Method for commissioning a hydrogen-based energy system and hydrogen-based energy system

Abstract

The embodiment of the present application provides a debugging method of a hydrogen-based energy system and the hydrogen-based energy system, which comprises the following steps: calling a system-level dynamic simulation model of the hydrogen-based energy system, performing multi-condition control simulation based on multiple groups of preset working condition parameters and corresponding multiple groups of preset control parameters, so as to obtain simulation output data under each parameter combination input, and constructing a sample data set; training a parameter performance prediction model based on the sample data set; generating a candidate control parameter set for actual working condition parameters; calling the parameter performance prediction model to perform performance prediction on the candidate control parameter set, and sorting the performance prediction results based on a preset evaluation index, and outputting recommended control parameters based on the sorting results; applying the recommended control parameters to the hydrogen-based energy system, collecting field operation data of the hydrogen-based energy system, and updating the system-level dynamic simulation model and the parameter performance prediction model according to the field operation data. The present application can improve the debugging efficiency and ensure the reliable operation of the hydrogen-based energy system.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of hydrogen-based energy system control, and particularly to a debugging method for hydrogen-based energy systems and hydrogen-based energy systems. Background Technology

[0002] Green hydrogen-based energy systems typically use wind and solar power as primary energy sources, producing hydrogen through water electrolysis and further synthesizing ammonia to achieve large-scale conversion and utilization of new energy. This system involves multiple subsystems and is characterized by multi-energy coupling, cross-timescale operation, and strong nonlinearity. Furthermore, it is affected by the fluctuations and uncertainties in wind and solar power output, resulting in frequent changes in system operating boundary conditions. The chemical processes such as ammonia synthesis and hydrogen electrolysis also impose strict constraints on the load change rate and operating range, leading to significant challenges in the commissioning phase of green hydrogen-based energy systems.

[0003] Existing commissioning methods rely heavily on manual experience to determine control parameters and employ separate commissioning for each subsystem. This results in high trial-and-error costs and long cycles during the commissioning process. Furthermore, it fails to fully consider the coupling relationships between wind power, photovoltaic output, electrolytic hydrogen production, hydrogen storage, and ammonia synthesis. Consequently, the consistency and repeatability of commissioning results are poor, the commissioning accuracy is low, and problems such as power distribution imbalance and process fluctuations are easily caused. Summary of the Invention

[0004] This invention provides a debugging method for a hydrogen-based energy system, as well as a hydrogen-based energy system, electronic device, storage medium, and computer program product, which can improve debugging efficiency and ensure the reliable operation of the hydrogen-based energy system.

[0005] In a first aspect, the debugging method for a hydrogen-based energy system provided in the embodiments of the present invention includes: The system-level dynamic simulation model of the hydrogen-based energy system is invoked to perform multi-condition control simulation based on multiple sets of preset operating parameters and corresponding sets of preset control parameters to obtain simulation output data under various parameter combinations. A sample dataset containing simulation input parameters and simulation output data is constructed. A parameter performance prediction model is trained based on the sample dataset. The parameter performance prediction model is used to characterize the mapping relationship between simulation input parameters and simulation output data. A set of candidate control parameters is generated for actual operating parameters. The parameter performance prediction model is invoked to predict the performance of the candidate control parameter set, and the performance prediction results are evaluated and ranked based on preset evaluation indicators. Recommended control parameters are output based on the ranking results. The recommended control parameters are applied to the hydrogen-based energy system, field operation data of the hydrogen-based energy system is collected, and the system-level dynamic simulation model and parameter performance prediction model are updated based on the field operation data.

[0006] Secondly, the debugging device for a hydrogen-based energy system provided in the embodiments of the present invention includes: The module is used to call the system-level dynamic simulation model of the hydrogen-based energy system to perform multi-condition control simulation based on multiple sets of preset operating condition parameters and corresponding multiple sets of preset control parameters, so as to obtain the simulation output data under each parameter combination input and construct a sample dataset containing simulation input parameters and simulation output data. The training module is used to train a parametric performance prediction model based on a sample dataset. The parametric performance prediction model is used to characterize the mapping relationship between simulation input parameters and simulation output data. The generation module is used to generate a set of candidate control parameters based on actual operating conditions. The output module is used to call the parameter performance prediction model to predict the performance of the candidate control parameter set, evaluate and rank the performance prediction results based on preset evaluation indicators, and output recommended control parameters based on the ranking results. The update module is used to apply recommended control parameters to the hydrogen-based energy system, collect field operation data of the hydrogen-based energy system, and update the system-level dynamic simulation model and parameter performance prediction model based on the field operation data.

[0007] Thirdly, the electronic device provided in the embodiments of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the debugging method of the hydrogen-based energy system as described in any embodiment of the present invention.

[0008] Fourthly, the computer-readable storage medium provided in the embodiments of the present invention stores computer instructions thereon, the computer instructions being used to cause a processor to execute and implement the debugging method of the hydrogen-based energy system as in any embodiment of the present invention.

[0009] Fifthly, the computer program product provided in the embodiments of the present invention includes a computer program that, when executed by a processor, implements the debugging method of the hydrogen-based energy system as described in any embodiment of the present invention.

[0010] In this embodiment of the invention, a system-level dynamic simulation model of a hydrogen-based energy system is invoked to perform multi-condition control simulations based on multiple sets of simulation input parameters. This obtains simulation output data under various parameter combinations, constructing a sample dataset containing simulation input parameters and simulation output data. This dataset considers the coupling relationship between hydrogen production, storage, and utilization, comprehensively covers the main operating conditions of the hydrogen-based energy system, and ensures broad representativeness, thereby improving the accuracy of the parameter performance prediction model. The parameter performance prediction model is trained based on this sample dataset. This model characterizes the mapping relationship between simulation input parameters and simulation output data, avoiding repeated control simulations and achieving rapid prediction of the hydrogen-based energy system performance while maintaining a certain level of accuracy, saving time and computing resources. A candidate control parameter set is generated based on actual operating condition parameters. The parameter performance prediction model is then invoked to evaluate the candidate control parameters. The system performs performance prediction using a set of parameters and evaluates and ranks the prediction results based on preset evaluation indicators. It then outputs recommended control parameters based on the ranking results. This allows for rapid evaluation and screening of a large number of candidate control parameters, reducing reliance on individual experience during commissioning and minimizing uncertainty caused by differences in experience among different commissioning personnel. This effectively improves commissioning efficiency and consistency. Applying the recommended control parameters to hydrogen-based energy systems and collecting on-site operating data allows for updating the system-level dynamic simulation model and parameter performance prediction model based on this data. This enables the system-level dynamic simulation model and parameter performance prediction model to continuously evolve with the accumulation of on-site operating data and to update in real time as the actual state of the hydrogen-based energy system changes. This makes the performance prediction results closer to the actual operating results, thereby improving commissioning accuracy and adaptability, and ensuring the reliable operation of the hydrogen-based energy system. Attached Figure Description

[0011] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a schematic flowchart of a debugging method for a hydrogen-based energy system provided in an embodiment of the present invention; Figure 2 This is another schematic flowchart of the debugging method for a hydrogen-based energy system provided in this embodiment of the invention; Figure 3 This is a schematic diagram of the structure of a system-level dynamic simulation model provided in an embodiment of the present invention; Figure 4 This is a schematic flowchart of determining recommended control parameters provided in an embodiment of the present invention; Figure 5 This is another flowchart illustrating the debugging method for a hydrogen-based energy system provided in this embodiment of the invention; Figure 6 This is a schematic diagram of a debugging device for a hydrogen-based energy system provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] Figure 1 This is a flowchart illustrating a debugging method for a hydrogen-based energy system provided in an embodiment of the present invention. This debugging method is applicable to scenarios where debugging parameters are recommended for green hydrogen-based energy systems. The debugging method can be executed by a debugging device for the hydrogen-based energy system provided in this embodiment, which can be implemented using software and / or hardware. In one specific embodiment, the device can be integrated into an electronic device, such as a computer, server, or workstation. The following embodiment illustrates this using the integration of the hydrogen-based energy system debugging device into an electronic device as an example. (See also...) Figure 1 The commissioning method for the hydrogen-based energy system in this embodiment may include the following steps: Step 101: Call the system-level dynamic simulation model of the hydrogen-based energy system to perform multi-condition control simulation based on multiple sets of preset operating condition parameters and corresponding multiple sets of preset control parameters, so as to obtain the simulation output data under each parameter combination input and construct a sample dataset containing simulation input parameters and simulation output data.

[0016] A hydrogen-based energy system is a comprehensive system that uses hydrogen as its core energy carrier to achieve hydrogen production, storage, and utilization through renewable energy power generation. Specifically, hydrogen-based energy systems typically use electricity generated from wind or solar power as input, producing hydrogen through water electrolysis. Furthermore, the system can further utilize the produced hydrogen for downstream applications, such as ammonia or methane synthesis, depending on the specific application scenario, thus achieving large-scale conversion and utilization of renewable energy.

