Fuel cell control methods, devices, computer-readable storage media, and vehicles

Abstract

This invention discloses a fuel cell control method, apparatus, computer-readable storage medium, and vehicle. The method includes: acquiring a historical power demand sequence of a target object, wherein the target object is equipped with a fuel cell, and the historical power demand sequence includes multiple historical power demands of the target object, each corresponding to a first moment within a first preset time period prior to the current moment; processing the historical power demand sequence to predict a target power demand sequence, wherein the target power demand sequence includes multiple target power demands of the fuel cell, each corresponding to a second moment within a second preset time period after the current moment; and controlling the fuel cell to operate according to the target power demand sequence. This invention solves the technical problem of power supply delay during fuel cell operation in the prior art.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicles, and more specifically, to a fuel cell control method, apparatus, computer-readable storage medium, and vehicle. Background Technology

[0002] With the growing popularity of environmental protection and green travel, more and more automakers are adopting hydrogen-oxygen fuel cells instead of traditional gasoline and diesel engines to power their vehicles. This is because hydrogen-oxygen fuel cells have a high energy conversion rate, providing better power to vehicles; and they do not produce large amounts of carbon oxides that pollute the air. However, fuel cells may be limited by the vehicle's control system, and their ability to adapt well to sudden changes in vehicle conditions can lead to delays in energy delivery.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a fuel cell control method, apparatus, computer-readable storage medium, and vehicle to at least solve the technical problem of power supply delay during fuel cell operation in the prior art.

[0005] According to one aspect of the present invention, a fuel cell control method is provided, comprising: acquiring a historical power demand sequence of a target object, wherein the target object is equipped with a fuel cell, and the historical power demand sequence includes: multiple historical power demands of the target object, each of the multiple historical power demands corresponding one-to-one with multiple first moments within a first preset time period prior to the current moment; processing the historical power demand sequence to predict a target power demand sequence, wherein the target power demand sequence includes: multiple target power demands of the fuel cell, each of the multiple target power demands corresponding one-to-one with multiple second moments within a second preset time period after the current moment; and controlling the fuel cell to operate according to the target power demand sequence.

[0006] Optionally, processing the historical demand power sequence to predict the target demand power sequence includes: processing the historical demand power sequence using a first prediction model to obtain a predicted demand power sequence, wherein the predicted demand power sequence includes: multiple predicted demand powers of the target object, each of which corresponds one-to-one with multiple second time points; obtaining target power parameters corresponding to the target time point within a second preset time period, wherein the target time point is any one of the multiple second time points, the time interval between the multiple second time points is a preset interval, and the target power parameters include: the target state of charge of the fuel cell and the target average demand power of the target object; processing the target power parameters corresponding to the target time point and the predicted demand power corresponding to the target time point to obtain the target demand power corresponding to the target time point; and obtaining the target demand power sequence based on the target demand power corresponding to the multiple time points.

[0007] Optionally, obtaining the target power parameters corresponding to the target time within the second preset time period includes: obtaining the target demand power corresponding to the historical time, the historical state of charge corresponding to the historical time, and the historical average demand power corresponding to the historical time, wherein the historical time is the time preceding the target time among multiple second times; obtaining the target state of charge based on the target demand power corresponding to the historical time and the historical state of charge; and obtaining the target average demand power corresponding to the target time based on the predicted demand power corresponding to the target time and the historical average demand power.

[0008] Optionally, the target power parameters and the predicted demand power at the target time are processed to obtain the target demand power at the target time, including: obtaining a first power algorithm at the target time based on the target state of charge and the target average demand power; using the first power algorithm to determine the power consumption corresponding to different demand powers of the fuel cell; and determining the demand power corresponding to the minimum power consumption as the target demand power.

[0009] Optionally, based on the target state of charge and the target average power demand, a first power algorithm corresponding to the target time is obtained, including: obtaining a first operator in the first power algorithm based on the target average power demand and a preset constant; determining the time difference between the target time and the end time of the second time period; obtaining a second operator in the first power algorithm based on the target state of charge, the state of charge corresponding to the current time, and the time difference; and obtaining the first power algorithm based on the first operator, the second operator, the target state of charge, the target average power demand, and the instantaneous hydrogen consumption of the fuel cell at the target time.

