Acquiring multi-source real-time data from a water conservancy project, and performing data preprocessing on the multi-source real-time data to obtain initial multi-source real-time data; The first convolution layer based on the CNN convolutional neural network uses 64 convolution kernels to extract local features of the input multi-source time series data; the second convolution layer uses 128 convolution kernels to further extract complex local features; the third convolution layer uses 256 convolution kernels to capture local information, and the step size of the convolution layer is set to 1, and the filling method is the same; the first LSTM layer of the LSTM neural network receives the local feature data output by the CNN convolutional neural network and converts it into a time series data format; the second LSTM layer is used to further process the output of the first LSTM layer to enhance the model's capture of long-term dependencies in the time series. The dropout rate of the LSTM layer is set to 0.2, and the return sequence is set to True. The hidden state output by the LSTM neural network is used as the query, key, and value. The attention score is obtained by calculating the dot product of the query and the key and dividing it by the scaling factor. The attention score is normalized using the Softmax function to obtain the attention weight of each input element. Finally, the value is weighted and summed according to the attention weight. The importance between water supply demand and each input variable is automatically learned through the attention mechanism, resulting in a CNN-LSTM-Attention demand prediction model. Inputting the initial multi-source real-time data into the CNN-LSTM-Attention demand forecasting model for prediction to obtain a water delivery demand curve; According to the water delivery demand curve, the objective function is set to minimize energy consumption and maximize supply-demand matching through the PPO reinforcement learning algorithm. By simulating different control actions, water delivery control instructions are obtained, and the gate opening and the start and stop status of the pump station are adjusted according to the water delivery control instructions.

2. The artificial intelligence-based water supply regulation method for a water conservancy project according to claim 1, characterized in that: The step of acquiring multi-source real-time data from a water conservancy project and performing data preprocessing on the multi-source real-time data to obtain initial multi-source real-time data includes: Obtain multi-source real-time data on water conservancy projects, including at least rainfall, evaporation, reservoir water levels, water pipeline pressure, and downstream water demand; Combining the Z-score method and the IQR method to perform outlier detection on the multi-source real-time data, and using a linear interpolation method to fill in missing values, to obtain first multi-source real-time data; Mapping the first multi-source real-time data to the interval [0, 1] using a Min-Max normalization method, and uniformly converting the collected data in different formats into numerical data to obtain second multi-source real-time data; The second multi-source real-time data is time-synchronized based on the time of the data center server, and the data is spatially aligned based on the geographic information of the water conservancy project and the location coordinates of each monitoring point to obtain the initial multi-source real-time data.

3. The method for regulating water delivery of a water conservancy project based on artificial intelligence according to claim 1, characterized in that: According to the water delivery demand curve, the objective function is set to minimize energy consumption and maximize supply-demand matching through the PPO reinforcement learning algorithm, and the water delivery control instructions are obtained by simulating different control actions, including: Define the state space and state space, and establish the state transfer equation according to the physical model of the water conservancy project and the dynamic characteristics of the water delivery system; Design an objective function that gives positive rewards when energy consumption decreases and the supply-demand match improves; and gives negative rewards when energy consumption increases or the supply-demand match decreases.

4. The artificial intelligence-based water supply regulation method for a water conservancy project according to claim 3, characterized in that: The objective function is set to minimize energy consumption and maximize supply-demand matching through the PPO reinforcement learning algorithm according to the water delivery demand curve, and water delivery control instructions are obtained by simulating different control actions, further comprising: The PPO reinforcement learning algorithm is used to simulate different control actions in the state space, and the reward value of each action is calculated based on the state transition equation and reward function; The control action that minimizes the objective function is selected as the optimal water delivery control instruction.

5. A water delivery regulation system for water conservancy projects based on artificial intelligence, characterized in that: The water delivery regulation system of the water conservancy project includes the following modules: A real-time data acquisition module is used to acquire multi-source real-time data in a water conservancy project, and perform data preprocessing on the multi-source real-time data to obtain initial multi-source real-time data; The prediction model establishment module is used to extract local features of the input multi-source time series data using 64 convolution kernels in the first convolution layer of the CNN convolutional neural network; the second convolution layer uses 128 convolution kernels to further extract complex local features; the third convolution layer uses 256 convolution kernels to capture local information, and the step size of the convolution layer is set to 1, and the padding method is the same; the first LSTM layer of the LSTM neural network receives the local feature data output by the CNN convolutional neural network and converts it into a time series data format; the second LSTM layer is used to further process the output of the first LSTM layer to enhance the model's ability to capture long-term dependencies in time series. The dropout rate of the LSTM layer is set to 0.2, and the return sequence is set to True; the hidden state output by the LSTM neural network is used as the query, key, and value, and the attention score is obtained by calculating the dot product of the query and the key and dividing it by the scaling factor; The attention scores are normalized using the Softmax function to obtain the attention weights of each input element. Finally, the values ​​are weighted and summed according to the attention weights. The Attention mechanism automatically learns the importance between water supply demand and each input variable, resulting in a CNN-LSTM-Attention demand prediction model. A water transmission demand prediction module is used to input the initial multi-source real-time data into the CNN-LSTM-Attention demand prediction model to perform prediction and obtain a water transmission demand curve; The water delivery control and adjustment module is used to set the objective function as minimizing energy consumption and maximizing supply-demand matching according to the water delivery demand curve through the PPO reinforcement learning algorithm, obtain water delivery control instructions by simulating different control actions, and adjust the gate opening and the start and stop status of the pump station according to the water delivery control instructions.

6. The artificial intelligence-based water conservancy project water delivery regulation system according to claim 5, characterized in that: The water delivery control and regulation module includes the following submodules: Definition submodule, used to define the state space and state space, and establish the state transfer equation according to the physical model of the water conservancy project and the dynamic characteristics of the water delivery system; The judgment submodule is used to design the objective function and provide positive rewards when energy consumption is reduced and the supply-demand matching is improved; Negative rewards are given when energy consumption increases or the matching between supply and demand decreases.

7. The artificial intelligence-based water conservancy project water delivery regulation system according to claim 5, characterized in that: The water delivery control and regulation module includes the following submodules: The simulation submodule is used to simulate different control actions in the state space through the PPO reinforcement learning algorithm and calculate the reward value of each action according to the state transition equation and reward function; The selection submodule is used to select the control action that minimizes the objective function as the optimal water delivery control instruction.

Images