[0017] A system-level dynamic simulation model is a mechanistic model that can describe the dynamic behavior and coupling relationships of key units such as wind and solar power generation, water electrolysis for hydrogen production, hydrogen storage, and hydrogen utilization in a hydrogen-based energy system from a holistic perspective. Specifically, when constructing a system-level dynamic simulation model for a hydrogen-based energy system, the system configuration parameters and equipment characteristic parameters of the hydrogen-based energy system can be collected first. Based on this, according to energy flow, material flow, and control logic, and considering operational constraints and the mutual coupling between key units, a comprehensive system-level dynamic simulation model can be constructed to reflect the dynamic response characteristics of the multi-energy system under different operating conditions and control strategies. Taking the synthesis of ammonia in a hydrogen-based energy system as an example, the system-level dynamic simulation model can include a power supply side model, an electrolysis hydrogen production model, a hydrogen storage model, and a synthesis ammonia model. System configuration parameters can include the capacity and system topology relationships of wind power, photovoltaic, hydrogen production, hydrogen storage, and ammonia synthesis devices; equipment characteristic parameters can include the energy consumption curve of the hydrogen electrolyzer, the thermal balance parameters of the ammonia synthesis reaction, etc.; and operational constraints can include power balance, hydrogen storage capacity limitations, and safety limits for temperature and pressure, etc.

[0018] Simulation input parameters refer to the set of external variables set when calling the system-level dynamic simulation model to perform control simulations under multiple operating conditions. These variables describe the external operating conditions and control strategies of the system. Specifically, simulation input parameters include preset operating condition parameters and corresponding preset control parameters. Specifically, preset operating condition parameters and corresponding sets of preset control parameters can be combined in pairs to form multiple sets of simulation input parameters. For example, if the preset operating condition parameter is X1, and the corresponding preset control parameters are X2.1, X2.2, and X2.3, then three parameter combinations can be formed: (X1, X2.1), (X1, X2.2), and (X1, X2.3). These parameter combinations serve as three sets of simulation input parameters. By repeatedly providing multiple preset operating condition parameters for different operating conditions and executing the above steps, simulation input parameters for constructing multiple operating conditions can be generated.

[0019] Operating condition parameters refer to a class of input parameters that describe the external conditions of system operation. Specifically, operating condition parameters reflect wind and solar conditions and downstream load demand. Their role is to provide boundary conditions for the system-level dynamic simulation model, simulating the system's operation under different conditions. Operating condition parameters may include the theoretical maximum power generation of wind and solar power, and the total load demand of the synthetic ammonia system over a control cycle, such as 24 hours. When presetting operating condition parameters, typical and extreme commissioning scenarios can be constructed based on the engineering experience of commissioning personnel to cover the main operating conditions that the system may face during actual commissioning. Multiple sets of preset operating condition parameters are set according to the main operating conditions. The constructed main operating conditions may include the following: Strong wind and solar power generation: wind and solar power output is significantly higher than the current system load demand; Insufficient wind and solar power generation: wind and solar power output is less than the system load demand, requiring compensation through energy storage or grid connection; Sudden wind and solar power generation: wind and solar power output fluctuates significantly in a short period of time, used to simulate abnormal or disturbed scenarios.

[0020] Control parameters are a type of input parameter used to describe the internal operating strategy of a system. Specifically, given a set of preset operating condition parameters, several sets of initial control parameters can be generated under the guidance of expert rules. These initial control parameters are then filtered using pre-defined constraints to exclude those exceeding limits, resulting in multiple sets of preset control parameters. Specifically, control parameters may include hydrogen production load allocation strategies, hydrogen storage and release control strategies, system power consumption principles, and process control parameters for hydrogen consumption stages.

[0021] Simulation output data refers to the results reflecting the dynamic response of the system obtained after simulation using a system-level dynamic simulation model for each set of simulation input parameters. Simulation output data typically includes the operating state variables of each key unit, energy and material flows, and hydrogen utilization efficiency indicators. Specifically, simulation output data reflects the operating results of a hydrogen-based energy system controlled by preset control parameters under typical operating conditions corresponding to preset operating parameters. Evaluation indicators can be calculated using simulation output data to further evaluate the control quality of preset control parameters under preset operating conditions. For example, if a hydrogen-based energy system is used to synthesize ammonia from hydrogen produced by water electrolysis, the simulation output data may include power-side response data and process-side response data. The power-side response data may include the actual power generation curves of wind and photovoltaic power generation, grid-connected or back-feed power curves, and hydrogen production load power curves. Process-side response data may include hydrogen storage capacity, hydrogen flow rate, hydrogen production output, and temperature and pressure of the hydrogen production reactor. Specifically, hydrogen production output may include ammonia storage capacity, ammonia flow rate, ammonia production, and ammonia conversion rate. Temperature and pressure of the hydrogen production reactor may include the temperature of different beds in the ammonia synthesis tower and the outlet pressure of the synthesis tower.

[0022] Specifically, multiple sets of different operating condition parameters can be set first, each set corresponding to a main operating condition. For each set of operating condition parameters, multiple sets of preset control parameters are further generated, each representing a feasible debugging strategy. The preset operating condition parameters and preset control parameters are combined as simulation input parameters, and a system-level dynamic simulation model is invoked to perform simulation, collecting the corresponding simulation output data. Thus, each set of simulation input parameters is used as the feature vector of a sample, and the corresponding simulation output data or evaluation indicators calculated based on the simulation output data are used as the label of the sample, together forming a sample dataset. The sample dataset can be used for subsequent training of machine learning models to establish a mapping relationship between operating conditions and control strategies and system response performance.

[0023] In this embodiment, the system-level dynamic simulation model of the hydrogen-based energy system is invoked to perform multi-condition control simulation based on multiple sets of simulation input parameters to obtain simulation output data under various parameter combinations. A sample dataset containing simulation input parameters and simulation output data is constructed, which can consider the coupling relationship between hydrogen production, hydrogen storage and hydrogen use, and comprehensively cover the main operating conditions of the hydrogen-based energy system, ensuring that the sample dataset has broad representativeness, thereby improving the accuracy of the parameter performance prediction model.

[0024] Step 102: Train a parameter performance prediction model based on the sample dataset. The parameter performance prediction model is used to characterize the mapping relationship between simulation input parameters and simulation output data.

[0025] Parametric performance prediction models are data-driven models that predict the actual dynamic response of hydrogen-based energy systems based on simulated input parameters. Specifically, these models use simulated input parameters as input features and simulated output data as output labels to characterize the mapping relationship between specific system operating conditions and control strategies and the system's dynamic response performance. Various data-driven models can be selected based on engineering requirements. Examples include random forest regression models, gradient boosting regression models, support vector machine regression models, Bayesian optimization models, and reinforcement learning models from machine learning models.

[0026] In this embodiment, a parameter performance prediction model is trained based on a sample dataset. This model is used to characterize the mapping relationship between simulation input parameters and simulation output data, which can avoid repeated control simulations and achieve rapid prediction of the performance of hydrogen-based energy systems while ensuring a certain level of accuracy, thus saving time and computing resources.

[0027] Step 103: Generate a set of candidate control parameters based on the actual operating conditions.

[0028] Actual operating condition parameters refer to the external condition variables faced by the hydrogen-based energy system in actual operating scenarios. Candidate control parameters refer to a set of feasible internal operating strategy variables generated for specific actual operating conditions to control the safe and stable operation of the hydrogen-based energy system. Each set of candidate control parameters constitutes a feasible debugging scheme under specific actual operating conditions. The candidate parameter set includes various candidate control parameters that may be adopted under the actual operating conditions, for subsequent optimization in control performance ranking. Specifically, the types of actual operating condition parameters and candidate control parameters are usually consistent with the preset operating condition parameters and preset control parameters in step 101 to ensure the continuity and portability of the parameter space. Candidate control parameter set. When the actual operating condition parameters have a high overlap rate with common typical operating condition parameters, the control parameter set corresponding to common typical operating conditions can be selected from the parameter set pre-set based on domain knowledge, operating experience, or historical best cases to form the candidate control parameter set; alternatively, a pre-built expert rule base can be called to generate a control parameter selection benchmark corresponding to the actual operating condition parameters, and then parameters can be sampled in the neighborhood of the selection benchmark using methods such as random sampling and Latin hypercube sampling to generate a diverse set of candidate control parameters.

[0029] Step 104: Call the parameter performance prediction model to predict the performance of the candidate control parameter set, evaluate and rank the performance prediction results based on the preset evaluation index, and output recommended control parameters based on the ranking results.

[0030] Preset evaluation indicators refer to a set of quantitative standards used to measure the operational quality of a hydrogen-based energy system. Specifically, there may be one or more preset evaluation indicators, which can evaluate the system's operational quality from multiple dimensions such as energy efficiency, stability, and economy. For example, when a hydrogen-based energy system uses hydrogen to synthesize ammonia, preset evaluation indicators may include the ammonia conversion rate, the rationality of the reactor bed temperature, and the amount of electricity wasted by the system. Recommended control parameters refer to one or more sets of control parameters that best perform under the current actual operating conditions, selected from the candidate control parameter set after evaluation and ranking based on the prediction results of the parameter performance prediction model and the preset evaluation indicators.

