Hydrogen production and energy supply simulation method and system

Abstract

The invention discloses a hydrogen production and energy supply simulation method and system, and relates to the technical field of hydrogen production, and the method comprises the steps: generating energy input information in an energy supply simulation system; calibrating the future energy prediction information according to the real-time energy output information to obtain calibrated energy prediction information; acquiring operation state information and hydrogen demand information of hydrogen production equipment in the energy supply simulation system; determining power distribution of the hydrogen production equipment; operating parameters of the hydrogen production equipment are adjusted according to the power distribution, the hydrogen production target and the hydrogen storage state; the operation state information of the energy supply simulation system is presented, and the operation process information of the energy supply simulation system is recorded. Optimized operation of the hydrogen production and energy supply system can be achieved, the efficiency, stability and reliability of the system are remarkably improved, and the actual operation risk is reduced.

Description

A method and system for simulating hydrogen production and energy supply Technical Field

[0001] This application relates to the field of hydrogen energy technology, and more specifically, to a method and system for simulating hydrogen production and energy supply. Background Technology

[0002] As the global energy transition accelerates, hydrogen energy, with its clean and efficient characteristics, is gradually becoming an important alternative to traditional fossil fuels. In practical applications, although some simulation tools for hydrogen production systems exist, they are often incomplete. For example, in the power distribution stage, the fluctuating output power of wind and solar energy can easily lead to uneven power distribution within the hydrogen production system, directly affecting the efficiency of the electrolyzer and the final hydrogen yield. Furthermore, these existing simulation tools lack flexibility in adjusting key parameters such as electrolyte temperature and controlling hydrogen supply, making it difficult to achieve optimal system operation. In addition, existing systems are also somewhat inadequate in data display and historical data management. They cannot provide real-time, intuitive displays of the system's current operating status, nor can they support in-depth review and analysis of past data, which undoubtedly limits operators' monitoring and optimization decisions regarding system performance. Therefore, existing technologies urgently need a more intelligent and comprehensive simulation method and system to overcome the problems of uneven power distribution caused by energy output fluctuations, lack of dynamic adjustment capability of key parameters, and weak data visualization and historical data management functions, so as to achieve optimized operation of hydrogen production and energy supply systems and support operators to conduct effective monitoring and decision-making. Summary of the Invention

[0003] This application discloses a method and system for simulating hydrogen production and energy supply, aiming to solve the problems of uneven power distribution under energy output fluctuations, lack of dynamic adjustment capability for key operating parameters, and weak data visualization and historical data management functions in existing hydrogen production and energy supply systems.

[0004] The technical solution of this application is as follows: In the first aspect, this application discloses a method for simulating hydrogen production and energy supply, comprising: generating energy input information in an energy supply simulation system, the energy input information including real-time energy output information and future energy prediction information; calibrating the future energy prediction information based on the real-time energy output information to obtain calibrated energy prediction information; acquiring the operating status information and hydrogen demand information of the hydrogen production equipment in the energy supply simulation system; determining the power allocation of the hydrogen production equipment based on the calibrated energy prediction information, the operating status information of the hydrogen production equipment, and the hydrogen demand information; adjusting the operating parameters of the hydrogen production equipment according to the power allocation, the hydrogen production target, and the hydrogen storage status; presenting the operating status information of the energy supply simulation system, and recording the operating process information of the energy supply simulation system.

[0005] Furthermore, determining the power allocation of the hydrogen production equipment based on calibrated energy forecast information, operating status information of the hydrogen production equipment, and hydrogen demand information includes: collecting hydrogen-oxygen permeability signals and local pressure difference signals across the membrane inside the hydrogen production equipment; preprocessing the collected hydrogen-oxygen permeability signals and local pressure difference signals across the membrane to obtain preprocessed multi-dimensional auxiliary signals; identifying the relative change relationships between the multi-dimensional auxiliary signals, including synchronous fluctuation characteristics or time series features; identifying early physical degradation-related abnormal patterns based on the relative change relationships; generating risk correction instructions based on the abnormal patterns, which include the identifier of the affected hydrogen production equipment, the correction type, and the correction magnitude; inserting the risk correction instructions into the input of the power allocation logic to forcibly correct the power allocation parameters of the hydrogen production equipment, including maximum power load limits or load penalty factor adjustments; and determining the power allocation of the hydrogen production equipment based on calibrated energy output forecast information, operating status information of the hydrogen production equipment, hydrogen demand information, and the corrected power allocation parameters.

[0006] Based on this, adjusting the operating parameters of the hydrogen production equipment according to power allocation, hydrogen production targets, and hydrogen storage status includes: collecting response characteristic data of the regulation mechanism inside the hydrogen production equipment; identifying performance degradation modes in the response characteristic data of the regulation mechanism; generating compensation strategy instructions based on the performance degradation modes; inserting the compensation strategy instructions into the input of the key parameter dynamic adjustment logic; forcibly correcting the operating parameter adjustment strategy of the hydrogen production equipment, which includes increasing the pre-regulation amount or adjusting the control parameters; and adjusting the operating parameters of the hydrogen production equipment according to power allocation, hydrogen production targets, and hydrogen storage status, combined with the corrected operating parameter adjustment strategy.

[0007] Furthermore, the system presents the operational status information of the energy supply simulation system and records the operational process information, including: recording the decision input parameters, execution results of the decision logic, and priority trade-off information involved in the decision at key decision points; when reproducing the operation process of the energy supply simulation system, it receives backtracking instructions from users based on time points or events, dynamically displays the input parameters of key decision points, the execution path of the decision logic, intermediate calculation results, and the final decision output; and it performs decision impact analysis based on backtracking instructions, which includes displaying the changes in decision results caused by changes in decision input parameters or priority trade-off information.

[0008] In some preferred embodiments, energy input information is generated in the energy supply simulation system. This energy input information includes real-time energy output information and future energy forecast information, including: constructing an energy output time series based on a micro-weather station model; and setting real-time energy output information and future energy forecast information under the simulated weather system according to the energy output time series.

[0009] As a technological improvement, the future energy forecast information is calibrated based on real-time energy output information to obtain calibrated energy forecast information, which includes: calculating the deviation data between real-time energy output information and future energy forecast information; analyzing the correlation between the deviation data and external environmental parameters and equipment operating parameters; identifying the change patterns between the physical environment and equipment characteristics based on the deviation data, external environmental parameters, and equipment operating parameters; generating prediction model parameter adjustment instructions containing energy type identifiers, correction types, and correction magnitudes based on the change patterns between the physical environment and equipment characteristics; adjusting the environmental adaptability parameters of the future energy forecast model based on the prediction model parameter adjustment instructions; and generating calibrated future energy forecast information based on the adjusted energy forecast model.

[0010] More specifically, the acquisition of hydrogen and oxygen permeability signals and local pressure difference signals across the membrane inside the hydrogen production equipment includes: simultaneously acquiring the raw signals output by multiple hydrogen and oxygen sensors and differential pressure sensors through a multi-channel data acquisition system; performing digital filtering on the raw signals to eliminate noise and interference in the raw signals; and performing signal enhancement processing on the digitally filtered raw signals to obtain the hydrogen and oxygen permeability signals and local pressure difference signals across the membrane.

[0011] Based on the above, the data acquisition of the regulation mechanism response characteristics inside the hydrogen production equipment includes: deploying multiple high-frequency response sensors near the key regulation actuators inside the hydrogen production equipment to synchronously acquire the real-time change curves of the regulation command input, actuator output, and the regulated parameter; preprocessing the real-time change curves, including time synchronization, noise suppression, and baseline calibration, to obtain preprocessed regulation mechanism response characteristic data; analyzing the waveform characteristics, frequency components, or phase relationships in the preprocessed regulation mechanism response characteristic data to identify abnormal modes related to physical degradation, including response time lag, decreased regulation efficiency, or nonlinear characteristics in the regulation process.

