Off-grid energy-storage-free PEM hydrogen production control method, device and equipment

Abstract

The invention provides an off-grid energy-storage-free PEM hydrogen production control method, device and equipment, and relates to the technical field of new energy hydrogen production and intelligent scheduling, and the method comprises the steps: obtaining current operation parameters of a photovoltaic array in a current time period, space correlation environment parameters and meteorological data of an area where the photovoltaic array is located, the current hydrogen production state and the power tracking deviation of the PEM hydrogen production tank are determined; performing feature extraction on the current operation parameters, the spatial correlation environment parameters and the meteorological data to obtain photovoltaic output spatial-temporal features; inputting the photovoltaic output spatial-temporal characteristics into a pre-trained photovoltaic power prediction model to obtain a power prediction sequence of the photovoltaic array in a future preset time period; and based on the power prediction sequence, the current hydrogen production state and the power tracking deviation, determining a target hydrogen production control parameter of the off-grid energy-storage-free PEM hydrogen production system in a future preset time period. According to the invention, adaptive adjustment of the hydrogen production control parameters of the off-grid energy-storage-free PEM hydrogen production system is realized.

Description

Technical Field

[0001] This application relates to the field of new energy hydrogen production and intelligent dispatch technology, specifically to an off-grid, energy storage-free PEM hydrogen production control method, device and equipment. Background Technology

[0002] With the advancement of the "dual carbon" goal, hydrogen energy, as a clean and efficient secondary energy carrier, has attracted much attention for its green production technology. Utilizing renewable energy sources such as solar photovoltaic to drive PEM electrolysis of water to produce hydrogen is an important path to achieve "green hydrogen" production. However, photovoltaic power output has significant intermittency, volatility, and unpredictability, especially in off-grid scenarios without energy storage, where hydrogen production systems directly face the challenge of drastic power fluctuations.

[0003] In existing technologies, most PEM hydrogen production systems adopt constant power or simple proportional control strategies, which are difficult to adapt to rapid changes in photovoltaic power. This not only leads to low energy utilization, poor system stability, and insufficient control precision, but also relies solely on real-time feedback adjustment, resulting in a delayed response and an inability to anticipate power change trends. Summary of the Invention

[0004] The purpose of this application is to provide an off-grid, energy storage-free PEM hydrogen production control method, apparatus, and equipment to solve the above-mentioned problems existing in the prior art, and to realize the adaptive adjustment of hydrogen production parameters of the off-grid, energy storage-free PEM hydrogen production system, thereby effectively improving the utilization efficiency of photovoltaic energy.

[0005] Firstly, an off-grid, energy storage-free PEM hydrogen production control method is provided, applied in the controller of an off-grid, energy storage-free PEM hydrogen production system, wherein the system further includes a photovoltaic array and a PEM hydrogen production cell. The method may include: The system acquires the current operating parameters, spatially related environmental parameters, and meteorological data of the photovoltaic array's location within the current time period, as well as the current hydrogen production status and power tracking deviation of the PEM hydrogen production cell. Feature extraction is performed on the current operating parameters, spatially related environmental parameters, and meteorological data to obtain the spatiotemporal characteristics of photovoltaic power output; The spatiotemporal characteristics of photovoltaic output are input into a pre-trained photovoltaic power prediction model to obtain the power prediction sequence of the photovoltaic array in a future preset time period; Based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation, the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system are determined for a future preset time period.

[0006] In an optional implementation, the photovoltaic power prediction model includes: The input layer is used to input the spatiotemporal characteristics of photovoltaic power output; The first LSTM layer is used to extract features and encode the temporal dimension of photovoltaic power output to obtain short-term temporal feature encoding. The second LSTM layer is used to perform deep temporal feature extraction on the short-term temporal feature encoding and fuse long-short-term information to obtain long-short-term fused feature encoding. The attention mechanism layer is used to perform attention weighting on the long-short fusion feature encoding to obtain a weighted feature vector; A fully connected layer is used to perform a nonlinear transformation on the weighted feature vector to obtain a power prediction sequence of the photovoltaic array in the future preset time period; The output layer is used to output the power prediction sequence of the photovoltaic array for a future preset time period.

