Hydrogen production control method, system and equipment based on predicted power and storage medium

Abstract

The invention relates to a hydrogen production control method, system and equipment based on predicted power and a storage medium, and the method comprises the steps: simulating the surrounding environment of an offshore wind turbine through employing obtained surrounding meteorological data, and obtaining predicted surrounding meteorological data; determining the wind power output prediction power of the offshore wind turbine by using a known wind turbine performance curve; extracting a feature vector of the wind power output power value; obtaining hydrogen production power of a hydrogen production device in a preset time period, arranging the hydrogen production power into a hydrogen production power input vector according to a time dimension, and extracting a feature vector of the hydrogen production power; calculating a differential feature vector between the feature vector of the wind power output power value and the feature vector of the hydrogen production power; inputting the differential feature vector into a classifier, and controlling a hydrogen production device according to a classification result; accurate prediction and efficient control of the offshore wind turbine hydrogen production device can be achieved, the response speed and flexibility of the system are improved, and meanwhile the stability and efficiency of the hydrogen production process are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power hydrogen production, and in particular to a hydrogen production control method, system, equipment and storage medium based on predicted power. Background Art

[0002] As a clean and sustainable form of energy, offshore wind power has received extensive attention and application in recent years. The offshore wind power hydrogen production system is a new energy system that integrates wind energy conversion, power storage and hydrogen production. It uses the electricity generated by offshore wind power to electrolyze water to produce hydrogen, thereby realizing energy storage and conversion, and providing a sustainable solution for future energy needs. However, the existing operation scheme for offshore wind power hydrogen production system lacks effective measures to deal with complex situations, thereby reducing the stability of hydrogen production.

[0003] For example, the "Wind power hydrogen production control method and system based on real-time meteorological data" disclosed in patent announcement number CN114204602B determines the instantaneous power forecast value of the wind farm based on real-time meteorological data; performs a difference operation on the instantaneous power forecast value of the wind farm and the instantaneous demand power forecast value of the power grid to form a difference prediction curve; obtains the average power difference within the set time range based on the difference prediction curve within the set time range; and adjusts the operation of the energy storage device and the hydrogen production device under different conditions based on the average power difference.

[0004] For example, the patent publication number CN113516274A discloses a “hydrogen energy system and its balance control method”, which determines and obtains a supply and demand balance strategy based on the predicted power supply of new energy and the predicted hydrogen demand, which can maximize the utilization rate of new energy, minimize the power consumption of the power grid and ensure that the hydrogen production meets the hydrogen demand; and controls the corresponding subsystems in the hydrogen energy system to operate according to the determined strategy to achieve hydrogen production.

[0005] Although existing methods can effectively evaluate the feasibility of hydrogen production in offshore wind farms, the operation scheme of the offshore wind power hydrogen production system has large deviations, resulting in the hydrogen production device being unable to maintain the optimal working state. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a hydrogen production control method, system, device and storage medium based on predicted power to solve the above problems.

[0007] The present invention provides the following technical solutions:

[0008] The hydrogen production control method based on predicted power includes the following steps:

[0009] S1. Obtaining the surrounding meteorological data D(T) of the offshore wind turbine within a predetermined time period;

[0010] S2. Using the acquired surrounding meteorological data D(T), an atmosphere-ocean coupling model is constructed to simulate the surrounding environment of offshore wind turbines and obtain the predicted surrounding meteorological data D(T future );

[0011] S3, according to the measured surrounding meteorological data D(T future ), using the known wind turbine performance curve to determine the predicted output power of offshore wind turbines P = f[D(T future )] = [x1, x2, ..., x t ], where x t represents the wind power output value at time point t;

[0012] S4. Extract the characteristic vector of wind power output value A=[a1,a2,...a t ];

[0013] S5, obtaining the hydrogen production power of the hydrogen production device within a predetermined time period, and arranging it into a hydrogen production power input vector according to the time dimension, and extracting the characteristic vector B of the hydrogen production power = [b1, b2, ...b t ];

[0014] S6. Calculate the difference eigenvector C between the eigenvector A of the wind power output value and the eigenvector B of the hydrogen production power = [c1, c2, ..., c t ];

