Model-predictive control-based hydrogen refueling system, method, and apparatus

Abstract

An object of the present invention is to improve the efficiency of the hydrogen filling / supply process while safely filling / supplying hydrogen fuel, and to improve the speed and real-time nature of the hydrogen filling / supply process. [Solution] The hydrogen fueling method for hydrogen-fueled mobility of the present invention is a hydrogen fueling method based on model predictive control, and is characterized by including the steps of acquiring a current state measurement value, predicting or acquiring a next state value using a model predictive control technique based on the current state measurement value, and generating a control command for hydrogen fueling based on a comparison result between the current state measurement value and the next state value.

Description

Technical Field

[0001] The present invention relates to control technology for hydrogen fueling / supply in hydrogen fueled mobility, and more particularly, to a hydrogen fueling process that enhances the efficiency of hydrogen fueling / supply, increases the speed and real-time performance of fueling / supply, control techniques for the process, and protocols for the control techniques.

Background Art

[0002] A hydrogen vehicle, a hydrogen electric vehicle, or a fuel cell electric vehicle (FCEV) means an environmentally friendly vehicle that runs on electrical energy generated when high-pressure hydrogen stored in the vehicle meets air in the atmosphere. A hydrogen electric vehicle utilizes hydrogen as an energy source and produces electricity using a fuel cell system. As is well known, a hydrogen electric vehicle not only emits only pure water (H2O) during the process of generating electricity, but also has a function of removing ultrafine dust in the atmosphere during operation, and thus is attracting attention as a future environmentally friendly mobility. It is in the spotlight as a technology with potential for use in the entire industry in terms of the fact that hydrogen as a fuel is infinite on the earth and the process of producing energy is environmentally friendly.

[0003] Hydrogen fueled mobility means mobility that uses hydrogen as an energy source or generates electrical energy using hydrogen as a fuel and drives an electric motor using this. In addition to the hydrogen electric vehicle described above, hydrogen fueled mobility may include, of course, Aerial Mobility, as well as industrial trucks, trains, ships, and aircraft that generate electrical energy using hydrogen as a fuel and drive using this. More comprehensively, buildings or facilities that use hydrogen as an energy source may also be included in the application fields to which the technical idea of the present invention can be applied. Hydrogen-electric vehicles (HEVs) safely store high-pressure hydrogen in a hydrogen fuel storage tank and supply oxygen through an air supply system to a fuel cell stack. An electrochemical reaction occurs between the hydrogen and oxygen to produce electrical energy. This electrical energy is converted into kinetic energy via a drive motor to power the HEV, and while driving, HEVs have the advantage of emitting only pure water through the exhaust.

[0004] Fuel cell systems play a role in powering hydrogen electric vehicles, replacing the engines of internal combustion engine vehicles. A fuel cell is a device that generates the electrical energy necessary for propulsion and is also called a "tertiary battery." Fuel cells convert thermal energy into electrical energy using the electrochemical reaction between oxygen and hydrogen. The electrical energy generated at this time is a pure chemical reaction product and, unlike fossil fuels, does not produce exhaust gases such as carbon dioxide. Fuel cell systems come in various types depending on the fuel and materials, such as PEMFC, SOFC, and MCFC. The configuration that uses fuel cells to produce power in hydrogen electric vehicles includes a fuel cell stack, a hydrogen supply system, an air supply system, and a thermal management system. For efficient electrical energy generation in a fuel cell stack, the operation of the operating system is necessary. Among these, the hydrogen supply system plays a crucial role in transferring hydrogen, safely stored in a hydrogen fuel storage tank, from a high-pressure state to a low-pressure state to the fuel cell stack, and can also improve hydrogen supply efficiency through a recirculation line. A thermal management system is a device that releases the heat generated when the fuel cell stack undergoes electrochemical reactions to the outside and maintains a constant temperature of the fuel cell stack by circulating cooling water. The thermal management system can affect the output and lifespan of the fuel cell stack. While the concept of a hydrogen fueled car (hydrogen-fueled vehicle), as opposed to a hydrogen electric vehicle, also involves using hydrogen as fuel, hydrogen fueled vehicles utilize a system where the heat generated by directly burning hydrogen in the engine drives the electric motor. The method of refueling / supplying hydrogen for hydrogen fueled vehicles is not significantly different from the method of refueling / supplying hydrogen for hydrogen electric vehicles.

[0005] Control techniques for refueling / supplying hydrogen to vehicles that use hydrogen as fuel ultimately aim to control the temperature (T) and pressure (P) of the compressed hydrogen storage system (CHSS) on the fuel cell side to operate under safe limit temperature / pressure conditions. Conventional hydrogen refueling / supply processes, control techniques, and protocols for hydrogen-electric vehicles were defined when wired / wireless technologies and computing techniques for control were not yet mature, and therefore fail to fully reflect the recent advancements in information and communication technology (ICT). Therefore, conventional hydrogen refueling / supply technologies for hydrogen-electric vehicles are inefficient and slow, and not suitable for large-volume hydrogen refueling. [Overview of the Initiative] [Problems that the invention aims to solve]

[0006] The objective of the present invention, in order to solve the problems described above, is to improve the efficiency of the hydrogen refueling / supply process while safely refueling / supplying hydrogen fuel, and to improve the speed and real-time capabilities of the hydrogen refueling / supply process.

[0007] The objective of this invention is to propose a hydrogen refueling control technique that ensures real-time performance of the model predictive control platform.

[0008] The objective of this invention is to propose a control technique that improves the accuracy of hydrogen refueling result prediction based on an artificial neural network model.

[0009] The objective of this invention is to improve the efficiency of hydrogen refueling control by integrating and managing data actually measured and state information predicted from models using an intelligent metasystem (IMS). [Means for solving the problem]

[0010] The hydrogen fueling method for hydrogen fueled mobility according to the present invention, which aims to achieve the above objective, is a hydrogen fueling method based on a model predictive control platform, and is characterized by including the steps of: obtaining a measurement of the current state; predicting or obtaining the next state value using a model predictive control technique based on the measurement of the current state; and generating a control command for hydrogen fueling based on the comparison result between the measurement of the current state and the next state value.

[0011] The hydrogen filling method of the present invention further includes a step of evaluating whether the measured value of the current state and the next state value satisfy the constraint conditions.

[0012] The constraint is that the temperature and pressure of the compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility do not exceed the critical temperature and critical pressure, respectively.

[0013] The step of generating control commands includes the step of generating control commands for the pressure ramp rate (PRR) for hydrogen refueling.

[0014] The stage of predicting or acquiring the next state value includes the stage of predicting multiple next state values ​​that form a prediction horizon using the model.

[0015] The control instruction generation stage generates multiple control instructions that form a control horizon corresponding to the prediction horizon, based on the comparison results between multiple next state values ​​and set points, so that the process by which the future response reaches the set point is optimized.

[0016] In the stages of predicting and acquiring the next state value and generating control commands, multiple control commands are acquired that form a control horizon corresponding to a prediction horizon containing multiple next state values, so as to optimize the process by which the future response reaches a set point using model predictive control techniques.