[0010] Optionally, based on the target demand power corresponding to multiple time points, a target demand power sequence is obtained, including: in response to determining the target demand power corresponding to the target time point, determining the target power change; based on the target demand power corresponding to historical time points and the target power change, updating the target demand power corresponding to the target time point to obtain the update result corresponding to the target time point; and based on the update results corresponding to multiple time points, obtaining the target demand power sequence.

[0011] Optionally, before obtaining the historical demand power sequence of the target object, the method further includes: obtaining the historical operating information of the target object within a first preset time period; and processing the historical operating information to obtain the historical demand power sequence.

[0012] According to another aspect of the present invention, a fuel cell control device is also provided, comprising: a first acquisition module for acquiring a historical power demand sequence of a target object, wherein the target object is equipped with a fuel cell, and the historical power demand sequence includes: multiple historical power demands of the target object, each of the multiple historical power demands corresponding one-to-one with multiple first moments within a first preset time period prior to the current moment; a first prediction module for processing the historical power demand sequence to predict a target power demand sequence, wherein the target power demand sequence includes: multiple target power demands of the fuel cell, each of the multiple target power demands corresponding one-to-one with multiple second moments within a second preset time period after the current moment; and a first control module for controlling the fuel cell to operate according to the target power demand sequence.

[0013] Optionally, the first prediction module includes: a first determining unit, used to process the historical demand power sequence using a first prediction model to obtain a predicted demand power sequence, wherein the predicted demand power sequence includes: multiple predicted demand powers of the target object, and the multiple predicted demand powers correspond one-to-one with multiple second time points; a first obtaining unit, used to obtain the target power parameters corresponding to the target time point within a second preset time period, wherein the target time point is any one of the multiple second time points, the time interval between the multiple second time points is a preset interval, and the target power parameters include: the target state of charge of the fuel cell and the target average demand power of the target object; a second determining unit, used to process the target power parameters corresponding to the target time point and the predicted demand power corresponding to the target time point to obtain the target demand power corresponding to the target time point; and a third determining unit, used to obtain the target demand power sequence based on the target demand power corresponding to the multiple time points.

[0014] Optionally, the first acquisition unit includes: a first acquisition subunit, used to acquire the target demand power corresponding to a historical time, the historical state of charge corresponding to a historical time, and the historical average demand power corresponding to a historical time, wherein the historical time is the time preceding the target time among a plurality of second times; a first determination subunit, used to obtain the target state of charge based on the target demand power corresponding to the historical time and the historical state of charge; and a second determination subunit, used to obtain the target average demand power corresponding to the target time based on the predicted demand power corresponding to the target time and the historical average demand power.

[0015] Optionally, the second determining unit includes: a third determining subunit, used to obtain a first power algorithm corresponding to the target time based on the target state of charge and the target average demand power; a fourth determining subunit, used to determine the power consumption corresponding to different demand power of the fuel cell using the first power algorithm; and a fifth determining subunit, used to determine the demand power corresponding to the minimum power consumption as the target demand power.

[0016] Optionally, the third determining subunit is further configured to: obtain a first operator in the first power algorithm based on the target average demand power and a preset constant; determine the time difference between the target time and the end time of the second time period; obtain a second operator in the first power algorithm based on the target state of charge, the state of charge corresponding to the current time, and the time difference; and obtain the first power algorithm based on the first operator, the second operator, the target state of charge, the target average demand power, and the instantaneous hydrogen consumption of the fuel cell at the target time.

[0017] Optionally, the third determining unit includes: a sixth determining subunit, used to determine the target power change in response to the target demand power corresponding to the determined target time; a first updating subunit, used to update the target demand power corresponding to the target time based on the target demand power corresponding to the historical time and the target power change, to obtain the update result corresponding to the target time; and a seventh determining subunit, used to obtain the target demand power sequence based on the update results corresponding to multiple times.

[0018] Optionally, the device further includes: a second acquisition module for acquiring historical operating information of the target object within a first preset time period; and a first determination module for processing the historical operating information to obtain a historical demand power sequence.