[0015] S7, input the differential feature vector C to the classifier, the classifier contains a matrix M = [m1, m2, ..., m j ], each column vector m j A characteristic vector representing a control method is used, and the similarity is calculated using the differential characteristic vector C and each column vector in the matrix M. The one with the highest similarity is the classification result, and the hydrogen production device is controlled according to the classification result;

[0016] S8. If the input power is large, the hydrogen production device reaches the rated hydrogen production power, and the excess wind power is input into the energy storage device; if the input power is small, the energy storage device is started to control the hydrogen production device to reach the rated hydrogen production power, thereby reducing the impact of the fluctuation of wind power input power of offshore wind turbines on the hydrogen production device.

[0017] Preferably, the surrounding meteorological data D(T) includes sea waves, temperature, humidity and wind speed;

[0018] In S2, historical surrounding meteorological data from sensors and observation stations are obtained and preprocessed to ensure data quality and consistency;

[0019] The historical surrounding meteorological data set is divided into training set, validation set and test set, and input into the machine learning model for training. The model parameters are optimized through repeated iterations to minimize the prediction error.

[0020] The trained model is applied to the prediction of meteorological data around offshore wind turbines to generate predicted surrounding meteorological data D(T future ), and update and optimize the model based on these data and future surrounding meteorological data.

[0021] Preferably, in S3, a machine learning algorithm is introduced to dynamically adjust performance parameters to regularly update the performance curve of the offshore wind turbine to reflect changes in actual operating conditions.

[0022] Preferably, in S4, the wind power output prediction power P is converted into the wind power output prediction power P by using the formula To obtain the characteristic vector A of wind power output power value;

[0023] Determine the convolution kernel size, select an appropriate convolution kernel size K, and initialize a set of weights W = [W0, W1, ..., W k-1 ] and a bias term b, where the weight W and the bias term b are automatically adjusted through the back-propagation algorithm during training;

[0024] Apply convolution operation to predict the output power of offshore wind turbines P = [x1, x2, ..., x t ], for each position i, by the formula Calculate the convolution result at this position;

[0025] Among them, K is the convolution kernel length, b is a bias term, and a i is the output eigenvalue at position i;

[0026] Repeat the above process until all possible positions i are covered, and finally get [a1,a2,...a t ] constitutes the characteristic vector A of the wind power output power value.

[0027] Preferably, in S5, the hydrogen production power input vector is first input into a convolutional neural network based on an attention mechanism, and then input into a convolutional neural network based on a time mechanism, so as to obtain a characteristic vector B of the hydrogen production characteristic power = [b1, b2, ... b t ].

[0028] Preferably, using the formula Calculate the differential eigenvector C;

[0029] Among them, μ A , μ Bare the average values ​​of the characteristic vector A of wind power output value and the characteristic vector B of hydrogen production characteristic power, are the variances of the eigenvector A of the wind power output power value and the eigenvector B of the hydrogen production characteristic power, respectively. α and β are weighting factors.

[0030] Preferably, in S8, assuming that the predicted output power P of the offshore wind turbine is greater than the rated power of the hydrogen production device, the classification result of the classifier is enabled, the hydrogen production device is controlled to reach the rated hydrogen production power and the charging module of the energy storage device is started to store the excess electric energy in the energy storage device;

[0031] Assuming that the predicted wind power output power P of the offshore wind turbine is less than the minimum power required by the hydrogen production device, the classification result of the classifier is enabled, and the discharge module of the energy storage device is started to control the power of the hydrogen production device in combination with the wind power input power to be within the range of the minimum hydrogen production power and the rated power.