[0017] The hydrogen fueling method for hydrogen fuel mobility of the present invention is an artificial neural network-based hydrogen fueling method, characterized in that it includes the steps of: acquiring a measurement of the current state; generating a fueling control command for hydrogen fueling based on the output of an artificial neural network that takes the measurement of the current state as input; acquiring the next state value based on the fueling control command; and evaluating whether the response by executing the fueling control command satisfies the constraint conditions.

[0018] In the stage of generating filling control commands, the commands are generated based on the output of an artificial neural network that has learned the function of generating filling control commands so that each future response after the measurement of the current state reaches the set point while satisfying the constraints.

[0019] In the stage of generating filling control instructions, multiple control instructions corresponding to multiple next state values ​​are generated based on the output of an artificial neural network that has learned the ability to predict multiple next state values ​​that minimize the cost function for the filling state.

[0020] The hydrogen fueling control device for hydrogen fuel mobility according to the present invention includes a processor and a memory for storing at least one instruction. The processor is characterized by obtaining a measurement of the current state by executing at least one instruction, and obtaining a fueling control instruction for hydrogen fueling and the next state value corresponding to the fueling control instruction based on at least one of a model predictive control technique based on the measurement of the current state and the output of an artificial neural network that takes the measurement of the current state as input.

[0021] The processor evaluates whether each response resulting from the execution of a fill control instruction satisfies the constraints.

[0022] The control command includes a control command for the pressure ramp rate (PRR) for hydrogen filling.

[0023] The processor predicts a plurality of next state values that form a prediction horizon by means of a model predictive control technique.

[0024] The processor generates a plurality of control commands that form a control horizon corresponding to the prediction horizon so that the process of the future response reaching the set point is optimized based on the comparison result between the plurality of next state values and the set point.

[0025] The processor evaluates whether each of the plurality of next state values satisfies the constraint conditions.

[0026] The processor obtains a plurality of control commands that form a control horizon corresponding to the prediction horizon that includes a plurality of next state values so that the process of the future response reaching the set point is optimized by means of a model predictive control technique.

Advantages of the Invention

[0027] According to the present invention, it is possible to improve the efficiency of the hydrogen filling / supply process while safely filling / supplying hydrogen fuel, and to improve the speed and real-time performance of the hydrogen filling / supply process.

[0028] According to the present invention, it is possible to provide a hydrogen filling control technique in which the real-time performance of the model predictive control base is ensured.

[0029] According to the present invention, it is possible to provide a control technique in which the prediction accuracy of the hydrogen filling result based on the artificial neural network model is improved. The accuracy of the prediction result can be improved by reflecting the real-time measurement values in the artificial neural network model that utilizes the actual filling data together with the theoretical simulation results.

[0030] According to the present invention, the efficiency of hydrogen refueling control can be improved by integrating and managing data actually measured and state information predicted from a model using an intelligent metasystem (IMS). [Brief explanation of the drawing]

[0031] [Figure 1] This is a conceptual diagram illustrating an example of the hydrogen refueling process for a hydrogen fuel cell electric vehicle (FCEV) according to the present invention. [Figure 2] This is a conceptual diagram illustrating an example of a logical process for refueling a hydrogen fuel cell electric vehicle (FCEV) according to the present invention. [Figure 3] This is a conceptual diagram illustrating an example of a state change that occurs during the hydrogen refueling process for a hydrogen fuel cell electric vehicle (FCEV) according to the present invention. [Figure 4] This is a conceptual diagram illustrating the concept of model predictive control for hydrogen refueling control for a hydrogen fuel cell electric vehicle (FCEV) according to the present invention. [Figure 5] This is an operation flowchart illustrating the model predictive control-based hydrogen refueling control method of the present invention. [Figure 6] This is a conceptual diagram illustrating the concept of an artificial neural network for hydrogen refueling control for a hydrogen fuel cell electric vehicle (FCEV) according to the present invention. [Figure 7] This is a conceptual diagram illustrating the hydrogen refueling control process for a fuel cell electric vehicle (FCEV) utilizing the artificial neural network and intelligent meta-system (IMS, Integrated Meta System) of the present invention. [Figure 8] This is an operation flowchart illustrating the artificial neural network-based hydrogen refueling control method of the present invention. [Figure 9] This is an operation flowchart illustrating the training process of the artificial neural network for hydrogen refueling control, based on the artificial neural network model of the present invention. [Figure 10] This is a conceptual diagram illustrating in detail a part of the process shown in Figure 9. [Figure 11] This is a conceptual diagram illustrating in detail a part of the process shown in Figure 9. [Figure 12] This is a conceptual diagram illustrating the hydrogen refueling control process based on the artificial neural network model prediction and control platform of the present invention. [Figure 13] This is a conceptual diagram illustrating an artificial neural network-based integrated control model for controlling the hydrogen refueling process of the present invention. [Figure 14] This diagram illustrates the event-based control process for the integrated control model shown in Figure 13. [Figure 15] This is an operation flowchart illustrating the integrated control method for hydrogen refueling according to the present invention. [Figure 16] This is a conceptual diagram illustrating an example of a generalized hydrogen refueling control device, hydrogen refueling control system, or computing system capable of performing at least part of the processes shown in Figures 1 to 15. [Modes for carrying out the invention]

[0032] The present invention can be modified in various ways and has many embodiments. Specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to specific embodiments, but rather should be understood to include all modifications, equivalents, or substitutes that fall within the spirit and technical scope of the present invention. In the description of each drawing, similar reference numerals are used for similar components. Terms such as First, Second, A, and B may be used to describe various components, but components should not be limited by these terms. Terms are used solely to distinguish one component from another. For example, without departing the scope of the invention, the First component may be named the Second component, and similarly, the Second component may be named the First component. The term "and / or" includes combinations of multiple related described items or any of multiple related described items. In the embodiments of this application, "at least one of A and B" may mean "A or at least one of B" or "at least one of one or more combinations of A and B". Also, in the embodiments of this application, "one or more of A and B" may mean "one or more of A or B" or "one or more of one or more combinations of A and B". When it is stated that one component is "connected" or "linked" to another component, it should be understood that it may be directly connected to or linked to the other component, but that other components may exist in between. Conversely, when it is stated that one component is "directly connected" or "directly linked" to another component, it should be understood that there are no other components in between. The terminology used in this application is used solely to describe specific embodiments and is not intended to limit the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as “includes” or “having” are intended to specify the presence of features, figures, stages, operations, components, parts, or combinations thereof described in the specification, and should be understood not to preemptively exclude the possibility of the presence or addition of one or more other features, figures, stages, operations, components, parts, or combinations thereof. Unless otherwise specified, all terms used herein, including technical or scientific terms, have the same meaning as those generally understood by a person of ordinary skill in the art to which this invention pertains. Terms as defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art, and not as ideal or overly formal unless expressly defined herein.

[0033] Some terms used in this specification are defined below.

[0034] A hydrogen vehicle, hydrogen electric vehicle, or fuel cell electric vehicle (FCEV) refers to a pollution-free vehicle that runs on electrical energy generated by the combination of high-pressure hydrogen stored in the vehicle and air from the atmosphere.

[0035] A Compressed Hydrogen Storage System (CHSS) is a component of a vehicle's fuel cell that compresses and stores hydrogen.

[0036] A Pressure Relief Device (PRD) is a device installed in a CHSS that can isolate stored hydrogen from the rest of the fuel system and the environment, and conversely, can release hydrogen to the outside.

