Energy control method, device and system of hybrid power vehicle and vehicle

Abstract

The invention provides an energy control method, device and system of a hybrid power vehicle and the vehicle, and relates to the technical field of vehicle control, and the method comprises the steps that vehicle driving information of a preset time window closest to the current time is acquired from a real-time data stream of the hybrid power vehicle; according to the vehicle driving information of the preset time window, working condition identification is conducted on the hybrid power vehicle, and the current operation working condition of the hybrid power vehicle at the current time is obtained; according to the charge state parameter of a power battery in the hybrid vehicle and the required power of the hybrid vehicle, a fuzzy controller corresponding to the current operation condition is adopted for fuzzy control, and the first output power of a fuel battery in the hybrid vehicle is obtained; and determining the second output power of the power battery according to the required power and the first output power of the fuel battery. The energy distribution efficiency of the hybrid power vehicle is improved, and the service life of the vehicle is prolonged.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle control, in particular to an energy control method, device, system and vehicle of a hybrid vehicle. BACKGROUND

[0002] At present, heavy traction vehicles driven by fuel cells and power batteries are mainly used for short-distance and high-frequency transportation operations or long-distance and continuous highway transportation. These two types of working conditions have fundamental differences in power output characteristics, energy consumption modes, and key component working stress, and have different technical requirements for the response ability, adjustment accuracy, and long-term reliability of the vehicle energy management system.

[0003] At present, the energy management strategy of fuel cell heavy traction vehicles is based on an experience rule control method, that is, according to the remaining battery power level and the current required driving power of the vehicle, the output power of the fuel cell system is determined through a preset threshold judgment or fixed logical relationship.

[0004] However, the prior art lacks accurate identification of actual operating conditions, resulting in a mismatch between the energy distribution strategy and the actual operating state, and the inability to distinguish between different working conditions, resulting in high fuel consumption of the fuel cell, increased invalid start-stop loss, and accelerated aging and failure of the fuel cell. SUMMARY

[0005] The purpose of the present application is to provide an energy control method, device, system and vehicle of a hybrid vehicle to improve the energy distribution efficiency of the hybrid vehicle and improve the service life of the vehicle.

[0006] To achieve the above purpose, the technical solutions adopted by the embodiments of the present application are as follows: In a first aspect, an embodiment of the present application provides an energy control method of a hybrid vehicle, the method comprising: obtaining vehicle driving information of a preset time window closest to the current time from real-time data flow of the hybrid vehicle; According to the vehicle driving information of the preset time window, the working condition of the hybrid vehicle is identified to obtain the current operating condition of the hybrid vehicle at the current time; According to the state of charge parameter of the power battery in the hybrid vehicle and the demand power of the hybrid vehicle, a fuzzy controller corresponding to the current operating condition is used for fuzzy control to obtain the first output power of the fuel cell in the hybrid vehicle; According to the demand power and the first output power of the fuel cell, a second output power of the power battery is determined; the first output power and the second output power are respectively used to control energy output of the fuel cell and the power battery in a next time window.

[0007] Optionally, the vehicle driving information in the preset time window is used to identify the working condition of the hybrid vehicle to obtain a current operation working condition of the hybrid vehicle at the current time, including: A current driving feature parameter is extracted from the vehicle driving data in the preset time window. According to the current driving feature parameter, a preset working condition identification model is used to identify the working condition to obtain the current operation working condition.

[0008] Optionally, before the current driving feature parameter is used to identify the working condition by using the preset working condition identification model to obtain the current operation working condition, the method further includes: A working condition database of a plurality of preset operation working conditions is obtained; actual vehicle driving data under a corresponding operation working condition is stored in the working condition database. Feature identification is performed on the working condition database of the preset operation working condition to obtain an operation feature library of the preset operation working condition, and a plurality of sets of driving feature parameters under the preset operation working condition are stored in the operation feature library. The operation feature library of the plurality of preset operation working conditions is used for model training to obtain the preset working condition identification model.

