Extended-range hydrogen fuel power ship propulsion system

Abstract

The invention discloses an extended-range hydrogen fuel power ship propulsion system, which relates to the technical field of ship propulsion and comprises an acquisition module, a quantum annealing optimization module and a quantum chip, the acquisition module is used for eliminating noise interference of acquired hydrogen energy ship power parameters through a Kalman filtering algorithm and generating a standardized data packet, and the quantum chip is used for receiving the standardized data packet and outputting the standardized data packet. The method comprises the following steps: mapping hydrogen energy ship power parameters into an Isin model, generating a control instruction according to a hydrogen fuel consumption rate, an equipment life attenuation coefficient and a navigation task priority weight, inputting the control instruction into a simulation model of a proton exchange membrane by a proton membrane regulation and control module, and dynamically regulating a hydrogen production rate and fuel cell power, according to the system, the efficient hydrogen energy closed-loop monitoring unit and the three-level safety protocol are adopted, the response speed and precision are improved, the stability and safety are remarkably enhanced, it is ensured that a ship can reliably operate under the complex working condition, and potential safety risks are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of ship propulsion, and in particular to a range-extended hydrogen fuel powered ship propulsion system. Background Art

[0002] As the world pays more attention to environmental protection and sustainable development, the application of hydrogen energy as a clean energy in the field of transportation has gradually attracted widespread attention; especially in ship propulsion systems, hydrogen fuel cells have become an important development direction for future green ships due to their zero emissions and high efficiency. In recent years, by combining the advantages of hydrogen fuel cells and lithium battery packs, not only the endurance and power performance of ships have been improved, but also the dependence on traditional fossil fuels has been reduced.

[0003] However, existing technologies still face many challenges. On the one hand, existing extended-range hydrogen fuel-powered ship propulsion systems usually rely on fixed control logic to adjust the working state of hydrogen fuel cells and lithium battery packs. This static control method cannot adapt to dynamically changing navigation conditions, thus affecting the overall energy efficiency. On the other hand, for the pressure monitoring and electrolysis current regulation of hydrogen storage tanks, although the traditional methods can achieve basic regulation functions, their response speed and accuracy are still insufficient when facing complex working conditions. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an extended-range hydrogen fuel-powered ship propulsion system to solve the problems that static control is not adaptable to dynamic changes and traditional methods have slow response.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: The present invention provides a range-extended hydrogen fuel powered ship propulsion system, which includes a collection module, which collects hydrogen fuel powered ship power parameters, eliminates noise interference through a Kalman filter algorithm, and generates a standardized data packet; Quantum annealing optimization module: After receiving the standardized data packet, the quantum chip maps the hydrogen ship power parameters into the Ising model and generates control instructions based on the hydrogen fuel consumption rate, equipment life attenuation coefficient and navigation mission priority weight; The proton membrane control module inputs control instructions into the simulation model of the proton exchange membrane, dynamically adjusts the hydrogen production rate and fuel cell power, and outputs real-time hydrogen storage tank pressure data; Safety monitoring module: Based on the real-time hydrogen storage tank pressure data, the hydrogen energy closed-loop monitoring unit dynamically adjusts the electrolysis current and fuel cell power ratio, simultaneously monitors the hydrogen purity and oxygen residue, and triggers the three-level safety protocol to output the electrolysis waste heat temperature, coolant flow rate and safety status code; Waste heat recovery and self-check module: Based on the parameters of electrolysis waste heat temperature and coolant flow rate, the waste heat recovery converter uses phase change materials to increase the coolant temperature and reduce cooling energy consumption, while the quantum chip performs equipment health self-check; The maintenance feedback module generates a maintenance recommendation report based on the self-inspection results and uploads it to the shore-based data center.

[0007] As a preferred solution of the extended-range hydrogen fuel-powered ship propulsion system described in the present invention, the hydrogen-powered ship power parameters include: the remaining power of the lithium battery pack, the internal pressure of the hydrogen storage tank, the real-time power demand of the propeller, the temperature of the fuel cell stack, the seawater flow rate, the ship's draft depth, the hydrogen fuel consumption rate, the equipment life attenuation coefficient and the navigation mission priority weight.

[0008] As a preferred solution of the extended-range hydrogen fuel-powered ship propulsion system of the present invention, the steps of obtaining the standardized data package are as follows: The collected hydrogen ship power parameters are subjected to multimodal data denoising through Kalman filtering, and after outliers are removed using the isolation forest algorithm, Min-Max normalization and One-Hot encoding are used to generate standardized data packets.

[0009] As a preferred solution of the extended-range hydrogen fuel-powered ship propulsion system of the present invention, the step of mapping the hydrogen-powered ship power parameters to the Ising model is as follows: The hydrogen fuel consumption rate is encoded as the antiferromagnetic coupling strength, the equipment life decay coefficient is mapped to the local magnetic field bias, and the navigation mission priority is converted into a constrained energy term; Based on the antiferromagnetic coupling strength, local magnetic field bias and constrained energy terms, a multi-objective energy function of the Ising model is constructed in the quantum simulation algorithm, and the propulsion parameters of hydrogen ships are mapped to the Ising model.

[0010] As a preferred solution of the extended-range hydrogen fuel-powered ship propulsion system of the present invention, the steps of obtaining the control instructions are as follows: After mapping the hydrogen ship power parameters to the Ising model, the antiferromagnetic coupling matrix, local magnetic field vector and constraint energy term are dynamically synthesized through the matrix operation framework of TensorFlow, and combined with the adaptive weight allocation algorithm, a multi-objective optimization Hamiltonian model is constructed; Based on the multi-objective optimization Hamiltonian model, the simulated annealing algorithm is used to iteratively solve the problem in the TensorFlow computing framework, and the spin state parameters are obtained by using distributed computing. According to the spin state parameters, control instructions for fuel cell power and hydrogen production rate are dynamically generated.