[0037] The hydrogen refueling process refers to the process of transferring high-pressure hydrogen from a hydrogen refueling station and storing it in a fuel cell.

[0038] The pressure ramp rate (PRR) is expressed in MPa / min and represents the rate of increase in the CHSS pressure.

[0039] The Average Pressure Ramp Rate (APRR) refers to the average value of the pressure increase rate from the start to the end of hydrogen fueling.

[0040] Pre-cooling refers to the process of cooling hydrogen at a hydrogen refueling station before it is filled.

[0041] A dispenser is a component that delivers pre-cooled hydrogen to the CHSS (Chemical Hydrogen Stabilizer).

[0042] A nozzle is a device connected to the hydrogen dispensing system at a hydrogen refueling station, which then connects to the receptacle of a hydrogen electric vehicle, allowing for the transfer of hydrogen fuel.

[0043] On the other hand, even if a technology is known prior to the filing date of this application, it may be included as part of the structure of the present invention as necessary, and such will be described herein to the extent that it does not obscure the spirit of the present invention. However, in describing the structure of the present invention, detailed explanations of matters that are known prior to the filing date and are obvious to those skilled in the art may obscure the spirit of the present invention, so overly detailed explanations of prior art will be omitted. For example, prior art known prior to the filing of this application can be used for technologies that utilize thermodynamic models for hydrogen refueling control, technologies that apply model predictive control techniques for generalized dynamic control, and technologies that construct and control artificial neural networks for training and inference of artificial neural networks, and at least some of these prior arts can be applied as elemental technologies necessary for carrying out the present invention. However, the purpose of this invention is not to assert rights over these prior arts, and the content of these prior arts may be included as part of this invention without departing from the spirit of this invention.

[0044] Preferred embodiments of the present invention will be described in detail below with reference to the attached drawings.

[0045] Figure 1 is a conceptual diagram illustrating an example of a hydrogen refueling process for a fuel cell electric vehicle (FCEV) to which one embodiment of the present invention is applied. As shown in Figure 1, pre-cooled hydrogen gas is supplied from a hydrogen refueling station (Station, 200) to a hydrogen fuel cell electric vehicle (FCEV, 300) via a dispenser 100. At this time, the hydrogen refueling process can be described by parameters including the rate of pressure increase (PRR) and / or the mean rate of pressure increase (APRR).

[0046] Figure 1 illustrates an example related to a hydrogen fuel cell electric vehicle (FCEV), but it will be obvious to those skilled in the art that the concept of the present invention can be applied to various types of hydrogen fueled mobility.

[0047] Hydrogen fuel mobility refers to a type of mobility that uses hydrogen as an energy source or generates electrical energy using hydrogen as fuel, which is then used to drive an electric motor.

[0048] Hydrogen fuel mobility includes not only hydrogen electric vehicles but also aerial mobility, as well as industrial trucks, trains, ships, and aircraft that use hydrogen as fuel to generate electrical energy and power themselves.

[0049] The hydrogen refueling process of the present invention can be applied not only to hydrogen fuel mobility but also to buildings or facilities that use hydrogen as an energy source.

[0050] Furthermore, although the embodiment shown in Figure 1 involves hydrogen gas, the concept of the present invention can also be applied to liquefied hydrogen.

[0051] In the following explanation, for the sake of clarity, the content of the present invention will be described using hydrogen fuel cell electric vehicles (FCEVs) and hydrogen gas as the main examples, but the scope of the rights of this application should not be interpreted restrictively based on such examples.

[0052] Generally, hydrogen storage systems attached to vehicles can be broadly divided into high-pressure hydrogen storage tanks, pressure control equipment, high-pressure piping, and external frames. High-pressure hydrogen storage tanks have been developed and commercialized with capacities of tens or hundreds of liters, and for vehicle applications, smaller and lighter storage tanks are connected in parallel to achieve high capacity.

[0053] High-pressure hydrogen storage tanks are widely known as compressed hydrogen storage systems (CHSS) 310, and for convenience of explanation, the term "storage tank" in this specification refers to a CHSS 310. In a typical hydrogen storage system, hydrogen storage is controlled by utilizing a boss unit that allows hydrogen gas to enter and exit the storage tank 310. Due to the fact that hydrogen injection and utilization cannot proceed simultaneously, a valve, a depressurization mechanism, and sensors for various measurements are attached to a single boss unit to control hydrogen storage.

[0054] The interface between the hydrogen refueling station 200 and the vehicle 300 is handled by the dispenser 100, which integrates information from the vehicle 300's storage tank 310 and the refueling station 200's fuel supply information to control the target pressure and injection rate, etc. The control logic currently used conforms to the SAE J2601 (2020-05) standard.

[0055] Conventional technology has two methods for transmitting information from vehicle 300 to dispenser 100: a communication method and a non-communication method. Even when communication is used, conventional technology simply transmits the temperature and pressure values ​​of the storage tank 310 of vehicle 300 to dispenser 100 in a unidirectional manner. Dispenser 100 does not actively utilize this information, but merely uses it as a safety standard, such as an emergency stop at the limit temperature and pressure.

[0056] The filling logic for safe and rapid filling is entirely controlled by the dispenser 100, and the storage tank 310 has only minimal safety control devices that automatically release hydrogen through the pressure discharge device (PRD) 320 under conditions such as overheating, without any active safety control system.

[0057] To address the phenomenon of rising hydrogen gas temperature during hydrogen refueling, as described later in Figure 3, the refueling station 200 includes a high-pressure hydrogen storage unit 220 and a precooler 210. The precooler 210 supplies hydrogen gas to the hydrogen electric vehicle 300 via the dispenser 100 after lowering the hydrogen gas temperature through pre-cooling.

[0058] In one embodiment of the present invention, a basic configuration similar to that of the prior art is used, but the filling control logic 110 inside the dispenser 100 actively controls the hydrogen fueling process by utilizing state information such as temperature and pressure received from the vehicle 300 and the filling station 200, as well as filling state information such as the filling rate (SOC, State of Charge) of the CHSS 310.

[0059] According to one embodiment of the present invention, the filling speed is controlled in real time by utilizing real-time temperature data of the storage tank 310, and is designed to operate at the highest filling speed that satisfies conditions below the safety limit, thereby reducing the filling time within the usable range.

[0060] Conventional filling protocols have the problem of excessive pre-cooling during supply, as the boundary conditions for safety are set too high, resulting in the temperature of most storage tanks 310 being measured at around 40-50°C at the time of filling completion.

[0061] According to one embodiment of the present invention, the cooling load of the filling station 200 can be optimized by actively adjusting the required amount of pre-cooling and the amount supplied, thereby increasing the operational efficiency of the hydrogen filling station 200.

[0062] Conventional protocols, which are primarily designed for lightweight hydrogen-electric vehicles, have the drawback that all variables must be reset and reflected in the standard when refueling new mobility vehicles.

[0063] According to one embodiment of the present invention, when applying a learnable fill logic based on an artificial neural network to a new device, the control technique, which updates the logic itself through a certain learning and training process, can be widely applied to various mobility domains.