[0007] In an optional implementation, based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation, target hydrogen production control parameters for the off-grid, storage-free PEM hydrogen production system are determined for a future preset time period, including: The power prediction sequence, the current hydrogen production status, and the power tracking deviation are input into a pre-trained hydrogen production control network to obtain the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system over a future preset time period.

[0008] In an optional implementation, the hydrogen production control network includes a feedforward control module and a feedback control module; The feedforward control module is used to convert the power prediction sequence into initial hydrogen production control parameters based on the dynamic characteristic model of the configured PEM hydrogen production cell; and to smooth the initial hydrogen production control parameters to obtain the initial hydrogen production control parameters. The feedback control module is used to generate a deviation correction amount based on the configured constraints of the PEM hydrogen production cell, the power prediction sequence, the current hydrogen production status, the initial hydrogen production control parameters, and the power tracking deviation; and to adjust the initial hydrogen production control parameters based on the deviation correction amount to obtain the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system in the future for a preset time period.

[0009] In an optional implementation, a deviation correction is generated based on the configured constraints of the PEM hydrogen production cell, the power prediction sequence, the current hydrogen production state, the initial hydrogen production control parameters, and the power tracking deviation, including: Using the power prediction sequence as a reference trajectory, the current hydrogen production state as the initial state, the power tracking deviation as the feedback input, and the constraints as constraints of a pre-set objective function, the objective function is solved using a rolling optimization method to obtain the optimal control sequence; the first term of the optimal control sequence is used as the deviation correction amount.

[0010] In an optional implementation, both the initial hydrogen production control parameters and the target hydrogen production control parameters include: hydrogen production power; The current hydrogen production status includes: the current hydrogen production capacity.

[0011] In an optional implementation, the power tracking deviation of the PEM hydrogen production cell is the difference between the initial hydrogen production power of the PEM hydrogen production cell in the previous time period and the current hydrogen production power of the PEM hydrogen production cell in the current time period. After determining the target hydrogen production control parameters for the off-grid, storage-free PEM hydrogen production system over a predetermined time period, the method further includes: The power tracking deviation of the PEM hydrogen production tank in the future preset time period is calculated based on the difference between the initial hydrogen production power of the PEM hydrogen production tank in the current time period and the current hydrogen production power of the PEM hydrogen production tank in the future preset time period.

[0012] Secondly, an off-grid, energy storage-free PEM hydrogen production control device is provided, which is applied in the controller of an off-grid, energy storage-free PEM hydrogen production system. The system further includes a photovoltaic array and a PEM hydrogen production tank. The device may include: The acquisition unit is used to acquire the current operating parameters of the photovoltaic array, spatially related environmental parameters, and meteorological data of the area where the photovoltaic array is located within the current time period, as well as the current hydrogen production status and power tracking deviation of the PEM hydrogen production cell. The feature extraction unit is used to extract features from the current operating parameters, spatially related environmental parameters, and meteorological data to obtain the spatiotemporal features of photovoltaic power output. The prediction unit is used to input the spatiotemporal characteristics of the photovoltaic output into a pre-trained photovoltaic power prediction model to obtain the power prediction sequence of the photovoltaic array in a future preset time period; The determining unit is used to determine the target hydrogen production control parameters of the off-grid, energy storage-free PEM hydrogen production system for a future preset time period based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation.

