Model predictive control based hydrogen filling system, method and device

The integration of model predictive control and artificial neural networks optimizes hydrogen filling/supplying processes for hydrogen-electric vehicles, addressing inefficiencies and safety limitations in conventional methods, achieving faster and more accurate hydrogen delivery.

JP2024543356AActive Publication Date: 2024-11-21HYUNDAI MOTOR CO LTD +2
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2024527121
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2021-11-03
Filing Date
2022-11-03
Publication Date
2024-11-21
Estimated Expiration
2042-11-03

AI Technical Summary

Technical Problem

Conventional hydrogen filling/supply processes for hydrogen-electric vehicles are inefficient, slow, and unsuitable for large-capacity filling, lacking integration with advanced ICT technologies for real-time control and safety management.

Method used

A model predictive control technique using an artificial neural network to optimize hydrogen filling by integrating real-time measurements and theoretical simulations, ensuring safe operation within critical temperature and pressure limits.

Benefits of technology

Improves the efficiency and speed of hydrogen filling/supplying processes while ensuring real-time performance and safety, enhancing the accuracy of prediction results through intelligent metasystem management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024543356000001_ABST
    Figure 2024543356000001_ABST
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a control technology for hydrogen fueling / supply for hydrogen fueled mobility, and more particularly to a hydrogen fueling process that increases the efficiency of hydrogen fueling / supply and increases the speed and real-time nature of the hydrogen fueling / supply, a control technique for the process, and a protocol for the control technique. [Background technology]

[0002] A hydrogen vehicle, hydrogen electric vehicle, or fuel cell electric vehicle (FCEV) is a non-polluting vehicle that runs on electrical energy generated by mixing high-pressure hydrogen stored in the vehicle with air in the atmosphere. Hydrogen electric vehicles use hydrogen as an energy source and generate electricity using a fuel cell system. As is well known, hydrogen electric vehicles use pure water (H 2 Not only does it emit only CO2 (carbon monoxide), but it also has the ability to remove ultra-fine dust particles from the atmosphere while in operation, so it is attracting attention as an environmentally friendly form of mobility of the future. Because hydrogen, the fuel, is infinite on Earth and the energy production process is environmentally friendly, it is garnering attention as a technology with potential for use across industries.

[0003] Hydrogen fueled mobility refers to a type of mobility that uses hydrogen as an energy source or hydrogen as fuel to generate electric energy and use it to drive an electric motor. In addition to the hydrogen electric vehicles mentioned above, hydrogen-fueled mobility can also include aerial mobility, as well as industrial trucks, trains, ships, and aircraft that use hydrogen as fuel to generate electrical energy and use it to run. More generally, buildings or facilities that use hydrogen as an energy source may also be included in the application field to which the technical concept of the present invention can be applied. A hydrogen electric vehicle produces electrical energy by delivering high-pressure hydrogen safely stored in a hydrogen fuel storage tank and oxygen supplied through an air supply system to a fuel cell stack, where an electrochemical reaction occurs between the hydrogen and oxygen. The electrical energy produced is converted into kinetic energy through the drive motor to power the hydrogen electric vehicle, and the hydrogen electric vehicle has the advantage of only emitting pure water through the exhaust when in motion.

[0004] Fuel cell systems power hydrogen electric vehicles instead of the engines of internal combustion vehicles. Fuel cells are devices that generate the electrical energy required for driving, and are also called "tertiary batteries." Fuel cells convert thermal energy into electrical energy using an electrochemical reaction between oxygen and hydrogen. The electrical energy generated is the result of a pure chemical reaction, and unlike fossil fuels, it does not produce exhaust gases such as carbon dioxide. There are various types of fuel cell systems, such as PEMFC, SOFC, and MCFC, depending on the fuel and material, and the structure that produces power using fuel cells in hydrogen electric vehicles includes a fuel cell stack, a hydrogen supply system, an air supply system, and a thermal management system. The fuel cell stack needs the help of operating devices to efficiently generate electrical energy. Among them, the hydrogen supply system changes the hydrogen safely stored in the hydrogen fuel storage tank from a high-pressure state to a low-pressure state and transfers it to the fuel cell stack, and also increases the efficiency of hydrogen supply through a recirculation line. A thermal management system is a device that maintains a constant temperature of the fuel cell stack by dissipating heat generated during electrochemical reactions in the fuel cell stack and circulating coolant. The thermal management system can affect the output and lifespan of the fuel cell stack. The concept of a hydrogen fueled car, which is not a hydrogen electric car, is also a vehicle that uses hydrogen as fuel, but hydrogen fueled cars use heat generated by burning hydrogen directly in the engine to drive an electric motor. The method of filling / supplying hydrogen for hydrogen fueled cars is not very different from that for hydrogen electric cars.

[0005] The control technique for filling / supplying hydrogen to vehicles that use hydrogen as fuel ultimately aims to control the temperature (T) and pressure (P) of the Compressed Hydrogen Storage System (CHSS) on the fuel cell side so that it operates within the limit temperature / pressure conditions for safety. The hydrogen filling / supply process, control techniques, and protocols for conventional hydrogen electric vehicles were established at a time when wired / wireless communication technologies and computing techniques for control were not yet mature, and therefore are unable to fully reflect the recent achievements of information and communications technology (ICT). Therefore, conventional hydrogen refueling / supply technologies for hydrogen electric vehicles are inefficient, slow and not suitable for large-volume hydrogen refueling. Summary of the Invention [Problem to be solved by the invention]

[0006] In order to solve the above problems, an object of the present invention is to safely fill / supply hydrogen fuel while improving the efficiency of the hydrogen filling / supply process and improving the speed and real-time nature of the hydrogen filling / supply process.