[0064] Conventional hydrogen electric vehicle (HEV) 300's storage tank 310 overheat prevention measures only involve releasing gas through the PRD320 when the tank overheats above a certain temperature.

[0065] According to one embodiment of the present invention, by installing a cooling system in the storage tank 310 itself to increase the filling speed, and by actively dealing with overheating of the storage tank 310, the safety of the hydrogen electric vehicle 300 can be improved.

[0066] According to one embodiment of the present invention, it is possible to improve the efficiency of the hydrogen refueling / supply process while safely refueling / supplying hydrogen fuel, and to improve the speed and real-time capabilities of the hydrogen refueling / supply process.

[0067] According to one embodiment of the present invention, a hydrogen refueling control technique can be provided in which the real-time capability of the model predictive control platform is ensured.

[0068] According to one embodiment of the present invention, a control technique is provided that improves the accuracy of hydrogen refueling result predictions based on an artificial neural network model. The accuracy of prediction results can be improved by incorporating real-time measurements into an artificial neural network model that utilizes actual refueling data along with theoretical simulation results.

[0069] According to one embodiment of the present invention, the efficiency of hydrogen refueling control can be improved by integrating and managing data actually measured and state information predicted from a model using an intelligent metasystem (IMS).

[0070] Figure 2 is a conceptual diagram illustrating an example of a logical process for hydrogen refueling for a fuel cell electric vehicle (FCEV) to which one embodiment of the present invention is applied.

[0071] As mentioned above, in conventional hydrogen refueling processes, the dispenser 100 is responsible for controlling the interaction between the vehicle 300 and the hydrogen refueling station 200. The dispenser 100 is equipped with a protocol that outlines how to inject hydrogen into the vehicle 300 according to established regulations, and it oversees the control process.

[0072] The protocol incorporated in dispenser 100 is based on the international standard SAE-J2601 (2020-05), which is also applied identically to embodiments of the present invention to the extent that it is consistent with the objectives of the present invention.

[0073] To determine the minimum safety requirements, simulations are conducted through thermodynamic modeling for various situations. The parameters derived from these simulations are then used to implement a table-based single injection method and a partial real-time correction method based on the MC-formula. Minimum safety requirements include upper limits for temperature and pressure conditions in CHSS310, as well as guidelines for State of Charge (SOC).

[0074] The simulation can be performed through thermodynamic modeling that utilizes boundary conditions, including best-to-worst-case scenarios.

[0075] Such configurations can also be applied to the configurations of embodiments of the present invention to the extent that they are consistent with the objectives of the present invention.

[0076] Even following the configurations shown in Figures 1 and 2, the following problems arise in conventional techniques where the state values ​​are not actively controlled by the dispenser 100. The problems described below also appear in conventional techniques that rely on simulations using simple thermodynamic models.

[0077] Since the injection rate is predetermined based on the worst-case boundary conditions (excessive boundary conditions) expected, there is a problem of unnecessary pre-cooling and a decrease in the overall filling rate. In this case, conventional technology simply determines the injection rate by the average pressure ramp rate (APRR), which can hinder proactive responses based on the situation. Unnecessary pre-cooling can lead to excessive energy costs and operating costs.

[0078] Because it depends on the simulation platform results, there are limitations on the capacity and form of the applicable storage tank 310, and in the case of new systems, there are problems that limit the scope of application, such as requiring separate resources for new development and application.

[0079] Thermodynamic models require a significant amount of time to derive the results of mathematical calculations, and their applicability is limited when variables derived through the model are not pre-calculated, resulting in a lack of flexibility in fine-tuning the model itself.

[0080] Conventional table-based systems are extremely inefficient because they do not utilize the temperature of pre-cooled hydrogen provided at the filling station 200 or the temperature of the storage tank 310 measured in the vehicle 300, and they have difficulty responding flexibly to changes in surrounding conditions. Conventional MC-Formula-based systems correct pre-cooling temperatures in real time, but their calculation and application methods are complex, limiting their applicability and making expansion difficult. The protocol was developed with the primary goal of ensuring safe filling completion, and there are no alternatives to proactively control unexpected situations such as excessive pre-cooling or overheating of the storage tank 310. As a result, problems such as increased operating costs due to overcooling and filling delays due to overheating are occurring.

[0081] The features of this invention were derived to solve the problems of the prior art, and are characterized by their low reliance on simulation and their attempt to actively control state variables by reflecting real-time measurement data.

[0082] Figure 3 is a conceptual diagram illustrating an example of a state change that occurs during the hydrogen refueling process for a hydrogen fuel cell electric vehicle (FCEV) to which one embodiment of the present invention is applied. As shown in Figure 3, when hydrogen is injected into the storage tank 310, the internal temperature rises due to the heat of compression, which in turn raises the temperature of the hydrogen gas inside the storage tank 310.

[0083] Temperature control during the hydrogen filling process is achieved by supplying pre-cooled hydrogen gas and controlling the internal temperature of the storage tank 310 to 85°C or lower when the final filling is complete. The storage tank 310 is configured such that the heat transfer efficiency of the carbon fiber surrounding the dome and body of the storage tank 310 is low in order to block heat exchange between the outside atmosphere and the hydrogen gas stored inside while the vehicle is in motion. When the temperature of the hydrogen gas inside the storage tank 310 rises during the filling process, the low heat transfer characteristics of the storage tank 310 mean that the temperature rise on the surface of the storage tank 310 is negligible compared to the internal temperature rise until the filling is completed.

[0084] These characteristics effectively block heat exchange with the outside air, which can mitigate the rapid temperature rise inside the storage tank 310 during filling. Therefore, separate temperature control measures are necessary. However, conventional technology does not include any other cooling means besides the supply of pre-cooled hydrogen gas from the filling station 200.

[0085] The time required for complete hydrogen refueling is managed by controlling pre-cooling and hydrogen injection rate at the hydrogen refueling station 200 to keep the temperature below 85°C, which is the upper limit for temperature management of the storage tank. However, there are no separate temperature management measures in place for the storage tank 310 of the vehicle 300. Therefore, especially in the summer when outside temperatures are high, it is difficult to control the temperature of the storage tank 310 at the filling station 200, which leads to problems such as filling delays.

[0086] In the embodiment of the present invention, although the characteristic curve in Figure 3 is used as the basic model, unlike the conventional technology, the operating load of the filling station 200 in Phase I (pre-cooling stage) and the filling rate (pressure increase rate, PRR) control generated during the filling process in Phases II to IV are optimized by considering real-time data from variables that appear in the actual surrounding environment (such as ambient temperature, atmospheric pressure, and weather conditions), thereby enabling the deriving of optimal control conditions that are suitable for the actual environment.

[0087] Figure 4 is a conceptual diagram illustrating the concept of model predictive control for hydrogen refueling control for a fuel cell electric vehicle (FCEV) according to one embodiment of the present invention.

[0088] In embodiments of the present invention, while ensuring a reasonable level of accuracy in the hydrogen filling model, future filling results can be predicted from the hydrogen filling model and current measurements, and the pressure increase rate / increase rate (PRR) can be controlled in real time based on the predicted values ​​and filling values ​​so that specific variables such as the hydrogen gas temperature Tgas or hydrogen gas pressure Pgas in the CHSS310 reach the optimal filling target without violating constraints.