[0009] Optionally, before the state of charge parameter of the power battery in the hybrid vehicle and the demand power of the hybrid vehicle are used to perform fuzzy control by using the fuzzy controller corresponding to the current operation working condition to obtain the first output power of the fuel cell in the hybrid vehicle, the method further includes: According to a preset battery state of charge interval, a preset demand power interval and a preset output power interval of the fuel cell, a first input variable, a second input variable and an output variable are respectively constructed, wherein the first input variable includes a plurality of first input fuzzy subsets in the preset battery state of charge interval, the second input variable includes a plurality of second input fuzzy subsets of the preset demand power interval under each preset operation working condition, and the output variable includes a plurality of output fuzzy subsets of the preset output power interval under each preset operation working condition. According to the first input variable, the second input variable corresponding to each preset operation working condition and the corresponding output variable, a fuzzy rule table corresponding to each preset operation working condition is used to construct a fuzzy controller corresponding to each preset operation working condition.

[0010] Optionally, the first input variable, the second input variable and the output variable are constructed according to the preset battery state of charge interval, the preset demand power interval and the preset output power interval of the fuel cell, comprising: The preset battery state of charge interval is divided into multiple intervals to obtain multiple groups of the first input variable; the first input fuzzy subsets in different groups of the first input variable are divided differently; The preset demand power interval is divided into multiple intervals to obtain multiple groups of the second input variable; the second input fuzzy subsets in different groups of the second input variable are divided differently; The preset output power interval of the fuel cell is divided into multiple intervals to obtain multiple groups of the output variable; the output fuzzy subsets in different groups of the output variable are divided differently.

[0011] Optionally, the fuzzy controller corresponding to each preset operating condition is constructed by using the fuzzy rule table corresponding to each preset operating condition according to the first input variable, the second input variable corresponding to each preset operating condition and the corresponding output variable, comprising: According to the multiple groups of the first input variable, the multiple groups of the second input variable and the multiple groups of the output variable, a plurality of groups of variable combinations corresponding to the preset operating condition are obtained; the variable combination comprises: one first input variable, one second input variable and one output variable; The particle swarm algorithm is used to determine a target variable combination satisfying a preset optimization objective function from the multiple groups of variable combinations; According to the first input variable, the second input variable and the corresponding output variable in the target variable combination, the fuzzy controller corresponding to each preset operating condition is constructed by using the fuzzy rule table corresponding to each preset operating condition.

[0012] Optionally, the particle swarm algorithm is used to determine a target variable combination satisfying a preset optimization objective function from the multiple groups of variable combinations, comprising: According to each group of the variable combination, fuel cell energy consumption prediction data, state of charge cumulative deviation data and fuel cell cumulative start-up times corresponding to the variable combination are determined; According to the corresponding fuel cell energy consumption prediction data, the state of charge cumulative deviation data and the fuel cell cumulative start-up times, the target optimization parameter corresponding to the variable combination is calculated by using the preset optimization objective function; According to the target optimization parameters corresponding to the multiple groups of variable combinations, the particle swarm algorithm is used to determine the target variable combination.

[0013] In a second aspect, another embodiment of the present application provides an energy control device, comprising: a processor and a memory, the memory storing machine readable instructions executable by the processor, when the computer device is running, the processor executes the machine readable instructions to perform the steps of the energy control method of the hybrid vehicle of any one of the first aspect.

[0014] In a third aspect, another embodiment of the present application provides a vehicle control system, comprising: an energy control device, a fuel cell, a power battery, and a vehicle controller; the energy control device is connected to the fuel cell and the power battery respectively, and the energy control device and the vehicle controller are in communication connection to obtain the demand power of the hybrid vehicle and the vehicle driving information of a preset time window. The energy control device is configured to perform the energy control method of the hybrid vehicle of any one of the first aspect.

[0015] In a fourth aspect, another embodiment of the present application provides a hybrid vehicle, comprising: a vehicle body and the vehicle control system of the third aspect.

[0016] In a fifth aspect, another embodiment of the present application provides an energy control device of a hybrid vehicle, comprising: An acquisition module is configured to acquire vehicle driving information of a preset time window closest to a current time from a real-time data stream of the hybrid vehicle. An identification module is configured to identify the working condition of the hybrid vehicle according to the vehicle driving information of the preset time window, to obtain a current operation working condition of the hybrid vehicle at the current time. A control module is configured to perform fuzzy control by using a fuzzy controller corresponding to the current operation working condition according to a state of charge parameter of a power battery in the hybrid vehicle and the demand power of the hybrid vehicle, to obtain a first output power of a fuel cell in the hybrid vehicle. A determination module is configured to determine a second output power of the power battery according to the demand power and the first output power of the fuel cell; the first output power and the second output power are respectively used to control the energy output of the fuel cell and the power battery in a next time window.