[0007] The object of the present invention is to propose a hydrogen filling control technique that ensures the real-time performance of a model predictive control base.

[0008] The object of the present invention is to propose a control technique that has improved accuracy in predicting hydrogen filling results based on an artificial neural network model.

[0009] The objective of the present invention is to improve the efficiency of hydrogen filling control by integrating and managing actually measured data and model-predicted state information using an intelligent meta-system (IMS). [Means for solving the problem]

[0010] To achieve the above object, 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 filling based on a comparison result between the current state measurement value and the next state value.

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

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

[0013] The step of generating a control command includes the step of generating a control command for a pressure ramp rate (PRR) for hydrogen filling.

[0014] Predicting or obtaining the next state value includes predicting a number of next state values ​​that form a prediction horizon using the model.

[0015] The step of generating control commands generates a plurality of control commands that form a control horizon corresponding to the prediction horizon so that a process in which a future response reaches a set point is optimized based on a comparison result between a plurality of next state values ​​and a set point.

[0016] In the steps of predicting or obtaining the next state value and generating the control command, a plurality of control commands are obtained that form a control horizon corresponding to a prediction horizon including a plurality of next state values ​​so that a process in which a future response reaches a set point is optimized by a model predictive control technique.

[0017] The hydrogen fueling method for hydrogen fueled mobility of the present invention is an artificial neural network-based hydrogen filling method, and is characterized in that it includes the steps of acquiring a measurement value of a current state, generating a filling control command for hydrogen filling based on the output of an artificial neural network that inputs the measurement value of the current state, acquiring a next state value based on the filling control command, and evaluating whether a response due to execution of the filling control command satisfies a constraint condition.

[0018] In the step of generating a filling control command, the filling control command is generated based on the output of an artificial neural network that has learned the function of generating a filling control command for each future response after the measurement value of the current state to reach a set point while satisfying the constraint conditions.

[0019] In the step of generating a filling control command, a plurality of control commands corresponding to a plurality of next state values ​​are generated based on the output of an artificial neural network that has been trained to predict a plurality of next state values ​​that minimize a cost function for the filling state.

[0020] The hydrogen fueling control device for hydrogen fueled mobility of the present invention includes a processor and a memory for storing at least one instruction, and the processor executes at least one instruction to obtain a measurement value of a current state, and obtains a filling control command for hydrogen filling and a next state value corresponding to the filling control command based on at least one of a model predictive control technique based on the measurement value of the current state and an output of an artificial neural network that receives the measurement value of the current state as an input.

[0021] The processor evaluates whether each response from the execution of the fill control instructions 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 number of next state values ​​that form a prediction horizon by a model predictive control technique.

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

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

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

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

[0028] According to the present invention, a hydrogen filling control technique that ensures real-time performance based on model predictive control can be provided.

[0029] According to the present invention, there is provided a control technique that improves the accuracy of prediction of hydrogen filling results based on an artificial neural network model. The accuracy of the prediction results can be improved by reflecting real-time measured values ​​in an artificial neural network model that uses actual filling data together with theoretical simulation results.

[0030] According to the present invention, the efficiency of hydrogen filling control can be improved by integrating and managing actually measured data and state information predicted from a model using an intelligent meta-system (IMS). [Brief description of the drawings]

[0031] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a hydrogen filling process for a hydrogen electric vehicle (FCEV) of the present invention. [Diagram 2] FIG. 1 is a conceptual diagram illustrating an example of a logical process for hydrogen filling for a hydrogen electric vehicle (FCEV) of the present invention. [Diagram 3] FIG. 2 is a conceptual diagram illustrating an example of state changes that occur during the hydrogen filling process for a hydrogen electric vehicle (FCEV) of the present invention. [Figure 4] FIG. 2 is a conceptual diagram illustrating the concept of model predictive control for hydrogen filling control for a hydrogen electric vehicle (FCEV) of the present invention. [Diagram 5] 2 is an operational flowchart illustrating a hydrogen filling control method based on model predictive control according to the present invention. [Figure 6] FIG. 2 is a conceptual diagram illustrating the artificial neural network concept for hydrogen filling control for a hydrogen electric vehicle (FCEV) of the present invention. [Figure 7] FIG. 2 is a conceptual diagram illustrating a hydrogen filling control process for a hydrogen electric vehicle (FCEV) using the artificial neural network and intelligent meta system (IMS) of the present invention. [Figure 8] 2 is an operational flowchart illustrating an artificial neural network-based hydrogen filling control method according to the present invention. [Figure 9] 4 is an operational flowchart illustrating a training process of an artificial neural network for hydrogen filling control based on an artificial neural network-model predictive control according to the present invention. [Figure 10] FIG. 10 is a conceptual diagram illustrating in detail a portion of the process of FIG. 9. [Figure 11] FIG. 10 is a conceptual diagram illustrating in detail a portion of the process of FIG. 9. [Figure 12] FIG. 2 is a conceptual diagram illustrating a hydrogen filling control process based on an artificial neural network-model predictive control according to the present invention. [Figure 13] FIG. 2 is a conceptual diagram illustrating an artificial neural network-based integrated control model for controlling a hydrogen filling process according to the present invention. [Figure 14] 14 is a diagram illustrating an event-based control process for the integrated control model of FIG. 13. [Figure 15] 4 is an operational flow chart illustrating the integrated control method for hydrogen filling of the present invention. [Figure 16] FIG. 16 is a conceptual diagram illustrating an example of a generalized hydrogen filling control device, hydrogen filling control system, or computing system capable of performing at least a portion of the processes of FIGS. 1 to 15. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0032] The present invention can be modified in various ways and can have various embodiments, and a specific embodiment will be illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, and it should be understood that the present invention includes all modifications, equivalents, and alternatives 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, B, etc. may be used to describe various components, but the components should not be limited by the terms. Terms are used only to distinguish one component from another. For example, a first component may be named a second component and similarly, the second component may be named a first component without departing from the scope of the invention. The term "and / or" includes a combination of multiple associated listed items or any multiple associated listed items. In the examples of this application, "at least one of A and B" may mean "at least one of A or B" or "at least one of a combination of one or more of A and B." Also, in the examples of this application, "one or more of A and B" may mean "one or more of A or B" or "one or more of a combination of one or more of A and B." When a component is said to be "coupled" or "connected" to another component, it should be understood that it may be directly coupled or connected to the other component, but there may be other components in between. Conversely, when a component is said to be "directly coupled" or "directly connected" to another component, it should be understood that there are no other components in between. The terms used in this application are merely used to describe certain embodiments and are not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, the terms "include" or "have" are intended to specify the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood not to preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention belongs. Terms as defined in commonly used dictionaries should be interpreted to have a meaning consistent with the meaning they have in the context of the relevant art, and should not be interpreted in an idealized or overly formal sense unless expressly defined in this application.