[0012] Preferably, identifying performance degradation modes in the regulation mechanism response characteristic data includes: performing multi-scale decomposition on the regulation mechanism response characteristic data to obtain multiple decomposed components reflecting changes at different time scales; for each of the multiple decomposed components, extracting characteristic parameters under different energy fluctuations and hydrogen production equipment operating conditions, including response time, overshoot, steady-state error, frequency components, or phase relationships; analyzing the mutual influence relationships between the multiple decomposed components and between the characteristic parameters of each decomposed component and the energy fluctuations and hydrogen production equipment operating conditions, and constructing correlation indicators; distinguishing and quantifying multiple nonlinear coupling degradation paths based on the correlation indicators, and identifying the performance degradation modes of the regulation mechanism.

[0013] Secondly, this application also discloses a system for simulating hydrogen production and energy supply, comprising: a generation module for generating energy input information in the energy supply simulation system, the energy input information including real-time energy output information and future energy prediction information; a calibration module for calibrating the future energy prediction information based on the real-time energy output information to obtain calibrated energy prediction information; an acquisition module for acquiring the operating status information and hydrogen demand information of the hydrogen production equipment in the energy supply simulation system; an allocation module for determining the power allocation of the hydrogen production equipment based on the calibrated energy prediction information, the operating status information of the hydrogen production equipment, and the hydrogen demand information; an adjustment module for adjusting the operating parameters of the hydrogen production equipment based on the power allocation, the hydrogen production target, and the hydrogen storage status; and a presentation module for presenting the operating status information of the energy supply simulation system and recording the operating process information of the energy supply simulation system.

[0014] The hydrogen production and energy supply simulation method disclosed in this application generates energy input information containing real-time energy output information and future energy forecast information in the energy supply simulation system, and calibrates the future energy forecast information based on the real-time energy output information. This effectively addresses the problem of unstable renewable energy output and improves the accuracy of energy forecasting. Based on this, the method acquires the operating status information and hydrogen demand information of the hydrogen production equipment, and determines the power allocation of the hydrogen production equipment based on the calibrated energy forecast information, the operating status information of the hydrogen production equipment, and the hydrogen demand information. This solves the problem of uneven power distribution caused by energy output fluctuations in existing technologies and optimizes the working efficiency of the electrolyzer. Furthermore, the method adjusts the operating parameters of the hydrogen production equipment according to the power allocation, hydrogen production target, and hydrogen storage status, overcoming the lack of flexibility in adjusting key parameters in existing simulation tools, enabling the system to reach its optimal operating state. Finally, by presenting the operating status information of the energy supply simulation system and recording the operating process information, the method compensates for the shortcomings of existing systems in data display and historical data management, providing operators with real-time, intuitive operating status and the ability to deeply review and analyze historical data, thereby supporting effective monitoring and optimization decision-making. In summary, the method of this application can optimize the operation of hydrogen production and energy supply systems, significantly improve system efficiency, stability and reliability, and reduce actual operational risks. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 is a schematic flowchart of the hydrogen production and energy supply simulation method in an embodiment of the present invention; Figure 2 is a schematic flowchart of the method for optimizing the power allocation of hydrogen production equipment in an embodiment of the present invention; Figure 3 is a schematic diagram of the system structure for the hydrogen production and energy supply simulation in an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0018] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0019] Specifically, Figure 1 shows a schematic flowchart of the hydrogen production and energy supply simulation method in an embodiment of the present invention, including: S101, generating energy input information in the energy supply simulation system; it should be noted that the energy input information includes real-time energy output information and future energy prediction information. The energy supply simulation system is a virtual environment used to simulate the operation of an actual hydrogen production and energy supply system, including energy input, hydrogen production process, hydrogen storage, and hydrogen output. Real-time energy output information reflects the actual energy output at the current moment or in the near future, such as the instantaneous power of wind power or solar power generation; future energy prediction information is an estimate of energy output over a future period of time, such as wind speed or solar radiation intensity predicted based on weather forecasts and historical data.

[0020] First, energy input information is generated in the energy supply simulation system. This energy input information includes real-time energy output information and future energy forecast information. One approach is to manually input preset energy output and forecast data to simulate specific energy scenarios. For example, one could input hourly power generation data of a simulated wind farm throughout the day, including real-time power generation and predicted power generation for the next 24 hours. Another approach is to import historical energy data and forecast model outputs from external data sources to simulate a more realistic energy environment. For example, one could import solar power generation data from the past week as real-time energy output information and import solar power generation forecasts for the next 48 hours generated based on a weather forecast model.

[0021] S102. The future energy prediction information is calibrated based on the real-time energy output information to obtain calibrated energy prediction information; secondly, the future energy prediction information is calibrated based on the real-time energy output information to obtain calibrated energy prediction information. As one implementation method, a simple linear regression model can be used to adjust the prediction information based on the deviation between the real-time energy output information and the future energy prediction information. For example, if the real-time wind power generation is consistently lower than the predicted value, the future wind power generation prediction value can be reduced proportionally. As another implementation method, a statistical method based on historical deviation data can be used to calculate the average deviation or trend between the real-time data and the predicted data, and apply it to the future prediction information. For example, by analyzing the difference between the real-time light intensity and the predicted light intensity over a past period, a systematic deviation in the prediction model within a specific time period can be identified, thereby correcting the future light prediction.

[0022] S103. Obtain the operating status information and hydrogen demand information of the hydrogen production equipment in the energy supply simulation system; the hydrogen production equipment is the core device that uses electrical energy to decompose water into hydrogen and oxygen. The operating status information includes parameters such as the current operating mode, temperature, pressure, current, and voltage of the hydrogen production equipment. The hydrogen demand information refers to the amount of hydrogen consumed or the storage target in the simulation scenario.

[0023] Next, the operating status information and hydrogen demand information of the hydrogen production equipment in the energy supply simulation system are obtained. One approach is to preset fixed operating parameters and a constant hydrogen demand for the hydrogen production equipment. For example, all electrolyzers can be set to operate at rated power, and a constant hydrogen consumption rate can be set. Another approach is to simulate the dynamic operating status of the hydrogen production equipment, such as changing the equipment's start-up and shutdown status, load level, etc., according to preset scheduling strategies or random events, and simulating changing hydrogen demand, such as dynamically adjusting hydrogen consumption based on simulated industrial production plans or transportation demands.

[0024] S104. Determine the power allocation of the hydrogen production equipment based on the calibrated energy prediction information, the operating status information of the hydrogen production equipment, and the hydrogen demand information; power allocation refers to the reasonable distribution of available electrical energy to each hydrogen production equipment in order to optimize the overall hydrogen production efficiency and stability.

[0025] Then, based on the calibrated energy forecast information, the operating status information of the hydrogen production equipment, and the hydrogen demand information, the power allocation for the hydrogen production equipment is determined. One implementation approach is a simple average allocation strategy, distributing available energy evenly across all operating hydrogen production equipment. For example, if there is 100MW of available electricity and 10 hydrogen production units, each unit is allocated 10MW. Another approach is to allocate power based on preset priority rules, such as prioritizing hydrogen demand and then allocating power according to equipment efficiency or maintenance status. For example, power is prioritized for more efficient electrolyzers, or the power load is reduced for equipment requiring maintenance.

[0026] S105. Adjust the operating parameters of the hydrogen production equipment according to the power allocation, the hydrogen production target, and the hydrogen storage status; the hydrogen production target is the desired hydrogen output of the system. The hydrogen storage status refers to information such as the current capacity and pressure of the hydrogen storage tank. The operating parameters refer to various adjustable parameters that affect the performance and efficiency of the hydrogen production equipment, such as the current density of the electrolyzer and the electrolyte temperature.

[0027] Subsequently, the operating parameters of the hydrogen production equipment are adjusted based on power allocation, hydrogen production targets, and hydrogen storage status. One approach is to directly adjust the current or voltage of the hydrogen production equipment based on the power allocation results to achieve the desired power input. For example, if the power allocated to a particular electrolyzer increases, its current is increased accordingly. Another approach is to dynamically adjust the electrolyte temperature or pressure of the hydrogen production equipment based on the hydrogen production targets and hydrogen storage status to optimize hydrogen production efficiency and hydrogen purity. For example, when the hydrogen storage tank is nearing full load, the operating load of the hydrogen production equipment can be appropriately reduced to avoid overproduction.

