An energy management method of a hydrogen-electricity combined supply system based on intelligent control

Abstract

The application is an energy management method of hydrogen electricity combined supply system based on intelligent control, comprising the following steps: establishing a heat and electricity coupling heat transfer model; performing an online electric pile working point optimization algorithm based on gradient descent, taking the maximization of system comprehensive energy efficiency as an objective function, considering the electric pile safety working range, hydrogen storage capacity and heat demand constraint, and updating the working point of the fuel cell electric pile in real time; performing a master-slave type multi-electric pile coordinated control strategy, the master controller collects electric pile operation parameters and system electric and heat demand, calculates the reference load of each electric pile, and the slave controller adjusts the electric pile operation parameters to track the reference load; and performing heat energy conversion optimization to recover waste heat. The application effectively solves the technical problems of the existing hydrogen electricity combined supply system, such as uncoordinated heat and electricity coupling, single multi-electric pile control strategy and poor off-grid variable load adaptability, and has the effects of energy efficiency improvement, operation cost reduction and carbon emission reduction.

Description

Technical Field

[0001] This invention relates to the field of clean energy technology, and in particular to an energy management method for a hydrogen-power cogeneration system based on intelligent control. Background Technology

[0002] Hydrogen energy, as a highly efficient, clean, and sustainable secondary energy source, boasts high energy density and a wide range of sources. Through the conversion and storage of "green electricity-green hydrogen" driven by renewable energy sources such as photovoltaics, and combined with fuel cells to convert hydrogen energy into electricity and heat energy on demand, a complete "hydrogen-energy" closed loop can be constructed, providing low-carbon energy supply for off-grid scenarios such as construction sites, emergency rescue, and remote areas without grid access.

[0003] Existing technologies have developed combined hydrogen power (CHP) systems that integrate water electrolysis for hydrogen production, hydrogen storage, fuel cell power generation, and waste heat recovery. However, in practical applications, such systems still face the following technical challenges:

[0004] (1) Incomplete thermoelectric coupling modeling: Existing studies mostly model hydrogen production by water electrolysis and fuel cell power generation as independent links, lacking integrated analysis of the thermoelectric coupling heat transfer process of the entire system. This makes it difficult to achieve accurate coordination of the thermoelectric ratio in system energy management, affecting the overall energy utilization efficiency.

[0005] (2) Single multi-stack coordination control strategy: Existing high-power hydrogen cogeneration systems usually use multiple fuel cell stacks to operate in parallel to meet power demand. However, their coordination control is mostly based on power average distribution or a simple distribution method that only considers stack efficiency. It does not take into account the capacity differences and remaining life of each stack at the same time, which leads to the accelerated aging of some stacks due to overload, uneven life of the whole system, and reduced system economy and operational reliability.

[0006] (3) Poor load adaptability: Existing energy management methods are mainly designed for grid-connected scenarios or stable load conditions. For off-grid scenarios, the photovoltaic output fluctuates greatly and the construction load is complex and variable. There is a lack of control strategies that can optimize the stack operating point in real time and dynamically adjust the thermoelectric ratio, making it difficult to ensure the efficient and stable operation of the system in a wide range of operating conditions.

[0007] Therefore, there is an urgent need for an energy management method for hydrogen cogeneration systems that can establish a complete thermoelectric coupling model, achieve coordinated and optimized control of multiple fuel cell stacks, and adapt to off-grid variable load conditions. Summary of the Invention

[0008] The present invention aims to address the shortcomings of the prior art by providing an energy management method for a hydrogen-power cogeneration system based on intelligent control.

[0009] To achieve the above objectives, the present invention adopts the following technical solution: an energy management method for a hydrogen-power cogeneration system based on intelligent control, comprising the following steps:

[0010] S1: Establish a thermoelectric coupling heat transfer model, including a water electrolysis hydrogen production heat generation model, a fuel cell heat generation and heat transfer model, and a heat exchanger model; among them, the water electrolysis hydrogen production heat generation model is used to calculate the heat generation amount of the water electrolysis hydrogen production unit during the water electrolysis hydrogen production process; the fuel cell heat generation and heat transfer model is used to calculate the heat generation amount and heat transfer amount of the fuel cell power generation unit during the fuel cell power generation process; the heat exchanger model is used to calculate the heat exchange amount of the waste heat recovery unit during the waste heat recovery process;