[0017] In a sixth aspect, another embodiment of the present application provides a storage medium, the storage medium storing a computer program, the computer program being executed by a processor to perform the steps of the energy control method of the hybrid vehicle of any one of the first aspect.

[0018] The present application has the following beneficial effects: The application provides an energy control method, device, system and vehicle of a hybrid vehicle, vehicle running information of a preset time window closest to a current time is acquired from a real-time data stream of the hybrid vehicle; working condition recognition is performed on the hybrid vehicle according to the vehicle running information of the preset time window, and a current operation working condition of the hybrid vehicle at the current time is obtained; a fuzzy controller corresponding to the current operation working condition is used to perform fuzzy control according to a state of charge parameter of a power battery in the hybrid vehicle and a demand power of the hybrid vehicle, and a first output power of a fuel cell in the hybrid vehicle is obtained; and a second output power of the power battery is determined according to the demand power and the first output power of the fuel cell. In the application, the current operation working condition of the vehicle is determined according to the vehicle running information, the corresponding fuzzy controller is determined according to the current operation working condition of the vehicle, the output powers of the fuel cell and the power battery of the vehicle under the current operation working condition are obtained, the fuel cell power distribution always meets the physical constraints and the life-sensitive characteristics under the current operation working condition, the hydrogen consumption is reduced, the battery state of charge fluctuation is stabilized, the invalid start-stop of the fuel cell is reduced, the process of controlling the hybrid power battery according to the demand power of the hybrid power is realized, and the energy control efficiency of the vehicle and the life of the vehicle are improved. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0020] Figure 1 An energy control method of a hybrid vehicle is provided in the embodiments of the application; Figure 2 A flowchart for determining a current operation working condition in an energy control method of a hybrid vehicle is provided in the embodiments of the application; Figure 3 A flowchart for determining a preset working condition recognition model in an energy control method of a hybrid vehicle is provided in the embodiments of the application; Figure 4 A flowchart for determining a fuzzy controller in an energy control method of a hybrid vehicle is provided in the embodiments of the application; Figure 5 A flowchart for determining a variable in an energy control method of a hybrid vehicle is provided in the embodiments of the application; Figure 6A flowchart illustrating the determination of a fuzzy controller in an energy control method for a hybrid vehicle provided in this application embodiment; Figure 7 A flowchart illustrating the determination of a target variable combination in an energy control method for a hybrid vehicle provided in this application embodiment; Figure 8 This is a schematic diagram of the structure of an energy control device for a hybrid vehicle provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of an energy control device provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of a vehicle control system provided in an embodiment of this application; Figure 11 This is a structural schematic diagram of a vehicle provided in an embodiment of this application. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0022] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0023] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0024] Fuel cell vehicles suffer from slow power response due to slow load changes and lack of energy recovery capabilities, necessitating the use of a power battery to smooth out energy peaks and valleys to compensate for the limitations of the fuel cell system. During vehicle operation, frequent load changes in the fuel cell system and excessively high or low state of charge in the power battery can shorten the lifespan of components. Currently, heavy-duty tractor vehicles powered by both fuel cells and power batteries primarily operate in short-distance, high-frequency transport or medium-to-long-distance, continuous highway trunk line transport. These two operating conditions differ fundamentally in power output characteristics, energy consumption patterns, and stress on key components, placing different demands on the responsiveness, adjustment precision, and long-term reliability of the vehicle's energy management system. To address this, this application provides an energy control method for hybrid vehicles. The method involves acquiring vehicle driving information from a preset time window closest to the current time from the real-time data stream of the hybrid vehicle; identifying the operating condition of the hybrid vehicle based on the driving information within the preset time window to obtain the current operating condition of the hybrid vehicle at the current time; performing fuzzy control using a fuzzy controller corresponding to the current operating condition based on the state-of-charge parameters of the power battery in the hybrid vehicle and the power demand of the hybrid vehicle to obtain the first output power of the fuel cell in the hybrid vehicle; determining the second output power of the power battery based on the power demand and the first output power of the fuel cell; and using the first and second output powers to control the energy output of the fuel cell and the power battery in the next time window, respectively. This application determines the first output power of the vehicle's fuel cell and the second output power of the power battery based on the current operating condition of the hybrid battery, optimizing overall vehicle hydrogen consumption, maintaining a stable state of charge of the power battery, reducing fuel cell fluctuations such as frequent start-stop cycles or drastic load changes, and improving the overall economy and reliability of the hybrid vehicle.

