Hydrogenation control method and device

Abstract

The invention provides a hydrogenation control method and device, and belongs to the field of new energy application, and the method comprises the steps: determining a target hydrogenation demand based on the basic information of a hydrogenation machine and the pressure information of a vehicle-mounted gas cylinder; determining a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on the target hydrogenation demand, the hydrogenation control precision of the plurality of hydrogenation control strategies being different; and performing hydrogenation control on the vehicle-mounted gas cylinder based on the target hydrogenation control strategy. According to the hydrogenation control method and device provided by the invention, the hydrogenation control efficiency can be improved, and the energy consumption can be reduced.

Description

Technical Field

[0001] The present disclosure belongs to the field of new energy application, and more specifically, relates to a hydrogenation control method and device. Background Art

[0002] When hydrogen fuel cell vehicles are refueled, the conventional method is to unload the hydrogen from the hydrogen long tube trailer, and then pass it through a high-pressure compressor and then pressurize it to a 35Mpa on-board gas cylinder. This traditional hydrogenation process not only has high transportation costs for the hydrogen tube trailer, but also high energy consumption.

[0003] Therefore, there is an urgent need for an energy-saving and efficient hydrogenation control method. Summary of the invention

[0004] The purpose of the present disclosure is to provide a hydrogenation control method and device to improve the efficiency of hydrogenation control and save energy consumption.

[0005] A first aspect of an embodiment of the present disclosure provides a hydrogenation control method, comprising: Determine the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder; Determining a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on the target hydrogenation demand, wherein the plurality of hydrogenation control strategies have different hydrogenation control accuracies; The hydrogenation of the vehicle-mounted gas cylinder is controlled based on the target hydrogenation control strategy.

[0006] A second aspect of the embodiments of the present disclosure provides a hydrogenation control device, comprising: A hydrogenation demand determination module is used to determine the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder; A control strategy determination module, configured to determine a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on the target hydrogenation demand, wherein the plurality of hydrogenation control strategies have different hydrogenation control accuracies; A hydrogenation control module is used to control the hydrogenation of the vehicle-mounted gas cylinder based on the target hydrogenation control strategy.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned hydrogenation control method when executing the computer program.

[0008] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned hydrogenation control method are implemented.

[0009] The beneficial effects of a hydrogenation control method and device provided by the embodiments of the present disclosure are: The present disclosure can more accurately determine the target hydrogenation demand by comprehensively considering the basic information of the hydrogenation machine and the pressure information of the on-board gas cylinder, thereby avoiding energy waste or safety hazards caused by inaccurate hydrogenation amount. Secondly, the present disclosure selects the most appropriate strategy from multiple hydrogenation control strategies according to the target hydrogenation demand. These strategies have different hydrogenation control precisions and can meet the hydrogenation needs in different scenarios. This flexible selection method not only improves the flexibility of hydrogenation control, but also ensures the stability and safety of the hydrogenation process. Finally, based on the target hydrogenation control strategy, the on-board gas cylinder is controlled to achieve precise hydrogenation operation, reduce the damage to the gas cylinder caused by improper hydrogenation, and extend the service life of the gas cylinder. At the same time, precise hydrogenation control also helps to improve hydrogenation efficiency, shorten hydrogenation time, and enhance user experience. Therefore, the present disclosure can improve the efficiency of hydrogenation control and save energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0011] Figure 1 A schematic flow chart of a hydrogenation control method provided in one embodiment of the present disclosure; Figure 2 A structural block diagram of a hydrogenation control device provided in one embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1A schematic flow chart of a hydrogenation control method provided in one embodiment of the present disclosure, the method comprising: S101: Determine the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder.

[0015] In this embodiment, the basic information of the hydrogen refueling machine may include information such as the model of the hydrogen refueling machine, the maximum hydrogen refueling pressure, the maximum hydrogen refueling flow rate, the compressor type, the specifications of the hydrogen refueling gun, and the parameters of related valves. The pressure information of the vehicle-mounted gas cylinder is the current hydrogen pressure value in the vehicle-mounted hydrogen fuel cell gas cylinder. The pressure value of the vehicle-mounted gas cylinder can be detected by the pressure sensor provided by the hydrogen refueling machine, which can be used to determine the current hydrogen stock status of the vehicle-mounted gas cylinder and how much hydrogen needs to be added.

[0016] This embodiment comprehensively considers the basic information of the hydrogen refueling machine and the current hydrogen pressure status of the onboard gas cylinder to determine the final hydrogen volume or pressure value to be achieved in this hydrogenation, which is the target demand.

[0017] In this embodiment, the target hydrogenation demand is determined based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder, including: Determine the model of the hydrogen refueling machine, the connecting equipment and the pressure value of the cylinder group; Determine the current pressure value of the onboard gas cylinder; Compare the cylinder group pressure value with the current pressure value to determine the hydrogen refueling demand of the onboard gas cylinder; Determine the number of hydrogenation control devices based on hydrogenation demand, hydrogenation machine model and connected equipment; Determine the status of the hydrogenation control equipment based on the hydrogenation demand, hydrogenation machine model and connected equipment; The hydrogenation demand of the on-board gas cylinders, the number of hydrogenation control devices, and the status of the hydrogenation control devices are all target hydrogenation demands.

[0018] The model of the hydrogenation machine and the equipment connected to the hydrogenation machine will affect the number and status of the hydrogenation control equipment. The connecting equipment of the hydrogenation machine can be a hydraulic press, a molding machine, etc., and the hydrogenation demand is different. When facing different hydrogenation machine models and connecting equipment, the target hydrogenation demand will also be dynamically adjusted, and the target hydrogenation demand is the ultimate desired demand.

[0019] S102: Determine a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on a target hydrogenation demand, wherein the hydrogenation control accuracies of the plurality of hydrogenation control strategies are different.

