A multi-scale coordinated control method for green hydrogen metallurgical integrated energy system

Abstract

The present invention discloses a multi-scale collaborative control method for a green hydrogen metallurgical integrated energy system, belonging to the field of energy system control technology. First, a detailed analysis is conducted on various flexible and adjustable resources within the green hydrogen metallurgical integrated energy system, and their regulation characteristics at different time scales are summarized. Secondly, the cross-link regulation characteristics of these resources in the interaction of multiple energy materials are explored, especially focusing on the time delay phenomenon in the transmission and conversion process of multiple energy materials. Then, an equivalent modeling method for the heterogeneous problems of each link is proposed to provide support for the multi-link collaborative control of the system. Finally, the impact of different production tasks on the distribution of multiple energy materials flows is studied, and the dynamic correlation of different production processes on the distribution of multiple energy materials flows is analyzed. To this end, an extended resource-task network modeling method is adopted, and a multi-model predictive control strategy combining prediction models and local models is combined to improve the control efficiency of the system and meet multiple requirements such as energy efficiency, flexibility, and risk control.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy system regulation and control, and specifically relates to a multi-scale coordinated regulation method for a green hydrogen metallurgical integrated energy system. Background Art

[0002] With the increasing global attention to emission reduction targets, green hydrogen metallurgy has gradually become an important way for the steel industry to achieve carbon neutrality. The green hydrogen metallurgical system uses renewable energy to produce hydrogen as an iron oxide reducing agent to replace traditional fossil fuels, thereby reducing carbon dioxide emissions. The successful promotion of this technology depends on the efficient coordinated regulation of multiple energy and mass flows (including electricity, heat, hydrogen, etc.) within the system to ensure that energy use and production in the metallurgical process are highly flexible and economical. However, the multi-link, multi-scale, and multi-energy and mass flows involved in the green hydrogen metallurgical integrated energy system are coupled with each other, posing huge challenges to the operation and regulation of the system.

[0003] Currently, most research on the multi-segment regulation of integrated energy systems focuses on economic efficiency, establishing optimization planning and scheduling models based on different time scales. These models primarily study the regulation characteristics of each link and assess the system's flexible regulation margin to improve system economics and operational efficiency. These models play an important role in optimizing energy flows, enhancing system flexibility, and improving control performance. However, existing research often focuses on optimizing a single energy form and often overlooks the complex coupling relationships between different energy qualities.

[0004] Although the existing multi-energy and mass flow control models have certain optimization capabilities, they still have obvious shortcomings when dealing with the complexity of the green hydrogen metallurgical integrated energy system. First, most of the current models fail to fully consider the joint impact of the internal operating status of the equipment, the external working conditions, and the dynamic environment of the multi-energy and mass flow distribution on the system regulation characteristics. Secondly, facing the actual needs of multi-energy, multi-time and multi-space complex coupling, and multi-process and multi-link cross-interaction, how to achieve integrated coordinated control of multiple links remains a difficult point. In addition, there is a relative lack of analysis on the continuity and dynamic constraints of multi-energy and mass flow sections, and the existing multi-scale control strategy needs to be improved in its ability to cope with such a complex environment. Therefore, a multi-link and multi-scale coordinated control strategy for the multi-energy and mass flow section constraints of the green hydrogen metallurgical integrated energy system urgently needs in-depth research. Summary of the Invention

[0005] In response to the above-mentioned deficiencies in the prior art, the multi-scale coordinated control method of the green hydrogen metallurgical integrated energy system provided by the present invention solves the problem that the existing related methods ignore the dynamic influence of the internal operating state of the equipment and the distribution of multiple energy and mass flows under external working conditions, and cannot fully meet the needs of multi-link and multi-scale coordinated control, especially the complex coupling of multiple energy and mass flows in time and space and the cross-interaction of multiple process links have not been fully solved.

[0006] In order to achieve the above-mentioned purpose of the invention, the technical solution adopted by the present invention is: a multi-scale coordinated control method of a green hydrogen metallurgical integrated energy system, comprising the following steps:

[0007] S1. Analyze the multi-timescale regulation characteristics of flexible and adjustable resources in the green hydrogen metallurgical integrated energy system and form a regulation response timescale matrix;

[0008] S2. According to the regulation response time scale matrix, the cross-link regulation characteristics in the multi-energy interaction are analyzed, and then equivalent modeling based on heterogeneous links is performed to obtain an equivalent model of regulation external characteristics;

[0009] S3. Based on dynamic correlation analysis, analyze the impact of different production tasks on the distribution of multiple energy and mass flows in the green hydrogen metallurgical integrated energy system, and establish an extended resource-task network model to characterize the relationship between production tasks and multiple energy and mass flows;

[0010] S4. Based on the task-resource allocation results obtained from the extended resource-task network model, the random variables involved in the production process at future moments are predicted and input into the multi-model prediction mechanism based on local model combination and multi-controller combination, and the energy and mass flow control strategy for the current working conditions is output to achieve coordinated control of the green hydrogen metallurgical integrated energy system.

[0011] Furthermore, in step S1, the method for analyzing the multi-time-scale adjustment characteristics of the flexible and adjustable resources is:

[0012] The regulation response characteristics of the energy supply, demand, energy conversion and storage links in the green hydrogen metallurgical integrated energy system at different time scales are analyzed, including energy supply regulation characteristics, demand side regulation characteristics, energy conversion link regulation characteristics and storage link regulation characteristics.

[0013] Furthermore, in step S2, the method for analyzing the cross-link regulation characteristics in the multi-energy interaction is specifically as follows:

[0014] By constructing an energy-mass flow coupling model and analyzing the time delay effect in the cross-link energy-mass interaction process, we analyze the impact of the mutual conversion and interaction between different energy materials on the overall scheduling of the green hydrogen metallurgical integrated energy system;

[0015] The delay effect includes cross-link energy transmission delay and conversion delay.

[0016] Furthermore, in step S2, equivalent modeling based on heterogeneous links is performed to obtain an equivalent model for adjusting external characteristics, specifically:

[0017] S21. Collect historical operating data of various equipment in the green hydrogen metallurgical integrated energy system;

[0018] The historical operating data is the regulation characteristic data of various types of equipment under different working conditions;

[0019] S22. Selecting a corresponding deep neural network based on different adjustment characteristic data of various types of equipment;

[0020] S23. Train the corresponding deep neural network based on the historical operation data and dynamically update it to obtain the external adjustment characteristic models corresponding to the different adjustment characteristics of various types of equipment.