[0011] As a preferred solution of the extended-range hydrogen fuel powered ship propulsion system of the present invention, the steps of acquiring the real-time hydrogen storage tank pressure data are as follows: Based on the control instructions, the hydrogen production rate setting value and the fuel cell power output are extracted and dynamically loaded into the simulation model of the proton exchange membrane, and the difference between the hydrogen generation and consumption rates is simultaneously calculated through the mass conservation equation; Based on the difference between hydrogen generation and consumption rates, the PID control algorithm and fluid dynamics algorithm are used to correct the set value of hydrogen production rate in real time, and the adaptive feedback adjustment mechanism of the equivalent circuit is combined to dynamically adjust the fuel cell power output; Based on the corrected hydrogen production rate set value and the adjusted fuel cell power output, the hydrogen storage tank pressure change curve is solved by Runge-Kutta numerical integration to obtain real-time hydrogen storage tank pressure data.

[0012] As a preferred solution of the extended-range hydrogen fuel-powered ship propulsion system of the present invention, the hydrogen energy closed-loop monitoring unit dynamically adjusts the ratio of electrolysis current to fuel cell power, the steps are as follows: Based on the real-time hydrogen storage tank pressure data, the pressure trend is predicted through Kalman filtering combined with long short-term memory network to generate a safe pressure threshold; The hydrogen energy closed-loop monitoring unit calculates the deviation percentage between the real-time hydrogen storage tank pressure and the safety pressure threshold, and divides the deviation levels. It matches different adjustment intensity weights according to the deviation levels and dynamically adjusts the ratio of electrolysis current to fuel cell power.

[0013] As a preferred solution of the extended-range hydrogen fuel-powered ship propulsion system of the present invention, the three-level safety protocol specifically includes: Define multi-dimensional thresholds based on hydrogen storage tank pressure, hydrogen purity, residual oxygen and electrolysis waste heat temperature; The multi-dimensional thresholds are graded into level one warning, level two production restriction and level three emergency shutdown.

[0014] As a preferred solution of the extended-range hydrogen fuel powered ship propulsion system of the present invention, the steps of the waste heat recovery converter increasing the coolant temperature and reducing the cooling energy consumption by using phase change materials are as follows: Based on the real-time data of electrolysis waste heat temperature and coolant flow, a simulation model of the thermal behavior of phase change materials is constructed through finite element analysis; Based on the thermal behavior simulation model of phase change materials, a virtual PID controller is used to adjust the virtual coolant flow parameters and generate the optimal flow control strategy. At the same time, the optimal flow control strategy is used to guide the cooling pump to adjust the actual coolant temperature.

[0015] As a preferred solution of the extended-range hydrogen fuel-powered ship propulsion system of the present invention, the steps of the quantum chip performing the equipment health self-check are as follows: The quantum chip uses a quantum annealing algorithm to analyze the power parameters of hydrogen ships and predicts fault modes through a deep neural network. It also dynamically adjusts the detection strategy based on reinforcement learning to achieve self-inspection of equipment health.

[0016] The beneficial effects of the present invention are: By collecting and processing the power parameters of hydrogen-powered ships in real time, and using advanced Kalman filter algorithms and quantum annealing optimization technology to generate precise control instructions, the output power of hydrogen fuel cells and lithium battery packs can be dynamically adjusted according to real-time navigation conditions, thereby significantly improving the overall energy efficiency of the ship. The use of an efficient hydrogen energy closed-loop monitoring unit and a three-level safety protocol dynamically adjusts the ratio of electrolysis current to fuel cell power based on real-time hydrogen storage tank pressure data, and matches different adjustment intensity weights according to the deviation level, which not only improves the response speed and accuracy, but also significantly enhances stability and safety, ensuring that the ship can operate reliably under complex working conditions and reducing potential safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 It is a schematic diagram of the extended-range hydrogen fuel-powered ship propulsion system of the present invention.

[0019] Figure 2 It is a flow chart of the steps of obtaining control instructions in the present invention.

[0020] Figure 3 This is a flow chart of the quantum annealing optimization module in the present invention.

[0021] Figure 4 This is a flow chart of obtaining control instructions through standardized data packets in the present invention. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] 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 term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0025] Reference Figure 1~Figure 4 , which is the first embodiment of the present invention, provides an extended-range hydrogen fuel-powered ship propulsion system, comprising the following steps: The acquisition module collects the hydrogen ship power parameters, eliminates noise interference through the Kalman filter algorithm, and generates a standardized data packet.