[0033] Some terms used in this specification are defined as follows:

[0034] A hydrogen vehicle, hydrogen electric vehicle, or fuel cell electric vehicle (FCEV) is a non-polluting vehicle that runs on electrical energy generated by mixing high-pressure hydrogen stored in the vehicle with atmospheric air.

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

[0036] A pressure relief device (PRD) is a device that is placed in a CHSS and can isolate stored hydrogen from the rest of the fuel system and the environment, or conversely, can discharge hydrogen to the outside.

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

[0038] Pressure Ramp Rate (PRR) is expressed in MPa / min and refers to the rate of increase in pressure of the CHSS.

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

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

[0041] The dispenser is the component that delivers pre-cooled hydrogen to the CHSS.

[0042] Nozzle refers to a device that is connected to a hydrogen dispensing system of a hydrogen filling station and is coupled to a receptacle of a hydrogen electric vehicle to allow delivery of hydrogen fuel.

[0043] Meanwhile, even if a technology is publicly known before the filing date of this application, it may be included as a part of the configuration of the present invention as necessary, and this will be described in this specification to the extent that it does not obscure the gist of the present invention. However, in describing the configuration of the present invention, a detailed description of the technology that is publicly known before the filing date and that a person skilled in the art can understand may obscure the gist of the present invention, so an excessively detailed description of the publicly known technology will be omitted. For example, a technology that uses a thermodynamic model for hydrogen filling control, a technology that applies a model predictive control technique for generalized dynamic control, a technology that configures and controls an artificial neural network for training and inference of the artificial neural network, etc. may use publicly known technologies before the filing of the present invention, and at least a part of these publicly known technologies may be applied as elemental technologies necessary to implement the present invention. However, the spirit of the present invention is not intended to claim any rights to these known techniques, and the content of the known techniques may be included as part of the present invention within the scope of the present invention.

[0044] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

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

[0046] Although FIG. 1 illustrates an embodiment related to a hydrogen electric vehicle (FCEV), it will be apparent to one skilled in the art that the concepts of the present invention may be applied to various types of hydrogen fueled mobility.

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

[0048] In addition to hydrogen electric vehicles, hydrogen-fueled mobility can include aerial mobility as well as industrial trucks, trains, ships, and aircraft that use hydrogen as fuel to generate electrical energy and use it to run their operations.

[0049] The hydrogen filling process of the present invention could be applied not only to hydrogen fueled mobility but also to hydrogen-powered buildings or facilities.

[0050] Also, while the embodiment of FIG. 1 illustrates an embodiment related to hydrogen gas, the concept of the present invention may also be applied to liquefied hydrogen.

[0051] For the sake of convenience, the present invention will be described below using a hydrogen electric vehicle (FCEV) and hydrogen gas as main examples. However, the scope of the present application should not be construed as being limited by these examples.

[0052] Generally, a hydrogen storage system attached to a vehicle can be roughly divided into a high-pressure hydrogen storage tank, a pressure control device, high-pressure piping, and an external frame. High-pressure hydrogen storage tanks have been developed and commercialized with capacities of tens to hundreds of liters, and for vehicles, small and lightweight storage tanks are connected in parallel to achieve high capacity.

[0053] High pressure hydrogen storage tanks are commonly known as compressed hydrogen storage systems (CHSS) 310, and for the purposes of this specification, the term "storage tank" refers to a CHSS 310. In a typical hydrogen storage system, the storage of hydrogen is controlled by utilizing a boss unit through which hydrogen gas can enter and exit the storage tank 310. Since hydrogen cannot be injected and used simultaneously, a valve, a pressure reducing mechanism, and various sensors for measurement are attached to one boss unit to control the storage of hydrogen.

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

[0055] In the conventional technology, there are a communication method and a non-communication method for transmitting information from the vehicle 300 to the dispenser 100. Even when communication is used, the temperature and pressure values ​​of the storage tank 310 of the vehicle 300 are simply transmitted unidirectionally to the dispenser 100 in the conventional technology, and the dispenser 100 does not actively use the information, but only uses it as a safety standard such as an emergency stop at the limit temperature and pressure.

[0056] All filling logic for safe and fast filling is managed by the dispenser 100, and the storage tank 310 has only minimal safety control devices that automatically release hydrogen in conditions such as overheating through a pressure relief device (PRD) 320, with no active safety control methods.