[0031] Specifically, actual operating parameters are combined with candidate control parameters to form a set of input data. This data is then input into a pre-trained parameter performance prediction model for performance prediction. The simulation output data of each candidate control parameter under actual operating conditions is obtained as the performance prediction result. The performance prediction results are evaluated and ranked using preset evaluation indicators. Recommended control parameters are output based on the ranking results. When there are multiple preset evaluation indicators, corresponding weight coefficients can be assigned according to the importance of each indicator. The weighted sum of the preset evaluation indicators yields a comprehensive evaluation indicator. The parameters are ranked based on the magnitude of the comprehensive evaluation indicator, and the candidate control parameter with the optimal comprehensive evaluation indicator is selected as the recommended control parameter. When there are conflicts between preset evaluation indicators, for example, the ammonia conversion rate and the system waste power may not be optimal simultaneously, a non-dominated ranking method can be used. This method performs non-dominated ranking and hierarchical division for multiple preset indicators. The ranking results clarify the dominance relationship between each candidate control parameter. The candidate control parameter corresponding to the preset evaluation indicator in the first level (i.e., the non-dominated level) can be selected as the recommended control parameter output, allowing commissioning personnel to further filter from the recommended control parameters according to actual control requirements.

[0032] In this embodiment, a set of candidate control parameters is generated based on actual operating conditions; the performance prediction model is called to predict the performance of the candidate control parameter set; the performance prediction results are evaluated and ranked based on preset evaluation indicators; and recommended control parameters are output based on the ranking results. This method can quickly complete the evaluation and screening of a large number of candidate control parameters, reduce the dependence on personal experience in the debugging process, reduce the uncertainty caused by the experience differences between different debugging personnel, and thus effectively improve debugging efficiency and consistency.

[0033] Step 105: Apply the recommended control parameters to the hydrogen-based energy system, collect on-site operation data of the hydrogen-based energy system, and update the system-level dynamic simulation model and parameter performance prediction model based on the on-site operation data.

[0034] Field operation data refers to the actual dynamic response data recorded in real time during the actual operation of the hydrogen-based energy system. Field operation data reflects the actual dynamic response of the system under recommended control parameters and may deviate from the prediction results of the simulation model.

[0035] Specifically, after applying the recommended control parameters to the actual operation control of the hydrogen-based energy system, the actual operating parameters and the recommended control parameters can be input into the system-level dynamic simulation model to obtain the simulation output data corresponding to the actual operating parameters. The consistency of the simulation output data corresponding to the actual operating parameters is compared with the field operation data to calculate the deviation between the two. When the deviation exceeds a preset threshold, the system-level simulation model is corrected based on the field operation data by adjusting the key parameters in the simulation model through optimization algorithms to minimize the deviation between the simulation output data and the field operation parameters. Then, the actual operating parameters, recommended control parameters, and corresponding actual operation results can be used to form a new training sample. The corrected system-level dynamic simulation model can also be re-executed under the actual operating parameters to generate new training samples. Finally, the new training samples are added to the sample dataset, and the parameter performance prediction model is retrained based on the updated sample dataset.

[0036] In this embodiment, by applying recommended control parameters to the hydrogen-based energy system, collecting on-site operating data of the hydrogen-based energy system, and updating the system-level dynamic simulation model and parameter performance prediction model based on the on-site operating data, the system-level dynamic simulation model and parameter performance prediction model can continuously evolve with the accumulation of on-site operating data and can be updated in real time when the actual state of the hydrogen-based energy system changes. This makes the performance prediction results closer to the actual operating results, thereby improving the accuracy of debugging and the adaptive capability, and ensuring the reliable operation of the hydrogen-based energy system.

[0037] In this embodiment, a multi-condition control simulation is performed based on multiple sets of simulation input parameters by calling the system-level dynamic simulation model of the hydrogen-based energy system. This obtains simulation output data under various parameter combinations, constructing a sample dataset containing simulation input parameters and simulation output data. This dataset considers the coupling relationship between hydrogen production, storage, and utilization, comprehensively covers the main operating conditions of the hydrogen-based energy system, and ensures broad representativeness, thereby improving the accuracy of the parameter performance prediction model. The parameter performance prediction model is trained based on this sample dataset. This model characterizes the mapping relationship between simulation input parameters and simulation output data, avoiding repeated control simulations and achieving rapid prediction of the hydrogen-based energy system performance while maintaining a certain level of accuracy, saving time and computing resources. A candidate control parameter set is generated based on actual operating condition parameters. The parameter performance prediction model is then used to analyze the candidate control parameters. The system performs performance predictions using a set of parameters and evaluates and ranks the prediction results based on preset evaluation indicators. Recommended control parameters are then output based on the ranking results. This allows for rapid evaluation and screening of a large number of candidate control parameters, reducing reliance on individual experience during commissioning and minimizing uncertainty caused by differences in experience among different commissioning personnel. This effectively improves commissioning efficiency and consistency. Applying the recommended control parameters to the hydrogen-based energy system involves collecting field operation data and updating the system-level dynamic simulation model and parameter performance prediction model based on this data. This allows the system-level dynamic simulation model and parameter performance prediction model to continuously evolve with the accumulation of field operation data and to update in real time as the actual state of the hydrogen-based energy system changes. This makes the performance prediction results closer to the actual operating results, thereby improving commissioning accuracy and adaptability, and ensuring the reliable operation of the hydrogen-based energy system.

[0038] The following is combined Figure 2 The debugging method of the hydrogen-based energy system provided in the embodiments of the present invention is further explained. Figure 2 This is another schematic flowchart illustrating the commissioning method of the hydrogen-based energy system provided in this embodiment of the invention. (See attached diagram.) Figure 2 The commissioning method for the hydrogen-based energy system in this embodiment may include the following steps: Step 201: Call the system-level dynamic simulation model of the hydrogen-based energy system to perform multi-condition control simulation based on the simulation input parameters, so as to obtain the simulation output data under various parameter combinations and construct a sample dataset containing simulation input parameters and simulation output data.

[0039] The system-level dynamic simulation model includes a power supply side model, an electrolytic hydrogen production model, a hydrogen storage model, and an ammonia synthesis model. The system-level dynamic simulation model is used to simulate the dynamic coupling characteristics of wind and solar power generation, electrolytic hydrogen production, hydrogen storage, and ammonia synthesis processes. Figure 3This is a schematic diagram of the system-level dynamic simulation model provided in this embodiment of the invention. Specifically, the system-level dynamic simulation model can be implemented using a centralized approach, integrating all key units such as the power supply side model, the electrolysis hydrogen production side model, the hydrogen storage model, and the ammonia synthesis model onto the same simulation platform, and performing overall coupled solution through a unified mathematical model and solver. Alternatively, it can be implemented using a hierarchical or modular structure, for example, deploying each key unit as an independent functional module and exchanging data through a standard interface.

[0040] The power supply side model is a mechanistic model describing the dynamic characteristics of wind and solar power generation units, and can further reflect the impact of wind and solar power fluctuations on downstream hydrogen production, hydrogen storage, and ammonia synthesis processes. Specifically, the power supply side model includes a wind and solar power model and a power balance model. For example, the wind and solar power model can be expressed by the following formula: ,in, Let be the total power generation at time t. Let be the wind power generation capacity at time t. Let be the photovoltaic power generation capacity. The power balance model can be expressed by the following formula: ,in Let be the power of the grid-connected or grid-connected power at time t (when When positive, it indicates the downstream grid power. When negative, it indicates the power of the grid power supply. Let be the electrical load power of the electrolytic cell at time t. Let t be the electrical load power for ammonia synthesis. Let t be the power of other public electrical loads, such as plant power and production lighting power.

[0041] The electrolytic hydrogen production model is a mechanistic model describing the dynamic response of the electrolyzer and the hydrogen production process. It can further reflect the impact of power fluctuations on the hydrogen production rate, energy consumption, and operating status. For example, the electrolytic hydrogen production model can be expressed by the following formula: ,in Let be the hydrogen production at time t. The efficiency factor for hydrogen production by electrolysis. Let t be the electrical power used for hydrogen production. This is the higher heating value of hydrogen.

[0042] Hydrogen storage models describe the mechanistic mechanisms of hydrogen storage and release during the storage process, and can further reflect the impact of upstream hydrogen supply fluctuations on the hydrogen storage status and downstream hydrogen consumption stability. For example, a hydrogen storage model can be expressed by the following formula. ,in, The hydrogen storage coefficient at time t+1 Let be the hydrogen storage coefficient at time t. Let be the amount of hydrogen gas flowing in at time t. Let be the hydrogen flow rate at time t. This represents the maximum hydrogen storage capacity.