[0026] The specific steps include: During the data collection process, advanced sensor networks are used and distributed in key parts of the ship, including lithium battery packs, hydrogen storage tanks, fuel cell stacks, thrusters, seawater environment monitoring points, ship draft depth monitoring points, hydrogen fuel consumption rate monitoring points, engines, compressors, and navigation mission control centers; In specific operations, the current integration method and open circuit voltage method are used to measure the remaining power of the lithium battery pack, the piezoresistive pressure sensor is used to monitor the internal pressure of the hydrogen storage tank, the power sensor is used to detect the real-time power demand of the thruster, the thermocouple and infrared temperature sensor are used to measure the temperature of the fuel cell stack, the seawater flow rate is measured by the Doppler sonar sensor, the draft of the ship is evaluated by the ultrasonic sensor or pressure sensor, the hydrogen fuel consumption rate is monitored by the flow meter or mass sensor, the equipment life attenuation coefficient is estimated by combining multiple source data such as vibration sensors and temperature sensors, and the navigation task priority weight is determined according to the task planning center; The collected ship power parameters are transmitted to the central processor to form the original data set. Due to the influence of environmental noise and sensor failure, the original ship power parameters usually contain interference and outliers, so further processing is required to improve the data quality. In order to eliminate noise interference and remove outliers, the adaptive Kalman filter algorithm is used to reduce the noise of the ship power parameters. Kalman filtering is a recursive optimal estimation method that can effectively eliminate noise interference in a dynamic environment. In the specific operation, the Kalman filter is initialized, and the predicted value of the ship power parameter at the current moment is obtained. The predicted value of the ship power parameter is updated based on the real-time observed ship power parameter and the process is continuously iterated to obtain a more accurate predicted value of the ship power parameter; After denoising by Kalman filtering, outliers are identified and removed through the isolation forest algorithm. The isolation forest algorithm randomly divides the ship power parameter set, quickly locates outliers and removes them from the ship power parameter set, thereby ensuring the reliability of the data. In specific operations, the isolation forest algorithm constructs multiple isolated trees and calculates the path length of each sample point of the ship power parameter in the isolated tree. Sample points with shorter paths are considered to be outliers and are removed. This unsupervised learning method can not only efficiently identify outliers, but also maintain the overall integrity of the data set, ensuring the accuracy of subsequent analysis. After noise reduction and outlier removal, standardization is performed to facilitate subsequent analysis and processing. First, the Min-Max normalization method is used to map the value range of each ship power parameter to the [0, 1] interval to eliminate the influence of different dimensions. In this way, all ship power parameters are converted to a unified scale to make them comparable. For categorical variables, such as navigation task priority weights, the One-Hot encoding method is used. One-Hot encoding converts each categorical value into an independent binary vector. For example, the navigation task priority can be represented as different binary vectors, each vector corresponding to a priority level. This encoding method converts categorical variables into numerical vectors, so that they can be directly used by machine learning algorithms. The pre-processed ship power parameters are integrated through data fusion and structured packaging technology to generate standardized data packets. These standardized data packets not only eliminate noise interference and outliers, but also unify the data format to facilitate subsequent analysis, providing a solid foundation for subsequent energy management and safety monitoring.

[0027] Quantum annealing optimization module: After receiving the standardized data packet, the quantum chip maps the hydrogen ship power parameters into the Ising model, and generates control instructions by taking into account the hydrogen fuel consumption rate, equipment life attenuation coefficient and navigation mission priority weight.

[0028] The specific steps include: When the standardized data packet is transmitted to the quantum chip, the quantum chip performs parsing and encoding processing. In order to meet the requirements of the quantum computing framework, a specific encoding method is used to convert different types of parameters in the standardized data packet into physical quantities such as antiferromagnetic coupling strength, local magnetic field bias, and constrained energy terms. The specific operations are as follows: Firstly, the interaction between various ship power parameters is identified and quantified by correlation analysis, and the nonlinear coupling coefficient matrix is ​​generated by partial least squares regression. Meanwhile, the nonlinear coupling coefficient matrix is ​​normalized by probability amplitude through quantum state density function, and the nonlinear coupling coefficient matrix is ​​energy-scaled by Ising parameter linear transformation to map the nonlinear coupling coefficient matrix into antiferromagnetic coupling strength. Secondly, for the influence of external environmental factors such as seawater temperature and flow rate on the propulsion process, the environmental modeling analysis method is used to obtain the influence pattern of external environmental factors on the ship propulsion performance through wavelet multi-scale analysis, and the parameterized conversion method is used to convert the influence pattern into a local magnetic field bias through local field parameter encoding; In addition, based on the standardized data packets, dynamic weight allocation is performed using particle swarm optimization through a priority algorithm to obtain constraint energy items to meet hard requirements such as navigation mission priority; The core of the encoding method is to abstract the complex multi-objective optimization problem into the physical quantity relationship in the Ising model, so as to facilitate the subsequent quantum simulation and optimization solution. In this process, an adaptive weight allocation algorithm is combined to dynamically adjust the weights for different optimization objectives to ensure that each objective can be reasonably balanced in the global optimization. Based on the encoded antiferromagnetic coupling strength, local magnetic field bias and constrained energy terms, the matrix operation framework of TensorFlow is used in the quantum simulation algorithm to dynamically synthesize the antiferromagnetic coupling matrix and local magnetic field vector, and the constrained energy terms are designed in combination with the adaptive weight allocation algorithm. A multi-objective energy function of the Ising model is constructed through multi-objective optimization modeling technology. At the same time, the interaction between power parameters, external environmental factors and task priority requirements are integrated into a unified multi-objective energy function expression to map the power parameters of hydrogen ships to the Ising model. After completing the mapping of ship power parameters, the multi-objective optimization stage begins. In this stage, the custom layer superposition technology based on TensorFlow is used to realize the fusion of antiferromagnetic coupling matrix, local magnetic field vector and constraint energy term. The dynamic weight distribution mechanism of the integrated LSTM network is used to adaptively adjust the constraint strength according to the real-time working condition data of the ship, and a multi-objective optimization Hamiltonian model is constructed. The multi-objective optimization Hamiltonian model comprehensively considers multiple optimization objectives, and comprehensively expresses the antiferromagnetic coupling matrix, local magnetic field vector and constraint energy term as a total energy function. In order to solve the total energy function, the simulated annealing algorithm is used. The simulated annealing algorithm is a global optimization method. It is particularly suitable for complex multi-objective optimization problems. In the specific operation, the parameters of the simulated annealing algorithm are initialized, including the initial temperature and cooling rate. Then, in each iteration, a new solution is randomly generated according to the current temperature and Hamiltonian model, and its energy value is evaluated. If the energy value of the new solution is lower, the solution is accepted. Otherwise, the new solution is accepted according to the current temperature and energy difference to avoid falling into the local optimal solution. Through the simulated annealing algorithm, the global optimal solution can be gradually approached in the complex solution space. At the same time, the distributed computing technology is fully utilized to assign the computing tasks of the simulated annealing algorithm to multiple nodes for parallel execution, which further shortens the solution time and improves the computing efficiency. After multiple iterations, the simulated annealing algorithm finally determines the spin state parameters. The spin state parameters are the embodiment of the multi-objective optimization results. They specifically reflect the optimal configuration of fuel cell power and hydrogen production rate under the constraints of meeting energy demand and equipment life management. Based on the spin state parameters, the control instructions of fuel cell power and hydrogen production rate are dynamically generated. In the specific operation, the feature extraction technology of the attention mechanism is used to analyze the spin state parameters through sliding window segmented sampling, and the optimization results related to fuel cell power and hydrogen production rate are extracted through the gradient boosting regression technology. Based on these results, specific control instructions are generated, including fuel cell power adjustment instructions, hydrogen production rate setting instructions and equipment collaborative linkage instructions. These control instructions directly guide the working status of fuel cells and hydrogen production equipment to ensure that they operate under optimal conditions. In order to further improve stability and reliability, a closed-loop feedback mechanism is designed to monitor the actual operating status of fuel cells and hydrogen production equipment in real time, and dynamically adjust the control instructions according to the feedback information to ensure continuous optimization. Through the above operations, through the combination of multiple advanced technical means, not only the response speed and accuracy are improved, but also the stability and security are significantly enhanced.