[0011] S2: Execute an online fuel cell stack operating point optimization algorithm based on gradient descent, with the objective function of maximizing the overall system energy efficiency. Considering the safe operating range of the fuel cell stack, hydrogen storage capacity, and thermal demand constraints, update the operating point of the fuel cell stack in real time and determine the total reference current of the system. ;

[0012] S3: Executes a master-slave multi-stacking coordinated control strategy. The master controller in the intelligent control unit collects the operating parameters of each stack and the system's electrothermal demand. The reference load of each stack is calculated according to the load distribution algorithm. The slave controller in the intelligent control unit adjusts the operating parameters of each stack to track the reference load, thereby achieving balanced operation of multiple stacks and modular expansion.

[0013] S4: Perform thermal energy conversion optimization, recover waste heat by optimizing the heat exchanger, and recover hydrogen thermal energy from the exhaust gas of the fuel cell power generation unit through the zero-emission hydrogen combustion device in the waste heat recovery unit.

[0014] In step S3, the load allocation factor is calculated based on a weighted average of efficiency, capacity, and lifetime. The calculation method is as follows: ;

[0015] In the formula, Let be the load allocation factor for the i-th stack; Let be the efficiency of the i-th fuel cell stack; The maximum output power of the i-th fuel cell stack; The weighting factor for the i-th fuel cell stack is determined by the remaining lifetime of the stack. Specifically, it is 1.00 when the remaining lifetime of the stack is 100% and 0.60 when the remaining lifetime of the stack is 60%. This refers to the number of fuel cells;

[0016] Furthermore, the master-slave multi-stacking coordinated control strategy determines the total system reference current in step S2. Based on this, the total reference current of the system is determined according to The optimization algorithm is decomposed into individual fuel cells, achieving closed-loop coupling between the optimization algorithm and the control strategy. Let be the reference current for the i-th fuel cell stack.

[0017] Specifically, in step S1, the thermal generation model for hydrogen production through water electrolysis is as follows: ;

[0018] In the formula, This is the electrolysis current; Battery voltage; This is the voltage of a reversible battery; Operating temperature; This represents the entropy change of the electrolysis reaction; The number of electrons transferred; It is Faraday's constant;

[0019] The voltage of a reversible battery is expressed as: ;

[0020] In the formula, The standard battery voltage at 298 K, i.e. =1.229 V; R is the gas constant, i.e. =8.314 J / (mol·K); , , These represent the pressures of hydrogen, oxygen, and water vapor on the electrode surface, respectively, in Pa.

[0021] Specifically, in step S1, the fuel cell heat generation model is as follows: ;

[0022] In the formula, This represents the total output power of the fuel cell stack. For electrical efficiency.

[0023] Specifically, in step S1, the heat exchanger model uses the logarithmic mean temperature difference method: ;

[0024] In the formula, The overall heat transfer coefficient; For heat exchange area; The temperature difference is the logarithmic mean.

[0025] Specifically, in step S2, the objective function is: ;

[0026] In the formula, For overall energy efficiency; For the electrical energy output of the fuel cell stack; The heat energy recovered by the heat exchanger; The electrical energy input is for the electrolysis of water to produce hydrogen.

[0027] Specifically, in step S2, the constraints include: fuel cell stack current density range: 0.2-1.0 A / cm². 2 ;

[0028] The hydrogen flow rate meets the requirements of the fuel cell stack.

[0029] Fuel cell stack operating temperature range: 50-80℃;

[0030] Hydrogen storage pressure range: 15-20 MPa.

[0031] Specifically, in step S4, the optimization of the heat exchanger fin geometry parameters adopts the response surface methodology, using fin thickness, fin spacing, and fin height as independent variables, and the overall heat transfer coefficient as the response value to establish a regression model:

[0032] ;

[0033] In the formula, This refers to the fin thickness; This refers to the fin spacing; This refers to the fin height; is the regression coefficient.

[0034] In particular, the hydrogen-electricity cogeneration system applied by this method includes a photovoltaic power generation unit, a water electrolysis hydrogen production unit, a hydrogen storage unit, a fuel cell power generation unit, a waste heat recovery unit, and an intelligent control unit. Moreover, the system is configured to operate independently of the municipal power grid and is suitable for low-carbon energy supply in off-grid scenarios.