[0020] In this embodiment, the target hydrogenation demand is the amount of hydrogen or pressure value that needs to be met in this hydrogenation, and can also be information such as the expected hydrogenation efficiency and energy consumption. The hydrogenation control strategy is a pre-set method for controlling the hydrogenation process, which can include the operation mode or sequence of each component of the hydrogenation machine, such as the start and stop of the compressor, speed adjustment, opening and closing of the valve, and opening adjustment, etc. It can also include the control logic of various parameters in the hydrogenation process, such as the control of parameters such as pressure, flow and temperature.

[0021] Hydrogenation control accuracy refers to the accuracy and precision of different hydrogenation control strategies in achieving target hydrogenation requirements.

[0022] If the target hydrogenation demand is hydrogenation at a first rate, any hydrogenation control strategy with a control accuracy greater than or equal to the first accuracy is required as the target hydrogenation control strategy; If the target hydrogenation demand is the second rate hydrogenation, any hydrogenation control strategy with a control accuracy less than the first accuracy is required as the target hydrogenation control strategy; The first rate is greater than the second rate.

[0023] The first rate hydrogenation is for rapid hydrogenation needs, which requires precise control to meet the hydrogenation needs. Higher control requirements are placed on the various components of the hydrogenator and related equipment to achieve rapid hydrogenation while ensuring safety. At this time, some energy consumption may be sacrificed. The second rate hydrogenation is for normal hydrogenation needs, and extensive control can complete hydrogenation with low energy consumption while ensuring safety.

[0024] After the target hydrogenation demand to be achieved in this hydrogenation has been clarified, this embodiment will screen from a plurality of pre-set hydrogenation control strategy libraries. Since the above strategies have differences in hydrogenation control accuracy, this embodiment will screen out the most suitable target hydrogenation control strategy for this hydrogenation operation through a certain decision-making mechanism according to the specific conditions of the target hydrogenation demand, such as the target hydrogenation amount, hydrogenation time limit, etc., to ensure that while meeting the hydrogenation demand, multiple factors such as efficiency, cost and safety are taken into account. The decision-making mechanism can be rule-based judgment, optimization algorithm or deep learning model, etc.

[0025] S103: Controlling the hydrogenation of the vehicle-mounted gas cylinder based on the target hydrogenation control strategy.

[0026] In this embodiment, the vehicle-mounted gas cylinder is a container installed on a hydrogen fuel cell vehicle for storing hydrogen, and is also the target object of hydrogen refueling. Hydrogen needs to be injected into it according to prescribed requirements to meet the operating requirements of the vehicle's hydrogen fuel cell.

[0027] After the target hydrogenation control strategy is determined, the on-board gas cylinder can be hydrogenated according to the set specific operating method or process. That is, by controlling the relevant equipment, the actions specified in the strategy are accurately executed to achieve safe, efficient and accurate hydrogen filling into the on-board gas cylinder, ensuring that the predetermined hydrogenation target is ultimately achieved.

[0028] For example, the 35MPa hydrogenation machine D03601A is directly connected to the 45MPa liquid drive machine (Pufa) C03603. After the hydrogenation vehicle arrives, connect the hydrogenation gun, press the hydrogenation switch, and detect the pressure of the onboard gas cylinder (which comes with the hydrogenation machine). Take hydrogenation gun 1 as an example.

[0029] The first step is to compare the onboard gas cylinder pressure with the 15-20Mpa cylinder group V03601 pressure (pressure gauge PRAS-V03601).

[0030] (1) When the pressure of the cylinder group is higher than the pressure of the onboard gas cylinder and the pressure difference is greater than 5MPa, open the switch valve XV-D03601A / 1 between the hydrogenation gun of the No. 1 hydrogen filling machine and the cylinder group pipeline, inflate the onboard gas cylinder to a pressure difference of 5MPa, and then close this switch valve.

[0031] (2) When the pressure of the cylinder group is higher than the pressure of the onboard gas cylinder and the pressure difference is ≤5MPa, or when the pressure of the onboard gas cylinder is greater than the pressure of the cylinder group, valve XV-D03601A / 1 will not be opened.

[0032] The second step is to directly charge the 45MPa liquid drive engine.

[0033] (1) When the 45MPa hydraulic drive machine C03603 is in the closed state, open the switch valve XV-C03603 / 1 and the compressor of the pipeline connected to this gun, and inflate until the pressure of the onboard gas cylinder is 35MPa. At the same time, detect the pressure of the low-pressure part (PT-V03602a) of the 45MPa bottle group V03602. If it is less than 30MPa, open the switch valve XV-V03602a / 3 of the low-pressure part of the 45MPa bottle group V03602, close the switch valve XV-C03603 / 1 of the hydrogenation gun, and inflate it to 37MPa; detect the pressure of the high-pressure part (PT-V03602b) of the 45MPa bottle group V03602. If it is less than 37MPa, open the switch valve XV-V03602b / 3 of the high-pressure part of the 45MPa bottle group V03602, close the switch valve XV-C03603 / 1 of the hydrogenation gun, and inflate it to 45MPa; when the pressure of the bottle group reaches 37MPa and 45MPa respectively, close the compressor and the switch valve between the compressor and the bottle group.

[0034] (2) When the 45MPa liquid drive machine is in the open state and the other hydrogenation gun of the hydrogenation machine is inflated (the switch valve XV-C03603 / 2 between the compressor and the other hydrogenation gun is in the open state), it is necessary to wait until the other hydrogenation gun is completed, close the switch valve of the other hydrogenation gun, and then open the switch valve XV-C03603 / 1 of this gun, inflate until the pressure of the on-board gas cylinder is 35MPa, and then follow the step (1) to detect the pressure and action of the 45MPa cylinder group.

