A ship power regulation method and system based on hydrogen fuel cells

Abstract

This invention discloses a method and system for ship power regulation based on hydrogen fuel cells, relating to the field of ship power control technology. The method includes: dynamically adjusting power output based on adaptive power allocation decision-making; calculating the required output power of the hydrogen fuel cell using a nonlinear predictive control method to obtain the theoretical hydrogen supply flow rate; optimizing the dynamic response characteristics of the hydrogen fuel cell based on the theoretical hydrogen supply flow rate and adjusting the opening of a micro proportional valve to obtain the actual power of the hydrogen fuel cell; comparing the actual power of the hydrogen fuel cell with the instantaneous power demand; and dynamically adjusting the hydrogen supply flow rate by combining reinforcement learning algorithms and nonlinear predictive control methods to optimize the power allocation strategy, resulting in an optimized power allocation strategy. This invention reduces the additional load on the hydrogen fuel cell caused by power fluctuations by using a nonlinear predictive control method to calculate the output power of the hydrogen fuel cell and combines this with real-time adjustment of the micro proportional valve opening, thereby improving stability and energy efficiency.

Description

Technical Field

[0001] This invention relates to the field of marine power control technology, and in particular to a method and system for marine power regulation based on hydrogen fuel cells. Background Technology

[0002] Hydrogen fuel cells, as a clean and efficient energy conversion device, have attracted widespread attention in the field of marine propulsion. Traditional ships mainly rely on diesel engines or gas turbines for power. While these methods offer high power output, their high emissions, high noise levels, and fuel consumption limit their development in the trend of green shipping. With the advancement of hydrogen energy technology, hydrogen fuel cells, due to their advantages such as high energy density, zero carbon emissions, and low noise, are gradually becoming an important development direction for ship propulsion.

[0003] Existing power allocation methods still have limitations in practical applications, the most significant being insufficient real-time performance. While optimization-based power allocation methods can improve energy utilization, their high computational complexity makes it difficult to quickly adjust to sudden load changes, resulting in power output lag. Developing a power allocation method that can rapidly respond to load changes to improve the real-time control capabilities of hydrogen fuel cells in ship propulsion is a pressing technological challenge. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention provides a ship power control method based on hydrogen fuel cells to solve the problem of poor real-time power distribution.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0006] In a first aspect, the present invention provides a ship power regulation method based on a hydrogen fuel cell, comprising: collecting ship operation data through multi-source sensors, calculating instantaneous power demand, and monitoring the power supply capabilities of the hydrogen fuel cell, lithium battery, and supercapacitor; constructing a power allocation model based on a reinforcement learning algorithm to generate an adaptive power allocation decision; dynamically adjusting the power output based on the adaptive power allocation decision, calculating the required output power of the hydrogen fuel cell using a nonlinear predictive control method to obtain the theoretical hydrogen supply flow rate; optimizing the dynamic response characteristics of the hydrogen fuel cell based on the theoretical hydrogen supply flow rate and adjusting the opening of a micro proportional valve to obtain the actual power of the hydrogen fuel cell; comparing the actual power of the hydrogen fuel cell with the instantaneous power demand, and dynamically adjusting the hydrogen supply flow rate by combining the reinforcement learning algorithm and the nonlinear predictive control method to optimize the power allocation strategy and obtain the optimized power allocation strategy.

[0007] As a preferred embodiment of the hydrogen fuel cell-based ship power regulation method of the present invention, the specific steps for collecting ship operation data through multi-source sensors and calculating instantaneous power demand are as follows:

[0008] The ship's operating data is obtained by collecting propulsion torque, speed, acceleration, load changes and environmental parameters, and then denoising and consistency correction is performed. Data fusion methods are used to integrate multi-source data to obtain ship operating status parameters.

[0009] The Kalman filter method is used to calculate the ship's current speed, acceleration, and load changes, and the real-time operating resistance of the ship is calculated through dynamic modeling.

[0010] Based on the ship's real-time operating resistance and operating status parameters, the instantaneous power demand of the ship is calculated using a power balance analysis method.

[0011] As a preferred embodiment of the hydrogen fuel cell-based ship power control method of the present invention, the method involves: monitoring the power supply capabilities of the hydrogen fuel cell, lithium battery, and supercapacitor; constructing a power allocation model based on a reinforcement learning algorithm; and generating adaptive power allocation decisions. The specific steps are as follows:

[0012] Collect real-time operating status parameters of hydrogen fuel cells, lithium batteries, and supercapacitors;

[0013] Using a state estimation algorithm, the instantaneous output power of the hydrogen fuel cell, the discharge power of the lithium battery, and the transient discharge power of the supercapacitor are calculated to obtain energy supply capacity data. Combined with the instantaneous power demand of the ship, a power demand matching method is used to construct the power allocation state space.

[0014] Based on the constructed power allocation state space and ship operation data, a reinforcement learning algorithm is used to train an intelligent power allocation model, and the output of the intelligent power allocation model is optimized through a policy optimization method to generate an adaptive power allocation decision.

[0015] As a preferred embodiment of the ship power control method based on hydrogen fuel cells described in this invention, the steps of dynamically adjusting power output based on adaptive power allocation decision-making, calculating the required output power of the hydrogen fuel cell using a nonlinear predictive control method, and obtaining the theoretical hydrogen supply flow rate are as follows:

[0016] Based on adaptive power allocation decision, a power control method is adopted to obtain the target output power of hydrogen fuel cells, lithium batteries and supercapacitors;

[0017] Based on the power supply capacity, ship operation data, and the ship's instantaneous power demand, the target output power is corrected. The output power of the hydrogen fuel cell is calculated using a nonlinear predictive control method, and the required theoretical hydrogen supply flow rate is calculated using a hydrogen supply demand calculation method.

[0018] As a preferred embodiment of the ship power control method based on hydrogen fuel cells described in this invention, the specific steps for optimizing the dynamic response characteristics of the hydrogen fuel cell and obtaining the actual power of the hydrogen fuel cell based on the theoretical hydrogen supply flow rate and adjusting the opening of the micro proportional valve are as follows.