[0025] To clearly describe the energy control method for a hybrid vehicle provided in this application, the method will be explained below with reference to several accompanying drawings. Figure 1 An energy control method for a hybrid vehicle provided in this application embodiment, such as Figure 1 As shown, the method includes: Step 101: Obtain vehicle driving information from the real-time data stream of the hybrid vehicle for the preset time window closest to the current time.

[0026] Hybrid vehicles refer to vehicles containing two or more power sources. In this application, the hybrid vehicle is a vehicle with a hybrid configuration of fuel cell and power battery. The hybrid vehicle can be a fuel cell heavy-duty truck, and the fuel cell can be a hydrogen fuel cell. The real-time data stream is data sent by the vehicle controller. The vehicle controller can send data at fixed intervals. The real-time data stream includes power data, power battery state-of-charge change data, and fuel consumption data of the fuel cell during vehicle operation. This application does not limit the specific data stream. The preset time window is the most recent time period before the current time, and the preset time window can be 90 seconds. Vehicle driving information can include the vehicle's speed and power demand at each time point within the preset time window.

[0027] Step 102: Based on the vehicle driving information within the preset time window, identify the operating conditions of the hybrid vehicle to obtain the current operating conditions of the hybrid vehicle at the current time.

[0028] The current operating conditions can include both short-term and high-speed operating conditions.

[0029] Optionally, the vehicle driving information within a preset time window is compared with the vehicle driving information in reverse short operating conditions and high-speed operating conditions to determine the operating condition corresponding to the vehicle driving information, thereby identifying the operating condition of the hybrid vehicle and obtaining the current operating condition of the hybrid vehicle at the current time.

[0030] Step 103: Based on the state-of-charge parameters of the power battery in the hybrid vehicle and the power demand of the hybrid vehicle, fuzzy control is performed using a fuzzy controller corresponding to the current operating conditions to obtain the first output power of the fuel cell in the hybrid vehicle.

[0031] In this context, the power demand of the hybrid vehicle is calculated by the vehicle controller based on the current driver's intention and the vehicle dynamics model. The fuzzy controller is a nonlinear controller based on fuzzy logic, mapping precise numerical inputs to fuzzy linguistic variables to obtain the first output power of the fuel cell. This first output power is the output power of the fuel cell.

[0032] Optionally, based on the state-of-charge parameters of the power battery in the hybrid vehicle and the power demand of the hybrid vehicle, a fuzzy controller corresponding to the current operating condition is used for fuzzy control to obtain the first output power of the fuel cell of the hybrid vehicle under the current operating condition.

[0033] Step 104: Determine the second output power of the power battery based on the required power and the first output power of the fuel cell.

[0034] The first output power and the second output power are used to control the energy output of the fuel cell and the power battery in the next time window, respectively. The second output power is the output power of the power battery.

[0035] Optionally, the difference between the required power and the first output power of the fuel cell is determined based on the required power and the first output power of the fuel cell, which is used to determine the second output power of the power battery.

[0036] In this embodiment, vehicle driving information within a preset time window closest to the current time is obtained from the real-time data stream of the hybrid vehicle. Based on the vehicle driving information within the preset time window, the operating condition of the hybrid vehicle is identified to obtain its current operating condition. Based on the state-of-charge parameters of the power battery and the power demand of the hybrid vehicle, fuzzy control is performed using a fuzzy controller corresponding to the current operating condition to obtain the first output power of the fuel cell in the hybrid vehicle. Based on the power demand and the first output power of the fuel cell, the second output power of the power battery is determined. This application determines the current operating condition of the vehicle based on its driving information, thereby determining the corresponding fuzzy controller and obtaining the output power of the fuel cell and power battery under the current operating condition. This ensures that the fuel cell power distribution always conforms to the physical constraints and lifespan sensitivity characteristics under the current operating condition. While meeting the overall vehicle power demand, it reduces hydrogen consumption, stabilizes battery state-of-charge fluctuations, and reduces ineffective fuel cell start-stops. This achieves the process of controlling the hybrid battery based on the power demand of the hybrid system, improving the vehicle's energy control efficiency and lifespan.