[0043] The ammonia synthesis model describes the dynamic characteristics of the ammonia synthesis process and the mechanism of ammonia production. It can further reflect the impact of hydrogen supply fluctuations and process parameters in the ammonia synthesis stage on ammonia synthesis efficiency, yield, and system stability. Specifically, the ammonia synthesis model can further include an ammonia production model, a bed temperature model, and a reaction tower pressure model. For example, an ammonia production model can be constructed using the chemical reaction formula for ammonia synthesis, the formula for calculating the ammonia synthesis reaction rate, and the formula for calculating the equilibrium constant of the ammonia synthesis reaction. The formula for calculating the ammonia synthesis reaction rate is as follows: Where v represents the ammonia synthesis reaction rate, and A represents the prefactor. Let R represent the activation energy, R represent the gas constant, and T represent the temperature; the formula for calculating the equilibrium constant of the ammonia synthesis reaction is: ,in This represents the equilibrium constant for the ammonia synthesis reaction. This represents the square of the ammonia concentration. Indicates nitrogen concentration. This represents the cube of the hydrogen concentration. The bed temperature model can be expressed by the following formula. ,in The bed temperature at time t+1 Let be the bed temperature at time t; Let be the time interval between time t and time t+1. For the heat capacity of the bed, The reaction is exothermic; To absorb heat for cooling, Related to cooling airflow; For other heat dissipation. The pressure model of the reaction tower can be expressed by the following formula: ,in, The pressure inside the reaction tower at time t+1 Let be the pressure of the reaction tower at time t, R be the gas constant, and T(t) be the gas temperature inside the reaction tower at time t. Let be the time interval between time t and time t+1. This refers to the intake airflow rate; V is the outlet gas flow rate; V is the reaction tower volume.

[0044] Optionally, the simulation input parameters include preset operating condition parameters and preset control parameters. The preset operating condition parameters include wind and solar power generation and hydrogen load demand, while the preset control parameters include hydrogen production load allocation strategy, hydrogen storage and release control strategy, system power consumption principles, and hydrogen consumption process control parameters.

[0045] Wind and solar power generation capacity refers to the theoretical maximum power output of wind and solar power calculated based on the characteristics of wind and solar resources within a given control period. Wind and solar power generation capacity reflects the maximum available energy input boundary of a hydrogen-based energy system. Hydrogen load demand refers to the target output of the hydrogen-using process within the control period. For example, when a hydrogen-based energy system uses hydrogen to synthesize ammonia, the hydrogen load demand can be the total amount of ammonia to be synthesized within the control period, the ammonia flow rate requirement at each control moment, or converted into the power equivalent corresponding to the ammonia synthesis reaction. Hydrogen load demand reflects the downstream production target of the hydrogen-based energy system. The control period can be manually set according to control requirements, for example, it can be set to 24 hours.

[0046] Hydrogen production load allocation strategy refers to the rules for distributing the required total hydrogen production power across different operating times to meet downstream hydrogen demand. Examples include the permissible operating range of hydrogen production equipment, load change rate limits, and conditions for increasing and decreasing the hydrogen production load. Hydrogen storage and release strategy refers to the logical rules for determining when to store excess hydrogen or release hydrogen to supplement downstream demand. Examples include setting upper and lower limits for hydrogen storage and the conditions for hydrogen storage and release. System power consumption principles refer to the management rules for system interaction with the external power grid and internal power consumption priorities. Specifically, this may include power thresholds for backflow prevention control (limiting the maximum power fed back to the grid), the maximum permissible power supplied to the grid (limiting the upper limit of power purchased from the grid), and the priority relationship between power curtailment and hydrogen production. For example, when wind and solar power generation is excessive, hydrogen production load is increased first, and power curtailment only occurs when the hydrogen production load reaches its maximum. Process control parameters in the hydrogen consumption stage refer to the control parameters of key processes in the hydrogen consumption stage, used to maintain the stability and efficiency of the reaction process. For example, when using hydrogen to synthesize ammonia, the process control parameters for the hydrogen-using stage may include control algorithm parameters for flow regulating valves such as fresh gas, circulating gas, and cooling gas in the reaction tower, such as the proportional, integral, and derivative gains in a proportional-derivative-integral control algorithm.

[0047] Optionally, the simulation output data includes power-side response data and process-side response data. The power-side response data includes the actual power generation of wind and solar power, the power supplied to the grid or back-feeding power, and the power consumption of hydrogen production load. The process-side response data includes hydrogen storage capacity, hydrogen flow rate, hydrogen production at the hydrogen consumption stage, and the temperature and pressure of the hydrogen consumption stage reaction unit.

[0048] Power-side response data characterizes the actual power consumption of hydrogen-based energy systems. Actual wind and solar power generation refers to the power generated by the system using wind and solar resources. Actual wind and solar power generation is influenced by hydrogen production load allocation strategies and system power consumption principles, and is typically less than the total wind and solar power generation. Grid-connected or backfeed power refers to the power exchanged between the system and the external power grid; positive values ​​indicate power purchased from the grid, while negative values ​​indicate power fed back to the grid. Hydrogen production load power consumption refers to the actual power consumed by hydrogen production equipment. Process-side response data characterizes the material flow and process status of actual hydrogen production, storage, and consumption. Hydrogen storage capacity refers to the total amount of hydrogen currently stored in the storage system. Hydrogen flow rate can be understood as the hydrogen flow rate at key nodes in the system, such as the hydrogen output from the electrolyzer, the hydrogen inflow and outflow from the storage tank, and the hydrogen flow rate supplied for ammonia synthesis. Hydrogen consumption output refers to the actual output indicators of downstream hydrogen-using processes. When using hydrogen to synthesize ammonia, hydrogen consumption output can include ammonia storage capacity, ammonia flow rate, and ammonia production. Temperature and pressure in hydrogen-using reactors refer to key process parameters in the hydrogen-using process. For example, when using hydrogen to synthesize ammonia, the temperature and pressure in the hydrogen-using reactor can specifically include the temperature of different beds in the ammonia synthesis tower and the outlet pressure of the synthesis tower.

[0049] Step 202: Train a parameter performance prediction model based on the sample dataset. The parameter performance prediction model is used to characterize the mapping relationship between simulation input parameters and simulation output data.

[0050] Step 203: Call the pre-built expert rule base to generate a control parameter selection benchmark corresponding to the actual operating condition parameters.

[0051] The expert rule base is a set of feasible constraints for control parameters, formed based on expert experience and the fundamental engineering principles of ammonia synthesis, hydrogen electrolysis, and system operation. The control parameter selection benchmark refers to the feasible reference values ​​or ranges of control parameters under actual operating conditions, determined through the expert rule base.

[0052] In this embodiment, by calling a pre-built expert rule base, a control parameter selection benchmark corresponding to the actual operating condition parameters is generated, which can ensure that the candidate control parameters meet the engineering experience constraints and has a certain degree of safety and operability.

[0053] Optionally, the expert rule base generates the control parameter selection benchmark by at least one of the following methods: (1) Based on the allowable operating range and load change rate limit of the hydrogen production equipment, a selection criterion for the hydrogen production load allocation strategy is generated.

[0054] The permissible operating range of a hydrogen production unit refers to the range of load power allowed for the safe and stable operation of the unit, typically including the minimum operating power and the rated power. The load variation rate limit of a hydrogen production unit refers to the permissible power variation range per unit time, including limits on the rate of increase and the rate of decrease.

[0055] The selection rules for hydrogen production load allocation strategies may also include: prioritizing the use of wind and solar power for hydrogen production; if the power output of wind and solar power is greater than the current hydrogen production load, then increasing the hydrogen production load to the upper limit, which is conducive to maximizing the absorption of wind and solar power and reducing power waste; if the power output of wind and solar power is lower than the lower limit of hydrogen production load, then considering purchasing electricity from the grid or adjusting the hydrogen production load allocation.

[0056] In this embodiment, a selection criterion for hydrogen production load allocation strategy is generated based on the allowable operating range and load change rate limit of the hydrogen production equipment. This can ensure the safe and continuous operation of the hydrogen production equipment, reduce equipment lifespan loss, and improve operational reliability.

[0057] (2) Based on the charging and discharging rate limit and safe capacity range of the hydrogen storage system, a selection criterion for hydrogen storage and discharging control strategy is generated.

[0058] The charge / discharge rate limit of a hydrogen storage system refers to the maximum rate at which hydrogen can be charged into or released from the storage device per unit time. The safe capacity range refers to the safe interval within which the storage device can store hydrogen, typically expressed as the minimum and maximum safe hydrogen storage capacities.

[0059] The selection rules for hydrogen storage and release control strategies can also include: when the hydrogen production is greater than the hydrogen consumption for ammonia synthesis but less than the hydrogen production, hydrogen storage is carried out until the maximum safe hydrogen storage capacity is reached; when the hydrogen consumption for ammonia synthesis is greater than the hydrogen production, hydrogen release is carried out until the minimum safe hydrogen storage capacity is reached. This can smooth out wind and solar power fluctuations and ensure the stable operation of downstream ammonia synthesis equipment.

[0060] In this embodiment, by generating a selection criterion for hydrogen storage and release control strategy based on the charging and discharging rate limit and safe capacity range of the hydrogen storage system, it is possible to effectively suppress the imbalance between hydrogen supply and demand caused by wind and solar fluctuations and improve the system's ability to support downstream hydrogen demand while ensuring the safety of hydrogen storage equipment.

[0061] (3) Based on the system's anti-backflow control requirements and the conditions for using the downstream power grid, a selection benchmark for the system's power consumption principles is generated.