[0019] Based on the theoretical hydrogen supply flow rate, the initial opening of the micro proportional valve is set through a flow control method.

[0020] The voltage, current and output power of the hydrogen fuel cell are monitored in real time. A dynamic adjustment algorithm is used to adjust the initial opening of the micro proportional valve. A gas flow calculation method is used to calculate the hydrogen-oxygen ratio of the hydrogen fuel cell and dynamically correct the opening of the micro proportional valve.

[0021] By combining load changes and the corrected hydrogen supply flow rate, an adaptive control method is used to optimize the dynamic response characteristics of the hydrogen fuel cell, and the actual power of the hydrogen fuel cell is obtained by using the instantaneous power calculation method.

[0022] As a preferred embodiment of the ship power control method based on hydrogen fuel cells described in this invention, the method employs a gas flow calculation method to calculate the hydrogen-oxygen ratio of the hydrogen fuel cell and dynamically correct the opening of the micro proportional valve. The specific steps are as follows:

[0023] Based on the adjusted opening of the micro proportional valve, the real-time hydrogen and oxygen supply flow rates of the hydrogen fuel cell are obtained, and the hydrogen-oxygen ratio of the hydrogen fuel cell is calculated using a gas flow calculation method.

[0024] The hydrogen-oxygen ratio deviation was calculated by comparing the hydrogen-oxygen ratio with the theoretical stoichiometry using a fuel cell stoichiometric analysis method.

[0025] A dynamic correction algorithm is adopted to adjust the hydrogen and oxygen supply flow matching method according to the hydrogen-oxygen ratio deviation, and an optimized control method is used to dynamically correct the opening of the micro proportional valve.

[0026] As a preferred embodiment of the hydrogen fuel cell-based ship power control method described in this invention, the following steps are taken: comparing the actual power and instantaneous power demand of the hydrogen fuel cell, combining reinforcement learning algorithms and nonlinear predictive control methods to dynamically adjust the hydrogen supply flow rate, optimize the power allocation strategy, and obtain the optimized power allocation strategy.

[0027] Based on the actual power of hydrogen fuel cells and the instantaneous power demand of ships, an error analysis method is used to calculate the power deviation, and a reinforcement learning algorithm and nonlinear predictive control method are used to optimize the hydrogen supply flow.

[0028] Based on the optimized hydrogen supply flow rate, the power output ratio of the hydrogen fuel cell, lithium battery, and supercapacitor is adjusted, and through continuous iteration, an optimized power allocation strategy is obtained.

[0029] Secondly, this invention provides a ship power control system based on a hydrogen fuel cell, comprising a power allocation module, a hydrogen supply calculation module, an actual power module, and a power optimization module. The power allocation module is used to collect ship operation data through multi-source sensors, calculate instantaneous power demand, monitor the power supply capabilities of the hydrogen fuel cell, lithium battery, and supercapacitor, construct a power allocation model based on a reinforcement learning algorithm, and generate adaptive power allocation decisions. The hydrogen supply calculation module is used to dynamically adjust power output based on the adaptive power allocation decisions, calculate the required output power of the hydrogen fuel cell using a nonlinear predictive control method, and obtain the theoretical hydrogen supply flow rate. The actual power module is used to optimize the dynamic response characteristics of the hydrogen fuel cell based on the theoretical hydrogen supply flow rate and by adjusting the opening of a micro proportional valve, thereby obtaining the actual power of the hydrogen fuel cell. The power optimization module is used to compare the actual power of the hydrogen fuel cell with the instantaneous power demand, and dynamically adjust the hydrogen supply flow rate by combining a reinforcement learning algorithm and a nonlinear predictive control method, thereby optimizing the power allocation strategy and obtaining an optimized power allocation strategy.

[0030] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein the computer program, when executed by the processor, implements any step of the hydrogen fuel cell-based ship power control method as described in the first aspect of the present invention.

[0031] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the hydrogen fuel cell-based ship power control method as described in the first aspect of the present invention.

[0032] The beneficial effects of this invention are as follows: By utilizing a nonlinear predictive control method to calculate the output power of the hydrogen fuel cell and combining this with real-time adjustment of the micro proportional valve opening, the hydrogen supply flow can be precisely matched to the actual power demand. This not only reduces the lag in power distribution but also lowers the additional load on the hydrogen fuel cell caused by power fluctuations, improving stability and energy efficiency. It also enhances the responsiveness of the hydrogen fuel cell in ship propulsion, improving the overall stability and reliability of the power system. Attached Figure Description

[0033] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of the hydrogen fuel cell-based ship power control method of the present invention.

[0035] Figure 2 This is a schematic diagram of the ship power control system based on hydrogen fuel cells according to the present invention.

[0036] Figure 3 This is a flowchart of the hydrogen fuel cell ship power control method of the present invention.

[0037] Figure 4 This is a flowchart illustrating the optimization of hydrogen supply flow rate according to the present invention. Detailed Implementation

[0038] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0039] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0040] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0041] Reference Figures 1-4 This is the first embodiment of the present invention, which provides a method for controlling ship power based on hydrogen fuel cells, including the following steps:

[0042] S1. Collect ship operation data through multi-source sensors and calculate instantaneous power demand.

[0043] The system collects propulsion torque, speed, acceleration, load changes, and environmental parameters to obtain ship operation data. It then performs noise reduction and consistency correction, and uses data fusion methods to integrate multi-source data to obtain ship operation status parameters.

[0044] It should be noted that the ship's propulsion torque, speed, acceleration, load changes, and environmental parameters are collected through multi-source sensors to form initial ship operation data. Since this initial data may contain noise and measurement errors, it undergoes preprocessing, including denoising and consistency correction, to improve its accuracy and reliability. Denoising is performed using filtering algorithms, such as Kalman filtering or wavelet denoising, to eliminate measurement errors caused by external interference. Consistency correction is based on time synchronization and data comparison to ensure that data collected by different sensors are consistent in time and value.