[0057] 3, the hydrogen gas temperature increases during hydrogen filling, and the hydrogen gas filling station 200 includes a high-pressure hydrogen storage unit 220 and a pre-cooler 210. The pre-cooler 210 supplies hydrogen gas to the hydrogen electric vehicle 300 via the dispenser 100 after lowering the temperature of the hydrogen gas 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 status information such as temperature, pressure, etc. received from the vehicle 300 and the filling station 200, and filling status 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 using real-time temperature data of the storage tank 310, and is designed to be operated at the highest filling speed that satisfies conditions below the safety limit, thereby reducing the filling time within the usable range.

[0060] The filling protocol of the prior art has excessive boundary conditions set for safety, which causes problems such as excessive pre-cooling of the storage tanks 310, with the temperature measured at around 40 to 50°C at the time of completion of filling.

[0061] According to an embodiment of the present invention, the pre-cooling requirement and provision can be actively adjusted to optimize the cooling load of the hydrogen filling station 200, thereby increasing the operational efficiency of the hydrogen filling station 200.

[0062] Conventional protocols, which were set up around lightweight hydrogen electric vehicles, have the problem that when new mobility is charged, all variables must be reconfigured to reflect the standard.

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

[0064] The only measure to prevent overheating of the storage tank 310 of the conventional hydrogen electric vehicle 300 is to release gas through the PRD 320 when the storage tank 310 overheats above a certain temperature.

[0065] According to one embodiment of the present invention, a cooling system is installed in the storage tank 310 itself to increase the filling speed and also to actively deal with overheating of the storage tank 310, thereby improving the safety of the hydrogen electric vehicle 300.

[0066] According to an embodiment of the present invention, it is possible to safely fill / supply hydrogen fuel while improving the efficiency of the hydrogen filling / supply process, and to improve the speed and real-time nature of the hydrogen filling / supply process.

[0067] According to an embodiment of the present invention, a hydrogen filling control technique that ensures real-time performance based on model predictive control can be provided.

[0068] According to an embodiment of the present invention, a control technique that improves the accuracy of prediction of hydrogen filling results based on an artificial neural network model may be provided. The accuracy of prediction results may be improved by reflecting real-time measurements in an artificial neural network model that uses actual filling data together with theoretical simulation results.

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

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

[0071] As mentioned above, in the conventional hydrogen filling process, the dispenser 100 is responsible for control between the vehicle 300 and the hydrogen filling station 200, and the dispenser 100 is equipped with a protocol, which is a method of injecting hydrogen into the vehicle 300 in accordance with established regulations, and which oversees the control.

[0072] The protocol installed in the dispenser 100 is based on the international standard SAE-J2601 (2020-05), which is equally applicable to the embodiments of the present invention within the scope consistent with the objectives of the present invention.

[0073] Regarding minimum safety requirements, simulations are carried out through thermodynamic modeling for various situations, and the parameters derived through this are used to implement the table-based single method and the MC-formula-based partial real-time correction method. Minimum safety requirements include upper limits for temperature and pressure conditions of CHSS310, as well as guidelines for State of Charge (SOC).

[0074] The simulation can be performed through thermodynamic modeling using boundary conditions including best to worst cases.

[0075] Such a configuration may be applied to the configuration of the embodiment of the present invention within the scope consistent with the object of the present invention.

[0076] 1 and 2, the following problems are found in the prior art in which the dispenser 100 does not actively control the state value. The following problems also appear in the prior art that relies on simulations using a simple thermodynamic model.

[0077] Since the injection rate is determined in advance assuming the worst possible boundary conditions (excessive boundary conditions), unnecessary pre-cooling occurs, resulting in a decrease in the overall filling rate. In this case, in the conventional technology, the injection rate is simply determined by the average pressure rise rate (APRR), which can be a factor that inhibits active response depending on the situation. Unnecessary pre-cooling can lead to excessive energy costs and operating costs.

[0078] Since it depends on the results of simulation, there are limitations on the capacity and shape of the storage tank 310 that can be applied, and in the case of a new system, separate resources are required for new development and application, so there are problems with limited application targets.

[0079] Thermodynamic models require a lot of time to derive the calculation results of mathematical formulas, and have limited applicability when there are no pre-calculated variables as they indirectly utilize variables derived through the model. They also have problems such as a lack of flexibility in terms of fine adjustments to the method itself.

[0080] The conventional table-based method is very inefficient because it does 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 has the problem of being difficult to flexibly respond to changes in the surrounding conditions. The conventional MC-Formula-based method corrects the pre-cooling temperature in real time, but the calculation and application method are complicated and there are limitations to the objects that can be applied, making it difficult to expand. The protocol was developed with the primary goal of completing the safe filling, and there was no alternative that could actively control unexpected situations such as excessive pre-cooling or overheating of the storage tank 310. This resulted in problems such as increased operating costs due to overcooling and filling delays due to overheating.

[0081] The present invention has been developed to solve the problems of the prior art, and is characterized in that it reduces the dependency on simulation and attempts to actively control state variables by reflecting real-time measurement data.

[0082] FIG. 3 is a conceptual diagram illustrating an example of state changes that occur during a hydrogen filling process for a hydrogen electric vehicle (FCEV) to which an embodiment of the present invention is applied. As shown in FIG. 3, when hydrogen is injected into the storage tank 310, the internal temperature increases due to the heat of compression, thereby increasing the temperature of the hydrogen gas inside the storage tank 310.

[0083] Temperature control during the hydrogen filling process is performed by supplying pre-cooled hydrogen gas and controlling the internal temperature of the storage tank 310 to be 85° C. or less at the time of final filling completion. The storage tank 310 is constructed so that the carbon fiber surrounding the dome and body of the storage tank 310 has low heat transfer efficiency 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 temperature rise appearing on the surface of the storage tank 310 is negligible compared to the internal temperature rise until filling is completed due to the low heat transfer characteristics of the storage tank 310.