[0013] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0014] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0015] This application integrates current photovoltaic operating parameters, spatially related environmental parameters, and regional meteorological data. After feature extraction, it uses a pre-trained prediction model to accurately output future power sequences. Then, by combining the current state of the PEM hydrogen production cell with the power tracking deviation, it optimizes the target control parameters, realizing the adaptive adjustment of hydrogen production parameters in the off-grid, energy storage-free PEM hydrogen production system. This effectively improves the utilization efficiency of photovoltaic energy, avoids the mismatch problem in hydrogen production system operation caused by photovoltaic power output fluctuations, and ensures the stable operation of the PEM hydrogen production cell in the future within a preset time period, providing reliable support for the efficient production of green hydrogen in off-grid, energy storage-free scenarios. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 An off-grid, energy storage-free PEM hydrogen production system is provided as an embodiment of this application; Figure 2 A schematic flowchart of an off-grid, energy storage-free PEM hydrogen production control method provided in an embodiment of this application; Figure 3 A comparison chart of hydrogen production DC power and photovoltaic active power when the hydrogen production current is adjusted to 3750A is provided for an embodiment of this application; Figure 4 A comparison chart of hydrogen production DC power and photovoltaic active power when the hydrogen production current is adjusted to 4000A is provided for an embodiment of this application; Figure 5 A comparison chart of the DC power of hydrogen production with the photovoltaic active power when the hydrogen production current is adjusted to 4250A is provided for an embodiment of this application. Figure 6 This application provides an embodiment of a PEM hydrogen production cell operating diagram that tracks the predicted value of optical power for hydrogen production. Figure 7 A schematic diagram of an off-grid, energy storage-free PEM hydrogen production control device provided in this application embodiment; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise defined, the technical or scientific terms used in this application should have the ordinary meaning understood by those skilled in the art. The words "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are only used to distinguish different components. The words "comprising" or "including," etc., mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, but do not exclude other elements or objects. The words "connected," "coupled," or "connected," etc., are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up," "down," "left," "right," etc., are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] The off-grid, energy storage-free PEM hydrogen production control method provided in this application embodiment can be applied to... Figure 1 In the system architecture shown, such as Figure 1 As shown, the off-grid, energy storage-free PEM hydrogen production system may include: a controller, a photovoltaic array, and a PEM hydrogen production cell; wherein, the controller is communicatively connected to both the photovoltaic array and the PEM hydrogen production cell; the controller is used to execute the off-grid, energy storage-free PEM hydrogen production control method provided in the embodiments of this application; the photovoltaic array is used to provide energy support for the PEM hydrogen production cell; and the PEM hydrogen production cell is used to electrolyze hydrogen under the energy support of the photovoltaic array.

[0020] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0021] Figure 2 This is a schematic flowchart illustrating an off-grid, energy storage-free PEM hydrogen production control method provided in an embodiment of this application. Figure 2 As shown, the method may include: Step S210: Obtain the current operating parameters of the photovoltaic array, spatially related environmental parameters, and meteorological data of the area where the photovoltaic array is located within the current time period, as well as the current hydrogen production status and power tracking deviation of the PEM hydrogen production cell.

[0022] The current operating parameters of the photovoltaic array in the current time period may include: real-time output active power, illuminance at the photovoltaic panel, DC voltage, and DC current; the meteorological data of the area where the photovoltaic array is located may include: current meteorological data and meteorological forecast data for the next preset time period; both current meteorological data and meteorological forecast data may include: ambient temperature, relative humidity, wind speed, cloud cover, and satellite cloud image data; satellite cloud image data may include cloud cover images and cloud movement trajectories in the target area where the photovoltaic array is located; spatially related environmental parameters may include: associated photovoltaic output data of multiple neighboring photovoltaic sites in the surrounding area of ​​the photovoltaic array; the current hydrogen production status may include: operating current, operating time, tank temperature, tank pressure, electrolysis voltage, actual hydrogen production power, and hydrogen production; meteorological data may be replaced with satellite remote sensing data or distributed photovoltaic cluster power data; the power tracking deviation is the difference between the initial hydrogen production power of the PEM hydrogen production cell in the previous time period and the current hydrogen production power of the PEM hydrogen production cell in the current time period.

[0023] In one embodiment of this application, after acquiring the current operating parameters of the photovoltaic array, spatially related environmental parameters, meteorological data of the area where the photovoltaic array is located, and the current hydrogen production status of the PEM hydrogen production cell in the current time period, the method may further include: performing wavelet denoising, sliding window smoothing, and / or missing value imputation on the acquired data to eliminate noise and outliers.

[0024] Step S220: Extract features from the current operating parameters, spatially related environmental parameters, and meteorological data to obtain the spatiotemporal characteristics of photovoltaic power output.