[0028] S106. Present the operating status information of the energy supply simulation system and record the operating process information of the energy supply simulation system.

[0029] Finally, the operating status information of the energy supply simulation system is presented, and the operating process information is recorded. One implementation method is to display key data such as current power allocation, hydrogen production, and hydrogen storage through a simple text interface. For example, the console can output the current power of each electrolyzer, hydrogen yield, and hydrogen storage tank level. Another implementation method is to generate a detailed operating log file, recording all input parameters, intermediate calculation results, and final decisions for each time step. For example, data such as energy input, power allocation decisions, operating parameter adjustments, and hydrogen production at each time point can be saved to a CSV file for subsequent analysis.

[0030] This application aims to overcome the shortcomings of existing technologies, achieve optimized operation of hydrogen production and energy supply systems, and support operators in effective monitoring and decision-making by introducing a mechanism for generating and calibrating energy input information, acquiring information on the operating status of hydrogen production equipment and hydrogen demand, determining power allocation based on multi-source information, dynamically adjusting operating parameters, and presenting and recording system operating status.

[0031] This application comprehensively considers calibrated energy forecast information, the operating status information of the hydrogen production equipment, and hydrogen demand information when determining the power allocation of the hydrogen production equipment. This makes the power allocation more flexible and intelligent. Compared with the simple average allocation or fixed rule allocation in the prior art, the allocation strategy of this application can better adapt to the dynamically changing energy supply and hydrogen demand, thereby improving hydrogen production efficiency and system stability.

[0032] Regarding the adjustment of operating parameters, this application adjusts the operating parameters of the hydrogen production equipment based on power distribution, hydrogen production targets, and hydrogen storage status, achieving dynamic adjustment of key parameters. This overcomes the lack of flexibility in existing technologies, enabling the hydrogen production system to be optimized in real time according to actual operating conditions to achieve the best operating state.

[0033] Finally, this application significantly enhances data visualization and historical data management capabilities by presenting the operational status information of the power supply simulation system and recording operational process information. This enables operators to monitor the system's operation in real time and intuitively, and to deeply review and analyze past data, thereby supporting effective monitoring and optimization decisions. Compared with the weak data display and management methods in existing technologies, this application provides more comprehensive and convenient tools, greatly improving the system's operability and maintainability.

[0034] In summary, the hydrogen production and energy supply simulation method of this application forms a complete and efficient hydrogen production and energy supply simulation solution by introducing the generation and calibration of energy input information, power allocation through multi-source information fusion, dynamic adjustment of operating parameters, and presentation and recording of system operating status. This solution not only solves many pain points in existing technologies but also provides strong technical support for the production and application of green hydrogen energy, demonstrating significant progressiveness and practical value.

[0035] Specifically, Figure 2 shows a schematic flowchart of the method for optimizing power allocation in a hydrogen production device according to an embodiment of the present invention. Determining the power allocation of the hydrogen production device based on the calibrated energy prediction information, the operating status information of the hydrogen production device, and the hydrogen demand information includes: S201, collecting hydrogen-oxygen permeability signals and local pressure difference signals across the membrane inside the hydrogen production device; specifically, during the operation of the hydrogen production device, hydrogen-oxygen permeability signals and local pressure difference signals across the membrane are collected in real time using sensors deployed inside the device. The hydrogen-oxygen permeability signal reflects the integrity and selectivity of the electrolyzer membrane; an abnormal increase may indicate membrane damage or aging. The local pressure difference signal across the membrane can reflect the uniformity of fluid distribution or the presence of blockages. These signals directly reflect the internal physical state of the hydrogen production device.

[0036] S202. The acquired hydrogen-oxygen permeability signal and the local pressure difference signal across the membrane are preprocessed to obtain a preprocessed multidimensional auxiliary signal. The purpose of preprocessing the acquired hydrogen-oxygen permeability signal and the local pressure difference signal across the membrane is to eliminate noise, drift, and other interference in the original signal, ensuring the accuracy of subsequent analysis. The preprocessed signal is integrated into a multidimensional auxiliary signal, providing a reliable data foundation for in-depth analysis of the internal state of the equipment.

[0037] S203. Identify the relative change relationships between the multidimensional auxiliary signals, including synchronous fluctuation characteristics or time series features. In practical applications, by analyzing the relative change relationships between multidimensional auxiliary signals, such as synchronous fluctuation characteristics or time series features, the dynamic patterns of interaction between internal components of the equipment can be revealed. Synchronous fluctuation characteristics may indicate that multiple parameters change abnormally simultaneously, while time series features can capture the trend and periodicity of parameter evolution over time. Based on these relative change relationships, abnormal patterns related to early physical degradation can be identified. For example, a continuous increase in hydrogen-oxygen permeability and abnormal fluctuations in local pressure differential may jointly indicate local damage to the electrolyzer membrane.

[0038] S204. Identify anomalous patterns related to early physical degradation based on the relative change relationship; once an anomalous pattern is identified, the system generates a risk correction instruction. This instruction not only includes the identifier of the affected hydrogen production equipment to accurately point to the problematic equipment, but also specifies the type of correction (e.g., reducing the load or adjusting the operating strategy) and the magnitude of the correction (e.g., the specific value of the maximum power load limit or the adjustment ratio of the load penalty factor).

[0039] S205. Generate a risk correction instruction based on the abnormal mode. The risk correction instruction includes the identifier of the affected hydrogen production equipment, the correction type, and the correction magnitude. S206. Insert the risk correction instruction into the input of the power allocation logic to forcibly correct the power allocation parameters of the hydrogen production equipment. It should be noted that the correction includes adjusting the maximum power load limit or the load penalty factor. Before the regular power allocation calculation, the system forcibly considers the degradation risk of the equipment. By forcibly correcting the power allocation parameters of the hydrogen production equipment, such as setting a maximum power load limit, the system prevents the equipment from operating under overload in a degraded state; or by adjusting the load penalty factor, the power allocation optimization algorithm allocates a lower priority or a more conservative load to equipment with degradation risk.

[0040] S207. Based on the calibrated energy output prediction information, the operating status information of the hydrogen production equipment, and the hydrogen demand information, and in conjunction with the corrected power allocation parameters, determine the power allocation of the hydrogen production equipment.

[0041] Therefore, when finalizing the power allocation for the hydrogen production equipment, not only were calibrated energy output predictions, equipment operating status information, and hydrogen demand information considered, but also risk-corrected power allocation parameters were incorporated. This ensures that the power allocation scheme meets both energy supply and hydrogen production needs while also taking into account the health and operational safety of the equipment.

[0042] This application's solution addresses the limitation of traditional power allocation methods that may overlook the internal health status of hydrogen production equipment by introducing a real-time monitoring and evaluation mechanism for the internal physical degradation state of the equipment. Specifically, by collecting hydrogen-oxygen permeability signals and local pressure difference signals across the membrane, microscopic data reflecting the health status of core components (such as electrolyzer membranes) can be directly obtained. After preprocessing and relationship identification, this data can accurately capture early, subtle signs of physical degradation, forming abnormal patterns. Once an anomaly is identified, the system immediately generates a risk correction instruction, which acts as a "safety valve" and is forcibly incorporated into the power allocation decision-making process. By limiting or adjusting power allocation parameters, such as reducing the maximum power load or increasing the load penalty factor, excessive pressure can be proactively avoided on equipment showing signs of degradation, thereby preventing accelerated degradation, extending equipment life, and ensuring operational safety. This mechanism transforms power allocation from merely optimizing external demand and macroscopic operating conditions into incorporating the results of internal equipment "health diagnostics," achieving smarter and safer energy management.