[0045] A data fusion approach is employed to integrate data from different sensors, eliminating potential measurement biases from individual sensors and improving the completeness and reliability of ship operation data. Based on the fused ship operation data, operational status parameters are extracted, including real-time speed, acceleration, propulsion load, and external environmental influencing factors, providing reliable input data for subsequent power demand calculations and power allocation optimization.

[0046] The Kalman filter method is used to calculate the ship's current speed, acceleration, and load changes, and the real-time operating resistance of the ship is calculated through dynamic modeling.

[0047] It should be noted that a Kalman filter model is established, where the state variables include the ship's current speed, acceleration, and load changes, and the observed variables are the corresponding data measured by sensors. Through the prediction-correction mechanism of the Kalman filter, the ship's speed, acceleration, and load changes at the next moment are first predicted based on its motion patterns. Then, the prediction results are corrected by combining real-time sensor data, making the calculated navigation state more consistent with the ship's actual operating conditions. Based on the speed, acceleration, and load change information calculated by the Kalman filter, the ship's operating resistance in the current environment is analyzed using dynamic modeling methods. The force situation is determined based on the ship's motion state, identifying the main sources of resistance, including the frictional force of the water on the ship, the pressure change resistance generated by the hull's movement in the water, and the additional inertial resistance caused by changes in ship acceleration. The resistance calculation is corrected based on ship operating data and empirical models to ensure the accuracy of the calculation results. Combined with ship operating data, the dynamic model is further optimized to better adapt to resistance changes in different navigation environments, and parameters are updated in real time during ship operation to improve the accuracy of ship resistance calculation, thus providing reliable input data for subsequent power allocation.

[0048] Based on the ship's real-time operating resistance and operating status parameters, the instantaneous power demand of the ship is calculated using a power balance analysis method.

[0049] It should be noted that the power demand of the ship under the current operating conditions is determined based on the power balance analysis method. The propulsion force required for the ship's motion in water is calculated according to Newton's second law. Taking into account factors such as propulsion efficiency and transmission losses, the shaft power required for propulsion is calculated. The ship's internal load power, including the power consumption of electric propulsion, navigation, communication, and auxiliary equipment, is considered, and the total load power of the ship is calculated. Based on the propulsion power and load power, the ship's instantaneous power demand is calculated. Using the power balance equation, the ship's current energy input and energy consumption are balanced to determine whether the current power supply meets the demand and to predict the short-term trend of power demand changes. The calculated instantaneous power demand data is input into the power management system for subsequent energy allocation and control.

[0050] S2 monitors the power supply capabilities of hydrogen fuel cells, lithium batteries, and supercapacitors, and constructs a power allocation model based on reinforcement learning algorithms to generate adaptive power allocation decisions.

[0051] Collect real-time operating status parameters of hydrogen fuel cells, lithium batteries, and supercapacitors.

[0052] It should be noted that key parameters such as current, voltage, power output, temperature, remaining charge, and health status of the hydrogen fuel cell, lithium battery, and supercapacitor are collected in real time using multi-source sensors. To ensure data accuracy, the collected data undergoes anomaly detection and filtering to remove abnormal data caused by measurement errors or interference. Data synchronization and time alignment algorithms are employed to ensure that the state parameters of each energy source can be analyzed according to a unified time reference, avoiding decision-making errors caused by data delays or asynchrony. Data fusion methods are used to integrate the real-time status information of the hydrogen fuel cell, lithium battery, and supercapacitor to form a complete description of energy supply capacity and provide high-precision input data for subsequent power allocation decisions, ensuring that regulation can accurately perceive the operating status of each energy storage unit and improve the real-time performance and adaptability of energy management.

[0053] A state estimation algorithm is used to calculate the instantaneous output power of the hydrogen fuel cell, the discharge power of the lithium battery, and the transient discharge power of the supercapacitor to obtain energy supply capacity data. Combined with the instantaneous power demand of the ship, a power demand matching method is used to construct the power allocation state space.

[0054] It should be noted that for hydrogen fuel cells, the instantaneous output power is calculated by collecting voltage, current, and efficiency parameters, combined with the power calculation formula, and the expression is as follows: ;

[0055] in, Indicates the current moment of the hydrogen fuel cell Instantaneous output power, Indicates the current moment of the hydrogen fuel cell The output voltage, Indicates the current moment of the hydrogen fuel cell ; output current;

[0056] For lithium batteries, the discharge power, i.e., the maximum output power that can be provided without affecting battery life, is calculated based on the remaining charge, state of health, and current load. The expression is: ;

[0057] in, Indicates the current time of the lithium battery Dischargeable power, Indicates the current time of the lithium battery The output voltage, Indicates the current time The maximum allowable discharge current, Indicates the current time The maximum safe discharge power is set;

[0058] For supercapacitors, considering voltage, current, and equivalent series resistance characteristics, the transient discharge power, i.e., the high power output that can be provided in a short time, is calculated using the following expression: ;

[0059] in, Indicates the current moment of the supercapacitor transient discharge power, This indicates the capacitance value of the supercapacitor. Indicates the current moment of the supercapacitor voltage, This indicates the discharge termination voltage threshold of the supercapacitor. Indicates the estimated discharge time window;

[0060] Based on power supply capacity data and instantaneous power demand, a power demand matching method is employed to compare the ship's power demand with the available power of each energy unit, initially allocating the power output ratio of different energy units. If a significant discrepancy exists between supply and demand, the target output power of each unit is adjusted, and potential supply-demand imbalances are recorded. Reinforcement learning algorithms or optimization control methods are used to train or optimize the power allocation state space to adapt to power allocation requirements under different operating conditions. The state space uses the power output range of hydrogen fuel cells, lithium batteries, and supercapacitors as state variables.

[0061] Based on the constructed power allocation state space and ship operation data, a reinforcement learning algorithm is used to train an intelligent power allocation model, and the output of the intelligent power allocation model is optimized through a policy optimization method to generate an adaptive power allocation decision.