[0062] System backflow prevention control requirements refer to the constraints set to prevent electricity from being fed back to the upstream power grid. Specifically, these may include the maximum permissible backflow power threshold, which is usually set to 0, meaning that power is not allowed to be fed back to the grid. Grid power usage conditions refer to the permissible conditions and restrictions for purchasing electricity from the grid. Specifically, this may include allowing grid power to be purchased only when wind and solar power generation does not meet the power requirements for hydrogen production, and the maximum power limit for grid power purchases.

[0063] The system's power consumption principles may also include allowing the abandonment of some wind and solar power generation only when the hydrogen production equipment has reached its maximum load and the hydrogen storage system has reached its safe capacity limit.

[0064] In this embodiment, by generating a selection criterion for the system's power consumption principle based on the system's anti-reverse flow control requirements and the conditions for using grid power, the system can reduce the cost of purchased electricity, improve the absorption rate of wind and solar power generation, and meet the safety requirements of the power grid.

[0065] (4) Based on the temperature protection threshold and pressure protection threshold of the hydrogen-using reactor, a selection basis for the process control parameters of the hydrogen-using process is generated.

[0066] Temperature protection thresholds refer to the permissible temperature range set for hydrogen-based reaction equipment to ensure reaction efficiency and equipment safety, including a lower temperature limit and an upper temperature limit. Pressure protection thresholds refer to the permissible pressure range for hydrogen-based reaction equipment, including a lower pressure limit and an upper pressure limit.

[0067] For example, when using hydrogen to synthesize ammonia, the temperature protection threshold may include the upper and lower limits of the bed temperature of the ammonia synthesis reaction tower, and the pressure protection threshold may include the upper and lower limits of the outlet pressure of the synthesis tower. The selection rules for process control parameters may also include: (1) If the bed temperature is close to the upper limit or the rate of increase is too fast, increase the cooling gas flow rate and reduce the fresh gas intake to suppress further temperature rise; (2) The control algorithm for the flow regulating valves used to control the flow of fresh gas, circulating gas, cooling gas, etc., adopts relatively conservative initial values. For example, when using the proportional-integral-derivative algorithm, the proportional gain, derivative gain, and integral gain parameters can be selected with relatively small initial values.

[0068] In this embodiment, by generating selection criteria for process control parameters based on the temperature protection threshold and pressure protection threshold of the hydrogen-using reactor, it is possible to prevent the hydrogen-using equipment from overheating and overpressure, reduce safety risks, ensure the continuous and stable operation of the hydrogen-using process, and thus guarantee product quality.

[0069] Step 204: Sample parameters within the neighborhood of the control parameter selection benchmark to generate a candidate control parameter set containing multiple sets of control parameters to be evaluated.

[0070] The neighborhood refers to the variable interval defined around the control parameter selection benchmark. The control parameters to be evaluated refer to a set of feasible control parameter combinations generated by parameter sampling methods within the neighborhood of the control parameter selection benchmark, which are then evaluated by the performance prediction model. Specifically, the feasible neighborhood of candidate control parameters can be formed by extending the control parameter selection benchmark in both positive and negative directions by a certain step size or proportion. Then, parameter sampling methods such as random sampling, grid sampling, and Latin hypercube sampling can be used to sample and generate a set of candidate control parameters within the neighborhood of the parameter selection benchmark. Alternatively, multiple parameter sampling methods can be used simultaneously to generate a certain proportion of the control parameters to be evaluated from the candidate control parameter sets.

[0071] Step 205: Combine each set of control parameters to be evaluated in the candidate control parameter set with the actual operating condition parameters to form multiple sets of input parameters to be evaluated.

[0072] Step 206: Input multiple sets of input parameters to be evaluated into the parameter performance prediction model, and the parameter performance prediction model outputs the prediction output data corresponding to each set of input parameters to be evaluated.

[0073] Specifically, actual operating condition parameters can be input into a pre-built expert rule model to generate a control parameter selection benchmark corresponding to the actual operating condition parameters. Then, multiple feasible input parameters to be evaluated are generated through parameter sampling. The actual operating condition parameters and the input data to be evaluated are combined to construct a feature vector, which is used as the input data for the parameter performance prediction model. The parameter performance prediction model can predict the dynamic response data of the hydrogen-based energy system under the control of various control parameters to be evaluated in actual operating conditions with a certain accuracy.

[0074] For example, the input parameter to be evaluated can be represented as ,in, This indicates the construction of eigenvectors. Indicates actual operating parameters. This represents the control parameter to be evaluated. The parameter performance prediction model can be a random forest regression model. ,in It consists of B regression trees, each regression tree The random forest regression model is trained using a subset of samples generated by bootstrapping, with a feature subset of samples randomly selected each time the nodes of the regression tree are split. The predicted output data of the random forest regression model is... .

[0075] Step 207: Evaluate the security of the predicted output data corresponding to each set of input parameters to be evaluated based on the preset security indicators.

[0076] The safety indicators include at least one of the following: equipment load upper and lower limits, equipment load change rate, reaction unit temperature and pressure, and hydrogen storage system safety margin. Safety indicators are evaluation metrics used to quantify the degree to which a hydrogen-based energy system meets various safety constraints during operation. Specifically, equipment load upper and lower limits, equipment load change rate, reaction unit temperature and pressure, and hydrogen storage system safety margin all have corresponding constraints. When any of the above safety indicators fails to meet the corresponding constraint at a certain control moment, a risk penalty value can be applied to that moment. Finally, the penalty values ​​for each control moment within the control cycle are summed to obtain the corresponding safety indicator value. For example, the equipment load constraint can be... ,in, Let t be the actual equipment load at time t. Let t be the lower limit of the equipment load. The upper limit of equipment load at time t; the constraint on the rate of change of equipment load can be... ,in, The power of the device at time t+1. Let be the device power at time t. This refers to the maximum allowable fluctuation value of the equipment power, where the equipment can be hydrogen production or hydrogen utilization equipment, etc., but this embodiment does not limit it. The temperature and pressure constraints of the reaction device can be... and in, This represents the inlet pressure of the reaction tower at time t. This indicates the lower limit of the inlet pressure of the reaction tower. Indicates the upper limit of the inlet pressure of the reaction tower. This represents the temperature of the i-th segment of the reaction tower at time t. This indicates the lower temperature limit of the i-th section of the reaction tower. This represents the upper temperature limit of the i-th section of the reaction tower. The safety margin constraint for the hydrogen storage system can be... ,in This represents the hydrogen storage coefficient at time t. This indicates the lower limit of the safety margin for hydrogen storage. This represents the upper limit of the safe hydrogen storage coefficient. The safety index can be expressed as... ,in denoted as the risk penalty value of indicator j, and t represents any control moment within the control period.

[0077] Step 208: Evaluate the economic efficiency of the predicted output data corresponding to each set of input parameters to be evaluated based on the preset economic indicators.

[0078] Economic indicators are evaluation metrics used to quantify the economic benefits and resource utilization efficiency of hydrogen-based energy systems during operation. These indicators include at least one of the following: energy cost indicators, wind and solar curtailment loss indicators, production matching degree indicators, and system energy efficiency indicators.

[0079] For example, energy cost indicators It can be calculated using the following formula , where t represents each control moment within the control cycle. This represents the power consumption at time t. This represents the electricity cost at time t. Indicates the length of the control period. Wind and solar curtailment loss index. It can be calculated using the following formula ,in Indicates the cost of curtailing electricity. This represents the amount of power curtailed at time t. Production matching index. It can be calculated using the following formula .in, This represents the ammonia production at time t. This represents the target ammonia production at time t. System energy efficiency index. It can be calculated using the following formula ,in This represents the electrical load for ammonia synthesis at time t. Economic evaluation indicators. It can be calculated using the following formula, ,in, This indicates the preset system energy efficiency target. These represent the weighting parameters for energy cost indicators, wind and solar curtailment loss indicators, output matching degree indicators, and system energy efficiency indicators, respectively.

[0080] Step 209: Perform a weighted calculation on the safety evaluation results and the economic evaluation results to obtain a comprehensive score for each set of input parameters to be evaluated.

[0081] Specifically, the safety evaluation results and economic evaluation results can be weighted and summed using preset safety weights and preset economic weights to obtain a comprehensive score for each set of input parameters to be evaluated. For example, if the safety evaluation result is... The economic evaluation result is Then the formula for calculating the comprehensive score J can be: ,in For the preset security weight, The preset economic weights.

[0082] Step 210: Sort the control parameters to be evaluated in the candidate control parameter set from high to low according to the comprehensive score.

[0083] Specifically, a higher overall score indicates better control quality of the hydrogen-based energy system under actual operating conditions, achieved by applying the control parameters to be tested.

[0084] Step 211: Apply the recommended control parameters to the hydrogen-based energy system and collect on-site operation data of the hydrogen-based energy system.

[0085] Step 212: Compare the field operation data with the simulation output data of the system-level dynamic simulation model under the same operating parameters to calculate the deviation between the two.