[0043] In some preferred embodiments, a specific example is given below. Assume a hydrogen production and energy supply simulation system comprising multiple electrolyzers for hydrogen production. During the operation of one electrolyzer 100, its internal hydrogen-oxygen sensors and differential pressure sensors continuously collect hydrogen-oxygen permeability signals and local pressure difference signals across the membrane. The system monitors that over the past 24 hours, the hydrogen-oxygen permeability signal of electrolyzer 100 exhibits a slow but continuous upward trend, while the local pressure difference signal across the membrane also shows slight periodic fluctuations. These changes might not be considered abnormal in routine operating status information. However, through time-series analysis of these preprocessed multidimensional auxiliary signals, the system identifies this as a typical early membrane degradation anomaly pattern.

[0044] Based on this abnormal mode, the system immediately generates a risk correction instruction, designating electrolyzer 100 as the affected device, with the correction type being "maximum power load limit" and the correction magnitude being "reduction of 15%". This instruction is inserted into the input of the power allocation logic. When the system calculates the power allocation of each hydrogen production device based on the calibrated energy forecast information, the operating status information of the hydrogen production equipment, and the hydrogen demand information, the power allocation parameters of electrolyzer 100 will be forcibly limited by this instruction, and its maximum power load will be limited to 85% of the original maximum load. Even if the energy supply is sufficient and the hydrogen demand is high at this time, the system will not increase the power allocation of electrolyzer 100 to its maximum load before degradation, thereby avoiding further damage to electrolyzer 100, which has already shown signs of degradation, ensuring its safe and stable operation, and providing a valuable time window for subsequent maintenance or replacement.

[0045] It should be noted that the method for adjusting the operating parameters of the hydrogen production equipment based on power allocation, hydrogen production targets, and hydrogen storage status includes the following specific steps: collecting response characteristic data of the regulation mechanism inside the hydrogen production equipment; identifying performance degradation modes in the response characteristic data of the regulation mechanism; generating compensation strategy instructions based on the performance degradation modes; inserting the compensation strategy instructions into the input of the key parameter dynamic adjustment logic; forcibly correcting the operating parameter adjustment strategy of the hydrogen production equipment, the correction including increasing the pre-adjustment amount or adjusting the control parameters; and adjusting the operating parameters of the hydrogen production equipment according to the power allocation, the hydrogen production targets, and the hydrogen storage status, combined with the corrected operating parameter adjustment strategy.

[0046] Specifically, collecting data on the response characteristics of the regulation mechanism within the hydrogen production equipment involves deploying high-frequency response sensors near key regulating actuators within the equipment to simultaneously collect real-time change curves of the regulation command input, actuator output, and the regulated parameters. This data reflects the dynamic characteristics of the regulation mechanism's physical response after receiving control commands, such as the valve opening and closing speed, pump flow rate changes, or heater temperature response.

[0047] Identifying performance degradation patterns in the response characteristic data of the regulation mechanism can be understood as analyzing the collected response characteristic data to detect whether the regulation mechanism is abnormal or its performance has degraded. This can be achieved by comparing the current data with the baseline data, analyzing waveform characteristics, frequency components, or phase relationships, thereby identifying degradation patterns such as response time lag, decreased regulation efficiency, or nonlinear characteristics in the regulation process.

[0048] In practical applications, generating compensation strategy instructions based on the performance degradation mode means that once performance degradation of the adjustment mechanism is identified, the system will automatically generate corresponding compensation instructions based on the type and degree of degradation. For example, if the response time is delayed, the compensation strategy may indicate that the adjustment instruction should be sent a certain time in advance; if the adjustment efficiency decreases, it may indicate that the magnitude of the adjustment instruction should be increased.

[0049] Furthermore, the compensation strategy instruction is inserted into the input of the key parameter dynamic adjustment logic. The purpose is to introduce compensation information for the decline of the adjustment mechanism into the control process before the regular operating parameter adjustment logic is executed, so as to ensure that the subsequent adjustment decision can take into account the actual performance of the equipment.

[0050] Therefore, the operating parameter adjustment strategy of the hydrogen production equipment is forcibly modified, including increasing the pre-adjustment amount or adjusting the control parameters. This means that, based on the conventional adjustment strategy, the adjustment parameters are forcibly adjusted according to the compensation strategy instructions. For example, when the response of the regulating valve slows down, the pre-adjustment amount for opening or closing the valve can be increased to offset the response lag; or the proportional, integral, and derivative parameters of the PID controller can be adjusted to better adapt to the dynamic characteristics of the current equipment.

[0051] Finally, based on the power allocation, the hydrogen production target, and the hydrogen storage status, and in conjunction with the revised operating parameter adjustment strategy, the operating parameters of the hydrogen production equipment are adjusted. This means that the final operating parameter adjustment is carried out on the basis of comprehensively considering external demand (power allocation, hydrogen production target, hydrogen storage status) and internal equipment health status (revised adjustment strategy), thereby achieving more precise and robust control.

[0052] The proposed solution actively monitors the response characteristics of the internal regulation mechanism of the hydrogen production equipment and identifies its performance degradation modes in real time, thereby generating targeted compensation strategy instructions. These instructions are effectively integrated into the input of the dynamic adjustment logic for key parameters, forcibly correcting traditional operating parameter adjustment strategies. It is precisely this real-time perception and adaptive correction capability of the equipment's internal health that enables the system to ensure precise adjustment of operating parameters even in the face of physical degradation of the regulation mechanism. In this way, even if the regulator actuator experiences response lag or efficiency decline, the system can offset these adverse effects by increasing the pre-regulation amount or adjusting the control parameters, thereby maintaining the stability and efficiency of the hydrogen production process.

[0053] In some preferred embodiments, a specific example is given below. Suppose that inside a hydrogen production plant, a key actuator used to regulate the current of the electrolyzer (e.g., a control module of a high-power DC power supply) experiences slight aging in its internal response circuit after long-term operation, resulting in a slight increase in its response time to control commands and a slight overshoot when reaching the target current value.

[0054] First, the system uses high-frequency response sensors to collect real-time change curves of the control module's adjustment command input, actual current output, and other relevant parameters, forming data on the adjustment mechanism's response characteristics. Next, by analyzing this data, the system identifies performance degradation modes in the control module, including response time lag and overshoot. For example, compared to baseline data from a new device, the slope of its current rise time is slower, and brief oscillations occur near the target value.

[0055] Based on the identified performance degradation patterns, the system generates corresponding compensation strategy instructions. Specifically, for response time lag, the instruction might require sending the target current command 50 milliseconds in advance; for overshoot, the instruction might require temporarily reducing the gain of the control signal by 10% when approaching the target current value. These compensation strategy instructions are then inserted into the input of the dynamic adjustment logic for key parameters of the hydrogen production equipment's power distribution module.

[0056] When the power allocation module determines a new power allocation based on calibrated energy forecast information, the operating status information of the hydrogen production equipment, and hydrogen demand information, and needs to adjust the electrolyzer current to match the hydrogen production target, the corrected operating parameter adjustment strategy will be activated. For example, if the target current is 1000 amperes, the system will send a command 50 milliseconds in advance, and when the current reaches 900 amperes, it will temporarily reduce the control gain to smoothly reach 1000 amperes and avoid overshoot. Through this forced correction, even if the control module experiences performance degradation, the hydrogen production equipment can still accurately and stably adjust the electrolyzer current, ensuring that hydrogen production efficiency and quality are not affected.

[0057] In this application, the operational status information of the energy supply simulation system is presented, and the operational process information of the energy supply simulation system is recorded, including: recording the decision input parameters, execution results of the decision logic, and priority trade-off information of the decision at key decision points; when reproducing the operational process of the energy supply simulation system, receiving backtracking instructions from users based on time points or events, dynamically displaying the input parameters, execution path of the decision logic, intermediate calculation results, and final decision output of the key decision points; and responding to decision impact analysis based on backtracking instructions, wherein the decision impact analysis includes displaying the changes in decision results caused by changes in the decision input parameters or the priority trade-off information.