[0019] According to another aspect of the present invention, a computer-readable storage medium is also provided, including a stored program, wherein, when the program is executed, the device on which the computer-readable storage medium is located executes the fuel cell control method of any one of the above-mentioned methods.

[0020] According to another aspect of the present invention, a processor is also provided, wherein the processor's program executes any of the above-described fuel cell control methods.

[0021] According to another aspect of the present invention, a target vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to perform the fuel cell control method of any one of the above.

[0022] In this embodiment of the invention, the following methods are employed: acquiring the historical power demand sequence of the target object; processing the historical power demand sequence to predict the target power demand sequence; and controlling the fuel cell to operate according to the target power demand sequence. By predicting the target power demand sequence of the fuel cell in the future period based on the historical power demand sequence of the target object in the previous period at the current time, and combining vehicle-specific factors, the accuracy and efficiency of the prediction are improved. This enables the fuel cell to operate in a timely manner according to the target power demand sequence, thereby reducing the operating delay caused by sudden changes in the vehicle and limitations of the vehicle system, and thus solving the technical problem of power supply delay during fuel cell operation in the prior art. Attached Figure Description

[0023] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0024] Figure 1 This is a flowchart illustrating a fuel cell control method according to an embodiment of the present invention;

[0025] Figure 2 This is a flowchart illustrating a demand power processing method according to an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of a demand power hierarchical optimization system according to an embodiment of the present invention;

[0027] Figure 4 This is a structural block diagram of a fuel cell control device according to an embodiment of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Unlike traditional vehicles that use engines as their primary power system, fuel cells convert chemical energy into electrical energy through chemical reactions within the fuel cell stack to provide power to the vehicle. The most common hydrogen-oxygen fuel cell uses hydrogen as fuel and oxygen as an oxidant to provide power to the vehicle through the reverse process of electrolysis. It ultimately produces water, which greatly avoids air pollution. At the same time, due to its high conversion efficiency, it is one of the most preferred fuel cells currently available.

[0031] However, the efficiency of fuel cell systems in vehicles is greatly limited by changes in power demand. Their slow dynamic response often prevents fuel cells from adjusting their power supply in a timely manner according to changes in vehicle operation, which may lead to insufficient power supply or wasted energy resources.

[0032] Example 1

[0033] According to an embodiment of the present invention, a method embodiment for controlling a fuel cell is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] Figure 1 This is a flowchart illustrating a fuel cell control method according to an embodiment of the present invention, such as... Figure 1As shown, the method includes the following steps:

[0035] Step S102: Obtain the historical power demand sequence of the target object.

[0036] The target object is equipped with a fuel cell, and the historical power demand sequence includes: multiple historical power demands of the target object, and each of the multiple historical power demands corresponds one-to-one with multiple first moments within the first preset time period before the current moment.

[0037] The aforementioned target objects can refer to tools with fuel cell systems, such as vehicles, yachts, aerospace and underwater equipment.

[0038] To ensure the correlation between the fuel cell and the target object itself, thereby reducing the power supply delay of the fuel cell due to system limitations, we can first obtain the historical power demand sequence of the target object, that is, obtain the power demand sequence required by the target object during the period before the current moment.

[0039] Optionally, obtaining the historical demand power sequence of the target object includes: obtaining the historical operating information of the target object within a first preset time period; and processing the historical operating information to obtain the historical demand power sequence.

[0040] The aforementioned historical operating information can refer to the target object's driving speed, operating consumption statistics, etc. After obtaining the target object's historical operating information, it can be processed to obtain the historical power demand sequence. For ease of distinction, let N be used. H This represents the first preset time period mentioned above, where k represents the current time, and P... req [kN H [k-1] represents the historical power demand mentioned above.

[0041] In one optional embodiment, a vehicle energy flow model can be used to process the aforementioned historical operating information. The specific method of using the vehicle energy flow model can be found in the prior art and will not be described in detail here.

[0042] Step S104: Process the historical demand power sequence to predict the target demand power sequence.

[0043] The target power demand sequence includes multiple target power demands of the fuel cell, and each of the multiple target power demands corresponds one-to-one with multiple second moments within a second preset time period after the current moment.