[0086] Specifically, the deviation is calculated by comparing the field operation data with the simulation output data obtained from the system-level dynamic simulation model under the same preset operating parameters. The deviation can be quantified based on the root mean square error, mean absolute error, or relative error of the simulation output data and the field operation data, and is used to determine the degree of consistency between the system-level dynamic simulation model and the actual operation.

[0087] Step 213: When the deviation value exceeds the preset threshold, the model parameters of the system-level dynamic simulation model are corrected based on the field operation data.

[0088] Specifically, when the deviation between the field operation data and the simulation output data of the system-level dynamic simulation model under the same operating parameters exceeds a preset threshold, it indicates that the current system-level dynamic simulation model has low accuracy in simulating the actual dynamic response of the hydrogen-based energy system. In this case, manual parameter identification or machine learning algorithms can be used to correct the key parameters of the system-level dynamic simulation model. Key parameters may include system configuration parameters and equipment characteristic parameters of the hydrogen-based energy system, so as to minimize the simulation output results of the corrected simulation model to better match the field operation data.

[0089] Step 214: Re-execute the simulation of the corrected system-level dynamic simulation model under actual operating parameters to generate new sample data.

[0090] Specifically, after the system-level dynamic simulation model is corrected, the actual operating parameters can be used as input to call the corrected system-level dynamic simulation model to recalculate and generate a new set of simulation output data. Then, the actual operating data and the new simulation output data are combined to form new sample data, which can be used as the basis for subsequent parameter performance prediction model updates.

[0091] Step 215: Add the new sample data to the sample dataset and retrain the parameter performance prediction model based on the updated sample dataset.

[0092] Specifically, the new sample data is integrated into the original sample dataset to form an updated sample dataset. Then, the parameter performance prediction model is retrained using the updated sample dataset. The training process can be carried out by complete retraining or incremental learning, so that the parameter performance prediction model can learn the latest operating characteristics of the system, thereby maintaining its prediction accuracy and adaptability, and providing a reliable foundation for subsequent control parameter optimization.

[0093] In this embodiment, the deviation value between the field operation data and the simulation output data of the system-level dynamic simulation model under the same operating parameters is calculated by comparing the consistency of the field operation data and the simulation output data of the system-level dynamic simulation model. When the deviation value exceeds a preset threshold, the model parameters of the system-level dynamic simulation model are corrected based on the field operation data. The corrected system-level dynamic simulation model is re-executed under the actual operating parameters to generate new sample data. The new sample data is added to the sample dataset, and the parameter performance prediction model is retrained based on the updated sample dataset. This ensures that the system-level dynamic simulation model and the parameter performance prediction model are corrected only under necessary conditions, avoiding frequent model corrections that would waste resources, while ensuring that the model can be corrected in a timely manner when the system characteristics deviate.

[0094] In this embodiment, a multi-condition control simulation is performed based on the simulation input parameters by calling the system-level dynamic simulation model of the hydrogen-based energy system to obtain simulation output data under various parameter combinations. A sample dataset containing simulation input parameters and simulation output data is constructed, which can consider the coupling relationship between hydrogen production, storage, and utilization, and comprehensively cover the main operating conditions of the hydrogen-based energy system. This ensures the sample dataset has broad representativeness and coverage, improving the accuracy of the parameter performance prediction model. The parameter performance prediction model is trained based on the sample dataset and is used to characterize the mapping relationship between simulation input parameters and simulation output data. A pre-built expert rule base is called to generate control parameter selections corresponding to the actual operating condition parameters. A benchmark ensures that candidate control parameters meet engineering experience constraints, providing a degree of safety and operability. Parameter sampling is performed within the neighborhood of the benchmark to generate a candidate control parameter set containing multiple sets of control parameters to be evaluated. Each set of control parameters to be evaluated in the candidate set is combined with actual operating condition parameters to form multiple sets of input parameters to be evaluated. These multiple sets of input parameters are then input into a parameter performance prediction model, which outputs predicted output data for each set of input parameters. This process allows for rapid evaluation and screening of a large number of candidate control parameters, reducing reliance on individual experience during commissioning and minimizing uncertainty caused by differences in experience among different commissioning personnel, thereby effectively improving... The system optimizes debugging efficiency and consistency; it evaluates the safety of the predicted output data for each set of input parameters to be evaluated based on preset safety indicators; it evaluates the economy of the predicted output data for each set of input parameters to be evaluated based on preset economic indicators; it weights the safety evaluation results and the economic evaluation results to obtain a comprehensive score for each set of input parameters to be evaluated; it sorts the control parameters in the candidate control parameter set from high to low according to the comprehensive score; it applies the recommended control parameters to the hydrogen-based energy system and collects the field operation data of the hydrogen-based energy system, which enables the evaluation results of the recommended control parameters to meet both the safety baseline and the economic optimum, avoiding decision imbalance caused by a single evaluation indicator; The system compares the field operation data with the simulation output data of the system-level dynamic simulation model under the same operating parameters to calculate the deviation between them. When the deviation exceeds a preset threshold, the model parameters of the system-level dynamic simulation model are corrected based on the field operation data. The corrected system-level dynamic simulation model is then re-executed under actual operating parameters to generate new sample data. The new sample data is added to the sample dataset, and the parameter performance prediction model is retrained based on the updated sample dataset. This ensures that the system-level dynamic simulation model and the parameter performance prediction model are corrected only under necessary conditions, avoiding frequent model corrections that would waste resources, while also ensuring that the model can be corrected in a timely manner when system characteristics deviate.

[0095] Figure 4This is a flowchart illustrating the determination of recommended control parameters provided in an embodiment of the present invention. (See attached diagram.) Figure 4 The process of recommending control parameters based on actual operating conditions can be divided into the following steps: First, the actual operating condition parameters X1 are collected and input into a pre-built expert rule model to obtain baseline parameters and feasible region constraints. Then, parameter sampling is performed based on the baseline parameters and feasible region constraints to generate a candidate parameter set. The candidate parameter set contains multiple sets of control parameters X2 to be evaluated. Multiple sets [X1, X2] are used as input parameters and input into a pre-trained random forest model. The random forest model can characterize the mapping relationship between the input parameters and the actual dynamic response of the hydrogen-based energy system. Subsequently, the preset evaluation index value is calculated based on the output parameters of the random forest model, and the evaluation index values ​​are weighted and summed. The evaluation index values ​​are sorted from largest to smallest, and the control parameter to be evaluated with the best evaluation index is output as the recommended debugging parameter for debugging control during the actual operation of the hydrogen-based energy system.

[0096] Figure 5 This is another flowchart illustrating the debugging method for a hydrogen-based energy system provided in this embodiment of the invention. (See attached diagram.) Figure 5 This method takes hydrogen-based energy systems as the research object. The main steps include system-level modeling, dynamic simulation of the system under multiple operating conditions, construction of sample datasets, construction of expert database rule models, construction of random forest regression models, recommendation through fusion intelligent recommendation models, and on-site debugging and parameter updates. The overall method flow is as follows: Step 1: System-level modeling. Collect basic system data, including but not limited to system configuration parameters such as the capacity and system topology of wind power, photovoltaic, hydrogen production, hydrogen storage, and ammonia synthesis units, as well as equipment characteristic parameters such as electrolyzer energy consumption curves and ammonia synthesis reaction heat balance parameters. Based on this, construct a system-level dynamic simulation model covering key units such as wind and solar power generation, water electrolysis for hydrogen production, hydrogen storage, and ammonia synthesis. This model reflects the dynamic response characteristics of the multi-energy system under different operating conditions and control strategies, providing a simulation foundation for subsequent analysis.

[0097] Step 2, System Multi-condition Dynamic Simulation: Based on the system-level dynamic simulation model, conduct multi-condition dynamic simulation analysis for debugging scenarios. The inputs to the simulation analysis include operating condition parameters. Control parameters And key results Y. Among them, (1) operating parameters Used to simulate abnormal or disturbed scenarios. The operating parameters include at least the theoretical maximum power generation of wind power and photovoltaic power and the total 24-hour load demand of the synthetic ammonia system. By manually setting the operating parameters, the following typical operating conditions can be constructed to cover the main operating conditions that the system may face during actual commissioning: Wind and solar power generation: wind and solar power output is significantly higher than the current system load demand; Wind and solar power shortage: wind and solar power output is less than the system load demand, and it needs to be compensated by energy storage or grid connection; Wind and solar power sudden change: wind and solar power output fluctuates greatly in a short period of time. (2) Control parameters Used to simulate different debugging control strategies. Under a given operating condition Under these conditions, different combinations of debugging logic and control parameters are further set to form control parameters. . It should include at least the hydrogen production load strategy, hydrogen storage and release strategy, system power consumption principle, and green ammonia synthesis process control logic: control logic for flow regulating valves such as fresh gas, circulating gas, and cooling gas. (3) The key output result Y is used to evaluate the safety, stability, and economy of the system operation under different commissioning strategies. Under a given operating condition input and control parameter input Under the given conditions, a system-level multi-condition dynamic simulation is performed to obtain the corresponding key output result Y. The key output result includes at least: power-side result data, such as the actual power generation curves of wind power and photovoltaic power, the power curves of power supplied to the grid or back-feeding, and the power consumption curve of hydrogen production load; and process-side result data, such as key process indicators including hydrogen storage capacity, ammonia storage capacity, hydrogen flow rate, ammonia flow rate, synthetic ammonia production, synthetic ammonia conversion rate, temperature of different beds in the synthetic ammonia reaction tower, and outlet pressure of the synthesis tower.