[0084] This characteristic can mitigate the rapid temperature rise inside the storage tank 310 that occurs during filling, but since it blocks heat exchange with the outside air, a separate temperature control measure is required. However, the prior art does not include any separate cooling means other than the supply of pre-cooled hydrogen gas from the filling station 200.

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

[0086] In an embodiment of the present invention, the characteristic curve of FIG. 3 is used as a basic model, but unlike the prior art, the operating load of the filling station 200 in the pre-cooling stage of Phase I and the filling rate (pressure rise rate, PRR) control occurring in the filling process of Phases II to IV are optimized in consideration of real-time data based on variables (outside air temperature, air pressure, weather conditions, etc.) that appear in the actual surrounding environment, thereby deriving optimal control conditions suited to the actual environment.

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

[0088] In an embodiment of the present invention, with the accuracy of the hydrogen filling model ensured at a considerable level, future filling results are predicted from the hydrogen filling model and current measurement values, and the pressure rise 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 the hydrogen gas pressure Pgas of the CHSS310 reach the optimal filling target without violating constraints.

[0089] In an embodiment of the present invention, model predictive control is used to calculate future output values ​​based on current measurements and model predicted values, and an operation parameter / variable is adjusted so that the predicted future response moves to a setpoint (or target) in an 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 the prediction horizon.

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

[0092] In practice, the first (i+1) control action of the n model predictions and control actions derived at the current time i can be transmitted to the system. As time passes, new (n) model predictions and control actions are derived again at the current time i+1, which form new prediction and control horizons, respectively.

[0093] This technique of controlling the system while expanding / moving the horizon is called model predictive control, and in an embodiment 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 the CHSS 310.

[0094] FIG. 5 is an operational flowchart illustrating a hydrogen filling control method based on model predictive control according to an embodiment of the present invention.

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

[0096] The current state measurements may include measurements of the temperature and pressure of the hydrogen gas within the CHSS 310 .

[0097] The hydrogen filling method according to an embodiment of the present invention may further include evaluating whether the measurement value of the current state and the next state value satisfy constraints (S540).

[0098] The constraint may be that the temperature and pressure of the compressed hydrogen storage system (CHSS) of the hydrogen electric vehicle (FCEV) do not exceed a limit temperature and limit pressure, respectively.

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

[0100] Predicting or obtaining a next state value (S530) may include predicting a number of next state values ​​forming a prediction horizon according to the model.

[0101] The step of generating control commands (S520) may generate a plurality of control commands that form a control horizon corresponding to the prediction horizon so that a process in which a future response reaches a set point is optimized based on a comparison result between a plurality of next state values ​​and a set point.

[0102] In the step of predicting or obtaining a next state value (S530) and the step of generating a control command (S520), a plurality of control commands forming a control horizon corresponding to a prediction horizon including a plurality of next states can be obtained so that a process in which a future response predicted by an artificial neural network model reaches a set point using a model predictive control technique is optimized.

[0103] The method may further include updating a cost function and variables / parameters for filling control based on the current state and the next state values ​​(S550).

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

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

[0106] The hydrogen gas temperature Tgas and the hydrogen gas pressure Pgas are values ​​measured on the CHSS 310 side of the hydrogen electric vehicle 300, and the actual measured values ​​can be input to the input layer.

[0107] In the training process of the artificial neural network, the actual measured value is transmitted to the input layer, and the next measured value is transmitted to the output layer, which can be used in the learning process of the artificial neural network. At this time, the learning process of the artificial neural network can be a process of learning a function that can predict the next measured value of the output layer based on a combination of input measured values. The correlation between the data input to the input layer and the data provided to the output layer is learned, and through this, predictions can be made using the real dynamic fueling data along with theoretical results.

[0108] In the inference or output process using an artificial neural network, an actual on-site measurement value is transmitted to the input layer, and a predicted value for the next measurement value can be obtained as an output from the operation of the artificial neural network.

[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 according to the purpose of the present invention.

[0110] The values ​​input through the input layer are transmitted to the output layer after undergoing weight-based calculations in the hidden layer. The state values ​​output by the output layer (predictions for the next state) may be used to calculate a state of charge variable, such as the fraction of charge (SOC), using at least a portion of a thermodynamic model.

[0111] In the embodiment of the present invention, a hybrid control combining a theoretical simulation model and an artificial neural network is also possible, so that a desired result can be achieved even through learning using a small amount of data, and performance that meets the objectives of the present invention can be derived even through a lightweight artificial neural network.

[0112] The real-time pressure rise rate (PRR) or mass flow rate of compressed hydrogen (kg / s) m derived from the feedback control process can affect the weights or parameters of the hidden layers of the artificial neural network.

[0113] The artificial neural network-based hydrogen filling method of the present invention can improve the accuracy of filling result prediction through a model. By utilizing actual filling data along with theoretical simulation results, real-time measurements can be reflected, further improving the accuracy of prediction results.

[0114] While the control protocol of the prior art calculates and predicts results through simulations tailored to individual situations, the embodiment of the present invention differs in that it utilizes a process of improving accuracy through repeated training for various situations. Due to this difference, in the embodiment of the present invention, the accuracy is gradually improved through updates as various theoretical values ​​and empirical results are added, and even if a new filling process using a new configuration of the storage tank 310 or a change in flow rate is introduced, the function can be updated to the model by adding actual data and training, so that it can be widely applied to various mobility fields.

[0115] FIG. 7 is a conceptual diagram illustrating a hydrogen filling control process for a hydrogen fuel cell electric vehicle (FCEV) using an artificial neural network and an integrated meta system (IMS) according to one embodiment of the present invention. As shown in Figure 7, the Intelligent Meta System (IMS) 400 provides the artificial neural network and model predictive control with the necessary information (gas temperature and pressure measured by CHSS 310 or predicted by the model, etc.) and manages distributed roles such as adjusting the pre-cooling temperature according to real-time environment changes, thereby realizing efficient filling speed control.