[0029] The proton membrane control module inputs control instructions into the simulation model of the proton exchange membrane, dynamically adjusts the hydrogen production rate and fuel cell power, and outputs real-time hydrogen storage tank pressure data.

[0030] The specific steps include: Based on the received control instructions, the initial hydrogen production rate setting value and the fuel cell power output are extracted. The hydrogen production rate setting value is the target value of hydrogen production per unit time of the hydrogen production equipment determined by the multi-objective optimization algorithm. The initial hydrogen production rate setting value and the fuel cell power output are dynamically loaded into the simulation model of the proton exchange membrane. The simulation model of the proton exchange membrane is a highly accurate mathematical model that can simulate the working state of the proton exchange membrane, including the process of hydrogen production by electrolysis of water and the electrochemical reaction of the fuel cell. The difference between the hydrogen generation and consumption rates is calculated synchronously through the mass conservation equation. The mass conservation equation ensures the balance between input and output, that is, the amount of hydrogen generated must be equal to the amount of hydrogen consumed plus the remaining hydrogen in the hydrogen storage tank. This step provides basic data for subsequent real-time corrections. The specific mathematical formula is: ;in, represents the sampling time, Indicates The difference between the hydrogen generation and consumption rates at the sampling moment, Indicates the initial hydrogen production rate setting value, Indicates The output value of the PID controller at the sampling time, Indicates The real-time power output value of the fuel cell at the sampling moment, represents the energy conversion efficiency of the fuel cell, Indicates the energy value released when a unit mass of hydrogen is completely burned; Based on the difference between hydrogen generation and consumption rates, PID control algorithm and fluid mechanics algorithm are used for real-time correction. PID control algorithm is a classic closed-loop control algorithm used to adjust the initial hydrogen production rate setting value. Its principle is to process the difference through three parts: proportional (P), integral (I) and differential (D), so as to achieve precise control. In specific operations, the expected value is first defined based on the dynamic balance between the hydrogen production rate setting value and the fuel cell power output and the change curve of the hydrogen storage tank pressure. When it is detected that the difference between the hydrogen generation and consumption rates deviates from the expected value, the PID controller will dynamically adjust the initial hydrogen production rate setting value according to the current difference, cumulative difference and the rate of change of the difference, so as to reduce the error and return the hydrogen content to a stable state. At the same time, the adaptive feedback regulation mechanism combined with the equivalent circuit dynamically adjusts the fuel cell power output. The equivalent circuit constructs a dynamic hybrid model of the fuel cell and uses online parameter identification technology combined with the maximum power point tracking algorithm to dynamically optimize the battery power output. The dynamic hybrid model is a simplified representation of the electrochemical process inside the fuel cell. It takes into account electrical characteristics such as resistance, capacitance and inductance. By monitoring the actual output voltage and current of the fuel cell, the resistance, capacitance and inductance parameters in the equivalent circuit can be adjusted in real time to optimize the power output of the fuel cell. This adaptive feedback regulation mechanism not only improves the response speed, but also enhances robustness and stability. Based on the corrected hydrogen production rate set value and the adjusted fuel cell power output, the Runge-Kutta numerical integration method is used to solve the hydrogen storage tank pressure change curve and obtain real-time hydrogen storage tank pressure data. This process first starts with establishing a hydrogen storage tank pressure change model. According to the ideal gas law or the actual gas state equation, the dynamic relationship between hydrogen flow and pressure is established through mass conservation differential, and the finite volume discretization and nonlinear correction technology are combined to construct a mathematical model to describe the gas state change in the hydrogen storage tank. This hydrogen storage tank pressure change model takes into account the influence of multiple factors on the hydrogen storage tank pressure, such as temperature, volume and molar number, to ensure that it can accurately reflect the actual situation inside the hydrogen storage tank. Next, a series of key parameters are initialized, including the initial pressure and temperature of the hydrogen storage tank. These initial key parameters are crucial for subsequent accurate calculations because they provide a starting point for the entire simulation process. After the key parameters are initialized, the fourth-order Runge-Kutta method (RK4) is used to perform numerical solution based on the hydrogen storage tank pressure change model. In the specific operation, the four local approximations of the hydrogen pressure state quantity in the current hydrogen storage tank within the time step are recursively predicted, and four intermediate points are obtained based on the Taylor expansion truncation error control. The slopes of the four intermediate points are calculated at the same time, and the hydrogen pressure state quantity in the hydrogen storage tank at the next time step is obtained based on the weighted average of these slopes. The hydrogen storage tank pressure change curve over time is finally generated through the adaptive step control technology to obtain the hydrogen storage tank pressure data. These hydrogen storage tank pressure data not only reflect the actual pressure change of hydrogen in the hydrogen storage tank, but also provide an important basis for subsequent energy management and safety monitoring. For example, under high load conditions, the hydrogen production rate and fuel cell power output can be dynamically adjusted according to the real-time hydrogen storage tank pressure data to ensure the adequacy and stability of hydrogen supply. In addition, through the adaptive feedback adjustment mechanism, potential problems can be discovered and corrected in time to avoid energy waste or safety hazards caused by insufficient or excessive hydrogen. Through the above operations, the simulation model of proton exchange membrane provides a solid technical guarantee for the efficient operation of hydrogen-powered ships.