[0098] Step 3: Sample Dataset Construction: By repeating Steps 1 and 2, a sample dataset covering multiple operating conditions and control strategies is constructed. This dataset is used to characterize the system's operational characteristics under different operating conditions and combinations of debugging parameters, and serves as the foundation for subsequent training of the intelligent recommendation model. Each sample data point in the sample dataset can be represented as... .

[0099] Step 4: Expert Rule Base Model Construction: Based on the fundamental engineering principles of hydrogen-based energy system operation, a mapping relationship model based on experience and mechanism constraints is formed as the expert rule base model. This expert rule base ensures that the recommended debugging parameters meet safety, operability, and engineering experience constraints. In the actual recommendation process, parameters can be determined based on actual operating conditions. Baseline parameter set can be obtained And feasibility constraints.

[0100] Step 5: Random Forest Regression Model Construction: Based on the sample dataset, the random forest regression model from the machine learning model is used to process the input parameters. The nonlinear relationship between the input and output features is learned to construct an input-output feature mapping model. .

[0101] Step 6: Integrated Intelligent Recommendation Model Recommendation: While ensuring engineering feasibility, the integrated intelligent recommendation model fully utilizes simulation data and the learning capabilities of the random forest regression model to provide recommended control parameters for the commissioning of the hydrogen-based energy system under different operating conditions. In the actual recommendation process, the baseline parameter set obtained in Step 4 is used... By combining actual operating parameters Multiple sets of input parameters can be obtained from the various control parameters in the baseline parameter set. By inputting it into a random forest regression model, the corresponding key output results can be obtained. By using pre-defined evaluation criteria, such as ammonia conversion rate, reactor bed temperature, and system power waste, evaluation results are calculated for key outputs. Multiple evaluation results are then weighted to obtain a comprehensive evaluation result. Based on this comprehensive evaluation result, baseline parameters are judged for their merits, allowing recommended commissioning control parameters for actual operating conditions to be selected from the baseline parameter set. .

[0102] Step 7, On-site Commissioning and Parameter Update: In the actual control of the hydrogen-based energy system, the intelligently recommended control strategy and commissioning steps are executed, system operation data is collected in real time, and the consistency is compared with the simulation output results. When there is a deviation between the on-site operation data and the simulation data, the system-level dynamic simulation model parameters and expert rule base model are updated through online identification and machine learning algorithms to achieve adaptive correction of the model and rules.

[0103] Figure 4 This is a schematic diagram of a debugging device for a hydrogen-based energy system provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes: Module 401 is used to call the system-level dynamic simulation model of the hydrogen-based energy system to perform multi-condition control simulation based on multiple sets of preset operating condition parameters and corresponding multiple sets of preset control parameters, so as to obtain simulation output data under various parameter combinations and construct a sample dataset containing simulation input parameters and simulation output data. Training module 402 is used to train a parameter performance prediction model based on a sample dataset. The parameter performance prediction model is used to characterize the mapping relationship between simulation input parameters and simulation output data. The generation module 403 is used to generate a set of candidate control parameters for actual operating conditions. Output module 404 is used to call the parameter performance prediction model to predict the performance of the candidate control parameter set, evaluate and rank the performance prediction results based on preset evaluation indicators, and output recommended control parameters based on the ranking results. The update module 405 is used to apply the recommended control parameters to the hydrogen-based energy system, collect the field operation data of the hydrogen-based energy system, and update the system-level dynamic simulation model and parameter performance prediction model based on the field operation data.

[0104] In one embodiment, the generation module 403 generates a set of candidate control parameters for actual operating condition parameters, including: Call the pre-built expert rule base to generate a control parameter selection benchmark that corresponds to the actual operating condition parameters; Parameters are sampled within the neighborhood of the control parameter selection benchmark to generate a candidate control parameter set containing multiple sets of control parameters to be evaluated.

[0105] In one embodiment, the expert rule base generates the control parameter selection criteria by at least one of the following methods: Based on the permissible operating range and load change rate limit of the hydrogen production equipment, a selection criterion for the hydrogen production load allocation strategy is generated. Based on the charging and discharging rate limits and safe capacity range of the hydrogen storage system, a selection criterion for the hydrogen storage and discharging control strategy is generated. Based on the system's backflow prevention control requirements and the conditions for using the grid power, a selection benchmark for the system's power consumption principles is generated. Based on the temperature protection threshold and pressure protection threshold of the hydrogen-using reactor, a selection benchmark for the process control parameters of the hydrogen-using process is generated.

[0106] In one embodiment, the output module 404 calls the parameter performance prediction model to perform performance prediction on the candidate control parameter set, including: Each set of control parameters to be evaluated in the candidate control parameter set is combined with the actual operating condition parameters to form multiple sets of input parameters to be evaluated. Multiple sets of input parameters to be evaluated are input into the parameter performance prediction model, and the parameter performance prediction model outputs the predicted output data corresponding to each set of input parameters to be evaluated.

[0107] In one embodiment, the output module 404 evaluates and ranks the performance prediction results based on preset evaluation indicators, including: The safety of the predicted output data corresponding to each set of input parameters to be evaluated is evaluated based on the preset safety indicators. The safety indicators include at least one of the following: equipment load upper and lower limit indicators, equipment load change rate indicators, reaction device temperature and pressure indicators, and hydrogen storage system safety margin indicators. The economic evaluation is carried out on the predicted output data corresponding to each set of input parameters to be evaluated based on the preset economic indicators. The economic indicators include at least one of the following: energy cost indicators, wind and solar curtailment loss indicators, output matching degree indicators, and system energy efficiency indicators. The safety evaluation results and economic evaluation results are weighted and calculated to obtain a comprehensive score for each set of input parameters to be evaluated; The control parameters to be evaluated in the candidate control parameter set are sorted from high to low according to the comprehensive score.

[0108] In one embodiment, the update module 405 updates the system-level dynamic simulation model and parameter performance prediction model based on field operation data, including: The consistency of the field operation data and the simulation output data of the system-level dynamic simulation model under the same operating parameters is compared to calculate the deviation between the two. When the deviation exceeds the preset threshold, the model parameters of the system-level dynamic simulation model are corrected based on the field operation data; The corrected system-level dynamic simulation model is re-executed under actual operating parameters to generate new sample data. New sample data is added to the sample dataset, and the parameter performance prediction model is retrained based on the updated sample dataset.

[0109] In one embodiment, the true input parameters include preset operating condition parameters and preset control parameters. The preset operating condition parameters include wind and solar power generation capacity and hydrogen load demand. The preset control parameters include hydrogen production load allocation strategy, hydrogen storage and release control strategy, system power consumption principle, and hydrogen consumption process control parameters.

[0110] In one embodiment, the simulation output data includes power-side response data and process-side response data. The power-side response data includes the actual power generation of wind and solar power, the power supplied to the grid or back-feeding power, and the power consumption of hydrogen production load. The process-side response data includes hydrogen storage capacity, hydrogen flow rate, hydrogen production at the hydrogen consumption stage, and the temperature and pressure of the hydrogen consumption stage reaction device.

[0111] In one embodiment, the system-level dynamic simulation model includes a power supply side model, an electrolytic hydrogen production model, a hydrogen storage model, and an ammonia synthesis model. The system-level dynamic simulation model is used to simulate the dynamic coupling characteristics of wind and solar power generation, electrolytic hydrogen production, hydrogen storage, and ammonia synthesis processes.

[0112] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0113] The apparatus of this invention calls a system-level dynamic simulation model of a hydrogen-based energy system to perform multi-condition control simulations based on multiple sets of simulation input parameters. This obtains simulation output data under various parameter combinations, constructing a sample dataset containing simulation input parameters and simulation output data. This dataset considers the coupling relationship between hydrogen production, storage, and utilization, comprehensively covers the main operating conditions of the hydrogen-based energy system, and ensures broad representativeness, thereby improving the accuracy of the parameter performance prediction model. The parameter performance prediction model is trained based on this sample dataset. This model characterizes the mapping relationship between simulation input parameters and simulation output data, avoiding repeated control simulations and achieving rapid prediction of the hydrogen-based energy system performance while maintaining a certain level of accuracy, saving time and computing resources. A candidate control parameter set is generated based on actual operating condition parameters; the parameter performance prediction model is then called to evaluate the candidate parameters. The system performs performance prediction using a set of control parameters and evaluates and ranks the prediction results based on preset evaluation indicators. Recommended control parameters are then output based on the ranking results. This allows for rapid evaluation and screening of a large number of candidate control parameters, reducing reliance on individual experience during commissioning and minimizing uncertainty caused by differences in experience among different commissioning personnel. This effectively improves commissioning efficiency and consistency. Applying the recommended control parameters to a hydrogen-based energy system involves collecting field operation data and updating the system-level dynamic simulation model and parameter performance prediction model based on this data. This allows the system-level dynamic simulation model and parameter performance prediction model to continuously evolve with the accumulation of field operation data and to update in real time as the actual state of the hydrogen-based energy system changes. This makes the performance prediction results closer to the actual operating results, thereby improving commissioning accuracy and adaptability, and ensuring the reliable operation of the hydrogen-based energy system.