[0035] Photovoltaic power generation units are used to convert solar energy into electrical energy;

[0036] The water electrolysis hydrogen production unit is connected to the photovoltaic power generation unit, including a proton exchange membrane electrolyzer, which is used to use electrical energy to electrolyze water to produce hydrogen and oxygen.

[0037] The hydrogen storage unit is connected to the water electrolysis hydrogen production unit and adopts a high-pressure hydrogen storage method with a storage pressure range of 15-20MPa to balance the time difference between hydrogen production and power generation.

[0038] The fuel cell power generation unit is connected to the hydrogen storage unit and includes multiple parallel proton exchange membrane fuel cell stacks, which are used to efficiently convert the chemical energy of hydrogen into electrical energy.

[0039] The waste heat recovery unit includes an optimized heat exchanger and a zero-emission hydrogen combustion device, which are used to recover the waste heat generated by the fuel cell power generation unit and the water electrolysis hydrogen production unit, as well as to burn unreacted hydrogen in the exhaust gas of the fuel cell power generation unit to recover heat energy, thereby realizing the cascade utilization of energy.

[0040] The intelligent control unit is connected to each of the above units to execute the online stack operating point optimization algorithm based on gradient descent and the master-slave multi-stack coordinated control strategy to realize thermoelectric proportional regulation and load adaptive control.

[0041] The beneficial effects of this invention are:

[0042] 1. A complete thermoelectric coupling heat transfer model was established, integrating the heat generation model for hydrogen production by water electrolysis, the heat generation and heat transfer model for fuel cells, and the heat exchanger model. The energy conversion and heat transfer mechanisms between the hydrogen production unit by water electrolysis, the power generation unit of fuel cells, and the waste heat recovery unit were clarified, providing a theoretical basis for the precise control of the system's thermoelectric ratio and the optimization and improvement of overall energy efficiency.

[0043] 2. A master-slave multi-stacking coordinated control strategy based on three-dimensional weighting is proposed. This strategy simultaneously incorporates efficiency, capacity, and lifetime dimensions into the calculation of the load allocation factor. The weighting factor is determined comprehensively based on the cumulative operating time of the stacks, voltage decay rate, and estimated remaining lifetime, achieving intelligent balanced operation of multiple stacks. This strategy solves the problem of accelerated stack overload aging caused by considering only a single factor in existing technologies, extending the overall system lifespan and improving operational economy.

[0044] 3. A closed-loop coupling of gradient descent optimization and multi-stall coordinated control was achieved. The online stack operating point optimization algorithm based on gradient descent was coupled with a master-slave multi-stall coordinated control strategy. The optimization algorithm determines the total reference current of the system, and the coordinated control strategy decomposes the total reference current to each stack according to a three-dimensional weighted allocation factor, forming a hierarchical closed-loop control architecture of "system-level optimization - unit-level allocation". This architecture can dynamically adjust the operating point and power allocation of each stack according to the real-time changes in photovoltaic output and load demand in off-grid scenarios, enhancing the system's adaptability to complex variable load conditions.

[0045] 4. The system can serve as an independent energy supply terminal to provide independent energy supply to energy-consuming entities, and can also serve as a supplementary energy source for the municipal power grid. It is suitable for low-carbon energy supply in off-grid engineering construction and operation and maintenance scenarios such as emergency rescue, remote areas without grid access, etc., and realizes near-zero carbon multi-energy coordinated supply.

[0046] This invention effectively solves the technical problems of uncoordinated thermoelectric coupling, single control strategy for multiple fuel cell stacks, and poor adaptability to off-grid variable loads in existing hydrogen-powered cogeneration systems, and has the effects of improved energy efficiency, reduced operating costs, and reduced carbon emissions. Attached Figure Description

[0047] Figure 1 This is a flowchart of the method of the present invention;

[0048] Figure 2 This is a schematic diagram of a hydrogen cogeneration system model for the application of the method of the present invention;

[0049] Figure 3 This is a flowchart of the online fuel cell stack operating point optimization algorithm based on gradient descent in step S2 of the method of the present invention;

[0050] The following will describe in detail, with reference to the accompanying drawings, embodiments of the present invention. Detailed Implementation