[0089] In an embodiment of the present invention, model predictive control can be used to calculate future output values ​​based on current measurements and model predictions, and the operation parameter can be adjusted so that the predicted future response moves to a setpoint or target in the most optimal manner.

[0090] As shown in Figure 4, n model predictions can be derived at the current time i. These n model-based predictions form a prediction horizon.

[0091] Each model-based prediction value, i.e., the prediction horizon, corresponds to the control horizon. In other words, the n control commands / actions required to make n model predictions can form the control horizon.

[0092] In reality, the first of the n model prediction and control actions derived at present time i, i+1 control action, can be transmitted to the system. As time progresses, at present time i+1, a new set of n model prediction and control actions are derived, each forming a new prediction horizon and control horizon.

[0093] This technique of controlling the system while expanding / shifting the horizon is called model predictive control, and in embodiments of the present invention, model predictive control-based control can be performed using measured and predicted values ​​for state information (state values), including the temperature and pressure of the hydrogen gas in CHSS310.

[0094] Figure 5 is an operation flowchart illustrating a model predictive control-based hydrogen refueling control method according to one embodiment of the present invention.

[0095] A hydrogen fueling method for a hydrogen fuel cell electric vehicle (FCEV) according to one embodiment of the present invention is a hydrogen fueling method based on a model predictive control platform, comprising the steps of: acquiring a measurement of the current state (S510); predicting or acquiring the next state value using an artificial neural network model (artificial neural network-model predictive control technique) based on the measurement of the current state (S530); and generating a control command for hydrogen fueling based on the comparison result between the measurement of the current state and the next state value (S520).

[0096] Current state measurements can include measurements of the temperature and pressure of the hydrogen gas inside the CHSS310.

[0097] A hydrogen filling method according to one embodiment of the present invention may further include a step (S540) of evaluating whether the measured value of the current state and the next state value satisfy the constraints.

[0098] The constraints may include ensuring that the temperature and pressure of the compressed hydrogen storage system (CHSS) of the fuel cell electric vehicle (FCEV) do not exceed the critical temperature and critical pressure, respectively.

[0099] The step of generating control commands (S520) may include a step of generating control commands for the pressure ramp rate (PRR) for hydrogen refueling.

[0100] The step of predicting or obtaining the next state value (S530) may include the step of predicting multiple next state values ​​that form a prediction horizon using the model.

[0101] The control instruction generation step (S520) can generate multiple control instructions that form a control horizon corresponding to the prediction horizon, based on the comparison results between multiple next state values ​​and set points, so as to optimize the process by which the future response reaches the set point.

[0102] In the steps of predicting or acquiring the next state value (S530) and generating control instructions (S520), multiple control instructions can be acquired that form a control horizon corresponding to a prediction horizon containing multiple next states, so as to optimize the process by which the artificial neural network model predicts the future response to reach a set point using model predictive control techniques.

[0103] The process may further include a step (S550) to update the cost function and variables / parameters for filling control based on the current state and the next state value.

[0104] Figure 6 is a conceptual diagram illustrating the concept of an artificial neural network for hydrogen refueling control for a hydrogen fuel cell electric vehicle (FCEV) according to one embodiment of the present invention. As shown in Figure 6, the current state measurement is input to the input layer.

[0105] At this time, the ambient temperature (Tamb), pre-cooled gas temperature (Tpre), and pre-cooled gas pressure (Tpre) can be measured at the nozzle of the dispenser 100 or filling station 200.

[0106] Hydrogen gas temperature Tgas and hydrogen gas pressure Pgas are values ​​measured on the CHSS310 side of the hydrogen electric vehicle 300, and the actual measured values ​​can be input to the input layer.

[0107] During the training process of an artificial neural network, the currently measured value is transmitted to the input layer, and the next measured value is transmitted to the output layer, which can then be used in the learning process of the artificial neural network. In this case, the learning process of the artificial neural network can be described as a process of learning a function that can predict the next measured value of the output layer based on the combination of input measured values. The correlation between the data input to the input layer and the data given to the output layer is learned, and through this, predictions can be made using actual dynamic fueling data as well as theoretical results.

[0108] In the inference or output process using an artificial neural network, on-site measurements are transmitted to the input layer, and the output generated by the operation of the artificial neural network can provide a predicted value for the next measurement.

[0109] The learning process of the artificial neural network used in the embodiments of the present invention may be either shallow learning or deep learning, and the artificial neural network may be selected from known neural networks that are suitable for the purpose of the present invention.

[0110] The values ​​input through the input layer are transmitted to the output layer via weighted value-based calculations in the hidden layer. The state values ​​(predicted values ​​for the next state) output by the output layer can be used to calculate packing state variables, such as the packing rate (SOC), using at least part of the thermodynamic model.

[0111] In the embodiments of the present invention, hybrid control combining a theoretical simulation model and an artificial neural network is also possible. This allows for achieving predetermined results even through learning using limited data, and enables the deriving of performance that conforms to the objectives of the present invention even through a lightweight artificial neural network.

[0112] The real-time pressure increase rate (PRR) or mass flow rate of compressed hydrogen (kg / s) m derived during the feedback control process may influence the weights or parameters of the hidden layer of the artificial neural network.

[0113] The artificial neural network-based hydrogen refueling technique of the present invention can improve the accuracy of refueling result predictions through the model. By utilizing actual refueling data along with theoretical simulation results, and by reflecting real-time measurements, the accuracy of prediction results can be further improved.

[0114] While conventional control protocols calculate and predict results through simulations tailored to individual situations, the embodiments of the present invention differ in that they utilize a process that improves accuracy through repeated training on a variety of situations. Due to these differences, the accuracy of the embodiment of the present invention gradually improves through updates as various theoretical values ​​and empirical results are added. Furthermore, even when a new filling process is introduced that uses a new storage tank 310 configuration or changes in flow rate, the model's functionality can be updated by adding actual data and training, making it widely applicable to various mobility fields.

[0115] Figure 7 is a conceptual diagram illustrating a hydrogen refueling control process for a fuel cell electric vehicle (FCEV) utilizing an artificial neural network and an intelligent meta-system (IMS) according to one embodiment of the present invention. As shown in Figure 7, efficient filling rate control can be achieved by integrating and managing distributed roles such as the mutual provision of necessary information (gas temperature and pressure measured by CHSS310 or predicted from the model) between the artificial neural network and model predictive control via the Intelligent Meta System (IMS) 400, and the adjustment of pre-cooling temperature in response to real-time environmental changes.

[0116] The filling station 200 can transmit the measured values ​​(conditions) of the pre-cooled gas to the IMS 400.

[0117] The hydrogen electric vehicle 300 can transmit the measured values ​​(conditions) of the CHSS310 to the IMS400.

[0118] In some embodiments of the present invention, the IMS400 may be located on the dispenser 100 side and can be implemented as an independent control device. The IMS400 may transmit control commands for refueling control to the refueling station 200 and the hydrogen electric vehicle 300, and such configurations will be described later through the embodiments shown in Figures 13 to 16.

[0119] The IMS400 can communicate with the artificial neural network 120 and, as needed, control the artificial neural network 120 by setting control variables to derive the optimal filling result. The next target pressure Ptarget is derived from the SOC predicted by the artificial neural network 120, and control parameters (PRR or m) for this can be set.