[0021] Furthermore, step S3 includes the following sub-steps:

[0022] S31. Dynamically analyze the correlation between production task types and multi-energy and mass flow distribution in the green hydrogen metallurgical integrated energy system, and construct a dynamic correlation model for production tasks;

[0023] S32. Dynamically analyze the correlation between the production process and the distribution of multiple energy and mass flows of production tasks in the green hydrogen metallurgical integrated energy system, and build a coordinated control model of energy and mass flows between processes;

[0024] S33. Based on the constructed dynamic correlation model of production tasks and the coordinated control model of energy and mass flow between processes, and by introducing the dynamic characteristics of time and space energy and mass flow, an extended resource-task network model is constructed.

[0025] Furthermore, the step S31 includes the following sub-steps:

[0026] S31-1. Classify the production tasks in the green hydrogen metallurgical integrated energy system according to production needs, and determine the energy and mass flow demand characteristics of each production task at different times;

[0027] S31-2. Fit the historical data corresponding to the demand characteristics of energy and mass flow for various production tasks in different time periods to establish dynamic demand curves for various production tasks;

[0028] S31-3. Dynamically generate multiple association models of different production task types based on the dynamic demand curves of various production tasks to obtain a dynamic association model of production tasks;

[0029] The production task types include continuous production tasks and discrete production tasks.

[0030] Furthermore, the step S32 includes the following sub-steps:

[0031] S32-1. Analyze the energy and quality demand characteristics of each production process in the green hydrogen metallurgical integrated energy system;

[0032] S32-2. Based on the energy demand characteristics corresponding to different production processes, the execution order of the production processes and the energy flow distribution of each production task are adjusted in real time through dynamic programming or optimization algorithms to achieve optimal coordinated scheduling between production processes, thereby obtaining a coordinated control model for energy flow between processes;

[0033] The inter-process energy and mass flow collaborative control model takes the time scheduling cost between production processes, the dependency between production processes and resource limitations as constraints.

[0034] Furthermore, in step S33, the extended resource-task network model constructed is a model for dynamically adjusting the supply of resources and the demand for tasks in the green hydrogen metallurgical integrated energy system according to time series data;

[0035] When the extended resource-task network model coordinates and controls resources involved in multiple production tasks, it processes their multi-correlations and establishes an optimization model with constraints to achieve multi-energy and quality supply coordination to match production task requirements. The constraints include resource supply capacity, dynamic allocation of energy and quality flows, and temporal dependencies of production tasks.

[0036] When the extended resource-task network model allocates resources and tasks, a dynamic optimization algorithm is used to dynamically adjust the execution order of production tasks and the energy and mass flow allocation strategy according to the current energy and mass flow distribution in the green hydrogen metallurgical integrated energy system.

[0037] Furthermore, in step S4, the multi-model prediction mechanism based on the combination of local models refers to:

[0038] Construct a local model for energy and mass flow distribution prediction under different operating conditions, and based on the conditional model switching mechanism, switch the optimal local model according to the operating status of the green hydrogen metallurgical integrated energy system to perform corresponding energy and mass flow distribution prediction;

[0039] The multi-model prediction mechanism based on multi-controller combination refers to:

[0040] On the basis of the energy and mass flow allocation strategy predicted by the multi-model prediction mechanism of local model combination, corresponding independent controllers are designed according to different energy and mass flow characteristics. In view of different working conditions and energy and mass flow control requirements, a collaborative mechanism based on constraint optimization is adopted, and a global objective function is introduced to optimize the control target of each independent controller to obtain the optimal energy and mass flow control strategy for the system as a whole. Among them, the outputs of each independent controller are interrelated.

[0041] Furthermore, the step S4 includes the following sub-steps:

[0042] S41. Based on the task-resource allocation results obtained from the extended resource-task network model, perform a time series characteristic analysis on the random variables involved in the production process;

[0043] S42. Construct a discrete-time prediction model based on the results of the temporal characteristics analysis of the random variables, and use the model to predict the random variables involved in the production process at future moments;

[0044] S43, inputting the predicted random variables into a multi-model prediction mechanism based on a local model, predicting energy and mass flow allocation strategies under different operating states, and inputting the predicted random variables into a multi-model prediction mechanism based on a multi-controller combination;

[0045] S44. In the multi-model prediction mechanism based on multiple controllers, on the basis of ensuring the scheduling consistency between independent controllers, the corresponding independent controller is selected to perform energy and mass flow regulation according to the energy and mass flow characteristics involved, and the energy and mass flow regulation strategy for the current working conditions is output to achieve coordinated regulation of the green hydrogen metallurgical integrated energy system.

[0046] The beneficial effects of the present invention are:

[0047] (1) The present invention provides a multi-scale collaborative control method for a green hydrogen metallurgical integrated energy system. First, a detailed analysis is conducted on various flexible and adjustable resources (such as grid access, renewable energy generation, electrolyzers, hydrogen storage systems, vertical furnaces and electric arc furnaces) within the green hydrogen metallurgical integrated energy system, and their regulation characteristics at different time scales are summarized, including continuous, discontinuous and interruptible regulation. Secondly, the cross-link regulation characteristics of these resources in the interaction of multiple energy materials are explored, especially the time delay phenomenon in the transmission and conversion process of multiple energy materials, and then an equivalent modeling method for the heterogeneous problems of each link is proposed to provide support for the multi-link collaborative control of the system. Finally, the influence of different production tasks (such as hydrogen production and storage) on the distribution of multiple energy materials flow is studied, and the dynamic correlation of different production processes on the distribution of multiple energy materials flow is analyzed. To this end, it is recommended to adopt an extended resource-task network modeling method and a multi-model predictive control strategy combining a prediction model and a local model combination to improve the control efficiency of the system and meet multiple requirements such as energy efficiency, flexibility and risk control.

[0048] (2) This invention is the first to analyze the regulation characteristics of flexible and adjustable resources in the green hydrogen metallurgical integrated energy system at multiple time scales, covering continuous, discontinuous and interruptible regulation, and proposes an equivalent modeling method based on heterogeneous links, which solves the time delay problem of transmission and conversion processes in the system, realizes multi-link coordinated regulation, and optimizes resource utilization efficiency and system responsiveness.