[0035] (3) When the 45MPa liquid drive machine is in the on-state and the gas cylinder group is inflated, open the switch valve C03603 / 1 of the hydrogenation gun, close the switch valves XV-V03602a / 3 and XV-V03602b / 3 of the gas cylinder group, inflate the vehicle-mounted gas cylinder to a pressure of 35MPa, and then test the pressure and action of the 45MPa cylinder group according to step (1).

[0036] (4) When the hydrogenation machine is not turned on and the 45MPa liquid drive machine is in the off state, detect the 45MPa bottle group pressure according to step (1). If the pressure is less than the set value, turn on the compressor and the switch valve connected to the bottle group, inflate it to the required value, and then turn off the compressor and the switch valve connected to the bottle group.

[0037] It can be concluded from the above that the present disclosure can more accurately determine the target hydrogenation demand by comprehensively considering the basic information of the hydrogenation machine and the pressure information of the on-board gas cylinder, thereby avoiding energy waste or safety hazards caused by inaccurate hydrogenation amount. Secondly, the present disclosure selects the most appropriate strategy from multiple hydrogenation control strategies according to the target hydrogenation demand. These strategies have different hydrogenation control precisions and can meet the hydrogenation needs in different scenarios. This flexible selection method not only improves the flexibility of hydrogenation control, but also ensures the stability and safety of the hydrogenation process. Finally, based on the target hydrogenation control strategy, the on-board gas cylinder is controlled to achieve precise hydrogenation operation, reduce the damage to the gas cylinder caused by improper hydrogenation, and extend the service life of the gas cylinder. At the same time, precise hydrogenation control also helps to improve hydrogenation efficiency, shorten hydrogenation time, and enhance user experience. Therefore, the present disclosure can improve the efficiency of hydrogenation control and save energy consumption.

[0038] In one embodiment of the present disclosure, the basic information includes a pressure value of the first bottle group, and the pressure information includes a pressure value of the vehicle-mounted gas bottle; Determine the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder, including: In response to the first bottle group pressure value being greater than the onboard gas bottle pressure value, calculating a pressure difference between the first bottle group pressure value and the onboard gas bottle pressure value; If the pressure difference is greater than the pressure difference threshold, the first hydrogenation demand is used as the target hydrogenation demand; If the pressure difference is less than or equal to the pressure difference threshold, the second hydrogenation demand is used as the target hydrogenation demand; The number of control devices for the first hydrogenation demand and the second hydrogenation demand is different.

[0039] In this embodiment, the pressure value of the first bottle group is the pressure value of the hydrogen in a certain bottle group. For example, if the 35MPa hydrogen filling machine D03601A is the first bottle group, the pressure value is 35MPa.

[0040] The on-board gas tank pressure value refers to the hydrogen pressure in the on-board gas tank storing hydrogen on a hydrogen fuel cell vehicle, reflecting the current hydrogen remaining status of the on-board gas tank.

[0041] The pressure difference threshold is a pre-set pressure difference standard used to determine the degree of difference between the pressure value of the first bottle group and the pressure value of the onboard gas bottle. Different degrees of difference require different hydrogen refueling requirements.

[0042] The first hydrogenation demand and the second hydrogenation demand are both one of the multiple hydrogenation demands, which may be associated with the combination of hydrogenation equipment, the operation mode and the pressure difference, and the number of hydrogenation control equipment involved may also be different. The number of hydrogenation control equipment required for the first hydrogenation demand is greater than the number of hydrogenation control equipment required for the second hydrogenation demand.

[0043] During the hydrogenation control process, first obtain the pressure value of the first bottle group in the basic information of the hydrogenation machine and the pressure value of the onboard gas cylinder in the pressure information of the onboard gas cylinder. When the pressure value of the first bottle group is greater than the pressure value of the onboard gas cylinder, calculate the pressure difference between the two. If the above pressure difference is greater than the pre-set pressure difference threshold, it means that the pressure difference between the two is large. At this time, the first hydrogenation demand is selected as the target hydrogenation demand for this time, and the subsequent hydrogenation operation will be carried out according to the control equipment and process corresponding to the first hydrogenation demand; if the pressure difference is less than or equal to the pressure difference threshold, it means that the pressures of the two are relatively close, then the second hydrogenation demand is selected as the target hydrogenation demand, and the corresponding number of control equipment is used to carry out the hydrogenation operation according to its corresponding control method.

[0044] In response to the pressure value of the first cylinder group being less than the pressure value of the onboard gas cylinder, the valve is not opened.

[0045] Assume that the pressure difference threshold is set to 5MPa. The pressure value of the first bottle group at the hydrogen refueling station is 35MPa, and the pressure value of the onboard gas cylinder of a hydrogen fuel cell vehicle is 18MPa. The calculated pressure difference is 12MPa. Since 12MPa>5MPa, the first hydrogenation demand is taken as the target hydrogenation demand. For example, the first hydrogenation demand can be to start the main compressor and two auxiliary valves for hydrogenation operation, involving 3 control devices.

[0046] Assume that the pressure value of the onboard gas cylinder of another vehicle is 26MPa, and the pressure difference is 4MPa, 4MPa≤5MPa, then the second hydrogenation demand is taken as the target hydrogenation demand. For example, the second hydrogenation demand can be met by starting only a small compressor and a valve, involving only two control devices. In this way, the appropriate combination of hydrogenation demand and control equipment can be selected according to different pressure conditions to achieve efficient hydrogenation control.

[0047] In this embodiment, the basic information also includes the pressure value of the second bottle group; In response to the second cylinder group pressure value being greater than the vehicle gas cylinder pressure value: If the pressure value of the vehicle-mounted gas cylinder is greater than or equal to the first pressure threshold, no new action is performed; If the pressure value of the vehicle-borne gas cylinder is less than the first pressure threshold, the vehicle-borne gas cylinder needs to be inflated until the pressure value of the vehicle-borne gas cylinder reaches the first pressure threshold.