[0116] The filling station 200 can communicate the measurements (conditions) of the pre-cooled gas to the IMS 400 .

[0117] The hydrogen electric vehicle 300 can communicate the measurements (conditions) of the CHSS 310 to the IMS 400 .

[0118] Depending on the embodiment of the present invention, the IMS 400 may be disposed in the dispenser 100 or may be embodied as an independent control device. The IMS 400 may transmit control commands for filling control to the filling station 200 and the hydrogen electric vehicle 300, and such a configuration will be described later through the embodiments of Figs. 13 to 16.

[0119] The IMS 400 can communicate with the artificial neural network 120 to set control variables as needed to control the artificial neural network 120 to achieve optimal filling results. The next target pressure Ptarget can be derived from the artificial neural network 120 with the predicted SOC, and the control parameters (PRR or m) for this purpose can be set.

[0120] At this time, the control parameters can be adjusted using a cost function so that the state values ​​satisfy the constraints in all situations.

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

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

[0123] The intelligent meta-system 400 may be subordinate to the dispenser 100 or may be located independently of the dispenser 100 .

[0124] The intelligent meta-system 400 may be centralized in one device or distributed across multiple pieces of hardware including the dispenser 100 and / or filling station 200 . The intelligent meta-system 400 may be implemented in the form of a cloud server.

[0125] Although the artificial neural network 120 is illustrated as being subordinate to the dispenser 100 in the embodiment shown, in other embodiments of the present invention, it may be implemented by being disposed in a position independent of the dispenser 100. For example, the artificial neural network 120 may be disposed and trained in a cloud system and used for controlling hydrogen filling via the dispenser 100 through wired / wireless communication.

[0126] Alternatively, a separate artificial neural network may be arranged and trained in the cloud system, and all or some of the parameters of the trained artificial neural network may be transferred to the local artificial neural network 120 arranged in 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] FIG. 8 is an operational flowchart illustrating an artificial neural network-based hydrogen filling control method according to one embodiment of the present invention.

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

[0129] In the step of generating a filling control command (S620), the filling control command may be generated based on the output of an artificial neural network that has learned the function of generating a filling control command for each future response after the measurement value of the current state to reach a set point while satisfying the constraint conditions.

[0130] In the step of generating a filling control command (S620), a plurality of control commands corresponding to a plurality of next state values ​​may be generated based on the output of an artificial neural network that has been trained to predict a plurality of next state values ​​that minimize a cost function for the filling state.

[0131] FIG. 9 is an operational flowchart illustrating a process of training an artificial neural network for hydrogen filling control based on an artificial neural network-model predictive control in accordance with one embodiment of the present invention.

[0132] In FIG. 9, we assume that n future predictions and corresponding control commands are obtained from an artificial neural network model 120 that has learned the function of obtaining an artificial neural network-based model predictive control-based prediction horizon and control horizon, and in particular, that the process in which a future response reaches a set point is optimized by model predictive control.

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

[0134] The real-time control system predicts future filling results and compares them with actual measured values ​​to control the filling speed / pressure increase rate / pressure increase speed. It can control within optimal values ​​by separately setting restrictions, control time intervals, sensitivity, etc. within the system logic.

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

[0136] 9, the control process starts with receiving an input of SOCsp specified by a customer (t=0, S710). For example, the current SOC may be 50% and the SOCsp may be 85%.

[0137] If the customer does not set a specific SOCsp, the SOCsp may be set to a pre-defined default value, for example, the default value may 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 kinetic model.

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

[0140] Step S730 may 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 may be determined whether the obtained n predictions are predictions / control commands that are optimized and consistent with the intended purpose.

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

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

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

[0144] FIG. 10 is a conceptual diagram illustrating in detail a portion of the process of FIG. 10, in step S730 of FIG 9, a state prediction value (T, P) that satisfies the temperature and pressure constraints for all arbitrary i, k can be generated, where i is an index representing the current time, and k is an index corresponding to each prediction / control command forming the moving horizon.

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

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

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

[0148] Condition measurements including temperature and pressure of the CHSS 310 at the output of the hydrogen electric vehicle 300 may be provided as feedback inputs to the artificial neural network model 120 .

[0149] Condition measurements including temperature and pressure of the pre-cooled hydrogen gas at the output of the hydrogen filling station 200 may be provided as feedback inputs to the artificial neural network model 120 .

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

[0151] The artificial neural network-model predictive control based control process is a control technique that utilizes both simulation and actual measurement data, and performs at least a partial simulation using an artificial neural network model 120 and uses the predicted results in the control process.

[0152] FIG. 13 is a conceptual diagram illustrating an artificial neural network-based integrated control model for controlling a hydrogen filling process in accordance with an embodiment of the present invention.

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

[0154] The protocol installed in the dispenser 100 can utilize the pre-cooled hydrogen gas data provided from the filling station 200 and the storage tank 310 data provided from the vehicle 300 as real-time input values, and control the filling rate / pressure rise rate / pressure rise speed (PRR or m) as output according to the installed model.

[0155] When an event condition such as a change in the external environment occurs, the pre-cooling temperature of the filling station 200 and the cooling system of the vehicle 300 can be directly controlled to generally control the filling speed / pressure rise rate / pressure rise speed (PRR or m) and process efficiency.

[0156] To complement the control protocol, the pre-cooling system / pre-cooler 210 of the hydrogen filling station 200 may be independently equipped with its own cooling stabilization system. In terms of temperature stabilization, the cooling stabilization system of the pre-cooler 210 may be independently controlled and the control target values ​​may be integrally changed with the protocol of the dispenser 100 .