[0062] It should be noted that, based on ship operation data and the power allocation state space, during the training of the intelligent power allocation model, the state space is constructed based on the ship's operating state, including instantaneous power demand, the energy supply capacity of hydrogen fuel cells, lithium batteries, and supercapacitors, as well as characteristics such as speed and acceleration; the action space is defined as the power output combination of the energy supply units, and a reward function is constructed to evaluate the performance of the current power allocation strategy in meeting load demand and stability; reinforcement learning algorithms (such as deep Q-networks or policy gradient methods) are used for training. In each round of training, the agent selects actions based on the current state, interacts with the environment to obtain feedback, and updates the policy. The policy parameters are optimized through policy gradient or value function approximation methods; after training convergence, the stability and generalization ability of the policy are further improved through policy optimization methods (such as PPO or Actor-Critic architecture), and an adaptive power allocation strategy is output.

[0063] S3. Based on adaptive power allocation decision, the power output is dynamically adjusted, and the output power required by the hydrogen fuel cell is calculated using a nonlinear predictive control method to obtain the theoretical hydrogen supply flow rate.

[0064] Based on adaptive power allocation decision-making, a power control method is adopted to obtain the target output power of hydrogen fuel cells, lithium batteries, and supercapacitors.

[0065] It should be noted that, based on adaptive power allocation decisions, the instantaneous power demand of the ship is determined, and the real-time operating status of the hydrogen fuel cell, lithium battery, and supercapacitor is acquired, including parameters such as voltage, current, remaining charge, and maximum output power. A power control method is used to compare the instantaneous power demand with the available power of the current power supply equipment, and the power allocation priority of each power supply equipment is calculated. Based on the dynamic response characteristics of the hydrogen fuel cell and the short-term power compensation capabilities of the lithium battery and supercapacitor, a preliminary target power allocation scheme is determined, in which the hydrogen fuel cell undertakes the basic power output, and the lithium battery and supercapacitor are used for medium- and long-term and transient power compensation, respectively.

[0066] Based on the operating status and historical power output records of the power supply equipment, the power allocation ratio is further optimized. If the hydrogen fuel cell is under high load, the power allocation ratio of the lithium battery and supercapacitor is appropriately increased to reduce the instantaneous power fluctuation of the fuel cell; if the load is low, the output power of the lithium battery and supercapacitor is reduced to increase the load rate of the hydrogen fuel cell and reduce the number of energy switching operations. Combining the optimized power allocation scheme, the target output power of the hydrogen fuel cell, lithium battery, and supercapacitor is determined and transmitted to the power supply control as input parameters for subsequent power scheduling and hydrogen supply calculations.

[0067] Based on the power supply capacity, ship operation data, and the ship's instantaneous power demand, the target output power is corrected. The output power of the hydrogen fuel cell is calculated using a nonlinear predictive control method, and the required theoretical hydrogen supply flow rate is calculated using a hydrogen supply demand calculation method.

[0068] It should be noted that the target output power is compared with the energy supply capacity to analyze the rationality of the current power allocation scheme. If the load on the hydrogen fuel cell is too high, its target output power is reduced, and the power compensation ratio of the lithium battery or supercapacitor is increased; if the load on the hydrogen fuel cell is too low, its target output power is appropriately increased to reduce the use of energy storage equipment. Based on the adjusted target output power, a nonlinear predictive control method is used, combined with ship operation data and current operating conditions, to predict the dynamic power output characteristics of the hydrogen fuel cell, and the optimized hydrogen fuel cell output power is calculated, expressed as: ;

[0069] in, Indicates the current time The calculated optimal output power of the fuel cell This indicates the search for the optimal value of the output power that minimizes the objective function. Indicates the current moment. Indicates the length of the control prediction time domain. Indicates the predicted time. Indicates the predicted time The output power of the fuel cell Indicates the predicted time Instantaneous power requirements of ships This represents the weighting factor for the control items. This indicates that the hydrogen supply flow rate should be minimized during optimization;

[0070] Based on the calculated output power of the hydrogen fuel cell, and taking into account factors such as the fuel cell's energy conversion efficiency, operating temperature, and pressure, the theoretical hydrogen supply flow rate is obtained using the hydrogen supply demand calculation method. The expression is as follows: ;

[0071] in, Indicates the theoretical hydrogen supply flow rate. This indicates the target output power allocated to the hydrogen fuel cell. Indicates the efficiency of hydrogen fuel cells. Indicates the operating voltage of the hydrogen fuel cell. Indicates the molar mass of hydrogen. This represents the Faraday constant, approximately 96485 C / mol;

[0072] If the hydrogen supply is insufficient, the hydrogen supply pressure will be increased appropriately or the opening of the hydrogen supply valve will be adjusted; if the hydrogen supply is excessive, the hydrogen supply will be reduced to prevent fuel waste. The calculated theoretical hydrogen supply flow rate will be used as a control command and transmitted, and the operating status of the hydrogen fuel cell will be monitored in real time to further optimize the hydrogen supply strategy and power distribution scheme in subsequent steps.

[0073] S4. Based on the theoretical hydrogen supply flow rate and by adjusting the opening of the micro proportional valve, the dynamic response characteristics of the hydrogen fuel cell are optimized to obtain the actual power of the hydrogen fuel cell.

[0074] Based on the theoretical hydrogen supply flow rate, the initial opening of the micro proportional valve is set through a flow control method.

[0075] It should be noted that, based on the calculated theoretical hydrogen supply flow rate and combined with the current operating status of the hydrogen fuel cell, including temperature, pressure, power requirements, etc., the flow characteristic curve of the micro proportional valve is queried, its hydrogen supply capacity at different opening degrees is analyzed, and an appropriate initial valve opening degree is matched according to the theoretical hydrogen supply flow rate.

[0076] Considering the response characteristics of hydrogen supply, including pressure loss, flow stability, and valve hysteresis in the hydrogen supply pipeline, an initial opening compensation value is calculated using flow control methods to reduce valve control errors. The calculated initial opening command is sent to the actuator of the miniature proportional valve, driving the valve to adjust to the target opening.