[0049] (3) The present invention proposes a multi-model predictive control strategy based on the combination of prediction models and local models for multi-variable random disturbances, which improves the control accuracy and response speed of the system in a dynamic environment, optimizes energy efficiency, flexibility and risk level, and provides an efficient and accurate regulation scheme for the green hydrogen metallurgical integrated energy system.

[0050] (4) The present invention proposes an extended resource-task network modeling method for analyzing the impact of different production tasks (such as hydrogen production and storage) on the distribution of multiple energy and mass flows. This method comprehensively integrates the distribution characteristics of multiple energy and mass flows with the specific requirements of production tasks by introducing dynamic correlation analysis. By extending the traditional resource-task network model, it can effectively describe the dynamic changes of multiple energy and mass flows in the production process and the complex relationship between them and task requirements, thereby providing a theoretical basis for optimizing production scheduling and resource allocation. This modeling method not only improves the understanding of the distribution of energy and mass flows between production processes, but also enhances the prediction accuracy of the system's responsiveness, providing reliable support for multi-task collaborative control.

[0051] (5) This invention systematically analyzes the regulation characteristics of the green hydrogen metallurgical integrated energy system, optimizes resource utilization efficiency and system responsiveness, effectively solves the problem of heterogeneous regulation between links, and enhances the stability of the production process through dynamic correlation analysis. Based on a multi-model predictive control strategy, the control accuracy of the system under multivariable disturbances is improved, energy efficiency, flexibility, and risk level are optimized, and an efficient and accurate regulation scheme is provided for system operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 Flowchart of the multi-scale coordinated control method for the green hydrogen metallurgical integrated energy system provided by the present invention.

[0053] Figure 2 This is a principle block diagram of the equivalent model for constructing and adjusting external characteristics provided by the present invention.

[0054] Figure 3 This is a principle framework diagram for constructing an extended resource-task network model provided by the present invention.

[0055] Figure 4 This is a framework diagram of the principle of energy and mass flow regulation using the multi-model prediction mechanism provided by the present invention. DETAILED DESCRIPTION

[0056] The specific embodiments of the present invention are described below to facilitate understanding of the present invention by those skilled in the art. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the appended claims, these changes are obvious, and all inventions and creations utilizing the concepts of the present invention are protected.

[0057] The embodiment of the present invention provides a multi-scale coordinated control method for a green hydrogen metallurgical integrated energy system, such as Figure 1 As shown, the following steps are included:

[0058] S1. Analyze the multi-timescale regulation characteristics of flexible and adjustable resources in the green hydrogen metallurgical integrated energy system and form a regulation response timescale matrix;

[0059] S2. According to the regulation response time scale matrix, the cross-link regulation characteristics in the multi-energy interaction are analyzed, and then equivalent modeling based on heterogeneous links is performed to obtain an equivalent model of regulation external characteristics;

[0060] S3. Based on dynamic correlation analysis, analyze the impact of different production tasks on the distribution of multiple energy and mass flows in the green hydrogen metallurgical integrated energy system, and establish an extended resource-task network model to characterize the relationship between production tasks and multiple energy and mass flows;

[0061] S4. Based on the task-resource allocation results obtained from the extended resource-task network model, the random variables involved in the production process at future moments are predicted and input into the multi-model prediction mechanism based on local model combination and multi-controller combination, and the energy and mass flow control strategy for the current working conditions is output to achieve coordinated control of the green hydrogen metallurgical integrated energy system.

[0062] In step S1 of the embodiment of the present invention, in order to achieve efficient coordinated operation of the system, it is first necessary to systematically analyze and model the regulation characteristics of different equipment in the green hydrogen metallurgical integrated energy system. Based on this, in this embodiment, the method for analyzing the multi-time scale regulation characteristics of flexible and adjustable resources is as follows:

[0063] The regulation response characteristics of the energy supply, demand, energy conversion and storage links in the green hydrogen metallurgical integrated energy system at different time scales are analyzed, including energy supply regulation characteristics, demand side regulation characteristics, energy conversion link regulation characteristics and storage link regulation characteristics.

[0064] In this embodiment, the above-mentioned flexible and adjustable resources cover various types of continuous, discontinuous and interruptibly adjustable equipment in the green hydrogen metallurgical integrated energy system; illustratively, the above-mentioned flexible and adjustable resources include grid access, renewable energy power generation, electrolyzers, hydrogen storage devices, vertical furnaces and electric arc furnaces, etc.

[0065] In an example of this embodiment, the following example is provided for analyzing the above energy supply adjustment characteristics:

[0066] Grid access and renewable energy generation (such as wind power and photovoltaics) are energy supply resources with volatility on a time scale. Therefore, a probabilistic model is needed to fit their volatility and to construct a characteristic description of energy supply fluctuations through time series models from hourly to minute levels.

[0067] The volatility of energy supply can be described by using a random process model. Assuming that the time series of wind power and photovoltaic power generation are P wind (t) and P pv (t), then the total energy supply power P supply (t) can be expressed as:

[0068] P supply (t) = P grid (t)+P wind (t)+P pv (t)(1)

[0069] Where: P grid (t) is the power supply from the grid.

[0070] The available probability distribution f(P wind ) and f(P pv ), usually expressed as a normal distribution or other distribution function:

[0071]

[0072] In an example of this embodiment, the following example is provided for analyzing the above-mentioned demand-side regulation characteristics:

[0073] The operating characteristics of demand-side equipment (such as electrolyzers, shaft furnaces, and electric arc furnaces) vary significantly. For example, electrolyzers operate continuously and are suitable for frequent adjustments. However, shaft furnaces and electric arc furnaces, due to their intermittent operation and high thermal inertia, require relatively low adjustment frequencies, necessitating special attention to energy consumption fluctuations during startup and shutdown. By modeling the adjustment frequency, response time, and energy efficiency indicators of these equipment in detail, we generate operating curves for these equipment at different time scales.