[0120] In this case, a cost function can be used to adjust the control parameters so that the state values ​​satisfy the constraints in all situations.

[0121] The target pressure Ptarget can be derived, for example, based on a baseline of 95% SOC at 15°C and NWP (Normal Working Pressure) conditions, in order to achieve the following control objectives.

[0122] The constraints addressed in the cost function may include, for example, conditions such as Tgas < 85°C, Pgas < 87.5 MPa, and SOC < 100%.

[0123] The intelligent metasystem 400 may be subordinate to the dispenser 100, or it may be configured independently of the dispenser 100.

[0124] The intelligent metasystem 400 may be centralized in a single device, or it may be distributed across multiple pieces of hardware, including a dispenser 100 and / or a filling station 200. The intelligent metasystem 400 can be implemented in the form of a cloud server.

[0125] Although an embodiment in which the artificial neural network 120 is subordinate to the dispenser 100 has been illustrated, in other embodiments of the present invention, it may be implemented in a location independent of the dispenser 100. For example, the artificial neural network 120 may be deployed and trained in a cloud system and used for hydrogen refueling control via wired / wireless communication through the dispenser 100.

[0126] Alternatively, a separate artificial neural network may be deployed and trained on a cloud system, and all or part of the parameters of the trained artificial neural network may be transferred to a local artificial neural network 120 deployed on the dispenser 100 and used for hydrogen filling control. In this case, parameters may be shared between the artificial neural network trained in the cloud and the local artificial neural network 120 using transfer learning or federated learning.

[0127] Figure 8 is an operation flowchart illustrating an artificial neural network-based hydrogen refueling control method according to one embodiment of the present invention.

[0128] A hydrogen fueling method for a hydrogen fuel cell electric vehicle (FCEV) according to one embodiment of the present invention is an artificial neural network-based hydrogen fueling method, which includes the steps of: acquiring a measurement of the current state (S610); generating a fueling control command for hydrogen fueling based on the output of an artificial neural network that takes the measurement of the current state as input (S620); acquiring the next state value based on the fueling control command (S630); and evaluating whether the response resulting from the execution of the fueling control command satisfies the constraints (S650).

[0129] In the stage of generating filling control commands (S620), filling control commands can be generated based on the output of an artificial neural network that has learned the function of generating filling control commands so that each future response after the measurement of the current state reaches the set point while satisfying the constraints.

[0130] In the stage of generating filling control instructions (S620), multiple control instructions corresponding to multiple next state values ​​may be generated based on the output of an artificial neural network that has learned the ability to predict multiple next state values ​​that minimize the cost function for the filling state.

[0131] Figure 9 is an operation flowchart illustrating the training process of an artificial neural network for hydrogen refueling control based on an artificial neural network model according to one embodiment of the present invention.

[0132] In Figure 9, we assume that the artificial neural network has learned the function of acquiring a prediction horizon and a control horizon, and that n future predictions and corresponding control commands have been acquired from the artificial neural network model 120 so that the process by which the future response reaches a set point is optimized through model predictive control.

[0133] In the embodiments of the present invention, a control system can be configured based on an artificial neural network model 120, and a real-time control system for a model predictive control platform can be configured while ensuring the accuracy of the artificial neural network model 120.

[0134] The real-time control system controls the filling rate, pressure increase rate, and pressure increase speed by predicting future filling results and comparing them with actual measurements. Limitations, control time intervals, sensitivity, etc., can be set separately within the system logic to control within optimal values.

[0135] Primarily, optimal control is performed based on real-time data from the refueling station 200 and the vehicle 300. However, if a specific event occurs during the operation of the system, a function can be added to directly control the pre-cooling temperature of the pre-cooler 210 and the cooling system of the vehicle 300, thereby increasing the overall efficiency of the hydrogen refueling process.

[0136] As shown in Figure 9, the control process is initiated upon receiving the SOCsp input identified by the customer (t=0, S710). For example, if the current SOC is 50%, the SOCsp may be 85%.

[0137] If the customer does not set a specific SOCsp, the SOCsp may be set to a pre-configured default value. For example, the default value could be 100%.

[0138] SOC(t) is given as a function of Tgas(t) and Pgas(t), and this process can be carried out based on a general dynamics model.

[0139] If the current SOC(t) is greater than or equal to SOCsp (S720), the customer can assume that refueling is complete because specific refueling conditions have been met and stop the hydrogen refueling process. If the current SOC(t) is less than SOCsp (S720), i=t is set and moving horizon prediction with an artificial neural network is performed (S730).

[0140] Step S730 can be performed by generating predictions based on the model predictive control shown in Figure 4 using an artificial neural network 120 or the like. In step S740, it can be determined whether the n predictions obtained are optimized and conform to the intended purpose as prediction / control commands.

[0141] If the n predictions obtained are optimized predictions, a control command PRR(t) can be obtained based on the n predictions and control commands, and PRR(t) can be applied to the dispenser 100-storage tank 310 (S750).

[0142] Thereafter, time t is increased to obtain new measured values ​​Tgas(t) and Pgas(t), which are then transmitted to the input of step S720.

[0143] If the n predictions obtained in step S730 are not optimized, step S730 can be performed again to obtain new n predictions and control instructions.

[0144] Figure 10 is a conceptual diagram that illustrates in detail a part of the process shown in Figure 9. As shown in Figure 10, in step S730 of Figure 9, state prediction values ​​(T, P) that satisfy the temperature and pressure limits can be generated for all arbitrary i and k. In this case, i is an index representing the current time, and k is an index corresponding to each prediction / control command that forms the moving horizon.

[0145] Based on the current time i (=t), n predicted state values ​​and corresponding control commands can be derived.

[0146] Figure 11 is a conceptual diagram that illustrates in detail a part of the process shown in Figure 9. As shown in Figure 11, step S740 in Figure 9 can be understood as the process of searching for a set of n predictions that minimize the cost function representing the control sensitivity Θ and whether the final control target, SOCsp, has been reached. The control sensitivity Θ can include PRR or the rate of change of m, etc.

[0147] Figure 12 is a conceptual diagram illustrating the hydrogen refueling control process based on an artificial neural network-model predictive control system according to one embodiment of the present invention. As shown in Figure 12, the dispenser 100 may include a fueling control logic 110 and an artificial neural network model 120.

[0148] The output of the hydrogen electric vehicle 300 allows state measurements, including temperature and pressure, of the CHSS310 to be provided as feedback input to the artificial neural network model 120.

[0149] At the output of the hydrogen refueling station 200, state measurements including temperature and pressure of the pre-cooled hydrogen gas can be provided as feedback input to the artificial neural network model 120.

[0150] Referring to the processes in Figures 9 to 11 along with Figure 12, the artificial neural network model 120 transmits the predicted output to the hydrogen refueling control logic 110, and the hydrogen refueling control logic 110 can input the future input to the artificial neural network model 120.

[0151] The artificial neural network-model predictive control process is a control technique that utilizes both simulation and actual measurement data. It is a control technique that uses the artificial neural network model 120 to perform simulations at least partially and utilizes the prediction results in the control process.

[0152] Figure 13 is a conceptual diagram illustrating an artificial neural network-based integrated control model for controlling the hydrogen filling process according to one embodiment of the present invention.