[0037] Based on the above embodiments, this application also provides a process for determining the current operating condition in the energy control method for hybrid vehicles. Figure 2 This is a flowchart illustrating the process of determining the current operating condition in an energy control method for a hybrid vehicle provided in an embodiment of this application, as shown below. Figure 2 As shown, in step 102 above, the process of identifying the operating condition of the hybrid vehicle based on the vehicle driving information within the preset time window to obtain the current operating condition of the hybrid vehicle at the current time includes: Step 201: Extract the current driving characteristic parameters from the vehicle driving data within the preset time window.

[0038] Among them, the driving characteristic parameters include maximum vehicle speed, average vehicle speed, idling time ratio, acceleration standard deviation, and average power demand.

[0039] Optionally, based on the vehicle speed data in the vehicle driving data within the preset time window, the highest vehicle speed in the preset time window is determined; based on the vehicle speed data in the vehicle driving data within the preset time window, the average speed in the preset time window is calculated; based on the vehicle speed data in the vehicle driving data within the preset time window, the proportion of time during which the vehicle speed is less than idle speed is determined, thereby obtaining the idle time proportion; based on the vehicle speed data in the vehicle driving data within the preset time window, the acceleration at each time point in the preset time window is calculated, and the standard deviation of acceleration in the preset time window is determined based on the acceleration at each time point; based on the power demand at each time point in the vehicle driving data within the preset time window, the average power demand at each time point in the preset time window is calculated, thereby determining the average power demand.

[0040] Step 202: Based on the current driving characteristic parameters, use the preset operating condition recognition model to identify the operating condition and obtain the current operating condition.

[0041] The preset working condition identification model is a genetic algorithm (GA)-support vector machine (SVM). The SVM is optimized by genetic factors to obtain the corresponding preset working condition identification model.

[0042] Optionally, a preset operating condition identification model can be used to identify the operating condition based on the current driving characteristic parameters, thereby obtaining the current operating condition.

[0043] In this embodiment, by extracting driving feature parameters, noise interference from single-point instantaneous data is avoided, while retaining the short-term dynamic characteristics of driving behavior. The preset working condition recognition model used determines the working condition type of the actual use scenario from the current driving feature parameters, thereby improving the energy management efficiency of the vehicle and making the energy management of the vehicle more compatible with the current working condition.

[0044] Based on the above embodiments, this application also provides a process for determining a preset operating condition identification model in the energy control method of a hybrid vehicle. Figure 3 This is a flowchart illustrating the process of determining a preset operating condition identification model in an energy control method for a hybrid vehicle provided in this application embodiment, as shown below. Figure 3 As shown, before obtaining the current operating condition by using a preset operating condition identification model based on the current driving characteristic parameters in step 202 above, the method further includes: Step 301: Obtain a database of operating conditions for multiple preset operating conditions.

[0045] The operating condition database stores actual vehicle driving data under corresponding operating conditions. The preset operating conditions are short-distance operating conditions and high-speed operating conditions. Correspondingly, the actual vehicle driving data includes the actual vehicle driving data under short-distance operating conditions and the actual vehicle driving data under high-speed operating conditions.

[0046] Optionally, the system can acquire the actual vehicle driving data under the short-distance operating condition and the high-speed operating condition.

[0047] Step 302: Perform feature recognition on the preset operating condition database to obtain the preset operating condition feature library.

[0048] The operational feature library stores multiple sets of driving feature parameters under preset operating conditions.

[0049] Optionally, feature recognition is performed on the actual vehicle driving data in the preset operating condition database to obtain the current driving characteristics corresponding to the actual vehicle driving data, which are parameters such as maximum vehicle speed, average vehicle speed, idling time ratio, acceleration standard deviation, and average demand power, thereby obtaining the operating feature library of the preset operating conditions.

[0050] Step 303: Train the model based on the operational feature library of multiple preset operating conditions to obtain the preset operating condition recognition model.