[0025] In practice, a sliding window technique is used to calculate the statistical characteristics of the current operating parameters within the current time period, thereby obtaining time-series statistical characteristics. These time-series statistical characteristics may include the average power, maximum power, minimum power, power standard deviation, mean light intensity, and fluctuation range within the sliding window. The time series difference calculation method is used to analyze the changes in the current operating parameters within the current time period in adjacent time sliding windows to obtain the time series change characteristics; among which, the time series change characteristics can include instantaneous power change rate, average change rate, power fluctuation frequency, and light intensity change rate. The frequency domain components in the current operating parameters are decomposed using Fourier transform or wavelet transform methods to obtain frequency domain characteristics; the frequency domain characteristics may include the daily periodic power rise or fall rate and short-term fluctuation amplitude. The sliding window trend calculation method is used to calculate the variation pattern of meteorological data in the current time period and obtain meteorological time series characteristics. Among them, meteorological time series characteristics can include the real-time change rate of temperature, humidity or wind speed, future cumulative change, cloud cover change rate and occlusion frequency. By using the correlation coefficient calculation method, a correlation model between meteorological parameters and photovoltaic power in the area where the photovoltaic array is located is established to obtain the meteorological-power correlation characteristics. Among them, the meteorological-power correlation characteristics can include the positive correlation coefficient between power and light intensity, the negative correlation coefficient with cloud cover, and comprehensive meteorological influencing factors. CNN image segmentation and boundary recognition methods are used to identify features in satellite cloud image data to obtain cloud spatial distribution features. These features may include cloud coverage area ratio, thickness level, and distance between cloud center and photovoltaic array. The continuous frame cloud image analysis method is used to analyze satellite cloud image data to obtain the spatiotemporal linkage characteristics of clouds. Among them, the spatiotemporal linkage characteristics of clouds can include cloud movement speed, direction, and cloud coverage area prediction mask within a preset time period in the future. The spatial correlation coefficient calculation method is used to calculate the spatial correlation characteristics of the associated photovoltaic power output data. The spatial correlation characteristics may include the power output correlation coefficient and power output difference between the array and neighboring sites. The Kriging interpolation modeling method is adopted to derive the theoretical output of the photovoltaic array based on the associated photovoltaic output data, and to obtain the spatial interpolation characteristics. The spatial interpolation characteristics may include the deviation of the array's theoretical output based on the data of neighboring sites.

[0026] Step S230: Input the spatiotemporal characteristics of photovoltaic output into the pre-trained photovoltaic power prediction model to obtain the power prediction sequence of the photovoltaic array in the future preset time period.

[0027] Among them, the photovoltaic power prediction model is obtained by training the photovoltaic array using the spatiotemporal characteristics of historical photovoltaic output and the corresponding historical power in different historical time periods; Photovoltaic power prediction models may include: The input layer is used to input the spatiotemporal characteristics of photovoltaic power output; The first LSTM layer is used to capture the short-term temporal dependencies in the spatiotemporal features of photovoltaic power output through the gating mechanism of the long short-term memory network, and to encode the spatiotemporal features of photovoltaic power output in the temporal dimension to obtain the short-term temporal feature encoding. The second LSTM layer is used to perform deep temporal feature extraction on short-term temporal feature encoding based on the long short-term memory characteristics of the long short-term memory network, and to fuse long and short-term information to obtain long and short-term fused feature encoding. The attention mechanism layer is used to perform attention weighting on the long-short fusion feature encoding to obtain a weighted feature vector; The fully connected layer is used to perform nonlinear transformation on the weighted feature vector through the ReLU activation function to enhance the model's feature representation capability; and adjusts the output dimension according to the number of power prediction nodes in the future preset time period to realize the mapping from feature encoding to prediction results, so as to obtain the power prediction sequence of photovoltaic array in the future preset time period. The output layer is used to output the power prediction sequence of the photovoltaic array for a future preset time period.

[0028] Step S240: Based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation, determine the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system in the future for a preset time period.

[0029] The hydrogen production control parameters may include: hydrogen production power, operating current of the PEM hydrogen production cell, IGBT duty cycle, cell temperature, and cell pressure.