[0077] During valve adjustment, the actual hydrogen supply flow rate is monitored in real time and compared with the theoretical hydrogen supply flow rate. If the error exceeds the set threshold, the initial opening is dynamically corrected, and the valve is adjusted to the new set value, bringing the hydrogen supply flow rate close to the theoretical value. Valve adjustment data is recorded for subsequent optimization of the hydrogen supply control strategy.

[0078] The voltage, current, and output power of the hydrogen fuel cell are monitored in real time. A dynamic adjustment algorithm is used to adjust the initial opening of the micro proportional valve, and a gas flow calculation method is used to calculate the hydrogen-oxygen ratio of the hydrogen fuel cell and dynamically correct the opening of the micro proportional valve.

[0079] It should be noted that, based on real-time monitoring of voltage, current, and power parameters, a dynamic adjustment algorithm is used to calculate the adjustment range of the micro proportional valve. The algorithm first determines whether the current hydrogen supply meets the fuel cell's requirements. If the hydrogen supply is too high or too low, it calculates an appropriate adjustment step size and generates an adjustment command to dynamically correct the initial opening of the micro proportional valve. During the adjustment process, the response speed and adjustment accuracy of the proportional valve are continuously monitored to ensure that the adjustment effect meets the set requirements.

[0080] Based on the adjusted micro proportional valve opening, the hydrogen and oxygen supply flow rates are measured in real time, and the hydrogen-oxygen ratio is calculated using a gas flow calculation method. During the calculation, pressure changes, flow fluctuations, and the instantaneous consumption characteristics of the hydrogen fuel cell are considered to ensure the accuracy of the results.

[0081] The calculated hydrogen-oxygen ratio is compared with the theoretical stoichiometric ratio. If the deviation exceeds a set threshold, a dynamic correction mechanism is triggered. The hydrogen or oxygen supply flow rate is adjusted according to the direction of the deviation, and the opening of the micro proportional valve is further optimized to gradually bring the hydrogen-oxygen ratio closer to the optimal value. Throughout the process, the adjustment effect is continuously monitored to ensure the stability of hydrogen supply control.

[0082] By combining load changes and the corrected hydrogen supply flow rate, an adaptive control method is used to optimize the dynamic response characteristics of the hydrogen fuel cell, and the actual power of the hydrogen fuel cell is obtained by using the instantaneous power calculation method.

[0083] It should be noted that an adaptive control method is used to adjust the operating parameters of the hydrogen fuel cell. The current hydrogen supply status is assessed, and the instantaneous power output change trend of the fuel cell is calculated in conjunction with real-time load demand. If power output lag or overshoot is detected, the rate of change of hydrogen supply flow is adjusted to match the dynamic load demand.

[0084] Using an adaptive control algorithm, the hydrogen-oxygen supply ratio is optimized in real time based on the hydrogen fuel cell's operating data and current operating status, adjusting the reaction rate and optimizing dynamic response characteristics. During the optimization process, parameters such as the hydrogen fuel cell's output power, current, and voltage are continuously monitored.

[0085] An instantaneous power calculation method is employed to calculate the actual power based on the real-time output voltage and current of the hydrogen fuel cell, and then compare it with the expected power. If the actual power deviates from the target value, the hydrogen and oxygen supply strategies are readjusted to correct the operating state of the hydrogen fuel cell. In the next control cycle, the hydrogen supply is further optimized to ensure precise matching of power output. Throughout the process, continuous data acquisition, calculation, and feedback adjustments are performed to ensure that the power response of the hydrogen fuel cell meets the load requirements, thus obtaining the actual power of the hydrogen fuel cell.

[0086] S5. A gas flow calculation method is used to calculate the hydrogen-oxygen ratio of the hydrogen fuel cell and dynamically correct the opening of the micro proportional valve.

[0087] Based on the adjusted opening of the micro proportional valve, the real-time hydrogen and oxygen supply flow rates of the hydrogen fuel cell are obtained, and the hydrogen-oxygen ratio of the hydrogen fuel cell is calculated using a gas flow calculation method.

[0088] It should be noted that real-time hydrogen and oxygen supply flow rates of the hydrogen fuel cell are obtained using flow sensors. The hydrogen supply flow rate is measured by a mass flow meter or thermal flow sensor installed in the hydrogen delivery pipeline, while the oxygen supply flow rate is calculated by an air flow meter or pressure sensor. The flow signals acquired by the sensors are converted into a standard data format and filtered and calibrated to remove environmental interference or sensor errors.

[0089] A gas flow rate calculation method was used, combined with hydrogen and oxygen supply flow rate data, to calculate the hydrogen-oxygen ratio of the hydrogen fuel cell. The obtained flow rates were converted to volumetric or mass flow rates under standard operating conditions (temperature, pressure), and then the current hydrogen-oxygen ratio was calculated based on the theoretical stoichiometric formula for hydrogen fuel cells. Simultaneously, time-series analysis was performed on the hydrogen-oxygen ratio data to determine whether the hydrogen and oxygen supply flow rates remained stable and whether there were any fluctuations or deviations.

[0090] The calculated hydrogen-oxygen ratio is compared with the theoretically optimal ratio. If the hydrogen-oxygen ratio deviates from the preset range, the current proportional valve opening, environmental parameters, and load status are recorded for subsequent adjustments. Simultaneously, the trend of hydrogen-oxygen ratio changes is calculated to provide a reference for the next step of hydrogen and oxygen supply regulation.

[0091] The hydrogen-oxygen ratio deviation was calculated by comparing the hydrogen-oxygen ratio with the theoretical stoichiometry using a fuel cell stoichiometric analysis method.

[0092] It should be noted that the stoichiometric analysis method for fuel cells is used to determine the theoretical stoichiometric ratio of the hydrogen fuel cell under the current operating conditions. Based on the reaction equation of the hydrogen fuel cell, the theoretical consumption ratio of hydrogen and oxygen is calculated, and combined with the rated operating parameters of the hydrogen fuel cell, the ideal hydrogen-oxygen supply ratio is determined. The actual hydrogen and oxygen supply flow rates at the current moment are acquired. The flow data is measured by flow sensors installed on the hydrogen and oxygen supply pipelines and converted to a standard format. The data processing unit filters the flow signals to reduce errors caused by sensor noise or environmental factors. Based on the actual hydrogen and oxygen supply flow rates, the real-time hydrogen-oxygen ratio is calculated. The measured flow data is normalized to standard temperature and pressure conditions to ensure the consistency of the calculation results. The current actual hydrogen-oxygen ratio is obtained using the hydrogen-oxygen ratio calculation formula.