[0044] The aforementioned target power demand sequence is a predicted power supply operation sequence of the fuel cell over a future period. To improve the accuracy of the determined target power demand sequence, instead of calculating the entire sequence all at once, it can be broken down into multiple target power demands at different times within a future period and calculated separately. For ease of distinction, let N be the denominator. P P represents the second preset time period mentioned above. FCS [k,k+N P ] represents the above target power demand sequence.

[0045] In one optional embodiment, a hierarchical optimization method can be used to establish an upper-level control module and a lower-level control module. First, the upper-level control module processes the historical demand power sequence, and then inputs the processing result into the lower-level control module for secondary optimization to predict the target demand power sequence. The specific processing method is described below.

[0046] In one optional embodiment, the upper-level control module can be a power processing model based on the A-PMP (Adaptive Pontryagin minimum principle) algorithm, and the lower-level control module can be a dynamic response control model based on the MPC (Model Predictive Control) algorithm.

[0047] Step S106: Control the fuel cell to operate according to the target power demand sequence.

[0048] Once the target power demand sequence is predicted, the fuel cell can be controlled to operate according to the target power demand sequence, thereby improving the energy supply capacity to the target object.

[0049] Through the above steps, the historical power demand sequence of the target object is obtained; the historical power demand sequence is processed to predict the target power demand sequence; and the fuel cell is controlled to operate according to the target power demand sequence. By predicting the target power demand sequence of the fuel cell in the future period based on the historical power demand sequence of the target object in the previous period, and combining the vehicle's own factors, the accuracy and efficiency of the prediction are improved. This enables the fuel cell to operate in a timely manner according to the target power demand efficiency, thereby reducing the operating delay caused by sudden changes in the vehicle and limitations of the vehicle system, and thus solving the technical problem of power supply delay in the operation of fuel cells in the prior art.

[0050] Regarding the aforementioned step S104 Figure 2 This is a flowchart illustrating a demand power processing method according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0051] Step S202: The historical demand power sequence is processed using the first prediction model to obtain the predicted demand power sequence.

[0052] The predicted demand power sequence includes multiple predicted demand powers of the target object, and each predicted demand power corresponds one-to-one with multiple second time points.

[0053] The first prediction model mentioned above can refer to the power prediction model constructed by the BP (BackPropagation) neural network. For the specific construction method, please refer to the relevant literature, which will not be elaborated here.

[0054] Before using the aforementioned upper-level control model to process historical demand power, the first prediction model can be used to predict the target object's predicted demand power sequence for a future period based on the aforementioned historical demand power sequence, and then the target demand power sequence can be determined from the predicted demand power sequence.

[0055] Step S204: Obtain the target power parameters corresponding to the target time within the second preset time period.

[0056] The target time is any one of multiple second times, the time interval between the multiple second times is a preset interval, and the target power parameters include: the target state of charge of the fuel cell and the target average power demand of the target object.

[0057] The aforementioned target power parameters can refer to parameters used to determine the target power demand, and may include, but are not limited to, the target state of charge of the fuel cell at the target time, the target average power demand, etc.

[0058] In one optional embodiment, the second preset time period can be divided into multiple target times. The specific number of divisions and methods can be set according to the actual situation and are not specifically limited.

[0059] Step S206: Process the target power parameters and the predicted demand power at the target time to obtain the target demand power at the target time.

[0060] Based on the target power parameters corresponding to the determined target time, and the predicted demand power corresponding to the predicted demand power sequence at the target time predicted by the aforementioned first prediction model, the target demand power of the fuel cell at the target time can be determined using a preset algorithm.

[0061] In an optional embodiment, the above-mentioned preset algorithm may be:

[0062]

[0063] Where k can refer to the k-th target time after partitioning, and the above u * (k) can refer to the target power demand, u(k) can refer to the power demand that the fuel cell can output at the target time, H(SOC(k),u(k),k,λ(k)) can refer to the Hamiltonian function, and SOC(k) can refer to the target state of charge of the fuel cell at the target time. Generally, the Hamiltonian function can be:

[0064]

[0065] Wherein, λ(k) can refer to the target costate variable corresponding to the Hamiltonian function at the target time, and γ(SOC,k) can refer to the target penalty function corresponding to the Hamiltonian function at the target time that satisfies the definition of charge maintenance performance. It can refer to the instantaneous hydrogen consumption of the fuel cell at the target time, and Δt can refer to...