[0058] Specifically, the recorded energy supply simulation system records the decision input parameters, execution results of decision logic, and priority trade-off information at key decision points, aiming to provide a detailed data foundation for subsequent analysis and backtesting. Decision input parameters can be understood as all relevant data influencing the system's specific decisions, such as calibrated energy forecast information, hydrogen production equipment operating status information, and hydrogen demand information. The execution results of the decision logic refer to the intermediate steps and final decisions calculated by the system based on these input parameters using preset algorithms or rules, such as the power allocation scheme for the hydrogen production equipment. The priority trade-off information reflects the weights or preferences when choosing between multiple conflicting objectives (such as maximizing hydrogen production, minimizing energy consumption, and ensuring equipment lifespan). This information is stored in a structured manner for rapid retrieval and analysis.

[0059] Furthermore, when reproducing the operation of the power supply simulation system, the system is designed to receive backtracking commands issued by the user based on a specific time point or event. For example, the user can specify a specific timestamp or a specific system event (such as "power allocation adjustment"), and the system will dynamically display all relevant information at the time of that key decision point. This includes the input parameters at that time, the specific execution path of the decision logic (e.g., which algorithm branch was activated, which conditions were met), intermediate calculation results (e.g., the iterative process of the optimization algorithm), and the final decision output (e.g., the final determined power allocation value). This dynamic display allows the user to intuitively understand the decision-making process.

[0060] Furthermore, backtracking instruction response-based decision impact analysis refers to the system's ability to simulate and demonstrate how decision outcomes change when input parameters or priority trade-offs change. For example, a user can modify an energy forecast or adjust the priority weights between hydrogen production and equipment lifespan; the system will immediately calculate and display the impact of these modifications on final power allocation or other operating parameters. This helps users assess the potential consequences of different strategies or parameter settings, thereby optimizing system configuration.

[0061] This application's solution constructs a comprehensive decision context by recording detailed data at key decision points. It is precisely because of the recording of decision input parameters, the execution results of decision logic, and the priority trade-offs in decision-making that the system can capture a complete "snapshot" of each key decision. Based on this, by providing backtracking instructions based on time points or events, users can reproduce any historical decision-making process as needed, thereby intuitively understanding how decisions are generated from input data and logic. Furthermore, through decision impact analysis, the system can simulate "hypothetical" scenarios—that is, how the decision outcome will respond when certain inputs or priorities change—providing users with powerful tools for decision verification and optimization.

[0062] Through the aforementioned technical solution, this application significantly enhances the transparency, traceability, and analyzability of hydrogen production and energy supply simulation systems. Compared to basic solutions that merely record the operational process, this application provides in-depth insights into the system's internal decision-making mechanisms, enabling users not only to know "what happened" but also to understand "why it happened." This greatly facilitates system debugging, verification, and optimization, helps to quickly pinpoint the root causes of problems, evaluate the effectiveness of different strategies, and ultimately improve the accuracy and reliability of the simulation. Especially in complex energy management and hydrogen production optimization scenarios, this refined management and analysis capability of the decision-making process can effectively reduce system operational risks and improve decision-making quality.

[0063] In some preferred embodiments, it is assumed that the energy supply simulation system needs to determine the power allocation of the hydrogen production equipment at a certain moment. The system first records the current decision input parameters. For example, calibrated energy forecast information shows that there is 100MW of renewable energy output in the next hour, the hydrogen production equipment operating status information indicates that the current efficiency of electrolyzer 100 is 80%, and the hydrogen demand information is 500kg per hour. Simultaneously, the system records the execution results of the decision logic. For example, based on these inputs and combined with preset priority trade-offs (e.g., prioritizing hydrogen demand, followed by maximizing renewable energy consumption), the optimization algorithm calculates that electrolyzer 100 should be allocated 80MW of power. This information, including input parameters, algorithm execution path, and the final 80MW power allocation, is recorded in detail.

[0064] When users want to understand this decision later, they can issue a backtracking command, specifying that point in time. The system will dynamically display all input data at that time, the execution process of the optimization algorithm, and the final power allocation result. Furthermore, if a user wants to know how the power allocation will change if hydrogen demand increases to 600 kg per hour, they can modify the hydrogen demand parameters through the decision impact analysis function. The system will immediately recalculate and display the changes; for example, the power allocation for electrolyzer 100 might increase to 90 MW, potentially triggering the startup or adjustment of other hydrogen production equipment. This capability allows users to intuitively evaluate decision responses under different scenarios, thereby better understanding and optimizing hydrogen production and energy supply strategies.

[0065] Specifically, the energy input information generated in the energy supply simulation system includes real-time energy output information and future energy forecast information, including: constructing an energy output time series based on a micro-weather station model; and setting real-time energy output information and future energy forecast information under the simulated weather system according to the energy output time series.

[0066] The micro-weather station model is a mathematical or computational model used to simulate and predict local meteorological conditions (such as solar radiation, wind speed, temperature, and humidity). This model can make high-precision predictions of short-term meteorological changes based on historical meteorological data and real-time observation data, aiming to provide accurate environmental input for energy output forecasting. The energy output time series is a series of time-series energy output data calculated and generated based on the meteorological conditions predicted by the micro-weather station model, combined with conversion efficiency models for specific energy types (such as solar and wind power). This time series data reflects the electrical or energy values ​​that the energy system is expected to generate at different points in time. The simulated meteorological system is a virtual environment whose meteorological conditions are set according to a preset energy output time series or generated by the micro-weather station model. This system aims to simulate the meteorological environment faced by energy systems in the real world, in order to test and optimize the performance of the hydrogen production and energy supply simulation system under controlled conditions. Real-time energy output information refers to the energy data actually generated by the energy system at the current moment or in the near future under the simulated meteorological system. This information reflects the actual operating performance of the energy system under current meteorological conditions. Future energy forecasting information refers to the predicted energy output of an energy system over a future period, based on energy output timing sequences under simulated weather conditions. This information is used to guide power allocation and operating parameter adjustments in hydrogen production facilities to achieve optimal energy utilization.

[0067] This application's solution first constructs an energy output time series based on a micro-weather station model, enabling refined simulation and prediction of the impact of local meteorological conditions on energy production. The micro-weather station model provides high-resolution meteorological data, making the construction of the energy output time series more accurate and reliable. Subsequently, real-time energy output information and future energy forecast information under the simulated meteorological system are set according to this energy output time series. This means that the energy production data in the simulated environment is generated based on real meteorological forecast logic, thereby ensuring the authenticity and validity of the energy input information. In this way, the hydrogen production and energy supply simulation system can obtain energy supply conditions that are closer to reality, providing a solid foundation for subsequent energy calibration, power allocation, and operating parameter adjustment.

[0068] The above technical solutions enable the refined generation of energy input information. Constructing energy output time series based on a micro-weather station model significantly improves the accuracy of energy forecasting, especially in localized and short-term predictions. This helps to more accurately reflect the volatility and intermittent nature of renewable energy sources (such as solar and wind power). Furthermore, by setting real-time energy output information and future energy forecast information under the simulated meteorological system according to the energy output time series, a high degree of consistency between the simulated environment and the actual operating environment is ensured. This improves the simulation accuracy and reliability of the entire hydrogen production and energy supply simulation system, providing a more precise decision-making basis for the optimized operation and energy management of hydrogen production equipment.

[0069] Specifically, calibrating the future energy prediction information based on the real-time energy output information to obtain calibrated energy prediction information includes: calculating the deviation data between the real-time energy output information and the future energy prediction information; analyzing the correlation between the deviation data and external environmental parameters and equipment operating parameters; identifying the change patterns between the physical environment and equipment characteristics based on the deviation data, the external environmental parameters, and the equipment operating parameters; generating a prediction model parameter adjustment instruction containing an energy type identifier, correction type, and correction magnitude based on the change patterns between the physical environment and equipment characteristics; adjusting the environmental adaptability parameters of the future energy prediction model based on the prediction model parameter adjustment instruction; and generating calibrated future energy prediction information based on the adjusted energy prediction model.