[0093] The calculated real-time hydrogen-oxygen ratio is compared with the theoretical stoichiometric ratio. An error calculation method is used to determine the deviation between the actual and theoretical values, and the direction (too high or too low) and magnitude (absolute value) of the deviation are analyzed. If the deviation exceeds a set threshold, the current state is marked as a deviation state, and relevant operating data, including the current hydrogen-oxygen ratio, flow sensor data, load conditions, and environmental parameters, are stored. Based on the hydrogen-oxygen ratio deviation, it is determined whether hydrogen or oxygen supply adjustments are needed. A dynamic correction algorithm is then used to calculate new hydrogen or oxygen supply flow rate setpoints for subsequent optimization of the hydrogen and oxygen supply matching method.

[0094] A dynamic correction algorithm is adopted to adjust the hydrogen and oxygen supply flow matching method according to the hydrogen-oxygen ratio deviation, and an optimized control method is used to dynamically correct the opening of the micro proportional valve.

[0095] It should be noted that the calculated hydrogen-oxygen ratio deviation is obtained, and the direction (high or low) and magnitude (absolute value) of the deviation are determined. Based on the deviation magnitude, an adjustment strategy is set, and it is determined whether dynamic correction is needed. If the deviation is within the set allowable range, the current hydrogen and oxygen supply flow rates are maintained unchanged; if the deviation exceeds the threshold, the dynamic correction algorithm is triggered to adjust the hydrogen and oxygen supply flow rate matching method. The sources of the hydrogen-oxygen ratio deviation are analyzed, including factors such as changes in hydrogen fuel cell load, ambient temperature, and pressure fluctuations, and the adjustment strategy is determined in conjunction with the current operating status. If the hydrogen-oxygen ratio is high, it indicates that there is too much hydrogen or insufficient oxygen supply, in which case the hydrogen flow rate needs to be reduced or the oxygen flow rate increased; if the hydrogen-oxygen ratio is low, it indicates that there is insufficient hydrogen or too much oxygen supply, in which case the hydrogen flow rate needs to be increased or the oxygen flow rate decreased.

[0096] The new hydrogen and oxygen supply flow rates are calculated using a dynamic correction algorithm, expressed as follows:

[0097] ; ;

[0098] in, Indicates the next moment Hydrogen supply flow rate, Indicates the current time Hydrogen supply flow rate, This represents the proportional control parameter. Indicates the deviation in the hydrogen-oxygen ratio. Indicates integral control parameters, This represents the policy deviation. Represents the differential control parameters. Indicates the rate of change. Indicates the next moment oxygen supply flow rate, The stoichiometric ratio of hydrogen to oxygen is usually 0.5, meaning that 1 mol of hydrogen reacts with 0.5 mol of oxygen. Represents the time variable of integration. Represents the time derivative. This indicates taking the derivative with respect to the variable;

[0099] Based on a feedback control strategy, the adjustment amounts for hydrogen and oxygen supply are calculated, and the matching method for hydrogen and oxygen supply flow rates is optimized. This includes adjusting the upper limit of the hydrogen supply flow rate, optimizing the oxygen supply intake, and changing the control parameters of the micro proportional valve. The corrected hydrogen and oxygen supply flow rate setpoints must ensure that the combustion reaction of the hydrogen fuel cell remains within a reasonable stoichiometric range while meeting the load power requirements.

[0100] Based on the optimized hydrogen and oxygen supply flow rate setpoints, an optimized control method is employed to dynamically adjust the opening of the micro proportional valve. The micro proportional valve opening adjustment command is executed, and the operating parameters of the hydrogen fuel cell, including output power, current, voltage, and hydrogen and oxygen supply flow rates, are monitored. If the hydrogen-oxygen ratio still does not return to the target range after adjustment, iterative adjustments continue until the hydrogen-oxygen ratio meets the set requirements, allowing for subsequent optimization of the hydrogen and oxygen supply regulation strategy.

[0101] S6. Compare the actual power and instantaneous power demand of the hydrogen fuel cell, and combine reinforcement learning algorithm and nonlinear predictive control method to dynamically adjust the hydrogen supply flow rate and optimize the power allocation strategy to obtain the optimized power allocation strategy.

[0102] Based on the actual power of the hydrogen fuel cell and the instantaneous power demand of the ship, an error analysis method is used to calculate the power deviation, and a reinforcement learning algorithm and a nonlinear predictive control method are used to optimize the hydrogen supply flow.

[0103] It should be noted that an error analysis method is used to calculate the power deviation of the hydrogen fuel cell. This involves comparing the actual output power of the fuel cell with the instantaneous power demand of the ship, calculating the difference, and determining the direction (power excess or deficiency) and magnitude of the deviation. If the deviation exceeds a set threshold, an optimization and adjustment process is initiated.