[0051] The present invention will be further described below with reference to embodiments:

[0052] like Figures 1-2 As shown, an energy management method for a hydrogen-power cogeneration system based on intelligent control includes the following steps:

[0053] S1: Establish a thermoelectric coupling heat transfer model, including a water electrolysis hydrogen production heat generation model, a fuel cell heat generation and heat transfer model, and a heat exchanger model; among them, the water electrolysis hydrogen production heat generation model is used to calculate the heat generation amount of the water electrolysis hydrogen production unit during the water electrolysis hydrogen production process; the fuel cell heat generation and heat transfer model is used to calculate the heat generation amount and heat transfer amount of the fuel cell power generation unit during the fuel cell power generation process; the heat exchanger model is used to calculate the heat exchange amount of the waste heat recovery unit during the waste heat recovery process;

[0054] The electrolysis hydrogen production heat generation model considers irreversible heat loss and reaction heat:

[0055] The heat generation model for hydrogen production through water electrolysis is as follows: ;

[0056] In the formula, Electrolysis current (A); Battery voltage (V); The voltage of the reversible battery is (V). Operating temperature (°C); The entropy change of the electrolysis reaction (J / (mol·K)); The number of electrons transferred; It is the Faraday constant (96485 C / mol);

[0057] The voltage of a reversible battery is expressed as: ;

[0058] In the formula, The standard battery voltage at 298 K, i.e. =1.229 V; R is the gas constant, i.e. =8.314 J / (mol·K); , , These represent the pressures (Pa) of hydrogen, oxygen, and water vapor on the electrode surface, respectively.

[0059] The fuel cell heat generation model considers irreversible heat loss from electrochemical reactions and latent heat of water vaporization:

[0060] The heat generation model for fuel cells is as follows: ;

[0061] In the formula, The total output power of the fuel cell stack is (kW). For electrical efficiency.

[0062] The heat transfer process in fuel cells is described by Newton's law of cooling, which describes convective heat transfer:

[0063] ;

[0064] In the formula, The convective heat transfer coefficient (W / (m) 2 ·K)), The heat transfer area is (m²). The operating temperature of the fuel cell stack is K. The temperature of the cooling medium is (K).

[0065] The heat exchanger model uses the logarithmic mean temperature difference method: ; ;

[0066] In the formula, The overall heat transfer coefficient (W / (m)) 2 ·K)), For heat exchange area (m) 2 ), The logarithmic mean temperature difference (K) and These represent the temperature difference (K) between the inlet and outlet of the heat exchanger for the hot and cold fluids, respectively.

[0067] Overall heat transfer coefficient Considering the heat transfer coefficients on the hot and cold fluid sides, fouling thermal resistance, and pipe wall thermal resistance:

[0068] ;

[0069] In the formula, and These are the convective heat transfer coefficients (W / (m²)) of the hot and cold fluid sides, respectively. 2 ·K)), and These are the fouling thermal resistances (m) on the hot and cold fluid sides, respectively. 2 ·K / W), The thickness of the heat exchanger tube wall is in meters (m). The value is the thermal conductivity of the pipe wall material (W / (m·K)).

[0070] Specifically, in this embodiment, a thermoelectric coupling heat transfer model is established:

[0071] Hydrogen production through water electrolysis: ;

[0072] Where, I = 500 A, U' = 1.9 V, = 1.23 V, = 343 K (70℃). = 163 J / (mol·K), n = 2, F = 96485 C / mol, calculated to = 479.86 kW.

[0073] Heat generation in fuel cells: ;

[0074] in, = 100 kW = 0.45, calculated as follows = 122.2 kW.

[0075] Heat exchanger heat transfer: ;

[0076] Where, U = 150 W / (m 2 ·K), = 50 m 2 , = 30 K, calculated as follows = 225 kW.

[0077] S2: Execute an online fuel cell stack operating point optimization algorithm based on gradient descent, with the objective function of maximizing the overall system energy efficiency. Considering the safe operating range of the fuel cell stack, hydrogen storage capacity, and thermal demand constraints, update the operating point of the fuel cell stack in real time and determine the total reference current of the system. ;

[0078] The objective function is: ;

[0079] In the formula, For comprehensive energy efficiency, The electrical energy output (W) of the fuel cell stack. The heat energy (W) recovered by the heat exchanger. Electrical energy input (W) for hydrogen production by water electrolysis.