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

[0158] The pre-cooler 210 according to an embodiment of the present invention may include control logic for autonomous temperature control and protocol coordination.

[0159] A forced cooling system may be installed in the storage tank 310 of the vehicle 300 to cool some of the compression heat generated during hydrogen filling and improve the filling speed, and the operation / control of the forced cooling system of the storage tank 310 may also be involved in the protocol.

[0160] In one embodiment of the present invention, temperature control may be provided to the storage tank 310 of the vehicle 300 to enhance hydrogen filling rates and complement the functionality of the integrated control protocol.

[0161] In one embodiment of the present invention, the storage tank 310 may configure 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 linking it with protocols.

[0162] In one embodiment of the present invention, such integrated control can not only improve the efficiency of the current filling, but also smoothly assist in preparation for the next filling.

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

[0164] In the case of T40, in which the pre-cooling temperature of the pre-cooler 210 is set to -40°C, if the pre-cooling temperature reaches the target value but the outside air 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 current status information can be transmitted to the vehicle 300 / storage tank 310 side to activate the self-cooling system of the storage tank 310. Conversely, if the pre-cooling temperature of the pre-cooler 210 is set to -40°C, but is determined to be excessive cooling when taking into account the external environment and actual data, the target value of the pre-cooling temperature can be adjusted (e.g., -35°C).

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

[0166] According to an embodiment of the present invention, the self-cooling systems of the vehicle 300 and the filling station 200 may be controlled independently, or may be controlled by transmitting a signal from the dispenser 100 .

[0167] FIG. 15 is an operational flow chart illustrating an integrated control method for hydrogen filling in accordance with one embodiment of the present invention.

[0168] A hydrogen fueling control method for a hydrogen electric vehicle (FCEV) according to one embodiment of the present invention is an integrated control method for hydrogen fueling, and includes a step of acquiring current state measurements (S810), a step of determining whether a second control command for at least one of the hydrogen filling station and the hydrogen electric vehicle is necessary in addition to a first control command executed by the dispenser side based on the current state measurements (S830), and a step of generating a second control command for at least one of the hydrogen filling station and the hydrogen electric vehicle based on the determination result (S840).

[0169] The second control instructions for the hydrogen filling station may include instructions to adjust a target value for a pre-cooling temperature of the hydrogen filling station.

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

[0171] The integrated control method for hydrogen filling according to an embodiment of the present invention may further include evaluating whether a measurement value of a current state satisfies a constraint condition.

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

[0173] The integrated control method for hydrogen filling according to an embodiment of the present invention may further include the step of generating a first control command to be executed at the dispenser side based on the measured value of the current state (S850).

[0174] Step S830 may be performed based on the result of performing step S820 of calculating the difference between the measured value and the predicted value of the current CHSS 310 state.

[0175] FIG. 16 is a conceptual diagram illustrating an example of a generalized hydrogen filling control device, hydrogen filling control system, or computing system capable of performing at least a portion of the processes of FIGS.

[0176] The hydrogen filling control device may be disposed on the side of the dispenser 100. The hydrogen filling control system may be disposed in a distributed manner in the dispenser 100, the hydrogen filling station 200, and the hydrogen electric vehicle 300 or disposed in at least a portion of the dispenser 100, the hydrogen filling station 200, and the hydrogen electric vehicle 300, and may control the operation of at least a portion of the dispenser 100, the hydrogen filling station 200, and the hydrogen electric vehicle 300.

[0177] The hydrogen filling controller and / or hydrogen filling control system may be embodied in the form of a computing system including a processor 1100 electronically coupled to a memory 1200 .

[0178] At least some of the processes of the model predictive control based hydrogen filling control method, the artificial neural network based hydrogen filling control method, and the integrated control method for hydrogen filling according to an embodiment of the present invention may be executed by the computing system 1000 of FIG.

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

[0180] The computing system 1000 according to an embodiment of the present invention may include at least one processor 1100 and a memory 1200 storing instructions for instructing the at least one processor 1100 to perform at least one step. At least some steps of a method according to an 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 represent a central processing unit (CPU), a graphics processing unit (GPU), or a special purpose processor on which methods according to embodiments of the present invention are performed.

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

[0183] The computing system 1000 may also include a communication interface 1300 for effecting communications over a wireless network. In addition, the computing system 1000 may further include a storage device 1400, an input interface 1500, an output interface 1600, and the like. In addition, each component included in the computing system 1000 is connected to a bus 1700 to perform communication.

[0184] The computing system 1000 of the present invention may be, for example, a communications-enabled desktop computer, a laptop computer, a notebook computer, a smart phone, a tablet PC, a mobile phone, a smart watch, smart glass, an e-book reader, a portable multimedia player (PMP), a portable game console, a navigation device, a digital camera, a digital multimedia broadcasting (DMB) player, a digital audio recorder, a digital audio player, a digital video recorder, a digital video player, a personal digital assistant (PDA), or the like.

[0185] The operation of the method according to the embodiment of the present invention may be embodied as a computer readable program or code in a computer readable recording medium. The computer readable recording medium includes all kinds of recording devices in which information readable by a computer system is stored. The computer readable recording medium may also be distributed among computer systems connected to a network, so that the computer readable program or code may be stored and executed in a distributed manner.

[0186] The computer-readable recording medium may also include a hardware device specially configured to store and execute program instructions, such as a ROM, RAM, flash memory, etc. The program instructions may include not only machine code, such as that produced by a compiler, but also high-level language code that may be executed by a computer using an interpreter, etc.