[0104] Based on the calculated power deviation, a reinforcement learning algorithm is used to optimize the hydrogen supply flow rate. The state space, action space, and reward function of the reinforcement learning algorithm are defined. State variables include the current power output, power demand, and hydrogen flow rate of the hydrogen fuel cell. Actions include adjusting the hydrogen supply flow rate by increasing or decreasing it. The reward function is set to minimize the power deviation, while also considering the fuel cell lifespan and hydrogen consumption efficiency. The optimal hydrogen supply adjustment strategy is obtained using the reinforcement learning algorithm, expressed as: ;

[0105] in, This represents the optimal hydrogen supply adjustment strategy. This represents the strategy for maximizing the objective function. , This represents calculating the expected value over all possible state-action paths. This represents the discount factor, with a value range of 0 < γ ≤ 1. Indicates the predicted time The reward value. During training, the hydrogen supply adjustment strategy is optimized based on environmental feedback, so that the output power of the hydrogen fuel cell gradually approaches the instantaneous power demand of the ship;

[0106] A nonlinear predictive control method is employed to optimize the hydrogen supply flow rate. Using the kinetic model and operating data of the hydrogen fuel cell, the impact of different hydrogen supply flow rate adjustment strategies on future power output is predicted. The optimal hydrogen supply flow rate adjustment strategy, calculated using a reinforcement learning algorithm, is then used to correct the power output at future time points, ensuring stable hydrogen supply flow rate adjustments and avoiding drastic fluctuations that could negatively impact fuel cell performance. The optimized hydrogen supply flow rate setpoint is input into the fuel cell's hydrogen supply control system, adjusting the opening of a micro proportional valve to change the hydrogen supply to the fuel cell, and the output power is monitored in real time. If the power deviation remains significant after adjustment, iterative optimization continues until the power requirement is met, and the optimization results are stored for subsequent adjustments.

[0107] Based on the optimized hydrogen supply flow rate, the power output ratio of the hydrogen fuel cell, lithium battery, and supercapacitor is adjusted, and through continuous iteration, an optimized power allocation strategy is obtained.

[0108] It should be noted that, based on the optimized hydrogen supply flow rate, the theoretical maximum output power of the hydrogen fuel cell is calculated to ensure its operation within a safe operating range. Taking into account the instantaneous hydrogen supply, current density, voltage characteristics, and power conversion efficiency of the hydrogen fuel cell, the upper limit of power that the hydrogen fuel cell can provide under current hydrogen supply conditions is determined. Current state data of the lithium battery and supercapacitor are obtained, including the state of charge, maximum discharge power, and charge / discharge efficiency of the lithium battery, and the transient discharge power and available capacity of the supercapacitor.

[0109] Based on the power supply capabilities of fuel cells, lithium batteries, and supercapacitors, and the instantaneous power demand of ships, a power allocation equation is established, and the power output ratio of the three is initially calculated. Optimization algorithms (such as linear programming or reinforcement learning) are employed to prioritize the stable power output of hydrogen fuel cells while ensuring power balance, and to rationally allocate the buffering role of lithium batteries, while utilizing supercapacitors to cope with instantaneous power surges.

[0110] The calculated power allocation scheme is input to dynamically adjust the output power of the hydrogen fuel cell while controlling the charging and discharging power of the lithium battery. If necessary, the supercapacitor is activated to discharge, meeting instantaneous power demands. The actual output power of each energy source is continuously monitored and compared with theoretical calculations to calculate power errors. Through iterative optimization, the power allocation strategy is adjusted based on hydrogen fuel cell data. If the power error is large or a certain energy source reaches a safety threshold (e.g., excessive fuel cell load or excessively low lithium battery SOC), the allocation ratio is re-optimized, and control parameters are updated until a stable power allocation scheme is found. Finally, the optimized power allocation strategy is applied to ensure that all energy sources work collaboratively to meet current navigation requirements.

[0111] This embodiment also provides a ship power control system based on a hydrogen fuel cell, including: a power allocation module, a hydrogen supply calculation module, an actual power module, and a power optimization module; the power allocation module is used to collect ship operation data through multi-source sensors, calculate instantaneous power demand, and monitor the power supply capacity of the hydrogen fuel cell, lithium battery, and supercapacitor, and construct a power allocation model based on a reinforcement learning algorithm to generate adaptive power allocation decisions; the hydrogen supply calculation module is used to dynamically adjust the power output based on the adaptive power allocation decisions, calculate the required output power of the hydrogen fuel cell using a nonlinear predictive control method, and obtain the theoretical hydrogen supply flow rate; the actual power module is used to optimize the dynamic response characteristics of the hydrogen fuel cell based on the theoretical hydrogen supply flow rate and by adjusting the opening of the micro proportional valve, thereby obtaining the actual power of the hydrogen fuel cell; the power optimization module is used to compare the actual power of the hydrogen fuel cell with the instantaneous power demand, and dynamically adjust the hydrogen supply flow rate by combining a reinforcement learning algorithm and a nonlinear predictive control method, thereby optimizing the power allocation strategy and obtaining the optimized power allocation strategy.

[0112] This embodiment also provides a computer device applicable to the ship power control method based on hydrogen fuel cells, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the ship power control method based on hydrogen fuel cells as proposed in the above embodiment.

[0113] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0114] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for controlling ship power based on a hydrogen fuel cell as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0115] In summary, this invention utilizes a nonlinear predictive control method to calculate the output power of the hydrogen fuel cell and combines this with real-time adjustment of the micro proportional valve opening, enabling the hydrogen supply flow to precisely match the actual power demand. This not only reduces the lag in power distribution but also lowers the additional load on the hydrogen fuel cell caused by power fluctuations, improving stability and energy efficiency. It also enhances the responsiveness of the hydrogen fuel cell in ship propulsion, improving the overall stability and reliability of the power system.