[0074] The dynamic response time of the electrolyzer τelectrolyzer and the power P elec The relationship between (t) can be described as a first-order dynamic model:

[0075]

[0076] Where, P set (t) is the set power. Similarly, the power P of the shaft furnace and electric arc furnace is furnace (t) and thermal inertia P set_furnace The dynamic characteristics of (t) can be expressed as:

[0077]

[0078] In one example of this embodiment, the energy conversion link includes an electrolytic hydrogen production process, and its nonlinear conversion efficiency needs to be modeled according to different working conditions and load conditions. Specifically, an example of its regulation characteristic analysis process is provided:

[0079] The power-to-hydrogen efficiency of the electrolyzer varies significantly under different loads. The conversion characteristics can be described by fitting experimental data or mechanism models, and the startup lag effect of the electrolyzer should be explicitly considered in the model.

[0080] The electrolysis efficiency of the electrolyzer is η elec (P) can be described by a nonlinear function, assuming that its relationship with the electrolytic cell input power P is:

[0081]

[0082] In actual operation, efficiency may show nonlinear characteristics with power changes, for example:

[0083] η elec (P) = aP 2 +bP+c(7)

[0084] Where: a, b, and c are fitting coefficients.

[0085] In an example of this embodiment, for the analysis of the regulation characteristics of the above storage link, taking a hydrogen storage device as an example, the following example is provided:

[0086] The response time and charge / discharge rates of hydrogen storage devices need to be optimized based on different requirements. The charging and discharging behavior of hydrogen storage devices is nonlinear, with significant efficiency degradation when full or empty, requiring description and modeling through function fitting or physical models.

[0087] Charging and discharging efficiency η of the hydrogen storage device storage (x) is usually related to the current storage state x (the amount of stored hydrogen) and can be expressed as:

[0088]

[0089] Where η0 is the initial charge and discharge efficiency, α is the efficiency attenuation coefficient, and x max The maximum capacity of the storage device.

[0090] In the present invention, by conducting a detailed analysis of the regulation characteristics of various types of equipment in the above-mentioned flexibly adjustable resources, a complete regulation response time scale matrix is ​​formed, providing a basis for cross-scale regulation of the system.

[0091] In the embodiment of the present invention, in the green hydrogen metallurgical integrated energy system, each link not only has its own regulation characteristics, but also needs to consider the impact of the mutual conversion and interaction between different energy qualities (electricity, hydrogen, heat) on the overall scheduling. For example, in the process of electrolytic hydrogen production, the conversion efficiency of electricity to hydrogen energy is not only limited by the electrolyzer itself, but also by the fluctuation of the upstream power grid energy supply.

[0092] Based on this, in step S2 of this embodiment, the method for analyzing the cross-link regulation characteristics in the multi-energy interaction is specifically as follows:

[0093] By constructing an energy flow coupling model and analyzing the delay effect in the cross-link energy interaction process, the impact of the mutual conversion and interaction between different energy materials on the overall scheduling of the green hydrogen metallurgical integrated energy system is analyzed; among them, the delay effect includes the cross-link energy transmission delay and conversion delay.

[0094] In this embodiment, an energy-mass flow coupling model is used to accurately describe the interaction between different energy materials in the system. In one example of this embodiment, taking an electrolyzer and a hydrogen storage device as an example, the following process for constructing the energy-mass flow coupling model is provided:

[0095] The energy-mass flow coupling model of the electrolyzer includes the functional relationship between electrical input and hydrogen output, and takes into account the efficiency of electricity-to-hydrogen conversion and dynamic changes in factors such as temperature and pressure; similarly, the energy-mass flow coupling between the hydrogen storage device and the vertical furnace also needs to be modeled through collaborative scheduling optimization.

[0096] In the energy-mass flow coupling of the electrolyzer, the process of converting electrical energy into hydrogen energy can be described by the following relationship:

[0097]

[0098] in, is the hydrogen production, P elect (t) is the input power of the electrolytic cell, η elec (P elec (t)) is the electricity-to-hydrogen conversion efficiency.

[0099] Similarly, the energy flow of the hydrogen storage device can be expressed as:

[0100]

[0101] in, is the hydrogen storage capacity, Q consurned (t) is the hydrogen consumption.

[0102] In this embodiment, the analysis of time delay effects during cross-link energy-quality interactions requires quantification through modeling. For example, when hydrogen generated by the electrolyzer flows to the hydrogen storage device or shaft furnace, there may be pipeline transmission delays, and transmission efficiency is affected by temperature and pressure. These effects can be described using time delay equations and efficiency decay models, accurately reflecting the losses and time delays in energy-quality transmission.

[0103] The time delay effect in energy and mass flow transmission can be described using delay differential equations. For example, the transmission of hydrogen from the electrolyzer to the hydrogen storage device has a time delay τ delay , then the equation for the change in hydrogen storage capacity is:

[0104]

[0105] Transmission efficiency η trans (t) may be affected by temperature and pressure and can be expressed as:

[0106]

[0107] Among them, η0 is the initial transmission efficiency, T(t) is the current temperature, β is the efficiency attenuation coefficient, and T0 is the reference temperature.

[0108] In the present invention, based on the above process, a global dynamic model is constructed by analyzing the dynamic coupling and delay effects of energy and mass flows to support subsequent system collaborative scheduling.

[0109] In step S2 of this embodiment of the present invention, after analyzing the cross-link regulation characteristics of multi-energy interactions, deep learning technology is introduced to assist in modeling, as the nonlinearity and uncertainty of various energy devices in actual systems cannot be fully described using traditional physical models. The key to this step is to construct a high-precision equivalent model of the regulation external characteristics through analysis of historical data.

[0110] Based on this, in the above step S2, equivalent modeling based on heterogeneous links is performed to obtain a method for adjusting the equivalent model of external characteristics:

[0111] S21. Collect historical operating data of various equipment in the green hydrogen metallurgical integrated energy system;

[0112] The historical operating data is the regulation characteristic data of various equipment under different operating conditions; for example, the historical operating data includes the regulation characteristic data of the electrolyzer, hydrogen storage device and shaft furnace under different operating conditions (such as input power, hydrogen output, energy efficiency, temperature change, etc.);

[0113] S22. Selecting a corresponding deep neural network based on different adjustment characteristic data of various types of equipment;

[0114] Exemplarily, the deep neural network includes a feedforward neural network (FFNN) or a long short-term memory network (LSTM), and the appropriate network structure is selected based on the time response characteristics of the device. Furthermore, the network input is the device control variable (such as input electrical power), and the output is the regulation result (such as hydrogen production or energy efficiency). Through training, it can accurately fit complex regulation behaviors.