[0032] A hydrogen production control system based on predicted power, used to implement the hydrogen production control method based on predicted power, comprises:

[0033] A data acquisition module, used to obtain the surrounding meteorological data D(T) of the offshore wind turbine within a predetermined time period;

[0034] The environmental simulation module uses the acquired surrounding meteorological data D(T) to build an atmosphere-ocean coupling model and simulate the surrounding environment to obtain the surrounding meteorological data D(T) predicted in the future. future );

[0035] The power prediction module is used to predict the surrounding meteorological data D(T future ), using the wind turbine performance curve to predict the offshore wind turbine wind power output predicted power P;

[0036] A feature extraction module, for extracting a feature vector A from the predicted wind power output P of the offshore wind turbine using a temporal encoder of a one-dimensional convolutional layer;

[0037] A hydrogen production data processing module is used to collect and pre-process the hydrogen production power data of the hydrogen production device within a predetermined time period, and convert it into a hydrogen production power input vector, and then use a multi-scale convolution encoder to extract a feature vector B of the hydrogen production characteristic power from the hydrogen production power input vector;

[0038] A feature comparison module is used to perform multi-eigenvalue weighted difference on the feature vector A extracted from the predicted output power P of offshore wind turbine wind power and the feature vector B of hydrogen production feature power to obtain a differential feature vector C;

[0039] The intelligent control module is used to input the differential feature vector C into the classifier to obtain a classification result, and the result is used to guide the hydrogen production efficiency control strategy of the hydrogen production device.

[0040] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for controlling hydrogen production based on predicted power as described above is implemented.

[0041] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the hydrogen production control method based on predicted power as described above.

[0042] The present invention has the following beneficial technical effects:

[0043] The present invention simulates the environment around offshore wind turbines by constructing an atmosphere-ocean coupling model, and can more accurately predict the performance and output power of offshore wind turbines;

[0044] Using known wind turbine performance curves to determine the predicted wind power output of offshore wind turbines can reduce uncertainty and errors and improve the accuracy of predictions;

[0045] Converting time series data into feature vectors can effectively capture and analyze patterns and trends in time series data, thereby improving the prediction accuracy of future hydrogen production power;

[0046] By calculating the differential eigenvector between the eigenvector of the output predicted power and the eigenvector of the hydrogen production power, the deviation between the input power demand and the actual power output of the hydrogen production device can be evaluated and identified; at the same time, the optimal control strategy can be quickly determined by using the differential eigenvector and the eigenvector matrix in the classifier for similarity calculation. This method not only improves the efficiency of control, but also can dynamically adjust the operating status of the hydrogen production device according to different meteorological conditions and wind power output volatility.

[0047] The present invention can achieve accurate prediction and efficient control of offshore wind turbine hydrogen production devices, improve the response speed and flexibility of the system, and ensure the stability and efficiency of the hydrogen production process. DETAILED DESCRIPTION

[0048] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0049] Example:

[0050] Hydrogen production control method and system based on predicted power:

[0051] S1. Obtaining the surrounding meteorological data D(T) of the offshore wind turbine within a predetermined time period, wherein the surrounding meteorological data D(T) mainly includes all factors that may affect the performance of the wind turbine, such as sea waves, temperature, humidity and wind speed;

[0052] S2. Using the acquired surrounding meteorological data D(T), an atmosphere-ocean coupling model is constructed to simulate the surrounding environment of offshore wind turbines and obtain the predicted surrounding meteorological data D(T future );

[0053] Obtain historical surrounding meteorological data from sensors and observation stations, and pre-process the data to ensure data quality and consistency;

[0054] The historical surrounding meteorological data set is divided into training set, validation set and test set, and input into a suitable physical or machine learning model for training. The model parameters are optimized through repeated iterations to minimize the prediction error.

[0055] The trained model is applied to the prediction of meteorological data around offshore wind turbines to generate predicted surrounding meteorological data, and the model is updated and optimized based on these data and future surrounding meteorological data.

[0056] S3, according to the predicted surrounding meteorological data D(T future ), using the known wind turbine performance curve to determine the predicted output power of offshore wind turbines P = f[D(T future )] = [x1, x2, ..., x t ], where x t represents the wind power output value at time point t;

[0057] By introducing machine learning algorithms to dynamically adjust performance parameters, the fan performance curve is regularly updated to reflect changes in actual operating conditions.