[0030] In practice, the power prediction sequence, the current hydrogen production status, and the power tracking deviation are input into a pre-trained hydrogen production control network to obtain the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system in the future for a preset time period. The hydrogen production control network includes a feedforward control module and a feedback control module. The feedforward control module is used to convert the power prediction sequence into initial hydrogen production control parameters based on the dynamic characteristic model of the configured PEM hydrogen production cell; and to smooth the initial hydrogen production control parameters using low-pass filtering and / or moving average algorithms to obtain the initial hydrogen production control parameters; wherein, the dynamic characteristic model may include: electrochemical impedance model and heat transfer model; The feedback control module is used to generate a deviation correction amount based on the configured constraints of the PEM hydrogen production cell, the power prediction sequence, the current hydrogen production status, the initial hydrogen production control parameters, and the power tracking deviation; and to adjust the initial hydrogen production control parameters based on the deviation correction amount to obtain the target hydrogen production control parameters for the off-grid PEM hydrogen production system without energy storage in the future preset time period. Specifically, using the power prediction sequence as the reference trajectory, the current hydrogen production state as the initial state, and the power tracking deviation as the feedback input, and taking the constraints as the constraints of a pre-set objective function, the objective function is solved using a rolling optimization method to obtain the optimal control sequence; the first term of the optimal control sequence is used as the deviation correction; where the objective function is... ; ; ; ; ;in, This indicates the minimum operating current value of the PEM hydrogen production cell, which is user-defined and configurable. This indicates the maximum operating current value of the PEM hydrogen production cell, which is user-defined. This represents the operating current value in the current hydrogen production state at time t; This represents the operating time in the current hydrogen production state at time t; This indicates the minimum operating time of the PEM hydrogen production tank, which is user-defined and configurable. This indicates the maximum operating time of the PEM hydrogen production tank, which is user-defined and configurable. This indicates the power change of the PEM hydrogen production cell; λ represents the range of minimum power variation in the electrolyzer; N represents the preset future time period; and λ represents the control weight. Indicates the control increment; i represents the time step; This represents the power prediction sequence at time step k+i; This represents the current hydrogen production power at time step k+i.

[0031] In one embodiment of this application, the feedback control module uses current, temperature, and pressure as state variables, and the initial hydrogen production control parameter adjustment amount or power correction amount as control variables to construct a discrete state-space model of the PEM hydrogen production cell.

[0032] In one embodiment of this application, the method may further include: calculating the power tracking deviation of the PEM hydrogen production tank in the future preset time period based on the difference between the initial hydrogen production power of the PEM hydrogen production tank in the current time period and the current hydrogen production power of the PEM hydrogen production tank in the future preset time period, so as to enable the controller to calculate the target hydrogen production control parameters for the next time period in the future preset time period.

[0033] In another embodiment of this application, the feedforward control module may employ fuzzy logic or a feedforward neural network; the feedback control module may be an adaptive PID or a sliding mode control.

[0034] In another embodiment of this application, the method may further include: performing incremental training on the hydrogen production control network and photovoltaic power prediction model on a regular basis based on machine learning technology, integrating local data and cloud-shared data, and optimizing model parameters; introducing an adaptive parameter adjustment mechanism, automatically triggering model retraining and updating the hydrogen production control network and constraint parameters when the prediction error continuously exceeds the threshold; and realizing the adaptive evolution of the control strategy to adapt to seasonal changes, equipment aging, and meteorological pattern migration.

[0035] This application achieves real-time, efficient, and stable matching of hydrogen production power to photovoltaic output, significantly improving renewable energy utilization and system operating economy. Furthermore, this application can be extended to hydrogen production scenarios driven by fluctuating energy sources such as wind power and tidal energy, demonstrating broad application prospects. This application also achieves high-precision, wide-range, and adaptive tracking of photovoltaic output, improving renewable energy utilization, ensuring stable and efficient system operation, and reducing system costs.

[0036] The technical effects of this application will be further explained below with reference to the accompanying drawings.

[0037] Figures 3 to 5 The off-grid PEM hydrogen production system using the off-grid energy storage-free PEM hydrogen production control method of this application demonstrates that the hydrogen production power can smoothly follow the changes in photovoltaic power in real time under different currents. This indicates that the off-grid energy storage-free PEM hydrogen production system can maintain stable tracking under different load conditions, avoiding frequent start-stop and improving energy utilization.