[0116] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for ship power control based on hydrogen fuel cells, characterized in that: include, Step 1: Collect ship operation data through multi-source sensors, calculate the ship's instantaneous power demand, monitor the power supply capacity of hydrogen fuel cells, lithium batteries and supercapacitors, build a power allocation model based on reinforcement learning algorithm, and generate adaptive power allocation decisions; Step 2: Based on adaptive power allocation decision-making, dynamically adjust the power output, and use nonlinear predictive control methods to calculate the required output power of the hydrogen fuel cell and obtain the theoretical hydrogen supply flow rate. Based on adaptive power allocation decision, a power control method is adopted to obtain the target output power of hydrogen fuel cells, lithium batteries and supercapacitors; Based on the power supply capacity, ship operation data and the ship's instantaneous power demand, the target output power is corrected. The optimized output power of the hydrogen fuel cell is calculated using a nonlinear predictive control method. The required theoretical hydrogen supply flow rate is calculated using a hydrogen supply demand calculation method. Step 3: Based on the theoretical hydrogen supply flow rate, adjust the opening of the micro proportional valve to optimize the dynamic response characteristics of the hydrogen fuel cell and obtain the actual power of the hydrogen fuel cell. Based on the theoretical hydrogen supply flow rate, the initial opening of the micro proportional valve is set through a flow control method. The voltage, current and output power of the hydrogen fuel cell are monitored in real time. A dynamic adjustment algorithm is used to adjust the initial opening of the micro proportional valve. A gas flow calculation method is used to calculate the hydrogen-oxygen ratio of the hydrogen fuel cell and dynamically correct the opening of the micro proportional valve. By combining load changes and the corrected hydrogen supply flow rate, an adaptive control method is used to optimize the dynamic response characteristics of the hydrogen fuel cell, and the actual power of the hydrogen fuel cell is obtained by using the instantaneous power calculation method. The method of calculating the hydrogen-oxygen ratio of the hydrogen fuel cell using a gas flow rate calculation method and dynamically correcting the opening of the micro proportional valve includes: obtaining the real-time hydrogen and oxygen supply flow rates of the hydrogen fuel cell based on the adjusted opening of the micro proportional valve, and calculating the hydrogen-oxygen ratio of the hydrogen fuel cell using a gas flow rate calculation method. The hydrogen-oxygen ratio deviation was calculated by comparing the hydrogen-oxygen ratio with the theoretical stoichiometry using a fuel cell stoichiometric analysis method. A dynamic correction algorithm is adopted to adjust the hydrogen and oxygen supply flow matching method according to the hydrogen-oxygen ratio deviation, and an optimized control method is used to dynamically correct the opening of the micro proportional valve. The new hydrogen and oxygen supply flow rates are calculated using a dynamic correction algorithm, expressed as follows: ； ； in, Indicates the next moment Hydrogen supply flow rate, Indicates the current time Hydrogen supply flow rate, This represents the proportional control parameter. Indicates the deviation in the hydrogen-oxygen ratio. Indicates integral control parameters, This represents the policy deviation. Represents the differential control parameters. Indicates the rate of change. Indicates the next moment oxygen supply flow rate, The stoichiometric ratio of hydrogen to oxygen is usually 0.5, meaning that 1 mol of hydrogen reacts with 0.5 mol of oxygen. Represents the time variable of integration. Represents the time derivative. This indicates taking the derivative with respect to the variable; Step 4: Compare the actual power and instantaneous power demand of the hydrogen fuel cell. Combining reinforcement learning algorithms and nonlinear predictive control methods, dynamically adjust the hydrogen supply flow rate and optimize the power allocation strategy to obtain the optimized power allocation strategy: Based on the actual power of hydrogen fuel cells and the instantaneous power demand of ships, an error analysis method is used to calculate the power deviation, and a reinforcement learning algorithm and nonlinear predictive control method are used to optimize the hydrogen supply flow. Based on the optimized hydrogen supply flow rate, the power output ratio of the hydrogen fuel cell, lithium battery, and supercapacitor is adjusted, and through continuous iteration, an optimized power allocation strategy is obtained.

2. The ship power control method based on hydrogen fuel cells as described in claim 1, characterized in that: The specific steps for collecting ship operation data through multi-source sensors and calculating instantaneous power demand are as follows: The ship's operating data is obtained by collecting propulsion torque, speed, acceleration, load changes and environmental parameters, and then denoising and consistency correction is performed. Data fusion methods are used to integrate multi-source data to obtain ship operating status parameters. The Kalman filter method is used to calculate the ship's current speed, acceleration, and load changes, and the real-time operating resistance of the ship is calculated through dynamic modeling. Based on the ship's real-time operating resistance and operating status parameters, the instantaneous power demand of the ship is calculated using a power balance analysis method.

3. The ship power control method based on hydrogen fuel cells as described in claim 2, characterized in that: The system monitors the power supply capabilities of hydrogen fuel cells, lithium batteries, and supercapacitors. A power allocation model is constructed based on a reinforcement learning algorithm to generate adaptive power allocation decisions. The specific steps are as follows: Collect real-time operating status parameters of hydrogen fuel cells, lithium batteries, and supercapacitors; Using a state estimation algorithm, the instantaneous output power of the hydrogen fuel cell, the discharge power of the lithium battery, and the transient discharge power of the supercapacitor are calculated to obtain energy supply capacity data. Combined with the instantaneous power demand of the ship, a power demand matching method is used to construct the power allocation state space. Based on the constructed power allocation state space and ship operation data, a reinforcement learning algorithm is used to train an intelligent power allocation model, and the output of the intelligent power allocation model is optimized through a policy optimization method to generate an adaptive power allocation decision.

4. A ship power control system based on a hydrogen fuel cell, based on the ship power control method based on a hydrogen fuel cell as described in any one of claims 1 to 3, characterized in that: It includes a power distribution module, a hydrogen supply calculation module, an actual power module, and a power optimization module; The power allocation module is used to collect ship operation data through multi-source sensors, calculate instantaneous power demand, monitor the power supply capacity of hydrogen fuel cells, lithium batteries and supercapacitors, build a power allocation model based on reinforcement learning algorithm, and generate adaptive power allocation decisions. The hydrogen supply calculation module is used to dynamically adjust the power output based on adaptive power allocation decision, calculate the output power required by the hydrogen fuel cell using nonlinear predictive control method, and obtain the theoretical hydrogen supply flow rate. The actual power module is used to optimize the dynamic response characteristics of the hydrogen fuel cell based on the theoretical hydrogen supply flow rate and by adjusting the opening of the micro proportional valve, so as to obtain the actual power of the hydrogen fuel cell. The power optimization module compares the actual power of the hydrogen fuel cell with the instantaneous power demand, and combines reinforcement learning algorithms and nonlinear predictive control methods to dynamically adjust the hydrogen supply flow rate and optimize the power allocation strategy, thus obtaining the optimized power allocation strategy.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the ship power control method based on hydrogen fuel cells as described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the ship power control method based on hydrogen fuel cells as described in any one of claims 1 to 3.

Images