[0058] S4, the wind power output value is passed through the temporal encoder of the one-dimensional convolutional layer using the formula To obtain the characteristic vector of wind power output value A=[a1,a2,...a t ]; the details are as follows:

[0059] Determine the convolution kernel size, select an appropriate convolution kernel size K, and initialize a set of weights W = [W0, W1, ..., W k-1 ] and a bias term b, where the weight W and the bias term b are automatically adjusted through the back-propagation algorithm during training;

[0060] Apply the convolution operation to the input prediction power sequence P = [x1, x2, ..., x t ], for each position i, by the formula Calculate the convolution result at this position;

[0061] Among them, K is the convolution kernel length, b is a bias term, and a i is the output eigenvalue at position i;

[0062] Repeat the above process until all possible positions i are covered, and finally get [a1, a2, ...a t ] constitutes the feature vector A of the output prediction power;

[0063] In addition to the above process, in some cases, in order to reduce the dimension of the feature vector or capture higher-level features, a pooling operation (such as maximum pooling or average pooling) can be further applied to obtain the feature vector.

[0064] S5, obtaining the hydrogen production power of the hydrogen production device at multiple time points within a predetermined time period, and preprocessing the collected data;

[0065] S6. Arrange the hydrogen production power of the hydrogen production device within a predetermined time period into a hydrogen production power input vector according to the time dimension.

[0066] S7, the hydrogen production power input vector is first input into the convolutional neural network based on the attention mechanism, and then input into the convolutional neural network based on the time mechanism, so as to obtain the characteristic vector B=[b1, b2, ...b t ];

[0067] Arranging the hydrogen production efficiencies of the hydrogen production device at multiple time points within the preset time period according to the time dimension as a hydrogen production power input vector;

[0068] A sequence encoder based on a trained network model (Clip model may be used) performs multi-scale convolution encoding on the hydrogen production power input vector to obtain a feature vector B of the hydrogen production power.

[0069] S8. Using formula Calculate the difference between the eigenvector A of the wind power output value and the eigenvector B of the hydrogen production power: C = [c1, c2, ..., c t ];

[0070] Among them, μ A , μ B are the average values ​​of the characteristic vector A of wind power output value and the characteristic vector B of hydrogen production power, are the variances of the eigenvector A of the wind power output value and the eigenvector B of the hydrogen production power, respectively. α and β are weighting factors.

[0071] Calculate the average values ​​μ of the predicted power eigenvector A and the hydrogen production power eigenvector BA , μ B and variance

[0072] Set the weight parameters α and β according to experience and specific problems;

[0073] Based on the formula Calculate the element c in the differential eigenvector C at each time point i i ;

[0074] The c calculated at each time point i i The values ​​are combined into a vector C, namely the differential eigenvector C = [c1, c2, ..., c t ].

[0075] S9. Input the differential feature vector C into the classifier, which contains a matrix M = [m1, m2, ..., m j ], each column vector m j The characteristic vector representing a control method is used to calculate the similarity between the differential characteristic vector C and each column vector in the matrix M. The one with the highest similarity is the classification result. The classification result is used to control the control strategy of the hydrogen production device, thereby controlling the hydrogen production efficiency.

[0076] S10. If the input power is large, the hydrogen production device reaches the rated hydrogen production power, and the excess wind power is input to the energy storage device. If the input power is small, the energy storage device is started to control the hydrogen production device to reach the rated hydrogen production power, thereby reducing the impact of the volatility of wind power input power on the hydrogen production device.

[0077] Assuming that the predicted wind power input power is greater than the rated power of the hydrogen production device, the classification result of the classifier is enabled, the hydrogen production device is controlled to reach the rated hydrogen production power and the charging module of the energy storage device is started to store the excess electric energy in the energy storage device;

[0078] Assuming that the predicted wind power input power is less than the minimum power required by the hydrogen production device, the classification result of the classifier is enabled, and the discharge module of the energy storage device is started to control the power of the hydrogen production device within the range of the minimum hydrogen production power and the rated power in combination with the wind power input power.