[0048] The second bottle group pressure value is the hydrogen pressure value of another bottle group, for example, the 45MPa liquid drive machine is the second bottle group, and the pressure value is 45MPa. The first pressure threshold is a pre-set pressure critical value, which is used to judge the high and low pressure value of the vehicle-mounted gas bottle to determine whether it is necessary to collect and perform actions such as filling. When the pressure value of the vehicle-mounted gas bottle is less than the first pressure threshold, the vehicle-mounted gas bottle needs to be inflated to reach the first pressure threshold.

[0049] When the pressure value of the second bottle group is greater than the pressure value of the onboard gas bottle, the relationship between the pressure value of the onboard gas bottle and the first pressure threshold is further determined. If the pressure value of the onboard gas bottle is greater than or equal to the first pressure threshold, the current state is maintained and no new operation is performed; if the pressure value of the onboard gas bottle is less than the first pressure threshold, the charging operation is started to increase the pressure in the onboard gas bottle to the first pressure threshold to meet the needs of subsequent hydrogenation or vehicle operation.

[0050] In actual hydrogenation control, further selection of target hydrogenation demand can be made based on whether to use the first bottle group or the second bottle group for hydrogenation.

[0051] It can be concluded from the above that this embodiment effectively avoids over-hydrogenation or under-hydrogenation, and improves hydrogenation efficiency and safety. This embodiment achieves flexible adjustment of hydrogenation demand under different pressure difference conditions by setting the pressure difference threshold. When the pressure difference is large, the first hydrogenation demand with more control equipment is selected to ensure the hydrogenation speed and efficiency; when the pressure difference is small, the second hydrogenation demand with fewer control equipment is selected to avoid unnecessary energy waste and equipment loss.

[0052] In one embodiment of the present disclosure, a hydrogenation control method further includes: In response to using the second bottle group to perform hydrogenation, detecting a pressure value of the first region and a pressure value of the second region of the second bottle group; If the pressure value of the first area is less than the second pressure threshold, inflating the first area to the second pressure value; If the pressure value of the second area is less than the third pressure threshold, inflating the second area to the third pressure value; The second pressure threshold is smaller than the third pressure threshold, and the second pressure value is smaller than the third pressure value.

[0053] In this embodiment, the first region is a low-pressure region, and the second region is a high-pressure region, both of which reflect the hydrogen storage status and supply capacity of the corresponding regions.

[0054] The second pressure threshold is a pre-set critical pressure value, which is used to determine whether the pressure in the first area needs to be supplemented with hydrogen. When the pressure value in the first area is lower than this threshold, a charging operation needs to be performed.

[0055] The third pressure threshold is a critical pressure value for judging whether the second area needs to be inflated, and its value is greater than the second pressure threshold. The second pressure value is the target pressure value to be achieved by inflating the first area, which is less than the third pressure value. The third pressure value is the target pressure value to which the second area is inflated, which is used to ensure that the second area has sufficient pressure and hydrogen supply during the hydrogenation process. In addition, when the pressure value of the first area meets the second pressure value, and the pressure value of the second area meets the third pressure value, the inflation operation can be stopped, for example, the compressor and the switch valve between the compressor and the second bottle group are turned off.

[0056] During the hydrogenation control process, if you choose to use the second bottle group for hydrogenation operation, you need to detect the pressure of different areas in the second bottle group. For the first area, if its pressure value is less than the second pressure threshold, then the inflation program should be started to increase the pressure of the area to the second pressure value to ensure that it can normally participate in the hydrogenation process or maintain its own stable state. For the second area, when it is detected that its pressure value is less than the third pressure threshold, the inflation operation should also be performed to make its pressure reach the third pressure value, so as to meet the hydrogenation demand or system operation requirements.

[0057] It can be concluded from the above that this embodiment achieves precise control of the hydrogenation process by carefully monitoring the pressure values ​​of different areas (the first area and the second area) of the second bottle group and setting the corresponding pressure thresholds and inflation target values. Among them, the second pressure threshold and the corresponding second pressure value are lower than the third pressure threshold and the third pressure value, which not only ensures the safety of the hydrogenation process, but also effectively avoids energy waste or equipment damage caused by over-inflation. This embodiment not only improves the hydrogenation efficiency, but also enhances the stability and reliability of the system.

[0058] In one embodiment of the present disclosure, a target hydrogenation control strategy is determined from a plurality of hydrogenation control strategies based on a target hydrogenation demand, including: Determining state space characteristics based on target hydrogenation demand; determining an action space characteristic of each hydrogenation control strategy based on each hydrogenation control strategy; The state space features and action space features are input into the target deep Q network model to obtain the target hydrogenation control strategy; the target deep Q network model is obtained by improving the deep Q network model according to the reference state space features and reference action space features.

[0059] In this embodiment, the state space characteristics are a set of various parameters related to the hydrogenation process, such as the pressure values ​​of each bottle group, the pressure values ​​of the on-board gas cylinders, the operating status of the compressor, and the opening and closing status of the valves, etc., which are digitally encoded to form the state vector of the target deep Q network model. The above status information can comprehensively reflect the current operating status of the hydrogenation station.

[0060] The action space characteristics correspond to each hydrogenation control strategy, which is the collective characteristics of various actions taken by the strategy during the hydrogenation process, such as starting or stopping a compressor, opening or closing a valve, and adjusting its opening degree. The design of the action space should cover all possible control operations to ensure that the model has sufficient ability to regulate the hydrogenation process.

[0061] The target Deep Q-Network (DQN) model is a reinforcement learning model based on deep learning. It is obtained by improving and training the original DQN model using reference state feature space features and reference action space features. It can learn the optimal hydrogenation control strategy based on the input reference state space features and reference action space features.