[0114] The following is for reference. Figure 7 It shows a schematic diagram of the structure of a computer system 700 suitable for implementing an electronic device according to embodiments of the present invention. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0115] like Figure 7As shown, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 702 or programs loaded from storage section 708 into Random Access Memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the computer system 700. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An Input / Output (I / O) interface 705 is also connected to the bus 704.

[0116] The following components are connected to I / O interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube, liquid crystal display, etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card, such as a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to I / O interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 710 as needed so that computer programs read from it can be installed into storage section 708 as needed.

[0117] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by central processing unit (CPU) 701, it performs the functions defined above in the system of this invention.

[0118] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, etc., or any suitable combination thereof.

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0120] The modules and / or units described in the embodiments of the present invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor can be described as including a construction module, a training module, a generation module, an output module, and an update module. The names of these modules do not necessarily limit the module itself.

[0121] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: The system-level dynamic simulation model of the hydrogen-based energy system is invoked to perform multi-condition control simulation based on multiple sets of preset operating parameters and corresponding sets of preset control parameters to obtain simulation output data under various parameter combinations. A sample dataset containing simulation input parameters and simulation output data is constructed. A parameter performance prediction model is trained based on the sample dataset. The parameter performance prediction model is used to characterize the mapping relationship between simulation input parameters and simulation output data. A set of candidate control parameters is generated for actual operating parameters. The parameter performance prediction model is invoked to predict the performance of the candidate control parameter set, and the performance prediction results are evaluated and ranked based on preset evaluation indicators. Recommended control parameters are output based on the ranking results. The recommended control parameters are applied to the hydrogen-based energy system, field operation data of the hydrogen-based energy system is collected, and the system-level dynamic simulation model and parameter performance prediction model are updated based on the field operation data.

[0122] The technical solution of this invention involves calling a system-level dynamic simulation model of a hydrogen-based energy system to perform multi-condition control simulations based on multiple sets of simulation input parameters. This obtains simulation output data under various parameter combinations, constructing a sample dataset containing both simulation input parameters and simulation output data. This dataset considers the coupling relationship between hydrogen production, storage, and utilization, comprehensively covers the main operating conditions of the hydrogen-based energy system, and ensures broad representativeness, thereby improving the accuracy of the parameter performance prediction model. The parameter performance prediction model is trained based on this sample dataset. This model characterizes the mapping relationship between simulation input parameters and simulation output data, avoiding repeated control simulations and achieving rapid prediction of the hydrogen-based energy system's performance while maintaining a certain level of accuracy, saving time and computing resources. Furthermore, a candidate control parameter set is generated based on actual operating condition parameters. The parameter performance prediction model is then used to analyze the candidate parameters. The system selects a set of control parameters for performance prediction and evaluates and ranks the prediction results based on preset evaluation indicators. Recommended control parameters are then output based on the ranking results. This allows for rapid evaluation and screening of a large number of candidate control parameters, reducing reliance on individual experience during commissioning and minimizing uncertainty caused by differences in experience among different commissioning personnel. This effectively improves commissioning efficiency and consistency. Applying the recommended control parameters to the hydrogen-based energy system, collecting on-site operating data, and updating the system-level dynamic simulation model and parameter performance prediction model based on this data allows these models to continuously evolve with the accumulation of on-site operating data and update in real time as the actual state of the hydrogen-based energy system changes. This makes the performance prediction results closer to the actual operating results, thereby improving commissioning accuracy and adaptability, and ensuring the reliable operation of the hydrogen-based energy system.

[0123] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the debugging method for a hydrogen-based energy system as provided in any embodiment of this invention.

[0124] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0125] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A debugging method for a hydrogen-based energy system, characterized in that, include: The system-level dynamic simulation model of the hydrogen-based energy system is invoked to perform multi-condition control simulation based on multiple sets of preset operating condition parameters and corresponding multiple sets of preset control parameters, so as to obtain the simulation output data under various parameter combinations and construct a sample dataset containing simulation input parameters and simulation output data. A parameter performance prediction model is trained based on the sample dataset. The parameter performance prediction model is used to characterize the mapping relationship between simulation input parameters and simulation output data. Generate a set of candidate control parameters based on actual operating conditions; The parameter performance prediction model is invoked to predict the performance of the candidate control parameter set, and the performance prediction results are evaluated and ranked based on preset evaluation indicators. Recommended control parameters are then output based on the ranking results. The recommended control parameters are applied to the hydrogen-based energy system, on-site operation data of the hydrogen-based energy system is collected, and the system-level dynamic simulation model and the parameter performance prediction model are updated based on the on-site operation data.

2. The method according to claim 1, characterized in that, A set of candidate control parameters is generated based on the actual operating conditions, including: The pre-built expert rule base is invoked to generate a control parameter selection benchmark corresponding to the actual operating condition parameters; Parameters are sampled within the neighborhood of the control parameter selection benchmark to generate the candidate control parameter set containing multiple sets of control parameters to be evaluated.

3. The method according to claim 2, characterized in that, The expert rule base generates the control parameter selection benchmark through at least one of the following methods: Based on the permissible operating range and load change rate limit of the hydrogen production equipment, a selection criterion for the hydrogen production load allocation strategy is generated. Based on the charging and discharging rate limits and safe capacity range of the hydrogen storage system, a selection criterion for the hydrogen storage and discharging control strategy is generated. Based on the system's backflow prevention control requirements and the conditions for using the grid power, a selection benchmark for the system's power consumption principles is generated. Based on the temperature protection threshold and pressure protection threshold of the hydrogen-using reactor, a selection benchmark for the process control parameters of the hydrogen-using process is generated.

4. The method according to claim 1, characterized in that, Invoking the parameter performance prediction model to perform performance prediction on the candidate control parameter set includes: Each set of control parameters to be evaluated in the candidate control parameter set is combined with the actual operating condition parameters to form multiple sets of input parameters to be evaluated. The multiple sets of input parameters to be evaluated are input into the parameter performance prediction model, and the parameter performance prediction model outputs the prediction output data corresponding to each set of input parameters to be evaluated.

5. The method according to claim 4, characterized in that, The performance prediction results are evaluated and ranked based on preset evaluation indicators, including: The safety of the predicted output data corresponding to each set of input parameters to be evaluated is evaluated based on the preset safety indicators. The safety indicators include at least one of the following: equipment load upper and lower limit indicators, equipment load change rate indicators, reaction device temperature and pressure indicators, and hydrogen storage system safety margin indicators. The predicted output data corresponding to each set of input parameters to be evaluated is evaluated economically based on preset economic indicators. The economic indicators include at least one of the following: energy cost indicators, wind and solar curtailment loss indicators, output matching degree indicators, and system energy efficiency indicators. The safety evaluation results and economic evaluation results are weighted and calculated to obtain a comprehensive score for each set of input parameters to be evaluated; The control parameters to be evaluated in the candidate control parameter set are sorted from high to low according to the comprehensive score.

6. The method according to claim 1, characterized in that, The system-level dynamic simulation model and the parameter performance prediction model are updated based on the field operation data, including: The consistency of the field operation data and the simulation output data of the system-level dynamic simulation model under the same operating parameters is compared to calculate the deviation value between the two. When the deviation value exceeds a preset threshold, the model parameters of the system-level dynamic simulation model are corrected based on the field operation data; The corrected system-level dynamic simulation model is re-executed under the actual operating parameters to generate new sample data. The new sample data is added to the sample dataset, and the parameter performance prediction model is retrained based on the updated sample dataset.

7. The method according to claim 1, characterized in that, The simulation input parameters include preset operating condition parameters and preset control parameters. The preset operating condition parameters include wind and solar power generation and hydrogen load demand. The preset control parameters include hydrogen production load allocation strategy, hydrogen storage and release control strategy, system power consumption principle, and hydrogen consumption process control parameters.

8. The method according to claim 1, characterized in that, The simulation output data includes power-side response data and process-side response data. The power-side response data includes the actual power generation of wind and solar power, the power supplied to the grid or back to the grid, and the power consumption of hydrogen production load. The process-side response data includes hydrogen storage capacity, hydrogen flow rate, hydrogen production at the hydrogen consumption stage, and the temperature and pressure of the hydrogen consumption stage reaction unit.

9. The method according to claim 1, characterized in that, The system-level dynamic simulation model includes a power supply model, an electrolytic hydrogen production model, a hydrogen storage model, and an ammonia synthesis model. The system-level dynamic simulation model is used to simulate the dynamic coupling characteristics of wind and solar power generation, electrolytic hydrogen production, hydrogen storage, and ammonia synthesis processes.

10. A hydrogen-based energy system, characterized in that, The system is debugged using the debugging method described in any one of claims 1 to 9.

Images