[0079] An intelligent control system for a hydrogen production device based on predicted power of an offshore wind turbine, comprising:

[0080] The data acquisition module is used to obtain the surrounding meteorological data D(T) of the offshore wind turbine within a predetermined time period, which mainly includes all factors that may affect the performance of the wind turbine, such as waves, temperature, humidity and wind speed;

[0081] The environmental simulation module is used to construct an atmosphere-ocean coupling model using the surrounding meteorological data D(T) of the offshore wind turbines and simulate the surrounding environment to obtain the surrounding meteorological data D(T) predicted in the future. future );

[0082] Power prediction module, used to obtain the surrounding meteorological data D(T future ), using the wind turbine performance curve to predict the offshore wind turbine wind power output predicted power P;

[0083] A feature extraction module, for extracting a feature vector A from the predicted wind power output P of the offshore wind turbine using a temporal encoder of a one-dimensional convolutional layer;

[0084] A hydrogen production data processing module is used to collect and pre-process the hydrogen production power data of the hydrogen production device within a predetermined time period, and convert it into a hydrogen production power input vector, and then use a multi-scale convolution encoder to extract a feature vector B of the hydrogen production characteristic power from the hydrogen production power input vector;

[0085] A feature comparison module is used to perform multi-eigenvalue weighted difference on the feature vector A extracted from the predicted output power P of offshore wind turbine wind power and the feature vector B of hydrogen production feature power to obtain a differential feature vector C;

[0086] The intelligent control module is used to input the differential feature vector C into the classifier to obtain a classification result, which is used to guide the hydrogen production efficiency control strategy of the hydrogen production device; when the input power exceeds the rated power of the hydrogen production device, the excess energy is stored; when the input power is insufficient, energy is supplemented from the energy storage device to maintain the stable operation of the hydrogen production device.

[0087] The above-mentioned embodiments only express the specific implementation of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A hydrogen production control method based on predicted power, characterized in that: The following steps are involved: S1. Obtaining the surrounding meteorological data D(T) of the offshore wind turbine within a predetermined time period; S2. Using the acquired surrounding meteorological data D(T), an atmosphere-ocean coupling model is constructed to simulate the surrounding environment of offshore wind turbines and obtain the predicted surrounding meteorological data D(T future ); S3, according to the measured surrounding meteorological data D(T future ), using the known wind turbine performance curve to determine the predicted output power of offshore wind turbines P = f[D(T future )] = [x1, x2, ..., x t ], where x t represents the wind power output value at time point t; S4. Extract the characteristic vector of wind power output value A=[a1,a2,...a t ]; S5, obtaining the hydrogen production power of the hydrogen production device within a predetermined time period, and arranging it into a hydrogen production power input vector according to the time dimension, and extracting the characteristic vector B of the hydrogen production power = [b1, b2, ...b t ]; S6. Calculate the difference eigenvector C between the eigenvector A of the wind power output value and the eigenvector B of the hydrogen production power = [c1, c2, ..., c t ]; S7, input the differential feature vector C to the classifier, the classifier contains a matrix M = [m1, m2, ..., m j ], each column vector m j A characteristic vector representing a control method is used, and the similarity is calculated using the differential characteristic vector C and each column vector in the matrix M. The one with the highest similarity is the classification result, and the hydrogen production device is controlled according to the classification result; S8. If the input power is large, the hydrogen production device reaches the rated hydrogen production power, and the excess wind power is input into the energy storage device; if the input power is small, the energy storage device is started to control the hydrogen production device to reach the rated hydrogen production power, thereby reducing the impact of the fluctuation of wind power input power of offshore wind turbines on the hydrogen production device.

2. The hydrogen production control method based on predicted power according to claim 1, characterized in that: The surrounding meteorological data D(T) include sea waves, temperature, humidity and wind speed; In S2, historical surrounding meteorological data from sensors and observation stations are obtained and preprocessed to ensure data quality and consistency; The historical surrounding meteorological data set is divided into training set, validation set and test set, and input into the machine learning model for training. The model parameters are optimized through repeated iterations to minimize the prediction error. The trained model is applied to the prediction of meteorological data around offshore wind turbines to generate predicted surrounding meteorological data D(T future ), and update and optimize the model based on these data and future surrounding meteorological data.