[0115] S23. Train the corresponding deep neural network based on the historical operation data and dynamically update it to obtain the external adjustment characteristic models corresponding to the different adjustment characteristics of various types of equipment.

[0116] In step S21 of this embodiment, the collected historical operation data is also standardized, including eliminating dimensional differences and removing abnormal data to improve modeling accuracy.

[0117] In an example of this embodiment, taking the construction of an adjustment external characteristic model corresponding to an electrolytic cell as an example, the following example is provided:

[0118] The input of the network is the control variable x of the device = [P elec (t), T(t), p(t)] (input power, temperature, pressure), the output is hydrogen production

[0119] The prediction model of the neural network can be expressed as:

[0120] Q H2 (t) = f NN (x(t)|θ)(13)

[0121] Among them, f NN is the neural network function, and θ is the network parameter. The network parameters are optimized by minimizing the loss function L(θ):

[0122]

[0123] The online learning update process can be achieved through incremental learning method based on the new observation data x new , Update network weights:

[0124]

[0125] Among them, α is the learning rate, L new is the loss function based on new data.

[0126] In the present invention, the introduction of deep learning models can further improve the control accuracy and response capability of the green hydrogen metallurgical system.

[0127] like Figure 2As shown, a principle framework diagram is provided from analyzing multi-time-scale regulation characteristics to constructing an equivalent model of external regulation characteristics to support the multi-link coordinated regulation of the green hydrogen metallurgical integrated energy system.

[0128] like Figure 3 As shown, step S3 of the embodiment of the present invention includes the following sub-steps:

[0129] S31. Dynamically analyze the correlation between production task types and multi-energy and mass flow distribution in the green hydrogen metallurgical integrated energy system, and construct a dynamic correlation model for production tasks;

[0130] S32. Dynamically analyze the correlation between the production process and the distribution of multiple energy and mass flows of production tasks in the green hydrogen metallurgical integrated energy system, and build a coordinated control model of energy and mass flows between processes;

[0131] S33. Based on the constructed dynamic correlation model of production tasks and the coordinated control model of energy and mass flow between processes, and by introducing the dynamic characteristics of time and space energy and mass flow, an extended resource-task network model is constructed.

[0132] In step S31 of this embodiment, in the green hydrogen metallurgical integrated energy system, each production task (such as hydrogen preparation, storage, etc.) is accompanied by dynamic changes in multiple energy and mass flows. Since the requirements of various tasks in time and space are different, it is necessary to establish a dynamic correlation model between production tasks and multiple energy and mass flows to accurately describe such changes.

[0133] Based on this, Figure 3 In the embodiment, step S31 includes the following sub-steps:

[0134] S31-1. Classify the production tasks in the green hydrogen metallurgical integrated energy system according to production needs, and determine the energy and mass flow demand characteristics of each production task at different times;

[0135] For example, in the green hydrogen metallurgical integrated energy system, tasks such as hydrogen production, electricity storage, hydrogen storage, and shaft furnace steelmaking have different energy and mass flow demand types and intensities. By classifying the tasks, the energy and mass flow demand characteristics of each task at different times can be clarified.

[0136] S31-2. Fit the historical data corresponding to the demand characteristics of energy and mass flow for various production tasks in different time periods to establish dynamic demand curves for various production tasks;

[0137] S31-3. Dynamically generate multiple association models of different production task types based on the dynamic demand curves of various production tasks to obtain a dynamic association model of production tasks; wherein the production task types include continuous production tasks and discrete production tasks.

[0138] In an example of this embodiment, in the above step S31-1, it is assumed that a task T i The available time t and task progress p for the demand for a certain energy flow (such as electricity, hydrogen, etc.) i (t), the energy and mass flow demand function can be defined as:

[0139] E i (t) = f(p i (t),t)(16)

[0140] Among them, E i (t) represents task T i The energy flow demand at time t, function f(p i (t),t) is fitted based on historical data to describe the dynamic changes of task requirements over time.

[0141] In an example of this embodiment, in the above steps S31-2 and S31-3, the distribution of energy and mass flow can be regarded as a function of time and task progress; by fitting historical data, a dynamic demand curve of the task is established, and multiple association models are generated for different task types to ensure that the distribution of energy and mass flow meets the real-time production demand. For example, for the entire system, the production task set {T1, T2, ..., T n The total energy and mass flow requirements in} are:

[0142]

[0143] The above describes the total demand of all tasks for a certain energy flow at any time t.

[0144] In step S32 of this embodiment, the energy and mass flows between production processes interact in a complex manner, and their execution order and time scheduling have a significant impact on the dynamic distribution of energy and mass flows. To achieve reasonable regulation of energy and mass flows, it is necessary to model the execution status and energy and mass flow requirements of each process.

[0145] Based on this, the above step S32 includes the following sub-steps:

[0146] S32-1. Analyze the energy and quality demand characteristics of each production process in the green hydrogen metallurgical integrated energy system;

[0147] For example, the hydrogen and electricity requirements of a shaft furnace during startup and operation are nonlinear, consuming a large amount of energy during startup and requiring less energy during steady operation. Similarly, the energy requirements of an electrolyzer vary at different stages.

[0148] S32-2. Based on the energy demand characteristics corresponding to different production processes, the execution order of the production processes and the energy flow distribution of each production task are adjusted in real time through dynamic programming or optimization algorithms to achieve optimal coordinated scheduling between production processes, thereby obtaining a coordinated control model for energy flow between processes;

[0149] The above-mentioned coordinated control model of energy and mass flow between processes is based on the time scheduling cost between production processes, the dependency between production processes, and resource limitations as constraints; for example, the energy and mass requirements of a process may affect the subsequent startup time and efficiency.

[0150] In an example of this embodiment, in the above step S32-1, it is assumed that a process J j The energy and mass flow demand can change with the start-up and operation stages of the process, and its demand can be expressed by the function g j (t) means:

[0151] E j (t) = g j (t)(18)

[0152] Among them, E j (t) is process J j Energy and mass flow demand at time t, g j (t) can be defined based on the process operating characteristics, such as nonlinear energy demand during the startup phase and lower demand during the steady state phase.

[0153] In an example of this embodiment, in the above step S32-2, it is assumed that J j and J j+1 For two adjacent processes, process J j The energy and mass flow requirements of process J j+1 The execution time t j+1 :

[0154] t j+1 =t j +τ j (19)

[0155] Among them, τ j Indicates process J j The execution time of process J j+1 The energy quality requirements meet the resource constraints:

[0156] E j+1 (t)≤R j (t)(20)

[0157] Among them, R j (t) is process J j The remaining energy and mass flow resources after completion.