[0062] The reference state space features and reference action space features are a large amount of known hydrogenation system states and corresponding control action data used in the model training process, which are used to train and optimize the DQN model so that it can adapt to the task requirements of hydrogenation control and thus determine the target hydrogenation control strategy.

[0063] Specifically, the step of determining a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on the target hydrogenation demand may be as follows: Firstly, according to the determined target hydrogenation demand, the state space characteristics of the related hydrogenation process are extracted. The above characteristics can comprehensively describe the specific situation of the current hydrogenation task.

[0064] Then, for each optional hydrogenation control strategy, its corresponding action space characteristics are determined, that is, the characteristics of various operating actions that may be involved in the execution of the strategy.

[0065] Finally, the extracted state space features and the action space features of each hydrogenation control strategy are input into the improved DQN model. Based on previous training and learning, this model will analyze and process the input features to output the target hydrogenation control strategy that best suits the current target hydrogenation demand, so as to achieve efficient and safe hydrogenation control.

[0066] It can be concluded from the above that this embodiment determines the target hydrogenation control strategy through the target DQN model, which can achieve efficient optimization selection and precise matching. This embodiment accurately captures the state space characteristics of the target hydrogenation demand and matches it with the action space characteristics of multiple hydrogenation control strategies. It uses the improved target deep Q network model for intelligent decision-making and can efficiently select the optimal solution from many strategies. It not only ensures the accuracy and stability of the hydrogenation process, but also significantly improves the efficiency and flexibility of hydrogenation control.

[0067] In one embodiment of the present disclosure, a hydrogenation control method further includes: Determine a reference Q value based on a reference state space feature and a reference action space feature; A target deep Q network model is determined based on the reference Q value.

[0068] In one embodiment of the present disclosure, determining a reference Q value based on a reference state space feature and a reference action space feature includes: A reference Q-value is determined based on a reference state space feature, a reference action space feature, a reward function, a discount factor, and an eligibility trace decay factor.

[0069] In this embodiment, the reference state space features are feature representations of a large number of known hydrogenation process states used in the model training process. The above features include various key information in the hydrogenation process, such as bottle group pressure, vehicle-mounted gas bottle pressure, equipment operating status, etc., which are used to provide basic data for model training.

[0070] The reference action space features correspond to the reference state space features. They are a set of features of various control actions taken under these known states, including descriptions of actions such as starting or stopping the compressor, switching valves, and adjusting valve openings. They are an important basis for model learning decisions.

[0071] The reward function is used to give a corresponding reward value according to the actual performance of the hydrogenation process after taking a certain action (i.e., the hydrogenation control strategy). The size of the reward value reflects the degree of benefit of the action in achieving the hydrogenation goal. For example, if an action can make the hydrogenation process more efficient and safe, it will get a higher positive reward; conversely, if it leads to adverse consequences such as abnormal pressure or inefficiency, it will get a negative reward.

[0072] The discount factor ranges from 0 to 1 and is used to measure the importance of future rewards to current decisions. A discount factor close to 1 means that the agent attaches more importance to long-term cumulative rewards and considers the impact of current actions on a series of future states and rewards; a discount factor close to 0 makes the agent pay more attention to the current immediate rewards and make decisions more inclined to actions that can bring high returns in the short term.

[0073] The eligibility trace decay factor ranges from 0 to 1, and determines the degree of influence of past experience on current learning. A larger eligibility trace decay factor allows the model to consider relatively distant past experience more in the learning process such as calculating Q value, which helps to capture long-term dependencies in the environment; a smaller eligibility trace decay factor makes the model focus more on recent experience and can adapt to immediate changes in the environment more quickly.

[0074] The reference Q value is a value calculated using information such as reference state space characteristics, reference action space characteristics, reward function, discount factor, and eligibility trace decay factor. It represents the estimated value of the expected cumulative reward for taking the corresponding reference action under a given reference state and is a key indicator for training the DQN model.

[0075] The target DQN model is the final model obtained after training and optimization using the reference state space features, reference action space features and related parameters. It can accurately output the optimal hydrogenation control strategy, namely the target hydrogenation control strategy, according to the actual hydrogenation system state and action requirements.

[0076] During the DQN model training phase, for each set of known reference state space features and the corresponding reference action space features, a reference Q value is calculated according to an improved algorithm based on the Bellman equation, combined with a pre-set reward function, discount factor, and eligibility trace decay factor. The reference Q value reflects the expected value of taking the reference action under the reference state, providing a goal and direction for the learning and optimization of the model.

[0077] In this embodiment, a large number of reference Q values ​​calculated by a large amount of reference state and action data are used as samples for training the DQN model. The DQN model continuously adjusts its own parameters during the training process so that its predicted Q value is as close as possible to these reference Q values. After multiple iterations and optimizations, a target DQN model that can accurately predict the Q value and output the optimal hydrogenation control strategy is finally obtained.

[0078] The calculation formula of reference Q value is as follows:

[0079] in, represents the current reference state space characteristics, represents the reference action space feature, Indicates that the agent is in state Take Action The reference Q value, Indicates that the agent is in state Take Action The reward value immediately obtained after Represents the discount factor, ranging from 0 to 1. Represents the qualification trace attenuation factor, ranging from 0 to 1. Indicates that the agent takes action After transferring to the new state, In the new state Under this condition, the agent takes all possible actions The Q value corresponding to the action with the largest median value is, is the set number of time steps, indicating the scope of considering past experience.

[0080] The calculation formula of the reference Q value not only takes into account the immediate reward after the current state transfer and the optimal Q value estimate for the next step, but also takes into account the Q value information of the state-action pair within a certain number of steps in the past through the qualification trace. This helps to utilize more historical information during the training process, allowing the agent to better capture the dynamics and long-term dependencies of the environment during the learning process, especially in environments with delayed rewards or complex time series characteristics, which can improve learning efficiency and decision quality.