[0038] This application can also achieve wide-range power adaptive matching, stably following the optical power prediction value throughout the entire process from startup, operation to shutdown, such as... Figure 6 As shown, throughout the entire operating cycle, including start-up, operation, and shutdown phases, the hydrogen production power consistently follows the predicted value, demonstrating the effectiveness of the predictive control and the robustness of the system, especially in off-grid environments with significant fluctuations. This application effectively replaces energy storage functions under off-grid conditions without energy storage, and by smoothing power fluctuations through control algorithms, it ensures the continuous, stable, and efficient operation of the off-grid, energy-storage-free PEM hydrogen production system.

[0039] Corresponding to the above method, this application also provides a control device for an off-grid, energy-storage-free PEM hydrogen production system, applied in the controller of the off-grid, energy-storage-free PEM hydrogen production system. The system also includes a photovoltaic array and a PEM hydrogen production tank, such as... Figure 7 As shown, the device includes: The acquisition unit 710 is used to acquire the current operating parameters of the photovoltaic array, spatially related environmental parameters, and meteorological data of the area where the photovoltaic array is located within the current time period, as well as the current hydrogen production status and power tracking deviation of the PEM hydrogen production cell. The feature extraction unit 720 is used to extract features from current operating parameters, spatially related environmental parameters and meteorological data to obtain the spatiotemporal characteristics of photovoltaic power output. The prediction unit 730 is used to input the spatiotemporal characteristics of photovoltaic output into a pre-trained photovoltaic power prediction model to obtain the power prediction sequence of the photovoltaic array in the future preset time period; The determination unit 740 is used to determine the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system in a future preset time period based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation.

[0040] The functions of each functional unit of the control device for the off-grid, energy-storage-free PEM hydrogen production system provided in the above embodiments of this application can be realized through the above-described methods and steps. Therefore, the specific working process and beneficial effects of each unit in the control device for the off-grid, energy-storage-free PEM hydrogen production system provided in the embodiments of this application will not be repeated here.

[0041] This application also provides an electronic device, such as... Figure 8 As shown, it includes a processor 810, a communication interface 820, a memory 830, and a communication bus 880, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 880.

[0042] Memory 830 is used to store computer programs; When the processor 810 executes the program stored in the memory 830, it performs the following steps: Acquire the current operating parameters of the photovoltaic array, spatially related environmental parameters, and meteorological data of the area where the photovoltaic array is located within the current time period, as well as the current hydrogen production status and power tracking deviation of the PEM hydrogen production cell; Feature extraction is performed on current operating parameters, spatially related environmental parameters, and meteorological data to obtain the spatiotemporal characteristics of photovoltaic power output; The spatiotemporal characteristics of photovoltaic output are input into a pre-trained photovoltaic power prediction model to obtain the power prediction sequence of the photovoltaic array in the future within a preset time period; Based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation, the target hydrogen production control parameters for the off-grid, storage-free PEM hydrogen production system are determined for a future preset time period.

[0043] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0044] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0045] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0046] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0047] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 2 The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0048] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform the control method of any of the off-grid, energy storage-free PEM hydrogen production systems described in the above embodiments.

[0049] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the control method of any of the off-grid, energy storage-free PEM hydrogen production systems described in the above embodiments.

[0050] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented 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.

[0051] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. 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 illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0052] 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.

[0053] 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.

[0054] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of this application.

[0055] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of this application and its equivalents, then these modifications and variations are also intended to be included in the embodiments of this application.

Claims

1. A method for controlling off-grid, energy storage-free PEM hydrogen production, characterized in that, In a controller for an off-grid, energy-storage-free PEM hydrogen production system, the system further includes a photovoltaic array and a PEM hydrogen production cell, the method includes: The system acquires the current operating parameters, spatially related environmental parameters, and meteorological data of the photovoltaic array's location within the current time period, as well as the current hydrogen production status and power tracking deviation of the PEM hydrogen production cell. Feature extraction is performed on the current operating parameters, spatially related environmental parameters, and meteorological data to obtain the spatiotemporal characteristics of photovoltaic power output; The spatiotemporal characteristics of photovoltaic output are input into a pre-trained photovoltaic power prediction model to obtain the power prediction sequence of the photovoltaic array in a future preset time period; Based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation, the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system are determined for a future preset time period.