[0066] Step S208: Based on the target demand power corresponding to multiple time points, obtain the target demand power sequence.

[0067] After obtaining the target power demand corresponding to multiple target moments within a future period, these target power demands can be combined into a target power demand sequence.

[0068] Optionally, obtaining the target power parameters corresponding to the target time within the second preset time period includes: obtaining the target demand power corresponding to the historical time, the historical state of charge corresponding to the historical time, and the historical average demand power corresponding to the historical time, wherein the historical time is the time preceding the target time among multiple second times; obtaining the target state of charge based on the target demand power corresponding to the historical time and the historical state of charge; and obtaining the target average demand power corresponding to the target time based on the predicted demand power corresponding to the target time and the historical average demand power.

[0069] Specifically, the target power parameters of a fuel cell at a target time can be determined by the parameters corresponding to the previous target time, such as the historical state of charge and historical average power demand. In other words, when determining the target power demand of a fuel cell at a target time, it can be calculated one by one from the current time backward according to the divided target times.

[0070] The target power parameters mentioned above can be obtained using the following formula:

[0071] Calculate the target state of charge of the fuel cell at the target time:

[0072]

[0073] Where k represents the target time, k-1 represents the previous target time, and V oc R represents the open-circuit voltage that the fuel cell can provide. int This represents the internal resistance of the fuel cell, Q. batt This represents the total power output of the fuel cell.

[0074] Calculate the target average power demand of the fuel cell at the target time:

[0075]

[0076] Among them, the above P avg (k) can refer to the target average power demand, as mentioned above, P req (k) can refer to the predicted power demand of the target object at the target time, as mentioned above, ΔtP avg (k-1) can refer to the target average power demand of the fuel cell at the previous target time.

[0077] Optionally, the target power parameters and the predicted demand power at the target time are processed to obtain the target demand power at the target time, including: obtaining a first power algorithm at the target time based on the target state of charge and the target average demand power; using the first power algorithm to determine the power consumption corresponding to different demand powers of the fuel cell; and determining the demand power corresponding to the minimum power consumption as the target demand power.

[0078] The aforementioned first power algorithm can refer to the Hamiltonian function. After determining the target state of charge and the target average power demand, the Hamiltonian function can be further updated to improve the accuracy of the determined target power demand, as shown below:

[0079] Optionally, based on the target state of charge and the target average power demand, a first power algorithm corresponding to the target time is obtained, including: obtaining a first operator in the first power algorithm based on the target average power demand and a preset constant; determining the time difference between the target time and the end time of the second time period; obtaining a second operator in the first power algorithm based on the target state of charge, the state of charge corresponding to the current time, and the time difference; and obtaining the first power algorithm based on the first operator, the second operator, the target state of charge, the target average power demand, and the instantaneous hydrogen consumption of the fuel cell at the target time.

[0080] The first operator mentioned above refers to the aforementioned target costate variable, and the second operator mentioned above refers to the aforementioned target penalty function.

[0081] To improve the accuracy of the determined target power requirement, the parameters in the Hamiltonian function can be updated for different target times, that is, the aforementioned target costate variables and target penalty function can be updated.

[0082] Specifically, the formula for calculating the target costate variable of the first power algorithm at the target time can be:

[0083]

[0084] Among them, p1, p2, p3, and p4 can be constants. After determining the target average power demand of the fuel cell at the target time, the target costate variable can be determined using the above formula.

[0085] The formula for calculating the target penalty function of the first power algorithm at the target time can be:

[0086]

[0087] Wherein, SOC(0) can refer to the current state of charge of the fuel cell at the current moment, T tot It can refer to the total duration of a predicted future period, T k This can refer to the target time interval between the target time and the current time, and μ can be a constant. After determining the target state of charge of the fuel cell at the target time, the target penalty function can be determined using the above formula.