[0081] In the hydrogenation control scenario, the working mechanism of the DQN model is as follows: First, the input of the DQN model is the reference state space feature, which fully describes the current state of the hydrogen refueling station. For example, the pressure value of the first bottle group, the pressure value of the second bottle group, the pressure value of different areas of the second bottle group, the pressure value of the onboard gas cylinder, the operating status of the compressor, the opening and closing status of the valve, and the opening degree. The above information constitutes a multidimensional vector as the input of the DQN model, enabling the model to understand the real-time situation of the hydrogen refueling station.

[0082] Secondly, for each hydrogenation control strategy, there is a corresponding reference action space feature. The action space covers all possible operations in the hydrogenation process, such as starting or stopping a specific compressor, opening or closing different valves, and adjusting the opening of the valves. The task of the DQN model is to select the best one from these possible actions under a given state.

[0083] Then, in the training phase, a large amount of reference state space feature and reference action space feature data is required. These data come from historical hydrogenation operation records or a large number of experiments in a simulated environment. The DQN model adjusts its own parameters by continuously learning on these data. Specifically, the DQN model selects an action based on the current state, and after executing the action, a reward feedback and a new state will be obtained. For example, if the selected action can make the hydrogenation process more efficient and safe, such as quickly increasing the pressure of the onboard gas cylinder and maintaining a stable state, a higher positive reward will be obtained; conversely, if it causes abnormal pressure or inefficiency, a negative reward will be obtained. The model uses these reward information and new states to update its own Q value estimate through algorithms such as the Bellman equation. This embodiment improves the Q value, which represents the expected cumulative reward for taking an action under a specific state. After a large number of training iterations, the DQN model gradually learns the strategy of selecting the optimal action under different states, so that it can accurately output the target hydrogenation control strategy according to the actual state of the hydrogenation system.

[0084] Finally, the trained and improved DQN model is used as the target DQN model.

[0085] From the above, it can be concluded that this embodiment introduces reference state space characteristics and reference action space characteristics to determine the reference Q value, making the hydrogenation process more precise and controllable, and improving the accuracy and stability of the control. Secondly, the reference Q value is calculated by combining the reward function, discount factor and qualification trace attenuation factor, which can comprehensively consider various factors in the hydrogenation process and optimize the control strategy. Finally, the target DQN model is determined based on the reference Q value, which provides strong support for the intelligent control of the hydrogenation process, helps to achieve more efficient and safer hydrogenation operations, and improves overall performance and reliability.

[0086] In one embodiment of the present disclosure, a hydrogenation control method further includes: Determine a reward function based on hydrogenation efficiency, hydrogenation energy consumption, and safety factor scores; Adjust the discount factor based on the overall efficiency of hydrogenation; Adjust the qualification trace decay factor based on the impact of historical experience factors.

[0087] In this embodiment, the hydrogenation efficiency is measured by indicators such as the amount of hydrogen added to the on-board gas cylinder per unit time during the hydrogenation process, or the time required to increase the pressure of the on-board gas cylinder to the target value. It can reflect the speed of the hydrogenation operation. The higher the efficiency, the more likely it is that the hydrogenation demand can be met in a shorter time.

[0088] Hydrogenation consumption refers to the energy consumed in the hydrogenation process, such as the electrical energy consumed by the operation of the compressor, etc. It is expressed as the energy consumption per unit of hydrogen refueling. The lower the energy consumption, the lower the hydrogenation cost and the more reasonable the resource utilization.

[0089] The safety factor score is used to quantify the safety of the hydrogenation process. Many factors are considered, such as whether the pressure is stable within the safety range during the hydrogenation process, whether the temperature rises abnormally, and whether there are hidden dangers of failure of valves and other equipment. The higher the score, the safer and more reliable the hydrogenation process is. A score close to 1 is an ideal safety state, and the closer to 0, the higher the risk.

[0090] Therefore, the reward function is calculated as:

[0091]

[0092] in, Represents the reward value, Both represent weight coefficients, which are used to adjust the relative importance of different factors in the reward function; represents the desired hydrogenation time, Indicates the actual hydrogenation time, The hydrogenation efficiency is Indicates the preset minimum energy consumption value, Indicates the actual hydrogenation energy consumption, represents the pre-set safety factor score, Indicates the actual safety factor score, ranging from 0 to 1.

[0093] Specifically, the actual safety factor score can be determined as follows: First, determine the pressure safety factor score based on the pressure fluctuation range.

[0094] This embodiment uses a pressure sensor to monitor the pressure changes of each bottle group of the vehicle-mounted gas cylinder and the hydrogen filling machine and the connected equipment in real time. For example, if the pressure fluctuation range is within ±0.5MPa, it is a safe and good state, and the fluctuation within ±1MPa is a basically safe state, and the safety risk increases when it exceeds ±1MPa. The corresponding score ratio can be determined according to the actual fluctuation range. Assuming that the score is 0.6 within ±0.5MPa, and 0.1 points are deducted for every 0.1MPa exceeding, then when the fluctuation is ±0.8MPa, the score is 0.3, and the minimum score is 0.

[0095] Second, determine the temperature safety factor score based on the operating temperature.

[0096] In this embodiment, the temperature of equipment (such as compressors, valves, etc.) is monitored by temperature sensors. Assuming that the normal operating temperature of the equipment is between 40-60°C, if the temperature exceeds this range, it means that the equipment may be abnormal. Assuming that the temperature is within the normal range, 0.2 points are awarded, and 0.05 points are deducted for every 5°C exceeding the range, and the minimum score is 0 points.

[0097] Third, determine the equipment status safety factor score based on whether there are any faults in the equipment operation.

[0098] 0.1 point is awarded for normal operation of the equipment and 0 point is awarded for equipment failure.

[0099] Fourth, determine the hydrogen safety factor score based on whether there is a hydrogen leak.