[0031] Safety monitoring module, based on real-time hydrogen storage tank pressure data, the hydrogen energy closed-loop monitoring unit dynamically adjusts the electrolysis current and fuel cell power ratio, simultaneously monitors hydrogen purity and oxygen residue, and triggers the three-level safety protocol to output electrolysis waste heat temperature, coolant flow and safety status code.

[0032] The specific steps include: Based on the real-time hydrogen storage tank pressure data, Kalman filtering technology is used to remove noise interference to ensure the accuracy and stability of the data. The hydrogen storage tank pressure data after noise reduction is input into the long short-term memory network (LSTM) for trend prediction. LSTM is a deep learning model. Its construction process is as follows: based on the input structure of the time series sliding window, a three-layer gated network is built through the Keras framework, where the input layer has 64 units, the hidden layer has 32 units, and the output layer has 1 unit. At the same time, the Sigmoid and Tanh activation functions are combined to realize the dynamic adjustment of the forget gate, input gate and output gate to complete the construction of the long short-term memory network model. Next, training is carried out, using the historical hydrogen storage tank pressure time series data for supervised learning, using the mean square error as the loss function, and the Adam optimizer for gradient descent. The Dropout layer and early stopping mechanism are introduced to prevent overfitting, and finally the trained long short-term memory network model is obtained; After training, the long short-term memory network model is particularly suitable for processing time series data and can capture long-term dependencies. By learning the historical hydrogen storage tank pressure data, LSTM can predict the pressure change trend in the future, including possible pressure peaks or downward trends. Based on the results of the pressure change trend prediction, combined with the ship's operating conditions and safety requirements, a dynamic safety pressure threshold is generated, which not only considers the current pressure state, but also integrates future trend predictions, providing a solid foundation for subsequent operations; The hydrogen energy closed-loop monitoring unit calculates the difference between the real-time hydrogen storage tank pressure and the safety pressure threshold according to the deviation percentage between the two, and divides it into different deviation levels, such as slight deviation, moderate deviation and severe deviation. Each level corresponds to a different adjustment intensity weight, which is used to guide the subsequent dynamic adjustment operation. In the specific operation, the deviation percentage between the real-time hydrogen storage tank pressure and the safety pressure threshold is first calculated, and then the deviation is divided into different levels according to the pre-set standards. For example, if the deviation is less than 5%, it is a slight deviation, if the deviation is between 5% and 10%, it is a moderate deviation, and if the deviation exceeds 10%, it is a severe deviation. Each deviation level corresponds to a specific adjustment intensity weight, and the electrolysis current and fuel cell power ratio are dynamically adjusted according to the adjustment intensity weight. For example, in the case of slight deviation, the electrolysis current is increased to accelerate the hydrogen production rate, and the fuel cell power is limited to reduce hydrogen consumption. In the case of severe deviation, the electrolysis current is reduced to slow down the hydrogen production rate, and the power output of the fuel cell is reduced rather than increased to reduce hydrogen consumption. This hierarchical adjustment strategy ensures flexibility and robustness under different working conditions, thereby maintaining stable operation of the ship; After dynamically adjusting the electrolysis current and fuel cell power ratio, the electrolysis waste heat temperature, coolant flow, hydrogen purity and oxygen residue are monitored synchronously to ensure the safe operation of the equipment. The electrolysis waste heat temperature is monitored in real time by the temperature sensor installed on the electrolysis equipment and transmitted to the control center. The control center determines whether the electrolysis equipment is within the safe working range based on the data of the electrolysis waste heat temperature, and starts the cooling pump as needed. The cooling pump adjusts the coolant flow. The adjusted coolant flow is monitored in real time by the flow meter and fed back to the control center. The acquisition of hydrogen purity and oxygen residue is mainly achieved through gas sensors. The hydrogen purity sensor is used to detect the impurity content in the generated hydrogen in real time to ensure that the hydrogen purity meets the working requirements of the fuel cell. At the same time, the oxygen residue sensor is used to monitor the amount of oxygen that may remain during the electrolysis process to prevent safety hazards caused by oxygen mixing into hydrogen. The monitoring data of electrolysis waste heat temperature, coolant flow, hydrogen purity and oxygen residue not only assist in real-time understanding of the working status of the electrolysis equipment, but also support other control decisions, such as adjusting the electrolysis current or fuel cell power output; To further improve safety, the hydrogen energy closed-loop monitoring unit defines multi-dimensional thresholds through hydrogen storage tank pressure, hydrogen purity, oxygen residue and electrolysis waste heat temperature, and classifies them into three levels of safety protocols: level one warning, level two production restriction and level three emergency shutdown; Based on the three-level safety protocol, the first-level threshold, second-level threshold and third-level threshold are defined by analyzing the safety range of hydrogen storage tank pressure, hydrogen purity, residual oxygen content and electrolysis waste heat temperature. When any parameter among the hydrogen storage tank pressure, hydrogen purity, residual oxygen content and electrolysis waste heat temperature exceeds the first-level threshold, a first-level warning is issued to prompt the operator to pay attention. At this time, some preventive measures are automatically taken, such as fine-tuning the electrolysis current or slightly reducing the fuel cell power output, to prevent the pressure from continuing to rise; If any of the parameters of the hydrogen storage tank pressure, hydrogen purity, residual oxygen and electrolysis waste heat temperature continues to deteriorate and reaches the secondary threshold, the secondary production limit state is entered. At this time, the power output of the fuel cell is limited, and backup energy such as lithium battery packs are started to reduce dependence on hydrogen. At the same time, auxiliary data such as electrolysis waste heat temperature and coolant flow are output for reference by operators. For example, when the hydrogen storage tank pressure continues to rise and reaches the secondary threshold, the power output of the fuel cell is automatically reduced, and the lithium battery pack is started as a temporary power source to ensure that basic operation is maintained without increasing hydrogen consumption. In addition, the electrolysis waste heat temperature and coolant flow are monitored in real time to ensure the normal operation of the equipment and prevent equipment damage due to overheating or other problems; When any of the parameters of hydrogen storage tank pressure, hydrogen purity, oxygen residue and electrolysis waste heat temperature reaches the third-level threshold, the emergency shutdown protocol is immediately triggered. At this time, all high-risk equipment such as fuel cells and electrolysis equipment will be forced to shut down, and a safety status code will be output to ensure the overall safety of the ship. For example, when the hydrogen storage tank pressure rises sharply and exceeds the third-level threshold, all related equipment will be stopped immediately, and a safety status code will be output to notify the operator to take further safety measures. The emergency shutdown mechanism is the last line of defense, ensuring that the source of danger can be quickly cut off in extreme cases to protect the safety of the ship and personnel; Through the above operations, comprehensive monitoring of the hydrogen storage tank pressure, hydrogen purity, oxygen residue and electrolysis waste heat temperature is achieved, ensuring efficient operation and safety under various working conditions and avoiding potential safety hazards.