[0070] Specifically, during calibration, the process begins by comparing the observed real-time energy output with previously predicted future energy data to calculate the deviation. This deviation quantifies the difference between the prediction and the actual output. Further analysis of the calculated deviation data explores its potential correlation with external environmental parameters (e.g., temperature, light intensity, wind speed) and the operating parameters of the hydrogen production equipment (e.g., equipment aging, operating efficiency). Based on this, dynamic change patterns between the physical environment and equipment characteristics are identified using the obtained deviation data, external environmental parameters, and equipment operating parameters. For example, systematic deviations in the prediction model may be found under specific environmental conditions or equipment operating states. Subsequently, based on the identified change patterns between the physical environment and equipment characteristics, a prediction model parameter adjustment instruction is generated. This instruction includes an energy type identifier specifying the energy prediction model requiring adjustment; a correction type indicating the specific adjustment method (e.g., bias correction, scaling factor adjustment); and a correction magnitude quantifying the adjustment amount. Based on the generated prediction model parameter adjustment instruction, the environmental adaptability parameters of the future energy prediction model are adjusted. This adjustment aims to enhance the accuracy and robustness of the forecasting model under different environmental conditions and equipment operating states. Ultimately, based on the adjusted energy forecasting model, calibrated future energy forecasts are generated. This calibrated information will more accurately reflect future energy output.

[0071] This application's solution addresses the prediction bias that traditional energy forecasting models may exhibit when facing complex and variable physical environments and equipment operating characteristics by introducing a dynamic feedback calibration mechanism. Specifically, by monitoring energy output in real time and comparing it with predicted values, the system can quantify prediction errors. Furthermore, by analyzing the correlation between these errors and external environmental and equipment operating parameters, the system can identify the underlying physical mechanisms or equipment degradation patterns that lead to these errors. Once these patterns are identified, the system can generate precise adjustment instructions to specifically correct the environmental adaptability parameters of the prediction model. This iterative learning and adjustment process enables the energy forecasting model to continuously optimize its adaptability to actual operating conditions, thereby significantly improving the accuracy of future energy forecasts.

[0072] According to the above-mentioned method for simulating hydrogen production and energy supply, the acquisition of hydrogen and oxygen permeability signals and local pressure difference signals across the membrane inside the hydrogen production equipment includes: simultaneously acquiring the raw signals output by multiple hydrogen and oxygen sensors and differential pressure sensors through a multi-channel data acquisition system; performing digital filtering on the raw signals to eliminate noise and interference in the raw signals; and performing signal enhancement processing on the digitally filtered raw signals to obtain hydrogen and oxygen permeability signals and local pressure difference signals across the membrane.

[0073] Specifically, the multi-channel data acquisition system is an integrated hardware and software system capable of simultaneously acquiring data from multiple sensors. This system is configured to synchronously acquire raw signals output from multiple hydrogen-oxygen sensors and differential pressure sensors. The hydrogen-oxygen sensors are used to monitor the real-time permeation of hydrogen and oxygen within the hydrogen production equipment; these sensors can be of the electrochemical or thermal conductivity types. The differential pressure sensors are used to measure the local pressure difference across the membrane; these can be piezoresistive or capacitive differential pressure sensors, and their purpose is to reflect the physical state of the membrane and the resistance to gas transmission. The raw signals refer to the unprocessed electrical signals directly output by the sensors, which may contain various noises and interferences.

[0074] Furthermore, the original signal undergoes digital filtering to eliminate noise and interference. Various algorithms can be employed for digital filtering, such as low-pass filters, band-pass filters, or Kalman filters, to remove high-frequency noise, power frequency interference, or other random fluctuations, thereby improving signal purity.

[0075] Furthermore, signal enhancement processing is performed on the original signal after digital filtering to further optimize signal quality and make it more clearly reflect the true physical state inside the hydrogen production equipment. Signal enhancement processing can include, but is not limited to, techniques such as wavelet denoising, empirical mode decomposition (EMD), or principal component analysis (PCA) to highlight key features in the signal and suppress residual noise components. Through the above processing, high-precision and high-reliability hydrogen-oxygen permeability signals and local pressure difference signals across the membrane are finally obtained.

[0076] This application ensures the accuracy and reliability of subsequent data analysis by specifying in detail the acquisition process of hydrogen-oxygen permeability signals and local pressure difference signals across the membrane. Specifically, the multi-channel data acquisition system can simultaneously acquire raw signals from multiple sensors, ensuring the temporal consistency and comprehensiveness of the data. Digital filtering effectively removes noise and interference from the raw signals, preventing noise from misleading subsequent analysis. Signal enhancement processing further improves signal quality, allowing the true variation patterns of hydrogen-oxygen permeability and local pressure difference across the membrane within the hydrogen production equipment to be captured more clearly. This provides high-quality input data for subsequently identifying the relative changes between multi-dimensional auxiliary signals and identifying abnormal patterns related to early physical degradation, enabling the power allocation logic to be corrected based on more accurate equipment status information, thereby improving the stability and safety of the hydrogen production equipment operation.

[0077] Specifically, the aforementioned data collection of the regulation mechanism response characteristics within the hydrogen production equipment includes: deploying multiple high-frequency response sensors near the key regulation actuators within the hydrogen production equipment to synchronously collect real-time change curves of the regulation command input, actuator output, and the regulated parameters; preprocessing the real-time change curves, including time synchronization, noise suppression, and baseline calibration, to obtain preprocessed regulation mechanism response characteristic data; analyzing the waveform characteristics, frequency components, or phase relationships in the preprocessed regulation mechanism response characteristic data to identify abnormal modes related to physical degradation, including response time lag, decreased regulation efficiency, or nonlinear characteristics during the regulation process.

[0078] Specifically, multiple high-frequency response sensors are deployed near key regulating actuators within the hydrogen production unit to accurately and in real-time capture the dynamic behavior of the regulating mechanism. These sensors are configured to synchronously acquire the real-time change curves of the regulating command input, actuator output, and the regulated parameters, thus comprehensively reflecting the response process of the regulating mechanism. The regulating command input refers to the control signal sent by the system to the actuator; the actuator output refers to the actual action or force generated by the actuator according to the command; and the regulated parameters refer to the key operating parameters of the hydrogen production unit affected by the actuators, such as temperature, pressure, and flow rate. High-frequency response sensors ensure accurate capture of these rapidly changing signals, avoiding data distortion.

[0079] Furthermore, preprocessing the acquired real-time change curves is a crucial step. This preprocessing includes time synchronization, noise suppression, and baseline calibration. Time synchronization ensures that data from different sensors are aligned on the time axis for accurate correlation analysis. Noise suppression uses techniques such as digital filtering to eliminate random noise and interference in the signal, improving data quality. Baseline calibration eliminates baseline shifts caused by sensor drift or environmental changes, ensuring data accuracy and comparability. These preprocessing steps yield high-quality regulation mechanism response characteristic data, laying the foundation for subsequent analysis.

[0080] Based on this, the preprocessed response characteristic data of the regulation mechanism are analyzed to identify anomalous patterns related to physical degradation. This analysis can focus on the waveform characteristics, frequency components, or phase relationships of the data. For example, waveform characteristics can reveal the shape, amplitude, and duration of the response; frequency components can reflect the dynamic response speed and stability of the regulation mechanism; and phase relationships can reveal the temporal correlation between different signals. Through in-depth analysis of these characteristics, various anomalous patterns can be identified, such as response time lag, decreased regulation efficiency, or nonlinear characteristics in the regulation process. Response time lag may indicate aging of the actuator or sensor; decreased regulation efficiency may mean wear or blockage of the regulation mechanism; and nonlinear characteristics may indicate friction, jamming, or other mechanical failures within the regulation system.