[0080] The constraints include:

[0081] Fuel cell stack current density range: 0.2-1.0 A / cm 2 ;

[0082] The hydrogen flow rate meets the requirements of the fuel cell stack.

[0083] Fuel cell stack operating temperature range: 50-80℃;

[0084] Hydrogen storage pressure range: 15-20 MPa.

[0085] The gradient descent method is used to update the operating point of the fuel cell stack in real time, and the stack operating parameters are adjusted according to the current electrothermal demand to achieve the optimization of the heat-power ratio.

[0086] like Figure 3 As shown in this embodiment, the algorithm flow for optimizing the online operating point of the fuel cell stack based on gradient descent is as follows:

[0087] Step 1: Initialize system parameters, including fuel cell stack performance curves, heat exchanger parameters, hydrogen storage status, etc.

[0088] Step 2: Collect data such as system heating demand, ambient temperature, and hydrogen storage pressure in real time;

[0089] Step 3: Calculate the overall energy efficiency of the current operating point. ;

[0090] Step 4: Determine If the optimal point has been reached, proceed to step 5 if not, otherwise keep the current working point and proceed to step 6.

[0091] Step 5: Optimize the efficiency gradient using gradient descent. Update the fuel cell stack operating point (current density, temperature, etc.);

[0092] Step 6: Check if the new operating point meets the constraints (current density 0.2-1.0 A / cm²). 2 (Temperature 50-80℃, hydrogen pressure 15-20 MPa) If these conditions are met, a new working point will be executed; otherwise, adjustments will be made within the constraint boundaries.

[0093] Step 7: Return to step 2 to perform real-time optimization.

[0094] Taking a construction site as an example, during the day when the photovoltaic power output is sufficient, priority is given to meeting the electricity demand for construction, and the surplus electricity is used for hydrogen electrolysis; at night or on cloudy or rainy days, fuel cell power generation meets the electricity demand, and the waste heat is used for heating the workers' dormitories. Through online optimization, the system maintains high efficiency under different operating conditions, with a comprehensive energy efficiency of 92.8%.

[0095] S3: Executes a master-slave multi-stacking coordinated control strategy. The master controller in the intelligent control unit collects the operating parameters (voltage, current, temperature, efficiency, etc.) of each stack and the system's electrothermal demand. It calculates the reference load for each stack based on the load distribution algorithm. The slave controller in the intelligent control unit adjusts the operating parameters (inlet flow, cooling flow, etc.) of each stack to track the reference load and achieve balanced operation of multiple stacks. The system can be modularly expanded by increasing the number of stacks to adapt to different power demand scenarios.

[0096] In step S3, the load allocation factor is calculated based on a weighted average of efficiency, capacity, and lifetime. The calculation method is as follows: ;

[0097] In the formula, Let be the load allocation factor for the i-th stack; Let be the efficiency of the i-th fuel cell stack; The maximum output power (W) of the i-th fuel cell stack; The weighting factor for the i-th fuel cell stack is determined by the remaining lifetime of the stack. Specifically, it is 1.00 when the remaining lifetime of the stack is 100% and 0.60 when the remaining lifetime of the stack is 60%. This refers to the number of fuel cells;

[0098] Furthermore, the master-slave multi-stacking coordinated control strategy determines the total system reference current in step S2. Based on this, the total reference current of the system is determined according to The optimization algorithm is decomposed into individual fuel cells, achieving closed-loop coupling between the optimization algorithm and the control strategy. Let i be the reference current for the i-th fuel cell stack. This is the total reference current for the system, determined based on the system's power requirements.

[0099] Specifically, this embodiment uses four fuel cell stacks with a rated power of 30 kW operating in parallel. Due to differences in manufacturing tolerances and aging levels, the performance of each stack varies.

[0100] The main controller collects parameters from each fuel cell stack:

[0101] Stack 1: Efficiency 0.46, maximum power 30 kW, weighting factor 1.00;

[0102] Stack 2: Efficiency 0.44, maximum power 27 kW, weighting factor 0.95;

[0103] Stack 3: Efficiency 0.45, maximum power 29 kW, weighting factor 0.98;

[0104] Fuel cell stack 4: efficiency 0.43, maximum power 25 kW, weighting factor 0.92;

[0105] The system's total power demand is 100 kW, and the total reference current is... = 400 A.