[0158] In step S33 of this embodiment, traditional resource-task network models typically assume that resources are static and independent. However, in a multi-energy flow system, the interactions between resources and tasks are dynamic and interdependent. To accommodate this complexity, the traditional resource-task network model needs to be expanded. This embodiment introduces the dynamic characteristics of time, space, and energy flow to construct an expanded resource-task network model.

[0159] Based on this, the extended resource-task network model in this embodiment is a model for dynamically adjusting the supply of resources and the demand for tasks in the green hydrogen metallurgical integrated energy system according to time series data.

[0160] In this embodiment, the temporal and spatial distribution of different energy flows (such as electricity, hydrogen, and heat) is crucial to the overall operation of the system. In a specific example of this embodiment, in the process of hydrogen production by electrolysis, the supply of electricity is closely related to the demand for hydrogen production. It is necessary to define the "supply and demand" node in the network model and introduce a time-varying function to describe the relationship between the two. Assuming that multiple energy flows (such as electricity E elec ,hydrogen ) in time and space are represented by functions h(t,x) and k(t,x) respectively. The extended resource-task network model can be defined as:

[0161] E elec (t,x)=h(t,x)(21)

[0162]

[0163] Where t is time, x is spatial position, and functions h and k describe the dynamic distribution of different energy flows in the time and space dimensions.

[0164] In this embodiment, when the extended resource-task network model performs collaborative regulation on resources involved in multiple production tasks, it performs multi-correlation processing on them, establishes an optimization model with constraints, and realizes the collaborative matching of multiple energy and quality supplies to production task requirements; wherein, the constraints include resource supply capacity, dynamic allocation of energy and quality flows, and timing dependencies of production tasks.

[0165] In a specific example of this embodiment, for a task T involving multiple resources i , whose goal is to minimize the consumption of energy and mass flow to meet the task requirements. The optimization problem can be expressed as:

[0166]

[0167] Among them, E r,i (t) represents the resource r in task T i The consumption of is subject to the following constraints:

[0168] E r,i (t)≥D r,i (t)(24)

[0169] Among them, D r,i (t) represents task T i The minimum demand for resource τ.

[0170] In this embodiment, in the extended resource-task network model, each task node not only represents the execution progress of the task, but also reflects the consumption of energy and mass flow; based on this, when the extended resource-task network model allocates resources and tasks, a dynamic optimization algorithm is used to dynamically adjust the execution order of production tasks and the energy and mass flow allocation strategy according to the current energy and mass flow distribution in the green hydrogen metallurgical integrated energy system to ensure optimal efficiency and stability of the system.

[0171] In this embodiment, the dynamic optimization algorithm in the above process may be a heuristic algorithm or a large-scale linear programming method; illustratively, the above heuristic algorithm includes a genetic algorithm and a particle swarm optimization algorithm).

[0172] In step S4 of the embodiment of the present invention, in a complex multi-energy and mass flow system, due to the volatility of energy and mass flows and the uncertainty of system requirements, traditional control strategies are difficult to achieve efficient production control. Therefore, it is necessary to implement a multi-model predictive control (MPC) strategy to achieve real-time control of system operation. In this embodiment, multiple random variable prediction models are designed, and production control is performed through a combination of multiple models to effectively address system complexity and uncertainty.

[0173] Based on this, Figure 4 As shown, step S4 of this embodiment includes the following sub-steps:

[0174] S41. Based on the task-resource allocation results obtained from the extended resource-task network model, perform a time series characteristic analysis on the random variables involved in the production process;

[0175] For example, the random variables involved in the production process include wind power, photovoltaic power generation, user-side load demand, etc. The prediction of these random variables is crucial for production regulation. It is necessary to establish a discrete-time prediction model to estimate the future changes of these variables in advance.

[0176] S42. Construct a discrete-time prediction model based on the results of the temporal characteristics analysis of the random variables, and use the model to predict the random variables involved in the production process at future moments;

[0177] S43, inputting the predicted random variables into a multi-model prediction mechanism based on a local model, predicting energy and mass flow allocation strategies under different operating states, and inputting the predicted random variables into a multi-model prediction mechanism based on a multi-controller combination;

[0178] S44. In the multi-model prediction mechanism based on multiple controllers, on the basis of ensuring the scheduling consistency between independent controllers, the corresponding independent controller is selected to perform energy and mass flow regulation according to the energy and mass flow characteristics involved, and the energy and mass flow regulation strategy for the current working conditions is output to achieve coordinated regulation of the green hydrogen metallurgical integrated energy system.

[0179] In an example of this embodiment, in the above step S41, the method for performing time series characteristic analysis on random variables involved in the production process is:

[0180] Perform time series analysis on each random variable to capture the volatility characteristics of its historical data. Classic time series models such as the Autoregressive Integrated Moving Average (ARIMA) model and the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model can be used to fit the volatility patterns of each random variable at different time scales.

[0181] For each random variable x t To perform time series analysis and capture its historical volatility characteristics, the autoregressive integrated moving average model (ARIMA) can be used to model random variables:

[0182] x t =φ1x t-1 +φ2x t-2 +…+φ p x t-p +ε t (25)

[0183] Among them, ε t is the noise term.

[0184] In an example of this embodiment, in the above step S42, a discrete time prediction model is constructed based on the results of the time series characteristic analysis. The model can discretize future time series fluctuations into several time steps (such as minutes, hours, days, etc.), thereby providing accurate prediction values ​​for production control.

[0185] In this embodiment, in order to further improve the prediction accuracy, an adaptive weighted prediction model can be introduced to perform weighted fusion on the results of multiple prediction methods such as neural networks and decision trees to generate more accurate prediction outputs.

[0186] Based on the characteristics of time series, a discrete time prediction model is constructed to predict the value of random variables at future moments. The prediction results of multiple models (such as neural networks and decision trees) are integrated through weighted prediction methods:

[0187]

[0188] In this embodiment, the discrete-time model constructed in step S42 above not only outputs a single predicted value but also provides a probability distribution for random variables. For example, in photovoltaic power generation forecasting, it is necessary not only to predict the expected value but also to provide a probability distribution for power generation within a certain range. By predicting the probability density function, we can better address system uncertainties, thereby providing richer information for subsequent control strategies.