[0033] The waste heat recovery and self-check module is based on the parameters of electrolysis waste heat temperature and coolant flow rate. The waste heat recovery converter uses phase change materials to increase the coolant temperature and reduce cooling energy consumption. At the same time, the quantum chip performs a self-check of the equipment health.

[0034] The specific steps include: In order to achieve efficient waste heat recovery, the finite element analysis (FEA) is used to construct a phase change material thermal behavior simulation model based on the parameters of electrolytic waste heat temperature and coolant flow rate. Finite element analysis is a numerical simulation method that is widely used in engineering fields, especially in heat conduction and fluid mechanics. The parameters of electrolytic waste heat temperature and coolant flow rate are input into the finite element analysis tool to construct a detailed phase change material thermal behavior simulation model. The phase change material thermal behavior simulation model takes into account various thermophysical parameters of the phase change material, such as melting point, latent heat, etc., as well as the dynamic characteristics of the coolant flow, to ensure that the performance of the phase change material under different working conditions can be accurately predicted. Through the phase change material thermal behavior simulation model, the heat transfer during the cooling process can be accurately simulated, thereby providing a basis for subsequent optimization; Based on the simulation model of thermal behavior of phase change materials, a virtual PID controller is used to adjust the virtual coolant flow parameters to simulate different operating conditions and find the best flow control strategy. This not only improves the coolant temperature and reduces external energy consumption, but also ensures the efficient operation of the ship. According to the generated optimal flow control strategy, the cooling pump is guided to adjust the actual coolant temperature. For example, when the temperature of electrolytic waste heat rises, the coolant flow rate is automatically increased to take away more heat. When the temperature returns to normal, the coolant flow rate is reduced to save energy. This intelligent dynamic adjustment mechanism not only improves the energy efficiency of the cooling process, but also extends the service life of the equipment. At the same time, the quantum chip performs the equipment health self-check function. First, the quantum annealing algorithm is used to analyze the power parameters of the hydrogen-powered ship, efficiently find the global optimal solution, and achieve the optimal configuration of the ship's power parameters to ensure that the equipment can operate in the best state. In addition, the deep neural network (DNN) is used to predict potential failure modes. The deep neural network is a powerful machine learning model that can learn complex patterns and laws from a large number of historical hydrogen-powered ship power parameters, and predict possible failure modes such as overheating and pressure abnormalities based on the real-time collected hydrogen-powered ship power parameters. In order to ensure the accuracy of the deep neural network model, a large number of historical hydrogen-powered ship power parameters are used for training, including the power parameters of hydrogen-powered ships under normal operating conditions and the power parameters of hydrogen-powered ships under various fault conditions. The prediction results of the failure mode obtained provide an important reference for subsequent maintenance and overhaul. For example, when the deep neural network model predicts that a key component is about to fail, the control center will issue an alarm in advance and recommend taking corresponding preventive measures; In order to further improve the accuracy and efficiency of equipment health self-check, reinforcement learning technology is used to dynamically adjust the detection strategy. Reinforcement learning is a machine learning method that learns the best action strategy through trial and error. By designing a reinforcement learning framework, the detection strategy is continuously optimized based on the feedback of real-time equipment health self-check. For example, during the detection process, if a sensor reading is found to be abnormal, the detection frequency is automatically increased or the detection range is expanded to more comprehensively evaluate the equipment status. In this way, potential problems can be responded to quickly and measures can be taken in time to avoid downtime or accidents caused by failures. Through the above operations, the cooling process is optimized, which can reduce external energy consumption while improving overall energy efficiency. At the same time, the equipment health self-check operation can promptly detect and solve potential problems and avoid downtime or accidents caused by faults.