[0106] Calculate the load distribution factor:

[0107] ;

[0108] ;

[0109] ;

[0110] ;

[0111] Reference current for each fuel cell stack:

[0112] ;

[0113] ;

[0114] ;

[0115] ;

[0116] The controller adjusts the hydrogen flow rate and cooling water flow rate of each fuel cell stack to make the actual current track the reference current, thereby achieving balanced operation and avoiding overload or underload of a single fuel cell stack.

[0117] S4: Perform thermal energy conversion optimization, recover waste heat by optimizing the heat exchanger, and recover hydrogen thermal energy from the exhaust gas of the fuel cell power generation unit through the zero-emission hydrogen combustion device in the waste heat recovery unit.

[0118] Among them, the optimization of heat exchanger fin geometric parameters adopts the response surface methodology, with fin thickness, fin spacing, and fin height as independent variables and the overall heat transfer coefficient as the response value, to establish a regression model:

[0119] ;

[0120] In the formula, This refers to the fin thickness; This refers to the fin spacing; This refers to the fin height; is the regression coefficient.

[0121] The zero-emission hydrogen combustion device mixes unreacted hydrogen from the fuel cell exhaust with air in a certain proportion and burns it in the combustion chamber. The combustion reaction is as follows:

[0122] ;

[0123] The heat generated by combustion is recovered by a heat recovery device and used for heating or hot water supply. The combustion efficiency is greater than 99%, and nitrogen oxide emissions are lower than the national standard limit, achieving zero-emission utilization of hydrogen.

[0124] like Figure 2 As shown, the hydrogen-electricity cogeneration system applied by this method includes a photovoltaic power generation unit, a water electrolysis hydrogen production unit, a hydrogen storage unit, a fuel cell power generation unit, a waste heat recovery unit, and an intelligent control unit. The system is configured to operate independently of the municipal power grid and is suitable for low-carbon energy supply in off-grid scenarios.

[0125] Photovoltaic power generation units are used to convert solar energy into electrical energy. Specifically, these units use monocrystalline silicon photovoltaic modules, with peak power determined based on site lighting conditions and electricity demand, typically configured as 50-200 kWp. The photovoltaic modules are connected to the DC bus via an MPPT controller to achieve maximum power point tracking.

[0126] The water electrolysis hydrogen production unit is connected to the photovoltaic power generation unit and includes a proton exchange membrane (PEM) electrolyzer. Its rated power is matched to the photovoltaic power generation unit, and it uses electrical energy to electrolyze water to produce hydrogen and oxygen. Specifically, the PEM electrolyzer has advantages such as fast response speed, high efficiency, and high hydrogen purity, making it suitable for coupling with fluctuating renewable energy sources. The electrolyzer typically operates at a temperature of 60-80℃, producing hydrogen at a pressure of 1.5-3.0 MPa, which is then pressurized to 15-20 MPa by a compressor before storage.

[0127] The hydrogen storage unit is connected to the water electrolysis hydrogen production unit and adopts a high-pressure hydrogen storage method with a storage pressure range of 15-20 MPa to balance the time difference between hydrogen production and power generation. Specifically, the hydrogen storage unit adopts a high-pressure hydrogen storage cylinder group with a storage pressure of 15-20 MPa. The hydrogen storage capacity is determined according to the number of consecutive rainy days and electricity demand, and is generally designed to meet the hydrogen consumption of 3-7 days.

[0128] The fuel cell power generation unit is connected to the hydrogen storage unit and includes multiple proton exchange membrane fuel cell (PEMFC) stacks connected in parallel to efficiently convert the chemical energy of hydrogen into electrical energy. Multiple stacks operate in parallel to meet high power requirements, with a single stack typically having a rated power of 5-30 kW. The number of stacks is determined based on the total power demand. The stacks operate at a temperature of 50-80℃, with a hydrogen utilization rate greater than 95%.