[0081] This application's solution deploys high-frequency response sensors near key regulating actuators within the hydrogen production unit and simultaneously acquires multi-dimensional real-time change curves, enabling comprehensive and accurate acquisition of dynamic response data of the regulating mechanism. Subsequently, a rigorous preprocessing procedure, including time synchronization, noise suppression, and baseline calibration, ensures data accuracy and reliability, effectively eliminating external interference and measurement errors. Finally, in-depth analysis of the preprocessed data's waveform characteristics, frequency components, and phase relationships identifies various anomaly modes related to physical degradation, such as response time lag, decreased regulating efficiency, or nonlinear characteristics during the regulating process. The identification of these anomaly modes provides accurate and reliable input for subsequent performance degradation mode analysis and compensation strategy generation, thereby enabling earlier and more accurate detection of potential problems in the hydrogen production unit's regulating mechanism.

[0082] To address this, the method for identifying performance degradation modes in the aforementioned regulation mechanism response characteristic data specifically includes: performing multi-scale decomposition on the regulation mechanism response characteristic data to obtain multiple decomposition components reflecting changes at different time scales; for each of the multiple decomposition components, extracting characteristic parameters under different energy fluctuations and the operating state of the hydrogen production equipment, the characteristic parameters including response time, overshoot, steady-state error, frequency components, or phase relationships; analyzing the mutual influence relationships between the multiple decomposition components, and between the characteristic parameters of each decomposition component and the energy fluctuations and the operating state of the hydrogen production equipment, constructing correlation indicators; and distinguishing and quantifying multiple nonlinearly coupled degradation paths based on the correlation indicators to identify the performance degradation mode of the regulation mechanism.

[0083] Specifically, multi-scale decomposition of regulation mechanism response characteristic data refers to decomposing the original regulation mechanism response characteristic data, such as the regulation command input, actuator output, and real-time change curves of the regulated parameters acquired by high-frequency response sensors, into a series of sub-signals or components with specific frequency or energy distributions at different time scales using signal processing techniques such as wavelet transform, empirical mode decomposition (EMD), or variational mode decomposition (VMD). These decomposed components can respectively reflect the behavioral characteristics of the regulation mechanism at different time scales, such as fast transient response, medium periodic fluctuations, and long-term trend changes.

[0084] Extracting feature parameters for each of the multiple decomposed components refers to quantifying key indicators that characterize the dynamic behavior and performance of each component. These feature parameters may include response time (the system's speed of response to changes in input); overshoot (the maximum extent by which the system response exceeds the target value); steady-state error (the deviation of the system from the target value in a steady state); frequency components (the energy distribution of different frequencies in the signal); and phase relationship (the relative time delay between different signals or components). Extracting these feature parameters helps to characterize the performance of the regulation mechanism from multiple dimensions.

[0085] In practical applications, analyzing the interactions between the multiple decomposition components and the interrelationships between the characteristic parameters of each component and the energy fluctuations and the operating status of the hydrogen production equipment, and constructing correlation indices, involves using statistical methods (such as correlation analysis and Granger causality tests) or machine learning models (such as deep learning and support vector machines) to explore whether there are interactions between the decomposition components at different time scales, and how the characteristic parameters of these components are affected by external energy fluctuations (such as intermittent changes in wind and solar power) and the operating status of the hydrogen production equipment (such as current density, temperature, and pressure). By constructing correlation indices, these complex relationships can be quantified, revealing potential coupling mechanisms.

[0086] Furthermore, distinguishing and quantifying various nonlinearly coupled degradation paths based on the aforementioned correlation indicators, and identifying the performance degradation modes of the regulation mechanism, refers to classifying degradation phenomena with similar correlation characteristics into specific performance degradation modes using methods such as cluster analysis, classification algorithms, or expert systems, based on the constructed correlation indicators. For example, a certain mode might manifest as a significant increase in the response time of high-frequency components under specific energy fluctuations, while exhibiting a strong nonlinear correlation with the temperature of the hydrogen production equipment. This could indicate performance degradation caused by local overheating of the membrane electrode assembly. By quantifying these degradation paths, specific problems with the regulation mechanism can be accurately diagnosed.

[0087] This application's solution decomposes the response characteristic data of the regulation mechanism into multiple scales, decoupling complex performance degradation phenomena across different time scales and avoiding omissions or misjudgments that might occur with single-time-scale analysis. The extraction of multi-dimensional characteristic parameters such as response time, overshoot, steady-state error, frequency components, or phase relationships from each decomposed component allows for a more comprehensive and refined characterization of the dynamic behavior and performance state of the regulation mechanism. Furthermore, by deeply analyzing the interactions between these decomposed components and their interactions with external energy fluctuations and the operating status of hydrogen production equipment, correlation indicators are constructed. This enables the system to identify and quantify nonlinearly coupled degradation paths that are difficult to capture using traditional methods. The ability to distinguish and quantify multiple nonlinearly coupled degradation paths allows for more accurate and in-depth identification of the regulation mechanism's performance degradation modes, providing a solid foundation for generating precise compensation strategy commands and effectively overcoming the limitations of traditional methods in identifying complex degradation modes.

[0088] As a specific implementation method, suppose a water electrolysis hydrogen production device experiences an abnormal response in its regulating valve during operation. Traditional methods may only observe fluctuations in hydrogen production, but it is difficult to determine the specific cause. Using the approach described in this application, firstly, multi-scale decomposition is performed by collecting real-time change curves of parameters such as the regulating command input, valve actuator output, and hydrogen flow rate from high-frequency response sensors. For example, wavelet transform is used to decompose the signal into high-frequency, mid-frequency, and low-frequency components.

[0089] Secondly, characteristic parameters are extracted for these decomposed components. In the high-frequency components, a significant lag in the response time of the valve actuator output signal may be observed, along with an increased phase difference with the input signal of the regulation command; in the mid-frequency components, an increase in the overshoot of the hydrogen flow rate may be observed; and in the low-frequency components, the steady-state error increases.

[0090] Next, the interactions between these decomposed components and between the characteristic parameters of each component and external energy fluctuations (such as photovoltaic power output fluctuations) and the operating status of the hydrogen production equipment (such as electrolyzer temperature and current density) were analyzed. For example, a strong nonlinear correlation was found between the high-frequency response time lag and the rapid fluctuation of the electrolyzer temperature, while the increase in the medium-frequency overshoot was related to the rate of change of the current density. By constructing these correlation indicators, it was found that when a rapid decrease in photovoltaic power output leads to a drastic change in current density, the mechanical wear of the valve actuator (manifested as high-frequency response lag) and the changes in the fluid dynamics inside the electrolyzer (manifested as medium-frequency overshoot) jointly lead to difficulties in regulating the hydrogen flow rate.

[0091] Finally, based on these correlation indicators, the degradation paths of two nonlinear couplings—"high-frequency response hysteresis caused by valve mechanical wear" and "mid-frequency overshoot caused by nonlinear coupling of fluid dynamics"—can be distinguished and quantified, and the performance degradation modes of the regulation mechanism can be identified. Based on this, more refined compensation strategy instructions can be generated, such as increasing the pre-regulation amount for valve wear and adjusting control parameters for fluid dynamic characteristics, thereby more effectively regulating the operating parameters of the hydrogen production equipment.

[0092] Specifically, Figure 3 shows a schematic diagram of the system structure for hydrogen production and energy supply simulation in an embodiment of the present invention, including: a generation module for generating energy input information in the energy supply simulation system, the energy input information including real-time energy output information and future energy prediction information; a calibration module for calibrating the future energy prediction information according to the real-time energy output information to obtain calibrated energy prediction information; an acquisition module for acquiring the operating status information and hydrogen demand information of the hydrogen production equipment in the energy supply simulation system; an allocation module for determining the power allocation of the hydrogen production equipment based on the calibrated energy prediction information, the operating status information of the hydrogen production equipment, and the hydrogen demand information; an adjustment module for adjusting the operating parameters of the hydrogen production equipment according to the power allocation, the hydrogen production target, and the hydrogen storage status; and a presentation module for presenting the operating status information of the energy supply simulation system and recording the operating process information of the energy supply simulation system.