[0153] The embodiment of the present invention aims to configure a real-time data-based integrated hydrogen refueling control protocol, and the system is realized by utilizing a variety of elemental technologies.

[0154] The protocol installed in the dispenser 100 utilizes data from pre-cooled hydrogen gas supplied from the filling station 200 and data from the storage tank 310 supplied from the vehicle 300 as real-time input values, and can control the filling rate / pressure increase rate / pressure increase rate (PRR or m) as an output depending on the installed model.

[0155] In the event of changes in the external environment or other event-related conditions, the pre-cooling temperature of the filling station 200 and the cooling system of the vehicle 300 can be directly controlled to comprehensively control the filling speed / pressure increase rate / pressure increase rate (PRR or m) and process efficiency.

[0156] To complement the control protocol, a self-cooling stabilization system may be independently installed in the pre-cooling system / precooler 210 of the hydrogen refueling station 200. In terms of temperature stabilization, the cooling stabilization system of the precooler 210 can be controlled independently, and the target values ​​of the control can be integrally modified by the protocol of the dispenser 100.

[0157] To improve the economic efficiency of the filling station 200 and complement the functionality of the integrated control protocol, the precooler 210 may be provided with additional functions related to temperature stabilization. The pre-cooling temperature will deviate depending on the initial temperature and flow rate of the hydrogen gas supplied to the pre-cooler 210. To compensate for this, a novel pre-cooler structure for stabilizing the temperature is proposed as one embodiment of the present invention.

[0158] A precooler 210 according to one embodiment of the present invention may include control logic for autonomous temperature control and coordination with a protocol.

[0159] A forced cooling system may be installed in the storage tank 310 of the vehicle 300, which can partially cool the compression heat generated during hydrogen refueling to improve the refueling speed, and the operation / control of the forced cooling system of the storage tank 310 can also be controlled by a protocol.

[0160] In one embodiment of the present invention, a temperature control function may be provided to the storage tank 310 of the vehicle 300 to improve the hydrogen refueling rate and to complement the functions of the integrated control protocol.

[0161] In one embodiment of the present invention, the storage tank 310 may include a system for self-cooling to increase the overall filling speed and improve the safety of the vehicle 300, and may include control logic for self-driving the system and coordinating with protocols.

[0162] In one embodiment of the present invention, not only can the current filling efficiency be improved through such integrated control, but preparation for the next filling can also be smoothly facilitated.

[0163] Figure 14 is a diagram illustrating the event-based control process for the integrated control model shown in Figure 13. As shown in Figure 14, if hydrogen refueling proceeds smoothly within the control standards even during normal operation, the target can be achieved by controlling only the dispenser 100 base.

[0164] In the case of T40, where the pre-cooling temperature of the pre-cooler 210 is set to -40°C, if the pre-cooling temperature has reached the target value but the ambient temperature is higher than the set value and the temperature rise on the storage tank 310 side is greater than expected, a control signal or information of the current state can be transmitted to the vehicle 300 / storage tank 310 side so that the storage tank 310's own cooling system is activated. Conversely, if the pre-cooling temperature of the pre-cooler 210 is set to -40°C, but this is deemed excessive cooling when considering the external environment and actual data, the target value of the pre-cooling temperature can be adjusted (e.g., to -35°C).

[0165] If additional pre-cooling target temperature and temperature control on the storage tank 310 side are required, control information or control commands may be transmitted from the dispenser 100 to both the vehicle 300 and the filling station 200.

[0166] According to embodiments of the present invention, the self-cooling systems of the vehicle 300 and the filling station 200 may be controlled independently, or they may be controlled by transmitting signals via the dispenser 100.

[0167] Figure 15 is an operation flowchart illustrating an integrated control method for hydrogen refueling according to one embodiment of the present invention.

[0168] A hydrogen fueling control method for a hydrogen fueling electric vehicle (FCEV) according to one embodiment of the present invention is an integrated control method for hydrogen fueling, comprising the steps of: obtaining a measurement of the current state (S810); determining, based on the measurement of the current state, whether a second control command is required for at least one of the hydrogen fueling station and the hydrogen fueling electric vehicle in addition to the first control command executed on the dispenser side (S830); and generating a second control command for at least one of the hydrogen fueling station and the hydrogen fueling electric vehicle based on the determination result (S840).

[0169] A second control command for the hydrogen refueling station may include a command to adjust the target value of the pre-cooling temperature of the hydrogen refueling station.

[0170] The second control command for a hydrogen-electric vehicle may include a cooling command for the compressed hydrogen storage system (CHSS) on the hydrogen-electric vehicle side.

[0171] An integrated control method for hydrogen refueling according to one embodiment of the present invention may further include a step of evaluating whether the measured values ​​of the current state satisfy the constraints.

[0172] The constraints may include ensuring that the temperature and pressure of the compressed hydrogen storage system (CHSS) 310 on the hydrogen electric vehicle side do not exceed the limit temperature and limit pressure, respectively.

[0173] An integrated control method for hydrogen refueling according to one embodiment of the present invention may further include the step (S850) of generating a first control command to be executed on the dispenser side based on a measurement of the current state.

[0174] Step S830 may be performed based on the results of step (S820), which calculates the difference between the measured and predicted values ​​of the current CHSS310 state.

[0175] Figure 16 is a conceptual diagram illustrating an example of a generalized hydrogen refueling control device, hydrogen refueling control system, or computing system capable of performing at least part of the processes shown in Figures 1 to 15.

[0176] The hydrogen refueling control device may be located on the dispenser 100 side. The hydrogen refueling control system may be distributed or located in at least some of the dispenser 100, the hydrogen refueling station 200, and the hydrogen electric vehicle 300 to control the operation of at least some of the dispenser 100, the hydrogen refueling station 200, and the hydrogen electric vehicle 300.

[0177] The hydrogen refueling control device and / or hydrogen refueling control system may be implemented in the form of a computing system including a processor 1100 electronically connected to a memory 1200.

[0178] At least some of the processes of the model predictive control-based hydrogen refueling control method, the artificial neural network-based hydrogen refueling control method, and the integrated control method for hydrogen refueling according to one embodiment of the present invention can be performed by the computing system 1000 shown in Figure 16.

[0179] As shown in Figure 16, a computing system 1000 according to one embodiment of the present invention may be configured to include a processor 1100, memory 1200, communication interface 1300, storage device 1400, input interface 1500, output interface 1600, and bus 1700.

[0180] A computing system 1000 according to one embodiment of the present invention may include at least one processor 1100 and a memory 1200 that stores instructions that the at least one processor 1100 perform at least one step. At least some steps of the method according to one embodiment of the present invention may be performed by the at least one processor 1100 loading and executing instructions from the memory 1200.

[0181] The processor 1100 may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which the method according to an embodiment of the present invention is performed.

[0182] Each of the memory 1200 and the storage device 1400 may consist of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory 1200 may consist of at least one of a read-only memory (ROM) and a random access memory (RAM).

[0183] Furthermore, the computing system 1000 may include a communication interface 1300 that performs communication over a wireless network. Furthermore, the computing system 1000 may further include a storage device 1400, an input interface 1500, an output interface 1600, and the like. Furthermore, each component included in the computing system 1000 can be connected by a bus 1700 to perform communication.