[0189] In this embodiment, the uncertainty in the system is handled by predicting the probability distribution of random variables. For example, the distribution information of random variables is obtained by predicting the probability density function f(x):

[0190]

[0191] In step S4 of this embodiment, due to the complexity of the system, a single model cannot cover all operating conditions of the system. Therefore, this embodiment introduces a multi-model predictive control (MPC) mechanism. By combining multiple local models, it can flexibly respond to different production scenarios and energy and mass flow distribution requirements. Therefore, in step S43 of this embodiment, the multi-model prediction mechanism based on local models predicts the energy and mass flow distribution strategy under different operating conditions.

[0192] In this embodiment, the multi-model prediction mechanism based on local model combination refers to:

[0193] A local model is constructed to realize energy and mass flow distribution prediction under different working conditions, and based on the conditional model switching mechanism, the optimal local model is switched according to the operating status of the green hydrogen metallurgical integrated energy system to perform corresponding energy and mass flow distribution prediction.

[0194] Specifically, in this embodiment, local models are constructed for different operating stages of the system. For example, the system's energy and mass flow distribution rules and response characteristics differ under low and high load conditions. For these different operating conditions, local models based on linear systems, nonlinear models, or machine learning models (such as long short-term memory networks (LSTMs) or support vector machines (SVMs)) can be established.

[0195] Build local models for different operating conditions of the system. For example, under different load conditions, the distribution rules of energy and mass flow are different, and different local models can be built for each. Assume that the system state equation is:

[0196] x t+1 =f i (x t ,u t )(28)

[0197] Among them, fi is the i-th local model.

[0198] In this embodiment, a conditional model switching mechanism is introduced into the aforementioned local model-based multi-model prediction mechanism, enabling the selection of appropriate local models under different system operating conditions. For example, when system load fluctuations are large, a local model suitable for highly fluctuating conditions can be switched, while a simple linear model can be selected when the system is operating smoothly. This model switching mechanism can be implemented using threshold settings, state observers, or dynamic discrimination methods based on real-time data.

[0199] In one example of this embodiment, a model switching threshold θ is set, and an appropriate local model is selected according to the system state:

[0200]

[0201] In this embodiment, the aforementioned multi-model prediction mechanism based on local models not only utilizes a conditional model switching mechanism to switch between single local models, but also improves control accuracy through combined optimization of multiple models. A model fusion strategy is employed to weighted average or fuse the prediction results of multiple local models, thereby achieving a more accurate system state prediction. Bayesian model averaging can be employed to dynamically adjust the weights of each model based on its historical prediction accuracy, thereby achieving the optimal prediction result.

[0202] In an example of this embodiment, the outputs of multiple models are weighted averaged or fused through a model fusion strategy.

[0203]

[0204] in is the output of the i-th model, ω i is the weight.

[0205] In step S4 of the embodiment of the present invention, based on the above-mentioned multi-model prediction mechanism based on local models, this embodiment also designs a multi-controller combination strategy to cope with different operating conditions and energy and mass flow control requirements. Through the local optimization and collaborative operation of different controllers, the stable operation of the system can be guaranteed. Based on this, in step S44 of this embodiment, energy and mass flow control for different operating conditions is carried out through the multi-model prediction mechanism based on multiple controllers, realizing the coordinated control of the green hydrogen metallurgical integrated energy system.

[0206] In this embodiment, the multi-model prediction mechanism based on the combination of multiple controllers refers to:

[0207] On the basis of the energy and mass flow allocation strategy predicted by the multi-model prediction mechanism of local model combination, corresponding independent controllers are designed according to different energy and mass flow characteristics. In view of different working conditions and energy and mass flow control requirements, a collaborative mechanism based on constraint optimization is adopted, and a global objective function is introduced to optimize the control target of each independent controller to obtain the optimal energy and mass flow control strategy for the system as a whole. Among them, the outputs of each independent controller are interrelated.

[0208] Specifically, in this embodiment, corresponding independent controllers are designed for different energy and mass flow characteristics; for example, for the electrolysis hydrogen production link, an energy controller based on model prediction can be designed to adjust the working power of the electrolyzer in real time; for the hydrogen storage system, a hydrogen storage controller based on inventory prediction can be designed to ensure the rationality of hydrogen reserves.

[0209] In this embodiment, the outputs of the independent controllers are interdependent, necessitating coordinated control through a collaborative mechanism. For example, the output of the hydrogen electrolysis controller could affect the operating state of the hydrogen storage controller. Therefore, a multi-controller collaborative algorithm is required to ensure scheduling consistency across the controllers. This can be achieved by employing a collaborative mechanism based on constrained optimization, introducing a global objective function, and optimizing the control objectives of each controller, thereby achieving optimal control of the entire system.

[0210] In this embodiment, based on the above-mentioned multi-controller-based multi-model prediction mechanism, a multi-controller combination based on distributed combinatorial optimization can also be constructed to deal with the information lag and computational burden that a centralized controller may face when the system is large in scale and the energy and mass flow links are widely distributed. At this time, a distributed optimization algorithm can be introduced to divide the system into multiple subsystems, each of which is independently controlled by a corresponding controller, and the subsystems collaborate through information exchange. Distributed optimization algorithms such as the alternating direction method of multipliers (ADMM) can be used to coordinate decisions between local controllers, thereby improving the efficiency of global control.