[0088] Optionally, based on the target demand power corresponding to multiple time points, a target demand power sequence is obtained, including: in response to determining the target demand power corresponding to the target time point, determining the target power change; based on the target demand power corresponding to historical time points and the target power change, updating the target demand power corresponding to the target time point to obtain the update result corresponding to the target time point; and based on the update results corresponding to multiple time points, obtaining the target demand power sequence.

[0089] The aforementioned target power change can refer to the change used to reduce the error in the determined target power demand.

[0090] After determining the target power demand at multiple target moments over a future period, to further improve its determinism and eliminate the power supply delay caused by slow dynamic response, the target power demand can be further updated using a lower-level control module. Specifically, the MPC algorithm can be used to track and calculate a more optimal change Δu. k The target power demand at the current target time is optimized by using the change in power and the target power demand at the previous target time. For specific methods of calculating the change in power, please refer to relevant literature. The optimization formula can be:

[0091]

[0092] in, It can refer to the optimized target power demand.

[0093] After optimizing the target power demand for all target times, an optimized target power demand sequence can be formed. Finally, the fuel cell can be controlled to operate according to the optimized target power demand sequence.

[0094] To clearly demonstrate the hierarchical optimization fuel cell control method described above, Figure 3 This is a schematic diagram of a demand power hierarchical optimization system according to an embodiment of the present invention, such as... Figure 3 As shown, the system is mainly divided into two parts: an upper-level control module and a lower-level control module. Before obtaining the target power demand using the upper-level control module, the historical operating information of the target object can be processed using the vehicle energy flow model to obtain the historical power demand sequence. Based on the historical power demand sequence and the power prediction model, the predicted power demand sequence of the target object in the future period is determined. Then, the predicted power demand sequence is input to the upper-level control module for processing to obtain the target power demand sequence. Finally, the lower-level control module optimizes the processed target power demand sequence to remove the power supply delay caused by slow dynamic response, and finally determines the target power demand sequence that the fuel cell needs to operate. That is, the optimized target power demand sequence is obtained, and the operation of the fuel cell is controlled.

[0095] like Figure 3 As shown, the upper-level control module is a power processing model derived from the A-PMP algorithm, while the lower-level control module is a dynamic response control model established based on the MPC algorithm.

[0096] Using this system to obtain the target power demand sequence of the fuel cell in advance can improve the accuracy of the determined power sequence while avoiding power supply delays caused by slow dynamic response and changes in vehicle driving status.

[0097] Example 2

[0098] According to another aspect of the embodiments of the present invention, corresponding to the above-described embodiments for fault diagnosis of charging equipment, this specification also provides a fuel cell control device, please refer to... Figure 4 , Figure 4This is a structural block diagram of a fuel cell control device according to an embodiment of the present invention. The device includes: a first acquisition module 402, for acquiring a historical power demand sequence of a target object, wherein a fuel cell is installed in the target object, and the historical power demand sequence includes: multiple historical power demands of the target object, each of which corresponds one-to-one with multiple first moments within a first preset time period before the current moment; a first prediction module 404, for processing the historical power demand sequence to predict a target power demand sequence, wherein the target power demand sequence includes: multiple target power demands of the fuel cell, each of which corresponds one-to-one with multiple second moments within a second preset time period after the current moment; and a first control module 406, for controlling the fuel cell to operate according to the target power demand sequence.

[0099] Optionally, the first prediction module 404 includes: a first determining unit, used to process the historical demand power sequence using a first prediction model to obtain a predicted demand power sequence, wherein the predicted demand power sequence includes: multiple predicted demand powers of the target object, and the multiple predicted demand powers correspond one-to-one with multiple second time moments; a first obtaining unit, used to obtain the target power parameters corresponding to the target time moment within a second preset time period, wherein the target time moment is any one of the multiple second time moments, the time interval between the multiple second time moments is a preset interval, and the target power parameters include: the target state of charge of the fuel cell and the target average demand power of the target object; a second determining unit, used to process the target power parameters corresponding to the target time moment and the predicted demand power corresponding to the target time moment to obtain the target demand power corresponding to the target time moment; and a third determining unit, used to obtain the target demand power sequence based on the target demand power corresponding to the multiple time moments.