[0035] The maintenance feedback module generates a maintenance recommendation report based on the self-inspection results and uploads it to the shore-based data center.

[0036] The specific steps include: After the quantum chip completes the self-check of the equipment health, it generates a detailed maintenance recommendation report based on the self-check results. First, it collects and analyzes the data of all relevant sensors, including electrolysis waste heat temperature, coolant flow, hydrogen purity, oxygen residue, etc. Sensor data is the basis for evaluating the health of the equipment. Any abnormal value may indicate a potential problem. For example, if the pressure value detected by a sensor is continuously higher than the normal range, the control center will record the abnormality and include it in the maintenance recommendation report. The maintenance recommendation report specifically points out the potential failure modes predicted by the deep neural network and proposes corresponding preventive measures. At the same time, in order to combine the information in the expert knowledge base, which contains a large number of best practices and solutions to common problems in equipment maintenance, the control center automatically matches the self-test results with the entries in the knowledge base and extracts relevant maintenance suggestions. For example, if a sensor reading is abnormal, the control center will search the expert knowledge base for similar treatment methods and add them to the maintenance recommendation report. This method of combining machine learning and expert knowledge makes the maintenance recommendation report both scientifically based and practically feasible. After the maintenance recommendation report is generated, it is first encrypted and transmitted to the shore-based data center using a secure and reliable communication protocol (such as HTTPS or MQTT). This method not only ensures security, but also effectively prevents the data in the maintenance recommendation report from being tampered with or lost during transmission. The shore-based data center receives and saves the maintenance recommendation report from the ship for subsequent query and analysis; After receiving the maintenance recommendation report, the shore-based data center will further process and analyze it to find potential trends and patterns. For example, by comparing and analyzing the data in the historical maintenance recommendation reports of multiple ships, the average service life of certain components can be found, thus providing a reference for future maintenance plans. In addition, the shore-based data center can also use big data analysis tools (such as Hadoop or Spark) to quickly process and mine massive data to find valuable information hidden behind the data in the maintenance recommendation report. For example, by analyzing the equipment failure rate in different sea areas and seasons, the team can formulate a more reasonable maintenance strategy and improve overall operational efficiency. Through the above operations, a maintenance recommendation report is generated, which significantly improves the reliability and operation and maintenance efficiency of the ship's power propulsion. The shore-based data center identifies potential trends and patterns through analysis, which not only reduces equipment failure rate and downtime, but also improves overall operational efficiency.

[0037] In summary, the present invention can dynamically adjust the output power of hydrogen fuel cells and lithium battery packs according to real-time navigation conditions by real-time acquisition and processing of power parameters of hydrogen ships, and generate accurate control instructions using advanced Kalman filter algorithms and quantum annealing optimization technology, thereby significantly improving the overall energy efficiency of ships. The invention adopts an efficient hydrogen energy closed-loop monitoring unit and a three-level safety protocol, dynamically adjusts the ratio of electrolysis current to fuel cell power based on real-time hydrogen storage tank pressure data, and matches different adjustment intensity weights according to the deviation level, which not only improves the response speed and accuracy, but also significantly enhances stability and safety, ensuring that ships can operate reliably under complex working conditions and reducing potential safety risks.

[0038] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An extended-range hydrogen fuel-powered ship propulsion system, characterized in that: include, The acquisition module uses the Kalman filter algorithm to eliminate noise interference from the collected hydrogen ship power parameters and generate a standardized data packet; Quantum annealing optimization module: After receiving the standardized data packet, the quantum chip maps the hydrogen ship power parameters into the Ising model and generates control instructions based on the hydrogen fuel consumption rate, equipment life attenuation coefficient and navigation mission priority weight; The proton membrane control module inputs control instructions into the simulation model of the proton exchange membrane, dynamically adjusts the hydrogen production rate and fuel cell power, and outputs real-time hydrogen storage tank pressure data; Safety monitoring module: Based on the real-time hydrogen storage tank pressure data, the hydrogen energy closed-loop monitoring unit dynamically adjusts the electrolysis current and fuel cell power ratio, simultaneously monitors the hydrogen purity and oxygen residue, and triggers the three-level safety protocol to output the electrolysis waste heat temperature, coolant flow rate and safety status code; Waste heat recovery and self-check module: Based on the parameters of electrolysis waste heat temperature and coolant flow rate, the waste heat recovery converter uses phase change materials to increase the coolant temperature and reduce cooling energy consumption, while the quantum chip performs equipment health self-check; The maintenance feedback module generates a maintenance recommendation report based on the self-inspection results and uploads it to the shore-based data center.