[0211] Specific embodiments are used in the present invention to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

[0212] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. A multi-scale coordinated control method for a green hydrogen metallurgical integrated energy system, characterized in that: The following steps are involved: S1. Analyze the multi-timescale regulation characteristics of flexible and adjustable resources in the green hydrogen metallurgical integrated energy system and form a regulation response timescale matrix; S2. According to the regulation response time scale matrix, the cross-link regulation characteristics in the multi-energy interaction are analyzed, and then equivalent modeling based on heterogeneous links is performed to obtain an equivalent model of regulation external characteristics; S3. Based on dynamic correlation analysis, analyze the impact of different production tasks on the distribution of multiple energy and mass flows in the green hydrogen metallurgical integrated energy system, and establish an extended resource-task network model to characterize the relationship between production tasks and multiple energy and mass flows; S4. Based on the task-resource allocation results obtained from the extended resource-task network model, the random variables involved in the production process at future moments are predicted and input into a multi-model prediction mechanism based on local model combination and multi-controller combination. The energy and mass flow control strategy for the current working conditions is output to achieve coordinated control of the green hydrogen metallurgical integrated energy system. In step S2, equivalent modeling based on heterogeneous links is performed to obtain an equivalent model for adjusting external characteristics, specifically: S21. Collect historical operating data of various equipment in the green hydrogen metallurgical integrated energy system; The historical operating data is the regulation characteristic data of various types of equipment under different working conditions; S22. Selecting a corresponding deep neural network based on different adjustment characteristic data of various types of equipment; S23. Train the corresponding deep neural network based on historical operation data and dynamically update it to obtain the external regulation characteristic models corresponding to the different regulation characteristics of various types of equipment; The step S3 includes the following sub-steps: S31. Dynamically analyze the correlation between production task types and multi-energy and mass flow distribution in the green hydrogen metallurgical integrated energy system, and construct a dynamic correlation model for production tasks; S32. Dynamically analyze the correlation between the production process and the distribution of multiple energy and mass flows of production tasks in the green hydrogen metallurgical integrated energy system, and build a coordinated control model of energy and mass flows between processes; S33. Based on the constructed production task dynamic association model and the inter-process energy and mass flow collaborative control model, and by introducing the dynamic characteristics of time and space energy and mass flow, an extended resource-task network model is constructed; The step S31 includes the following sub-steps: S31-1. Classify the production tasks in the green hydrogen metallurgical integrated energy system according to production needs, and determine the energy and mass flow demand characteristics of each production task at different times; S31-2. Fit the historical data corresponding to the demand characteristics of energy and mass flow for various production tasks in different time periods to establish dynamic demand curves for various production tasks; S31-3. Dynamically generate multiple association models of different production task types based on the dynamic demand curves of various production tasks to obtain a dynamic association model of production tasks; The production task types include continuous production tasks and discrete production tasks; The step S32 includes the following sub-steps: S32-1. Analyze the energy and quality demand characteristics of each production process in the green hydrogen metallurgical integrated energy system; S32-2. Based on the energy demand characteristics corresponding to different production processes, the execution order of the production processes and the energy flow distribution of each production task are adjusted in real time through dynamic programming or optimization algorithms to achieve optimal coordinated scheduling between production processes, thereby obtaining a coordinated control model for energy flow between processes; The inter-process energy and mass flow collaborative control model takes the time scheduling cost between production processes, the dependency between production processes and resource limitations as constraints; In step S33, the extended resource-task network model constructed is a model for dynamically adjusting resource supply and task demand in the green hydrogen metallurgical integrated energy system according to time series data; When the extended resource-task network model coordinates and controls resources involved in multiple production tasks, it processes their multi-correlations and establishes an optimization model with constraints to achieve multi-energy and quality supply coordination to match production task requirements. The constraints include resource supply capacity, dynamic allocation of energy and quality flows, and temporal dependencies of production tasks. When allocating resources and tasks, the extended resource-task network model adopts a dynamic optimization algorithm to dynamically adjust the execution order of production tasks and the allocation strategy of energy and mass flow according to the current energy and mass flow distribution in the green hydrogen metallurgical integrated energy system; The extended resource-task network model is defined as: ； ； in, For time, is the spatial position, function and Describe the dynamic distribution of different energy and matter flows in the space-time dimensions.

2. The multi-scale coordinated control method of the green hydrogen metallurgical integrated energy system according to claim 1 is characterized in that: In step S1, the method for analyzing the multi-time scale adjustment characteristics of the flexible and adjustable resources is: The regulation response characteristics of the energy supply, demand, energy conversion and storage links in the green hydrogen metallurgical integrated energy system at different time scales are analyzed, including energy supply regulation characteristics, demand side regulation characteristics, energy conversion link regulation characteristics and storage link regulation characteristics.

3. The multi-scale coordinated control method of the green hydrogen metallurgical integrated energy system according to claim 1 is characterized in that: In step S2, the method for analyzing the cross-link regulation characteristics in the multi-energy interaction is specifically as follows: By constructing an energy-mass flow coupling model and analyzing the time delay effect in the cross-link energy-mass interaction process, we analyze the impact of the mutual conversion and interaction between different energy materials on the overall scheduling of the green hydrogen metallurgical integrated energy system; The delay effect includes cross-link energy transmission delay and conversion delay.

4. The multi-scale coordinated control method of the green hydrogen metallurgical integrated energy system according to claim 1 is characterized in that: In step S4, the multi-model prediction mechanism based on local model combination refers to: Construct a local model for energy and mass flow distribution prediction under different operating conditions, and based on the conditional model switching mechanism, switch the optimal local model according to the operating status of the green hydrogen metallurgical integrated energy system to perform corresponding energy and mass flow distribution prediction; The multi-model prediction mechanism based on multi-controller combination refers to: On the basis of the energy and mass flow allocation strategy predicted by the multi-model prediction mechanism of local model combination, corresponding independent controllers are designed according to different energy and mass flow characteristics. In view of different working conditions and energy and mass flow control requirements, a collaborative mechanism based on constraint optimization is adopted, and a global objective function is introduced to optimize the control target of each independent controller to obtain the optimal energy and mass flow control strategy for the system as a whole. Among them, the outputs of each independent controller are interrelated.

5. The multi-scale coordinated control method of the green hydrogen metallurgical integrated energy system according to claim 4 is characterized in that: The step S4 comprises the following sub-steps: S41. Based on the task-resource allocation results obtained from the extended resource-task network model, perform a time series characteristic analysis on the random variables involved in the production process; S42. Construct a discrete-time prediction model based on the results of the temporal characteristics analysis of the random variables, and use the model to predict the random variables involved in the production process at future moments; S43, inputting the predicted random variables into a multi-model prediction mechanism based on a local model, predicting energy and mass flow allocation strategies under different operating states, and inputting the predicted random variables into a multi-model prediction mechanism based on a multi-controller combination; S44. In the multi-model prediction mechanism based on multiple controllers, on the basis of ensuring the scheduling consistency between independent controllers, the corresponding independent controller is selected to perform energy and mass flow regulation according to the energy and mass flow characteristics involved, and the energy and mass flow regulation strategy for the current working conditions is output to achieve coordinated regulation of the green hydrogen metallurgical integrated energy system.

Images