2. The method as described in claim 1, characterized in that, The photovoltaic power prediction model includes: The input layer is used to input the spatiotemporal characteristics of photovoltaic power output; The first LSTM layer is used to extract features and encode the temporal dimension of photovoltaic power output to obtain short-term temporal feature encoding. The second LSTM layer is used to perform deep temporal feature extraction on the short-term temporal feature encoding and fuse long-short-term information to obtain long-short-term fused feature encoding. The attention mechanism layer is used to perform attention weighting on the long-short fusion feature encoding to obtain a weighted feature vector; A fully connected layer is used to perform a nonlinear transformation on the weighted feature vector to obtain a power prediction sequence of the photovoltaic array in the future preset time period; The output layer is used to output the power prediction sequence of the photovoltaic array for a future preset time period.

3. The method as described in claim 1, characterized in that, Based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation, the target hydrogen production control parameters for the off-grid, storage-free PEM hydrogen production system are determined for a future preset time period, including: The power prediction sequence, the current hydrogen production status, and the power tracking deviation are input into a pre-trained hydrogen production control network to obtain the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system over a future preset time period.

4. The method as described in claim 3, characterized in that, The hydrogen production control network includes a feedforward control module and a feedback control module; The feedforward control module is used to convert the power prediction sequence into initial hydrogen production control parameters based on the dynamic characteristic model of the configured PEM hydrogen production cell; and to smooth the initial hydrogen production control parameters to obtain the initial hydrogen production control parameters. The feedback control module is used to generate a deviation correction amount based on the configured constraints of the PEM hydrogen production cell, the power prediction sequence, the current hydrogen production status, the initial hydrogen production control parameters, and the power tracking deviation; and to adjust the initial hydrogen production control parameters based on the deviation correction amount to obtain the target hydrogen production control parameters for the off-grid, energy storage-free PEM hydrogen production system in the future for a preset time period.

5. The method as described in claim 4, characterized in that, Based on the configured constraints of the PEM hydrogen production cell, the power prediction sequence, the current hydrogen production status, the initial hydrogen production control parameters, and the power tracking deviation, a deviation correction amount is generated, including: Using the power prediction sequence as a reference trajectory, the current hydrogen production state as the initial state, the power tracking deviation as the feedback input, and the constraints as constraints of a pre-set objective function, the objective function is solved using a rolling optimization method to obtain the optimal control sequence; the first term of the optimal control sequence is used as the deviation correction amount.

6. The method as described in claim 4, characterized in that, Both the initial hydrogen production control parameters and the target hydrogen production control parameters include: hydrogen production power; The current hydrogen production status includes: the current hydrogen production capacity.

7. The method as described in claim 6, characterized in that, The power tracking deviation of the PEM hydrogen production cell is the difference between the initial hydrogen production power of the PEM hydrogen production cell in the previous time period and the current hydrogen production power of the PEM hydrogen production cell in the current time period. After determining the target hydrogen production control parameters for the off-grid, storage-free PEM hydrogen production system over a predetermined time period, the method further includes: The power tracking deviation of the PEM hydrogen production tank in the future preset time period is calculated based on the difference between the initial hydrogen production power of the PEM hydrogen production tank in the current time period and the current hydrogen production power of the PEM hydrogen production tank in the future preset time period.

8. An off-grid, energy storage-free PEM hydrogen production control device, characterized in that, A controller for an off-grid, energy-storage-free PEM hydrogen production system, the system further including a photovoltaic array and a PEM hydrogen production tank, the device comprising: The acquisition unit is used to acquire the current operating parameters of the photovoltaic array, spatially related environmental parameters, and meteorological data of the area where the photovoltaic array is located within the current time period, as well as the current hydrogen production status and power tracking deviation of the PEM hydrogen production cell. The feature extraction unit is used to extract features from the current operating parameters, spatially related environmental parameters, and meteorological data to obtain the spatiotemporal features of photovoltaic power output. The prediction unit is used to input the spatiotemporal characteristics of the photovoltaic output into a pre-trained photovoltaic power prediction model to obtain the power prediction sequence of the photovoltaic array in a future preset time period; The determining unit is used to determine the target hydrogen production control parameters of the off-grid, energy storage-free PEM hydrogen production system for a future preset time period based on the power prediction sequence, the current hydrogen production status, and the power tracking deviation.

9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-7.

Images