[0187] Some aspects of the invention have been described in the context of an apparatus, but they may also be represented as corresponding method descriptions, where the blocks or apparatus correspond to method steps or features of the method steps. Similarly, aspects described in the context of a method may also be represented as corresponding blocks or items or features of the corresponding apparatus. Some or all of the method steps may be performed by (or using) a hardware apparatus, such as, for example, a microprocessor, a programmable computer, or electronic circuitry. In some embodiments, at least one or more of the most significant method steps may be performed by such an apparatus.

[0188] In some 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 some embodiments, a field programmable gate array may operate in conjunction with a microprocessor to perform one of the methods described herein. In general, it is preferred that the methods be performed by some hardware device.

[0189] Although the present invention has been described with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and variations of the present invention may be made without departing from the spirit and scope of the present invention as set forth in the following claims. [Explanation of symbols]

[0190] 100 Dispenser 110 Hydrogen refueling control 120 Artificial Neural Networks 200 Hydrogen filling station, filling station 210 Precooler 220 High Pressure Hydrogen 300 Hydrogen fueled mobility, mobility, hydrogen electric vehicles, vehicles 310 Compressed Hydrogen Storage System (CHSS), storage tanks 320 Pressure Relief Device (PRD) 400 Intelligent Metasystem 1000 Computing Systems 1100 Processor 1200 Memory 1300 Communication Interface 1400 Storage 1500 Input User Interface 1600 Output User Interface 1700 Bus

Claims

1. 1. A hydrogen fueling method for hydrogen fueled mobility, comprising: obtaining a current state measurement; predicting or obtaining a next state value using a model predictive control technique based on the measurements of the current state; and generating a control command for hydrogen filling based on the comparison result between the measured value of the current state and the next state value.

2. 2. The method of claim 1, further comprising: evaluating whether the current state measurement value and the next state value satisfy a constraint condition.

3. 3. The method of claim 2, wherein the constraint condition is that the temperature and pressure of a compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility do not exceed a limit temperature and a limit pressure, respectively.

4. The step of generating the control command comprises:

2. The method of claim 1, further comprising: generating a control command for a pressure ramp rate (PRR) for the hydrogen filling.

5. The step of predicting or obtaining a next state value comprises:

2. The method of claim 1, further comprising predicting a plurality of the next state values ​​forming a prediction horizon according to a model.

6. The step of generating the control command comprises:

6. The method of claim 5, further comprising: generating a plurality of the control commands that form a control horizon corresponding to the prediction horizon so that a process of a future response reaching the set point is optimized based on a comparison result between the plurality of next state values ​​and a set point.

7. In the steps of predicting or obtaining a next state value and generating a control command, 6. The method of claim 5, wherein a plurality of the control commands are obtained that form a control horizon corresponding to the prediction horizon including the plurality of next state values ​​so that a process of a future response reaching a set point is optimized by a model predictive control technique.

8. 1. A hydrogen fueling method for hydrogen fueled mobility, comprising: obtaining a current state measurement; generating a filling control command for filling the hydrogen tank based on the output of an artificial neural network that uses the current state measurements as inputs; obtaining a next state value based on the filling control command; and and evaluating whether a response to the execution of the filling control command satisfies a constraint condition.

9. 10. The artificial neural network-based hydrogen filling method of claim 8, wherein the constraint is that the temperature and pressure of a compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility do not exceed a limit temperature and a limit pressure, respectively.

10. The step of generating a filling control command comprises:

9. The method of claim 8, further comprising: generating a control command for a pressure ramp rate (PRR) for the hydrogen filling.

11. In the step of generating a filling control command, 9. The hydrogen filling method based on an artificial neural network as claimed in claim 8, wherein the filling control command is generated based on the output of the artificial neural network that has learned the function of generating the filling control command so that each of the future responses after the measurement value of the current state satisfies the constraint condition and reaches a set point.

12. In the step of generating a filling control command, 9. The method of claim 8, wherein the control commands corresponding to the next state values ​​are generated based on the output of the artificial neural network that has learned the function of predicting the next state values ​​that minimize a cost function for the filling state.

13. A hydrogen fueling control device for hydrogen fueled mobility, comprising: A processor, and a memory for storing at least one instruction; The processor executes the at least one instruction to: Obtain a current state measurement; A hydrogen filling control device characterized in that it obtains a filling control command for hydrogen filling and a next state value corresponding to the filling control command based on at least one of a model predictive control technique based on the measurement value of the current state and the output of an artificial neural network to which the measurement value of the current state is input.

14. The processor, The hydrogen filling control device according to claim 13, characterized in that each response resulting from the execution of the filling control command is evaluated as to whether it satisfies a constraint condition.

15. The hydrogen filling control device according to claim 14, wherein the constraint condition is that the temperature and pressure of a compressed hydrogen storage system (CHSS) of the hydrogen fuel mobility do not exceed a limit temperature and a limit pressure, respectively.

16. The control command is: The hydrogen filling control device according to claim 13, further comprising a control command for a pressure ramp rate (PRR) for the hydrogen filling.

17. The processor, The hydrogen filling control device according to claim 13, characterized in that a plurality of the next state values ​​forming a prediction horizon are predicted by a model predictive control technique.

18. The processor, The hydrogen filling control device of claim 17, further comprising: generating a plurality of the control commands that form a control horizon corresponding to the prediction horizon so that a process of a future response reaching the set point is optimized based on a comparison result between the plurality of next state values ​​and a set point.

19. The processor, 18. The hydrogen filling control device according to claim 17, wherein each of the plurality of next state values ​​is evaluated to see if it satisfies a constraint condition.

20. The processor, The hydrogen filling control device of claim 17, further comprising: a plurality of control commands that form a control horizon corresponding to the prediction horizon including the plurality of next state values, so that a process in which a future response reaches a set point is optimized by a model predictive control technique.

Citation Information

Patent Citations

  • Gas filling method

    WO2019235386A1