[0100] Optionally, the first acquisition unit includes: a first acquisition subunit, used to acquire the target demand power corresponding to a historical time, the historical state of charge corresponding to a historical time, and the historical average demand power corresponding to a historical time, wherein the historical time is the time preceding the target time among a plurality of second times; a first determination subunit, used to obtain the target state of charge based on the target demand power corresponding to the historical time and the historical state of charge; and a second determination subunit, used to obtain the target average demand power corresponding to the target time based on the predicted demand power corresponding to the target time and the historical average demand power.

[0101] Optionally, the second determining unit includes: a third determining subunit, used to obtain a first power algorithm corresponding to the target time based on the target state of charge and the target average demand power; a fourth determining subunit, used to determine the power consumption corresponding to different demand power of the fuel cell using the first power algorithm; and a fifth determining subunit, used to determine the demand power corresponding to the minimum power consumption as the target demand power.

[0102] Optionally, the third determining subunit is further configured to: obtain a first operator in the first power algorithm based on the target average demand power and a preset constant; determine the time difference between the target time and the end time of the second time period; obtain a second operator in the first power algorithm based on the target state of charge, the state of charge corresponding to the current time, and the time difference; and obtain the first power algorithm based on the first operator, the second operator, the target state of charge, the target average demand power, and the instantaneous hydrogen consumption of the fuel cell at the target time.

[0103] Optionally, the third determining unit includes: a sixth determining subunit, used to determine the target power change in response to the target demand power corresponding to the determined target time; a first updating subunit, used to update the target demand power corresponding to the target time based on the target demand power corresponding to the historical time and the target power change, to obtain the update result corresponding to the target time; and a seventh determining subunit, used to obtain the target demand power sequence based on the update results corresponding to multiple times.

[0104] Optionally, the device further includes: a second acquisition module for acquiring historical operating information of the target object within a first preset time period; and a first determination module for processing the historical operating information to obtain a historical demand power sequence.

[0105] Example 3

[0106] According to another aspect of the present invention, a computer-readable storage medium is also provided, including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the fuel cell control method in the above embodiments.

[0107] Example 4

[0108] According to another aspect of the present invention, a processor is also provided, wherein the processor's program executes the fuel cell control method described in the above embodiments.

[0109] Example 5

[0110] According to another aspect of the present invention, a target vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to perform the fuel cell control method described in the above embodiments.

[0111] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0117] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A fuel cell control method characterized by, The method comprises: obtaining a historical demand power sequence of a target object, wherein the target object is provided with the fuel cell, and the historical demand power sequence comprises a plurality of historical demand powers of the target object, which correspond to a plurality of first time points within a first preset time period before a current time point; processing the historical demand power sequence to obtain a target demand power sequence, wherein the target demand power sequence comprises a plurality of target demand powers of the fuel cell, which correspond to a plurality of second time points within a second preset time period after the current time point; controlling the fuel cell to operate according to the target demand power sequence; wherein processing the historical demand power sequence to obtain the target demand power sequence comprises: processing the historical demand power sequence by using a first prediction model to obtain a predicted demand power sequence, wherein the predicted demand power sequence comprises a plurality of predicted demand powers of the target object, which correspond to the plurality of second time points; obtaining a target power parameter corresponding to a target time point within the second preset time period, wherein the target time point is any one of the plurality of second time points, the time interval of the plurality of second time points is a preset interval, and the target power parameter comprises a target state of charge of the fuel cell and a target average demand power of the target object; processing the target power parameter corresponding to the target time point and the predicted demand power corresponding to the target time point by using a first power algorithm to obtain a target demand power corresponding to the target time point; and obtaining the target demand power sequence based on the target demand powers corresponding to the plurality of second time points; processing the target power parameter corresponding to the target time point and the predicted demand power corresponding to the target time point to obtain the target demand power corresponding to the target time point comprises: obtaining a first power algorithm corresponding to the target time point based on the target state of charge and the target average demand power; determining the consumed power corresponding to different demand powers of the fuel cell by using the first power algorithm; and determining that the demand power corresponding to the minimum consumed power is the target demand power obtaining the target demand power sequence based on the target demand powers corresponding to the plurality of second time points comprises: determining a target power change amount in response to determining the target demand power corresponding to the target time point; updating the target demand power corresponding to the target time point based on the target demand power corresponding to a historical time point and the target power change amount to obtain an update result corresponding to the target time point, wherein the historical time point is a time point preceding the target time point among the plurality of second time points; and obtaining the target demand power sequence based on the update results corresponding to the plurality of second time points.