[0129] The waste heat recovery unit includes an optimized heat exchanger and a zero-emission hydrogen combustion device. It recovers waste heat generated by the fuel cell power generation unit and the water electrolysis hydrogen production unit, and also recovers heat energy by burning unreacted hydrogen in the exhaust gas of the fuel cell power generation unit, achieving cascaded energy utilization. The optimized heat exchanger uses a plate heat exchanger or a finned tube heat exchanger to recover waste heat generated by the fuel cell and electrolyzer. The zero-emission hydrogen combustion device includes a hydrogen burner, a combustion chamber, and a heat recovery device, with a combustion efficiency greater than 99% and nitrogen oxide emissions below national standard limits; it is used to recover approximately 3-5% of unreacted hydrogen in the fuel cell exhaust gas.

[0130] The intelligent control unit is connected to each of the aforementioned units and is used to execute an online fuel cell stack operating point optimization algorithm based on gradient descent and a master-slave multi-fuel cell stack coordinated control strategy to achieve thermoelectric proportional regulation and load adaptive control. Specifically, the intelligent control unit includes a data acquisition module, a control decision module, and an execution regulation module. The data acquisition module collects the operating parameters of each unit in real time; the control decision module executes the online optimization algorithm and coordinated control strategy; and the execution regulation module outputs control signals to regulate the operation of each unit.

[0131] Specifically, in this embodiment, a construction site uses this system and configures it as follows:

[0132] Photovoltaic power generation: 100 kWp; PEM electrolyzer: 80 kW; Hydrogen storage capacity: 200 kg (15 MPa); Fuel cell: 4 × 30 kW PEMFC; Optimized heat exchanger: Overall heat transfer coefficient 178 W / (m²) 2 ·K);

[0133] Operational results show that replacing diesel generators reduces annual carbon emissions by approximately 280 tons of CO2; the system's overall energy efficiency is 92.8%, which is higher than that of diesel generators (35%); it meets the continuous power demand of the construction site, and the waste heat can meet the heating needs of a dormitory for 200 people; and the operating cost is reduced by approximately 25% compared to diesel generators.

[0134] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a connection that allows communication between them; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components, unless otherwise explicitly limited. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0135] The present invention has been described above by way of example. Obviously, the specific implementation of the present invention is not limited to the above-described manner. Any improvements made by adopting the inventive concept and technical solution of the present invention, or direct application to other occasions without modification, are all within the protection scope of the present invention.

Claims

1. An energy management method for a hydrogen-power cogeneration system based on intelligent control, characterized in that, Includes the following steps: S1: Establish a thermoelectric coupling heat transfer model, including a water electrolysis hydrogen production heat generation model, a fuel cell heat generation and heat transfer model, and a heat exchanger model; among them, the water electrolysis hydrogen production heat generation model is used to calculate the heat generation amount of the water electrolysis hydrogen production unit during the water electrolysis hydrogen production process; the fuel cell heat generation and heat transfer model is used to calculate the heat generation amount and heat transfer amount of the fuel cell power generation unit during the fuel cell power generation process; the heat exchanger model is used to calculate the heat exchange amount of the waste heat recovery unit during the waste heat recovery process; S2: Execute an online fuel cell stack operating point optimization algorithm based on gradient descent, with the objective function of maximizing the overall system energy efficiency. Considering the safe operating range of the fuel cell stack, hydrogen storage capacity, and thermal demand constraints, update the operating point of the fuel cell stack in real time and determine the total reference current of the system. ; S3: Executes a master-slave multi-stacking coordinated control strategy. The master controller in the intelligent control unit collects the operating parameters of each stack and the system's electrothermal demand. The reference load of each stack is calculated according to the load distribution algorithm. The slave controller in the intelligent control unit adjusts the operating parameters of each stack to track the reference load, thereby achieving balanced operation of multiple stacks and modular expansion. S4: Perform thermal energy conversion optimization, recover waste heat by optimizing the heat exchanger, and recover hydrogen thermal energy from the exhaust gas of the fuel cell power generation unit through the zero-emission hydrogen combustion device in the waste heat recovery unit. In step S3, the load allocation factor is calculated based on a weighted average of efficiency, capacity, and lifetime. The calculation method is as follows: ; In the formula, Let be the load allocation factor for the i-th stack; Let be the efficiency of the i-th fuel cell stack; The maximum output power of the i-th fuel cell stack; The weighting factor for the i-th fuel cell stack is determined by the remaining lifetime of the stack. Specifically, it is 1.00 when the remaining lifetime of the stack is 100% and 0.60 when the remaining lifetime of the stack is 60%. This refers to the number of fuel cells; Furthermore, the master-slave multi-stacking coordinated control strategy determines the total system reference current in step S2. Based on this, the total reference current of the system is determined according to The optimization algorithm is decomposed into individual fuel cells, achieving closed-loop coupling between the optimization algorithm and the control strategy. Let be the reference current for the i-th fuel cell stack.