2. The extended-range hydrogen fuel-powered ship propulsion system according to claim 1, characterized in that: The power parameters of the hydrogen-powered ship include: the remaining power of the lithium battery pack, the internal pressure of the hydrogen storage tank, the real-time power demand of the propeller, the temperature of the fuel cell stack, the seawater flow rate, the draft depth of the ship, the hydrogen fuel consumption rate, the equipment life attenuation coefficient and the navigation mission priority weight.

3. The extended-range hydrogen fuel powered ship propulsion system according to claim 1, characterized in that: The steps for obtaining the standardized data packet are as follows: The collected hydrogen ship power parameters are subjected to multimodal data denoising through Kalman filtering, and after outliers are removed using the isolation forest algorithm, Min-Max normalization and One-Hot encoding are used to generate standardized data packets.

4. The extended-range hydrogen fuel powered ship propulsion system according to claim 1, characterized in that: The steps of mapping the hydrogen ship power parameters to the Ising model are as follows: The hydrogen fuel consumption rate is encoded as the antiferromagnetic coupling strength, the equipment life decay coefficient is mapped to the local magnetic field bias, and the navigation mission priority is converted into a constrained energy term; Based on the antiferromagnetic coupling strength, local magnetic field bias and constrained energy terms, a multi-objective energy function of the Ising model is constructed in the quantum simulation algorithm, and the propulsion parameters of hydrogen ships are mapped to the Ising model.

5. The extended-range hydrogen fuel-powered ship propulsion system according to claim 4, characterized in that: The steps of obtaining the control instruction are as follows: After mapping the hydrogen ship power parameters to the Ising model, the antiferromagnetic coupling matrix, local magnetic field vector and constraint energy term are dynamically synthesized through the matrix operation framework of TensorFlow, and combined with the adaptive weight allocation algorithm, a multi-objective optimization Hamiltonian model is constructed; Based on the multi-objective optimization Hamiltonian model, the simulated annealing algorithm is used to iteratively solve the problem in the TensorFlow computing framework, and the spin state parameters are obtained by using distributed computing. According to the spin state parameters, control instructions for fuel cell power and hydrogen production rate are dynamically generated.

6. The extended-range hydrogen fuel powered ship propulsion system according to claim 1, characterized in that: The steps for obtaining the real-time hydrogen storage tank pressure data are as follows: Based on the control instructions, the hydrogen production rate setting value and the fuel cell power output are extracted and dynamically loaded into the simulation model of the proton exchange membrane, and the difference between the hydrogen generation and consumption rates is simultaneously calculated through the mass conservation equation; Based on the difference between hydrogen generation and consumption rates, the PID control algorithm and fluid dynamics algorithm are used to correct the set value of hydrogen production rate in real time, and the adaptive feedback adjustment mechanism of the equivalent circuit is combined to dynamically adjust the fuel cell power output; Based on the corrected hydrogen production rate set value and the adjusted fuel cell power output, the hydrogen storage tank pressure change curve is solved by Runge-Kutta numerical integration to obtain real-time hydrogen storage tank pressure data.

7. The extended-range hydrogen fuel-powered ship propulsion system according to claim 6, characterized in that: The hydrogen energy closed-loop monitoring unit dynamically adjusts the ratio of electrolysis current to fuel cell power, the steps are as follows: Based on the real-time hydrogen storage tank pressure data, the pressure trend is predicted through Kalman filtering combined with long short-term memory network to generate a safe pressure threshold; The hydrogen energy closed-loop monitoring unit calculates the deviation percentage between the real-time hydrogen storage tank pressure and the safety pressure threshold, and divides the deviation levels. It matches different adjustment intensity weights according to the deviation levels and dynamically adjusts the ratio of electrolysis current to fuel cell power.

8. The extended-range hydrogen fuel powered ship propulsion system according to claim 1, characterized in that: The three-level security protocol specifically includes: Define multi-dimensional thresholds based on hydrogen storage tank pressure, hydrogen purity, residual oxygen and electrolysis waste heat temperature; The multi-dimensional thresholds are graded into level one warning, level two production restriction and level three emergency shutdown.

9. The extended-range hydrogen fuel powered ship propulsion system according to claim 1, characterized in that: The steps of the waste heat recovery converter to increase the coolant temperature and reduce the cooling energy consumption by using phase change materials are as follows: Based on the real-time data of electrolysis waste heat temperature and coolant flow, a simulation model of the thermal behavior of phase change materials is constructed through finite element analysis; Based on the thermal behavior simulation model of phase change materials, a virtual PID controller is used to adjust the virtual coolant flow parameters and generate the optimal flow control strategy. At the same time, the optimal flow control strategy is used to guide the cooling pump to adjust the actual coolant temperature.

10. The extended-range hydrogen fuel powered ship propulsion system according to claim 1, characterized in that: The steps for the quantum chip to perform a device health self-check are as follows: The quantum chip uses a quantum annealing algorithm to analyze the power parameters of hydrogen ships and predicts fault modes through a deep neural network. It also dynamically adjusts the detection strategy based on reinforcement learning to achieve self-inspection of equipment health.

Images