[0093] This system, through a modular design, integrates functions such as the generation and calibration of energy input information, the acquisition of hydrogen production equipment operating status and hydrogen demand information, the determination of power allocation based on multi-source information, the dynamic adjustment of operating parameters, and the presentation and recording of system operating status. Therefore, this application aims to overcome the problems in existing technologies, such as uneven power distribution due to unstable renewable energy output, lack of dynamic adjustment capabilities for key parameters, and weak data visualization and historical data management functions. This will enable optimized operation of the hydrogen production and energy supply system and support operators in effective monitoring and decision-making.

[0094] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for simulating hydrogen production for energy supply, characterized in that, include: Energy input information is generated in the energy supply simulation system, which includes real-time energy output information and future energy forecast information. The future energy prediction information is calibrated based on the real-time energy output information to obtain calibrated energy prediction information. The system acquires the operating status information and hydrogen demand information of the hydrogen production equipment in the energy supply simulation system; determines the power allocation of the hydrogen production equipment based on the calibrated energy prediction information, the operating status information of the hydrogen production equipment, and the hydrogen demand information; adjusts the operating parameters of the hydrogen production equipment according to the power allocation, the hydrogen production target, and the hydrogen storage status; presents the operating status information of the energy supply simulation system, and records the operating process information of the energy supply simulation system.

2. The method for simulating hydrogen production and energy supply according to claim 1, characterized in that, The process of determining the power allocation of the hydrogen production equipment based on the calibrated energy forecast information, the operating status information of the hydrogen production equipment, and the hydrogen demand information includes: collecting hydrogen-oxygen permeability signals and local pressure difference signals across the membrane inside the hydrogen production equipment; preprocessing the collected hydrogen-oxygen permeability signals and local pressure difference signals across the membrane to obtain preprocessed multidimensional auxiliary signals; identifying the relative change relationships between the multidimensional auxiliary signals, the relative change relationships including synchronous fluctuation characteristics or time series characteristics; identifying early physical degradation-related abnormal patterns based on the relative change relationships; generating risk correction instructions based on the abnormal patterns, the risk correction instructions including the identifier of the affected hydrogen production equipment, the correction type, and the correction magnitude; inserting the risk correction instructions into the input of the power allocation logic to forcibly correct the power allocation parameters of the hydrogen production equipment, the correction including maximum power load limitation or load penalty factor adjustment; and determining the power allocation of the hydrogen production equipment based on the calibrated energy forecast information, the operating status information of the hydrogen production equipment, and the hydrogen demand information, combined with the corrected power allocation parameters.

3. The method for simulating hydrogen production and energy supply according to claim 1, characterized in that, The step of adjusting the operating parameters of the hydrogen production equipment according to the power allocation, the hydrogen production target, and the hydrogen storage status includes: collecting response characteristic data of the regulation mechanism inside the hydrogen production equipment; identifying performance degradation modes in the response characteristic data of the regulation mechanism; generating compensation strategy instructions based on the performance degradation modes; correcting the operating parameter adjustment strategy of the hydrogen production equipment according to the compensation strategy instructions, wherein the correction includes increasing the pre-regulation amount or adjusting the control parameters; and adjusting the operating parameters of the hydrogen production equipment according to the power allocation, the hydrogen production target, and the hydrogen storage status, and in conjunction with the corrected operating parameter adjustment strategy.

4. The method for simulating hydrogen production and energy supply according to claim 1, characterized in that, The presentation of the operating status information of the energy supply simulation system and the recording of the operating process information of the energy supply simulation system include: recording the decision input parameters, execution results of the decision logic, and priority trade-off information of the decision at key decision points; when reproducing the operating process of the energy supply simulation system, receiving backtracking instructions from users based on time points or events, dynamically displaying the input parameters, execution path of the decision logic, intermediate calculation results, and final decision output of the key decision points; and responding to decision impact analysis based on backtracking instructions, wherein the decision impact analysis includes displaying the changes in decision results caused by changes in the decision input parameters or the priority trade-off information.

5. The method for simulating hydrogen production and energy supply according to claim 1, characterized in that, The generation of energy input information in the energy supply simulation system, which includes real-time energy output information and future energy forecast information, includes: constructing an energy output time series based on a micro-weather station model; and setting real-time energy output information and future energy forecast information under the simulated weather system according to the energy output time series.

6. The method for simulating hydrogen production and energy supply according to claim 1, characterized in that, The step of calibrating the future energy prediction information based on the real-time energy output information to obtain calibrated energy prediction information includes: calculating the deviation data between the real-time energy output information and the future energy prediction information; analyzing the correlation between the deviation data and external environmental parameters and equipment operating parameters; identifying the change patterns between the physical environment and equipment characteristics based on the deviation data, the external environmental parameters, and the equipment operating parameters; generating a prediction model parameter adjustment instruction containing an energy type identifier, correction type, and correction magnitude based on the change patterns between the physical environment and equipment characteristics; adjusting the environmental adaptability parameters of the future energy prediction model based on the prediction model parameter adjustment instruction; and generating calibrated future energy prediction information based on the adjusted energy prediction model.

7. The method for simulating hydrogen production and energy supply according to claim 2, characterized in that, The acquisition of hydrogen-oxygen permeability signals and local pressure difference signals across the membrane inside the hydrogen production equipment includes: simultaneously acquiring raw signals output by multiple hydrogen-oxygen sensors and differential pressure sensors through a multi-channel data acquisition system; performing digital filtering on the raw signals to eliminate noise and interference in the raw signals; and performing signal enhancement processing on the digitally filtered raw signals to obtain hydrogen-oxygen permeability signals and local pressure difference signals across the membrane.

8. The method for simulating hydrogen production and energy supply according to claim 3, characterized in that, The acquisition of regulation mechanism response characteristic data within the hydrogen production equipment includes: deploying multiple high-frequency response sensors near key regulation actuators within the hydrogen production equipment to synchronously acquire real-time change curves of regulation command input, actuator output, and regulated parameters; preprocessing the real-time change curves, including time synchronization, noise suppression, and baseline calibration, to obtain preprocessed regulation mechanism response characteristic data; analyzing the waveform characteristics, frequency components, or phase relationships in the preprocessed regulation mechanism response characteristic data to identify abnormal modes related to physical degradation, including response time lag, decreased regulation efficiency, or nonlinear characteristics during the regulation process.

9. The method for simulating hydrogen production and energy supply according to claim 3, characterized in that, The process of identifying performance degradation patterns in the response characteristic data of the regulation mechanism includes: performing multi-scale decomposition on the response characteristic data of the regulation mechanism to obtain multiple decomposed components reflecting changes at different time scales; for each of the multiple decomposed components, extracting characteristic parameters under different energy fluctuations and the operating state of the hydrogen production equipment, the characteristic parameters including response time, overshoot, steady-state error, frequency components, or phase relationships; analyzing the mutual influence relationships between the multiple decomposed components, and between the characteristic parameters of each decomposed component and the energy fluctuations and the operating state of the hydrogen production equipment, and constructing correlation indicators; and distinguishing and quantifying multiple nonlinearly coupled degradation paths based on the correlation indicators to identify the performance degradation patterns of the regulation mechanism.

10. A system for simulating hydrogen production and energy supply, characterized in that, include: The generation module is used to generate energy input information in the energy supply simulation system, the energy input information including real-time energy output information and future energy prediction information; The calibration module is used to calibrate the future energy prediction information based on the real-time energy output information to obtain calibrated energy prediction information; The acquisition module is used to acquire the operating status information and hydrogen demand information of the hydrogen production equipment in the energy supply simulation system; the allocation module is used to determine the power allocation of the hydrogen production equipment based on the calibrated energy prediction information, the operating status information of the hydrogen production equipment, and the hydrogen demand information. The adjustment module is used to adjust the operating parameters of the hydrogen production equipment according to the power distribution, the hydrogen production target, and the hydrogen storage status. The presentation module is used to present the operating status information of the energy supply simulation system and record the operating process information of the energy supply simulation system.

Images