[0184] The computing system 1000 of the present invention may include, for example, a communicative desktop computer, laptop computer, notebook computer, smartphone, tablet PC, mobile phone, smart watch, smart glasses, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant), etc.

[0185] The operation of the method according to the embodiment of the present invention can be embodied in a computer-readable program or code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices on which information readable by a computer system is stored. Furthermore, the computer-readable recording medium can be distributed across a network of computer systems, and computer-readable programs or code can be stored and executed in a distributed manner.

[0186] Furthermore, computer-readable recording media can include hardware devices specially configured to store and execute program instructions, such as ROM, RAM, and flash memory. Program instructions can include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.

[0187] Some aspects of the present invention have been described in the context of apparatus, but this can also represent a description by a corresponding method, where a block or apparatus corresponds to a method step or feature of a method step. Similarly, aspects described in the context of a method can also be represented by a corresponding block or item or feature of a corresponding apparatus. Some or all of the method steps may be carried out by (or using) a hardware device such as, for example, a microprocessor, a programmable computer, or an electronic circuit. In some embodiments, at least one of the most important method steps may be carried out by such a device.

[0188] In embodiments, a programmable logic device (e.g., a field-programmable gate array) may be used to perform some or all of the functions of the methods described herein. In embodiments, a field-programmable gate array may operate in conjunction with a microprocessor to perform one of the methods described herein. Generally, the methods are preferably performed by some hardware device.

[0189] Although preferred embodiments of the present invention have been described above with reference to the present invention, those skilled in the art will understand that the present invention can be modified and altered in various ways without departing from the spirit and scope of the invention as described in the following claims. [Explanation of Symbols]

[0190] 100 dispensers 110 Hydrogen refueling control 120 Artificial Neural Networks 200 hydrogen refueling stations, refueling stations 210 Precooler 220 High-pressure hydrogen 300 Hydrogen fuel mobility, mobility, hydrogen electric vehicles, vehicles 310 Compressed Hydrogen Storage System (CHSS), Storage Tanks 320 Pressure Relief Device (PRD) 400 Intelligent Metasystems 1000 Computing Systems 1100 processor 1200 memory 1300 Communication Interfaces 1400 storage 1500 Input User Interface 1600 Output User Interface 1700 bus

Claims

1. A hydrogen refueling method for hydrogen fuel mobility, The step of receiving a measurement of the current state of the compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility from the hydrogen fuel mobility, A step of predicting the next state value that will form the moving horizon using a model predictive control technique based on the measured value of the current state, and A model-predictive control-based hydrogen refueling method, characterized by comprising the step of generating a control command for hydrogen refueling based on a pressure ramp rate (PRR) corresponding to the following state value.

2. The model predictive control-based hydrogen filling method according to claim 1, further comprising the step of evaluating whether the measured value of the current state and the next state value satisfy the constraint conditions.

3. The aforementioned constraints are characterized in that the temperature and pressure of the compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility do not exceed the limit temperature and limit pressure, respectively, as described in claim 2.

4. The step of predicting the next state value is: By moving the aforementioned moving horizon, The moving horizon is configured to form a prediction horizon. The model predictive control-based hydrogen filling method according to claim 1, characterized by including the step of predicting a plurality of the next state values ​​that form the prediction horizon by a model predictive control technique.

5. The step of generating the aforementioned control command is: The model predictive control-based hydrogen refueling method according to claim 4, comprising the step of generating a plurality of control commands that form a control horizon corresponding to the prediction horizon, such that the process by which the future response reaches the set point is optimized based on the comparison results between the plurality of next state values ​​and the set point.

6. In the step of predicting the next state value and the step of generating the control command, The model predictive control-based hydrogen refueling method according to claim 4, characterized in that a plurality of control commands are obtained that form a control horizon corresponding to the prediction horizon, which includes a plurality of the next state values, so as to optimize the process by which the future response reaches a set point using a model predictive control technique.

7. A hydrogen refueling method for hydrogen fuel mobility, The step of receiving a measurement of the current state of the compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility from the hydrogen fuel mobility, The steps include: predicting the next state value that forms the moving horizon based on the output of an artificial neural network that takes the measured value of the current state as input, and obtaining the pressure ramp rate (PRR) corresponding to the next state value; and An artificial neural network-based hydrogen refueling method, characterized by comprising the step of generating a refueling control command for hydrogen refueling based on the following state value and pressure increase rate, such that the cost function for hydrogen supply satisfies predetermined conditions.

8. Further comprising the step of evaluating whether the result of executing the filling control command satisfies the constraint conditions, The artificial neural network-based hydrogen refueling method according to claim 7, characterized in that the constraints are that the temperature and pressure of the compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility do not exceed the limit temperature and limit pressure, respectively.

9. In the step of generating the aforementioned filling control command, The artificial neural network-based hydrogen filling method according to claim 8, characterized in that the filling control command is generated based on the output of the artificial neural network which has learned the function of generating the filling control command to reach a set point while each of the future responses after the measurement of the current state satisfies the constraint conditions.

10. In the step of generating the aforementioned filling control command, The artificial neural network-based hydrogen filling method according to claim 7, characterized in that a plurality of control commands corresponding to the plurality of next state values ​​are generated based on the output of the artificial neural network which has learned the function of predicting a plurality of next state values ​​that minimize the cost function for the filling state.

11. A hydrogen fueling control device for hydrogen fuel mobility, Processor, and It includes memory for storing at least one or more instructions, The processor executes at least one of the instructions: The current state measurement of the compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility is received from the hydrogen fuel mobility, A hydrogen refueling control device characterized by predicting the next state value that forms a moving horizon based on at least one of a model predictive control technique based on the measured value of the current state and the output of an artificial neural network that takes the measured value of the current state as input, and obtaining a refueling control command for hydrogen refueling based on the pressure ramp rate (PRR) corresponding to the next state value.

12. The aforementioned processor, The hydrogen refueling control device according to claim 11, characterized in that it evaluates whether each response resulting from the execution of the refueling control command satisfies the constraint conditions.

13. The hydrogen refueling control device according to claim 12, characterized in that the aforementioned constraints ensure that the temperature and pressure of the compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility do not exceed the limit temperature and limit pressure, respectively.

14. The aforementioned processor, By moving the aforementioned moving horizon, The moving horizon is configured to form a prediction horizon. The hydrogen refueling control device according to claim 11, characterized in that it predicts a plurality of the next state values ​​that form the prediction horizon by model predictive control technique.

15. The aforementioned processor, The hydrogen refueling control device according to claim 14, characterized in that it generates a plurality of control commands that form a control horizon corresponding to the prediction horizon, based on the comparison result between the plurality of next state values ​​and a set point, so as to optimize the process by which the future response reaches the set point.

16. The aforementioned processor, The hydrogen refueling control device according to claim 14, characterized in that it evaluates whether each of the plurality of subsequent state values ​​satisfies the constraint conditions.

17. The aforementioned processor, The hydrogen refueling control device according to claim 14, characterized in that a plurality of control commands are obtained to form a control horizon corresponding to the prediction horizon, which includes a plurality of the next state values, so as to optimize the process by which the future response reaches a set point using a model predictive control technique.

Images