[0100] If no hydrogen leakage is detected, 0.1 point will be awarded; if a hydrogen leakage is detected, 0 point will be awarded.

[0101] Fifth, the pressure safety factor score, temperature safety factor score, equipment status safety factor score and hydrogen safety factor score are added together to obtain the actual safety factor score.

[0102] The reward function is the key to guiding the model to learn the optimal strategy in reinforcement learning. According to the performance of the hydrogenation station after taking actions in different states, such as hydrogenation efficiency, hydrogenation energy consumption and safety factor score, corresponding reward values ​​are given. The DQN model will tend to choose actions that can obtain high rewards to achieve better hydrogenation control.

[0103] In this embodiment, the overall hydrogenation efficiency includes the hydrogenation efficiency in the first time period and the hydrogenation efficiency in the second time period, and the first time period is less than the second time period; Adjust the discount factor based on the overall efficiency of hydrogenation, including: If the overall hydrogenation efficiency is the hydrogenation efficiency in the first time period, then the reference value of the discount factor is reduced based on the first frequency step to obtain a first discount factor; If the overall hydrogenation efficiency is the hydrogenation efficiency in the second time period, the reference value of the discount factor is increased based on the first frequency step to obtain a second discount factor; The first discount factor is smaller than the second discount factor.

[0104] The reference value of the discount factor is the initial discount factor. The hydrogenation efficiency in the first time period indicates that the overall efficiency of hydrogenation takes short-term efficiency into consideration and pays more attention to immediate rewards. At this time, it is necessary to reduce the initial discount factor (i.e. the reference value of the discount factor) and adjust the initial discount factor according to the change trend in the first time period to obtain the first discount factor.

[0105] The hydrogenation efficiency in the second time period indicates that the overall efficiency of hydrogenation takes into account long-term efficiency and pays more attention to long-term accumulated rewards. At this time, it is necessary to increase the initial discount factor and adjust the initial discount factor according to the changing trend of the second time period to obtain the second discount factor.

[0106] The discount factor is used in reinforcement learning algorithms (such as DQN) to weigh the importance of current rewards and future rewards. It takes a value between 0 and 1. When it is close to 1, the model decision focuses more on long-term cumulative rewards, and when it is close to 0, it focuses more on immediate rewards. Adjustment based on the overall efficiency of hydrogenation can make the model decision adapt to the characteristics of the hydrogenation process.

[0107] The impact value of the historical experience factor represents the degree to which the experience information such as a series of states, actions and corresponding results in past hydrogenation operations affects the current hydrogenation decision, reflecting the importance of historical experience in the current learning process. Adjusting the qualification trace attenuation factor accordingly can enable the model to make reasonable use of historical experience.

[0108] Adjust the qualification decay factor based on the impact of historical experience factors, including: If the influence value of the historical experience factor is greater than or equal to the first influence threshold, increasing the reference value of the qualification trace attenuation factor based on the second frequency step to obtain a first qualification trace attenuation factor; If the influence value of the historical experience factor is less than the first influence threshold, the reference value of the qualification trace attenuation factor is reduced based on the second frequency step to obtain a second qualification trace attenuation factor; The first qualification trace attenuation factor is greater than the second qualification trace attenuation factor. The first impact threshold can be dynamically adjusted according to actual conditions.

[0109] When the influence value of the historical experience factor is greater than or equal to the first influence threshold, it indicates that the agent will consider relatively distant past experience more in the learning process such as calculating the Q value, so that the long-term behavior sequence and state transition information can continue to have an impact on the current decision, which helps to capture the long-term dependencies and complex dynamics in the environment.

[0110] When the influence value of the historical experience factor is less than the first influence threshold, the agent focuses more on recent experience and can adapt to immediate changes in the environment more quickly, but will ignore some long-term potential rules.

[0111] The impact of historical experience factors can be determined based on time range and frequency. First, the total number of hydrogenation operations within a specific time window (such as the past month or quarter) is counted. , and the number of hydrogenation operations similar to the current hydrogenation scenario (e.g. same vehicle type, similar starting and target pressures, etc.) within this time window The impact of historical experience factors It can be calculated by For example, if 100 hydrogen refueling operations were performed in the past month, and 30 of them were for the current model with a starting pressure in a similar range, then .

[0112] The eligibility trace decay factor determines the weight of the influence of past experience on current learning. Its value ranges from 0 to 1. A value close to 1 makes the model refer more to distant past experience and capture long-term dependencies; a value close to 0 focuses on recent experience and quickly adapts to immediate changes.

[0113] From the above, it can be concluded that this embodiment realizes the optimization goal orientation of the hydrogenation process and improves the comprehensive benefits of the hydrogenation operation by designing a reward function that comprehensively considers hydrogenation efficiency, energy consumption and safety factor. At the same time, the discount factor is dynamically adjusted according to the overall efficiency of hydrogenation, which can flexibly respond to different working conditions and ensure the long-term effectiveness of the strategy. In addition, the introduction of historical experience factors to adjust the qualification trace attenuation factor fully utilizes past data and enhances the system's adaptive ability and decision-making accuracy. This embodiment significantly improves the intelligence level of hydrogenation control and ensures the high efficiency, energy saving and safety of the hydrogenation process.

[0114] A hydrogenation control method corresponding to the above embodiment, Figure 2 This is a structural block diagram of a hydrogenation control device provided in one embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The hydrogenation control device 20 includes: a hydrogenation demand determination module 21, a control strategy determination module 22 and a hydrogenation control module 23.

[0115] The hydrogenation demand determination module 21 is used to determine the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder; A control strategy determination module 22, configured to determine a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on a target hydrogenation demand, wherein the hydrogenation control accuracies of the plurality of hydrogenation control strategies are different; The hydrogenation control module 23 is used to control the hydrogenation of the vehicle-mounted gas cylinder based on the target hydrogenation control strategy.