2. The method of claim 1, wherein, obtaining the target power parameter corresponding to the target time point within the second preset time period comprises: obtain a target demand power corresponding to a historical moment, a historical state of charge corresponding to the historical moment, and a historical average demand power corresponding to the historical moment, wherein the historical moment is a moment preceding the target moment in the plurality of second moments; obtain the target state of charge based on the target demand power corresponding to the historical moment and the historical state of charge; obtain a target average demand power corresponding to the target moment based on the predicted demand power corresponding to the target moment and the historical average demand power.

3. The method of claim 1, wherein, obtain a first power algorithm corresponding to the target moment based on the target state of charge and the target average demand power, including: obtain a first operator in the first power algorithm based on the target average demand power and a preset constant; determine a time difference between the target moment and an end moment of the second preset time period; obtain a second operator in the first power algorithm based on the target state of charge, a state of charge corresponding to the current moment, and the time difference; obtain the first power algorithm based on the first operator, the second operator, the target state of charge, the target average demand power, and an instantaneous hydrogen consumption amount of the fuel cell corresponding to the target moment.

4. The method of claim 1, wherein, obtain a historical demand power sequence of a target object, including: obtain historical running information of the target object in the first preset time period; process the historical running information to obtain the historical demand power sequence.

5. A fuel cell control device characterized by comprising: including: a first obtaining module, which obtains a historical demand power sequence of a target object, wherein the target object is installed with the fuel cell, and the historical demand power sequence includes a plurality of historical demand powers of the target object, the plurality of historical demand powers corresponding to a plurality of first moments in a first preset time period before a current moment one by one; a first prediction module, which is configured to process the historical demand power sequence to obtain a target demand power sequence, wherein the target demand power sequence includes a plurality of target demand powers of the fuel cell, the plurality of target demand powers corresponding to a plurality of second moments in a second preset time period after the current moment one by one; a first control module, which is configured to control the fuel cell to operate according to the target demand power sequence; The first prediction module comprises: a first determination unit configured to process the historical demand power sequence by using a first prediction model to obtain a predicted demand power sequence, wherein the predicted demand power sequence comprises a plurality of predicted demand powers of the target object, and the plurality of predicted demand powers correspond to the plurality of second time points one by one; a first acquisition unit configured to acquire a target power parameter corresponding to a target time point in the second preset time period, wherein the target time point is any one of the plurality of second time points, the time interval of the plurality of second time points is a preset interval, and the target power parameter comprises a target state of charge of the fuel cell and a target average demand power of the target object; a second determination unit configured to process the target power parameter corresponding to the target time point and the predicted demand power corresponding to the target time point based on a first power algorithm to obtain a target demand power corresponding to the target time point; and a third determination unit configured to obtain the target demand power sequence based on the target demand powers corresponding to the plurality of second time points. The second determination unit comprises: a third determination sub-unit configured to obtain a first power algorithm corresponding to the target time point based on the target state of charge and the target average demand power; a fourth determination sub-unit configured to determine a consumed power corresponding to different demand powers of the fuel cell by using the first power algorithm; and a fifth determination sub-unit configured to determine that a demand power corresponding to a minimum consumed power is the target demand power. The third determination unit comprises: a sixth determination sub-unit configured to determine a target power change amount in response to determining the target demand power corresponding to the target time point; a first update sub-unit configured to update the target demand power corresponding to the target time point based on a target demand power corresponding to a historical time point and the target power change amount to obtain an update result corresponding to the target time point, wherein the historical time point is a time point preceding the target time point among the plurality of second time points; and a seventh determination sub-unit configured to obtain the target demand power sequence based on the update results corresponding to the plurality of second time points.

6. A computer-readable storage medium, characterized in that, A computer readable storage medium storing a program, wherein the program controls a device in which the computer readable storage medium is located to perform the method of any one of claims 1-4 when the program is running.

7. A vehicle comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.

Images