3. The hydrogen production control method based on predicted power according to claim 1, characterized in that: In S3, a machine learning algorithm is introduced to dynamically adjust performance parameters and regularly update the performance curve of offshore wind turbines to reflect changes in actual operating conditions.

4. The hydrogen production control method based on predicted power according to claim 1, characterized in that: In S4, the wind power output prediction power P is passed through the temporal encoder of the one-dimensional convolutional layer using the formula To obtain the characteristic vector A of wind power output power value; Determine the convolution kernel size, select an appropriate convolution kernel size K, and initialize a set of weights W = [W0, W1, ..., W k-1 ] and a bias term b, where the weight W and the bias term b are automatically adjusted through the back-propagation algorithm during training; Apply convolution operation to the predicted output power of offshore wind turbines P = [x1, x2, ..., x t ], for each position i, by the formula Calculate the convolution result at this position; Among them, K is the convolution kernel length, b is a bias term, and a i is the output eigenvalue at position i; Repeat the above process until all possible positions i are covered, and finally get [a1, a2, ...a t ] constitutes the characteristic vector A of the wind power output power value.

5. The hydrogen production control method based on predicted power according to claim 4, characterized in that: In S5, the hydrogen production power input vector is first input into a convolutional neural network based on an attention mechanism, and then input into a convolutional neural network based on a time mechanism, so as to obtain a feature vector B = [b1, b2, ...b t ].

6. The hydrogen production control method based on predicted power according to claim 5, characterized in that: Using the formula Calculate the differential eigenvector C; Among them, μ A , μ B are the average values ​​of the characteristic vector A of wind power output power and the characteristic vector B of hydrogen production power, are the variances of the eigenvector A of the wind power output power value and the eigenvector B of the hydrogen production characteristic power, respectively. α and β are weighting factors.

7. The hydrogen production control method based on predicted power according to claim 1, characterized in that: In S8, assuming that the predicted output power P of the offshore wind turbine is greater than the rated power of the hydrogen production device, the classification result of the classifier is enabled, the hydrogen production device is controlled to reach the rated hydrogen production power and the charging module of the energy storage device is started to store the excess electric energy in the energy storage device; Assuming that the predicted wind power output power P of the offshore wind turbine is less than the minimum power required by the hydrogen production device, the classification result of the classifier is enabled, and the discharge module of the energy storage device is started to control the power of the hydrogen production device in combination with the wind power input power to be within the range of the minimum hydrogen production power and the rated power.

8. A hydrogen production control system based on predicted power, used to implement the hydrogen production control method based on predicted power according to any one of claims 1 to 7, characterized in that: include: A data acquisition module, used to obtain the surrounding meteorological data D(T) of the offshore wind turbine within a predetermined time period; The environmental simulation module uses the acquired surrounding meteorological data D(T) to build an atmosphere-ocean coupling model and simulate the surrounding environment to obtain the surrounding meteorological data D(T) predicted in the future. future ); The power prediction module is used to predict the surrounding meteorological data D(T future ), using the wind turbine performance curve to predict the offshore wind turbine wind power output predicted power P; A feature extraction module, for extracting a feature vector A from the predicted wind power output P of the offshore wind turbine using a temporal encoder of a one-dimensional convolutional layer; A hydrogen production data processing module is used to collect and pre-process the hydrogen production power data of the hydrogen production device within a predetermined time period, and convert it into a hydrogen production power input vector, and then use a multi-scale convolution encoder to extract a feature vector B of the hydrogen production characteristic power from the hydrogen production power input vector; A feature comparison module is used to perform multi-eigenvalue weighted difference on the feature vector A extracted from the predicted output power P of offshore wind turbine wind power and the feature vector B of hydrogen production feature power to obtain a differential feature vector C; The intelligent control module is used to input the differential feature vector C into the classifier to obtain a classification result, and the result is used to guide the hydrogen production efficiency control strategy of the hydrogen production device.

9. An electronic 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 program, the hydrogen production control method based on predicted power as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the hydrogen production control method based on predicted power as described in any one of claims 1 to 7 is implemented.

Images