[0116] In one embodiment of the present disclosure, the basic information includes a pressure value of the first bottle group, and the pressure information includes a pressure value of the vehicle-mounted gas bottle; The hydrogenation demand determination module 21 is specifically used for: In response to the first bottle group pressure value being greater than the onboard gas bottle pressure value, calculating a pressure difference between the first bottle group pressure value and the onboard gas bottle pressure value; If the pressure difference is greater than the pressure difference threshold, the first hydrogenation demand is used as the target hydrogenation demand; If the pressure difference is less than or equal to the pressure difference threshold, the second hydrogenation demand is used as the target hydrogenation demand; The number of control devices for the first hydrogenation demand and the second hydrogenation demand is different.

[0117] In one embodiment of the present disclosure, a hydrogenation control device 20 further includes: a pressure detection module; A pressure detection module, configured to detect a pressure value of a first region and a pressure value of a second region of the second bottle group in response to using the second bottle group for hydrogenation; If the pressure value of the first area is less than the second pressure threshold, inflating the first area to the second pressure value; If the pressure value of the second area is less than the third pressure threshold, inflating the second area to the third pressure value; The second pressure threshold is smaller than the third pressure threshold, and the second pressure value is smaller than the third pressure value.

[0118] In one embodiment of the present disclosure, the control strategy determination module 22 is specifically configured to: Determining state space characteristics based on target hydrogenation demand; determining an action space characteristic of each hydrogenation control strategy based on each hydrogenation control strategy; The state space features and action space features are input into the target deep Q network model to obtain the target hydrogenation control strategy; the target deep Q network model is obtained by improving the deep Q network model according to the reference state space features and reference action space features.

[0119] In one embodiment of the present disclosure, a hydrogenation control device 20 further includes: a model building module; A model building module for determining a reference Q value based on a reference state space feature and a reference action space feature; A target deep Q network model is determined based on the reference Q value.

[0120] In one embodiment of the present disclosure, the model building module is specifically used to: A reference Q-value is determined based on a reference state space feature, a reference action space feature, a reward function, a discount factor, and an eligibility trace decay factor.

[0121] In one embodiment of the present disclosure, the model building module is further used to: Determine a reward function based on hydrogenation efficiency, hydrogenation energy consumption, and safety factor scores; Adjust the discount factor based on the overall efficiency of hydrogenation; Adjust the qualification trace decay factor based on the impact of historical experience factors.

[0122] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0123] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0124] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0125] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0126] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of a hydrogenation control method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0127] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0128] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0129] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0131] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0133] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0134] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A hydrogenation control method, characterized in that: include: Determine the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder; Determining a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on the target hydrogenation demand, wherein the plurality of hydrogenation control strategies have different hydrogenation control accuracies; The hydrogenation of the vehicle-mounted gas cylinder is controlled based on the target hydrogenation control strategy.

2. A hydrogenation control method according to claim 1, characterized in that: The basic information includes the pressure value of the first bottle group, and the pressure information includes the pressure value of the vehicle-mounted gas bottle; The method of determining the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder includes: In response to the first bottle group pressure value being greater than the vehicle-mounted gas bottle pressure value, calculating a pressure difference between the first bottle group pressure value and the vehicle-mounted gas bottle pressure value; If the pressure difference is greater than the pressure difference threshold, the first hydrogenation demand is used as the target hydrogenation demand; If the pressure difference is less than or equal to the pressure difference threshold, taking the second hydrogenation demand as the target hydrogenation demand; The number of control devices for the first hydrogenation demand and the number of control devices for the second hydrogenation demand are different.

3. A hydrogenation control method according to claim 2, characterized in that: Also includes: In response to using the second bottle group to perform hydrogenation, detecting a pressure value of the first region and a pressure value of the second region of the second bottle group; If the pressure value of the first area is less than the second pressure threshold, inflating the first area to the second pressure value; If the pressure value of the second area is less than a third pressure threshold, inflating the second area to the third pressure value; The second pressure threshold is smaller than the third pressure threshold, and the second pressure value is smaller than the third pressure value.

4. A hydrogenation control method according to claim 1, characterized in that: The determining a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on the target hydrogenation demand comprises: determining a state space characteristic based on the target hydrogenation demand; determining an action space characteristic of each hydrogenation control strategy based on each hydrogenation control strategy; The state space characteristics and the action space characteristics are input into a target deep Q network model to obtain the target hydrogenation control strategy; the target deep Q network model is obtained by improving the deep Q network model according to the reference state space characteristics and the reference action space characteristics.

5. A hydrogenation control method according to claim 4, characterized in that: Also includes: Determine a reference Q value based on the reference state space feature and the reference action space feature; A target deep Q network model is determined based on the reference Q value.

6. A hydrogenation control method according to claim 5, characterized in that: The determining of a reference Q value based on the reference state space feature and the reference action space feature comprises: A reference Q value is determined based on the reference state space feature, the reference action space feature, a reward function, a discount factor, and an eligibility trace decay factor.

7. A hydrogenation control method according to claim 6, characterized in that: Also includes: Determining the reward function based on hydrogenation efficiency, hydrogenation energy consumption and safety factor score; adjusting the discount factor based on the overall efficiency of hydrogenation; The qualification trace decay factor is adjusted based on the impact value of historical experience factors.

8. A hydrogenation control device, characterized in that: include: A hydrogenation demand determination module is used to determine the target hydrogenation demand based on the basic information of the hydrogenation machine and the pressure information of the onboard gas cylinder; A control strategy determination module, configured to determine a target hydrogenation control strategy from a plurality of hydrogenation control strategies based on the target hydrogenation demand, wherein the plurality of hydrogenation control strategies have different hydrogenation control accuracies; A hydrogenation control module is used to control the hydrogenation of the vehicle-mounted gas cylinder based on the target hydrogenation control strategy.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images