2. The energy management method for a hydrogen-power cogeneration system based on intelligent control according to claim 1, characterized in that, In step S1, the thermal generation model for hydrogen production through water electrolysis is as follows: ; In the formula, This is the electrolysis current; Battery voltage; This is the voltage of a reversible battery; Operating temperature; This represents the entropy change of the electrolysis reaction. The number of electrons transferred; It is the Faraday constant, and F = 96485 C / mol; The voltage of a reversible battery is expressed as: ; In the formula, The standard battery voltage at 298 K, i.e. =1.229 V; R is the gas constant, i.e. =8.314 J / (mol·K); , , These represent the pressures of hydrogen, oxygen, and water vapor on the electrode surface, respectively.

3. The energy management method for a hydrogen-power cogeneration system based on intelligent control according to claim 1, characterized in that, In step S1, the fuel cell heat generation model is as follows: ; In the formula, This represents the total output power of the fuel cell stack. For electrical efficiency.

4. The energy management method for a hydrogen-power cogeneration system based on intelligent control according to claim 1, characterized in that, In step S1, the heat exchanger model uses the logarithmic mean temperature difference method: ; In the formula, The overall heat transfer coefficient; For heat exchange area; The temperature difference is the logarithmic mean.

5. The energy management method for a hydrogen-power cogeneration system based on intelligent control according to claim 1, characterized in that, In step S2, the objective function is: ; In the formula, For overall energy efficiency; For the electrical energy output of the fuel cell stack; The heat energy recovered by the heat exchanger; The electrical energy input is for the electrolysis of water to produce hydrogen.

6. The energy management method for a hydrogen-power cogeneration system based on intelligent control according to claim 1, characterized in that, In step S4, the optimization of the heat exchanger fin geometry parameters adopts the response surface methodology, using fin thickness, fin spacing, and fin height as independent variables, and the overall heat transfer coefficient as the response value to establish a regression model: ； In the formula, This refers to the fin thickness; This refers to the fin spacing; This refers to the fin height; is the regression coefficient.

7. The energy management method for a hydrogen-power cogeneration system based on intelligent control according to claim 1, characterized in that, The hydrogen-electricity cogeneration system applied by this method includes a photovoltaic power generation unit, a water electrolysis hydrogen production unit, a hydrogen storage unit, a fuel cell power generation unit, a waste heat recovery unit, and an intelligent control unit. The system is configured to operate independently of the municipal power grid and is suitable for low-carbon energy supply in off-grid scenarios. Photovoltaic power generation units are used to convert solar energy into electrical energy; The water electrolysis hydrogen production unit is connected to the photovoltaic power generation unit, including a proton exchange membrane electrolyzer, which is used to use electrical energy to electrolyze water to produce hydrogen and oxygen. The hydrogen storage unit is connected to the water electrolysis hydrogen production unit and adopts a high-pressure hydrogen storage method with a storage pressure range of 15-20MPa to balance the time difference between hydrogen production and power generation. The fuel cell power generation unit is connected to the hydrogen storage unit and includes multiple parallel proton exchange membrane fuel cell stacks, which are used to efficiently convert the chemical energy of hydrogen into electrical energy. The waste heat recovery unit includes an optimized heat exchanger and a zero-emission hydrogen combustion device, which are used to recover the waste heat generated by the fuel cell power generation unit and the water electrolysis hydrogen production unit, as well as to burn unreacted hydrogen in the exhaust gas of the fuel cell power generation unit to recover heat energy, thereby realizing the cascade utilization of energy. The intelligent control unit is connected to each of the above units to execute the online stack operating point optimization algorithm based on gradient descent and the master-slave multi-stack coordinated control strategy to realize thermoelectric proportional regulation and load adaptive control.

Images