[0051] Optionally, a genetic algorithm is used to optimize the key parameters of the support vector machine (SVM). By setting different key parameters for the SVM, multiple sets of driving feature parameters in the operational feature library are predicted to obtain the corresponding operating conditions. The key parameters of the SVM with the most accurate prediction are taken as the target key parameters, and the target key parameters are used as the parameters of the SVM, thereby obtaining the preset operating condition recognition model. The key parameters can be a penalty factor C and kernel function parameters g.

[0052] In this embodiment, a comprehensive and clearly defined multi-condition database is constructed, providing a high-quality real-world data foundation for model learning. Feature identification and extraction of the raw data effectively transforms complex driving data into regular parameters that the model can understand, thereby enhancing the model's ability to capture the essential differences in operating conditions. Model training based on this enables the final condition identification model to possess generalization performance and robustness in accurately identifying different operating conditions from actual operating data.

[0053] Based on the above embodiments, this application also provides a process for determining a fuzzy controller in the energy control method of a hybrid vehicle. Figure 4 This application provides a flowchart illustrating the determination of a fuzzy controller in an energy control method for a hybrid vehicle, as shown in the embodiments of the present application.Figure 4 As shown, before obtaining the first output power of the fuel cell in the hybrid vehicle by performing fuzzy control using a fuzzy controller corresponding to the current operating condition based on the state-of-charge parameters of the power battery in the hybrid vehicle and the power demand of the hybrid vehicle in step 103 above, the method further includes: Step 401: Based on the preset battery state of charge range, preset power demand range, and preset output power range of the power battery, construct the first input variable, the second input variable, and the output variable respectively.

[0054] The first input variable includes multiple first input fuzzy subsets within the preset battery state of charge range; the second input variable includes multiple second input fuzzy subsets within the preset demand power range under each preset operating condition; and the output variable includes multiple output fuzzy subsets within the preset output power range under each preset operating condition.

[0055] Optionally, the preset battery state of charge interval is divided according to the preset battery state of charge interval to obtain multiple first input fuzzy subsets. The multiple first input fuzzy subsets are divided according to {VS (very low), S (low), M (medium), B (high), VB (very high)}, and the number of first input fuzzy subsets is 5.

[0056] For example, if the preset state of charge range of the power battery is [0.3, 0.8], then multiple first input fuzzy subsets can be {VS: [0.3, 0.35, 0.4]; S: [0.35, 0.45, 0.55]; M: [0.5, 0.6, 0.7]; B: [0.65, 0.7, 0.75]; VB: [0.7, 0.75, 0.8]}.

[0057] Optionally, the preset demand power range is divided according to the preset demand power range to obtain multiple second input fuzzy subsets. The multiple second input fuzzy subsets are divided according to {VS (very small), S (small), M (medium), B (large), VB (very large)}, and the number of second input fuzzy subsets is 5.

[0058] For example, if the preset power demand range is [0, 190] kW, when the preset operating condition is reverse short-circuit operating condition, multiple second input fuzzy subsets can be {VS: [0, 10, 30]; S: [20, 40, 60]; M: [50, 80, 110]; B: [100, 130, 160]; VB: [150, 170, 190]}. When the preset operating condition is high-speed operating condition, multiple second input fuzzy subsets can be {VS: [0, 30, 60]; S: [50, 80, 110]; M: [100, 130, 160]; B: [150, 170, 190]; VB: [180, 190, 200]}.

[0059] Optionally, the preset output power range is divided according to a preset output power range to obtain multiple output fuzzy subsets. When the preset operating condition is reverse short-circuit operating condition, the multiple output fuzzy subsets are divided according to {Z (zero), VS (very small), S (small), M (medium), B (large), VB (very large)}, and the number of output fuzzy subsets is 5. When the preset operating condition is high-speed operating condition, the multiple output fuzzy subsets are divided according to {S (very small), S (small), M (medium), B (large), VB (very large)}, and the number of output fuzzy subsets is 5.

[0060] For example, if the preset output power range is [0, 200] kW, multiple output fuzzy subsets can be {Z[0,0,20]; VS: [10,30,50]; S: [40,60,80]; M: [70,100,130]; B: [120,150,180]; VB: [170,190,200]}. When the preset operating condition is high-speed operating condition, multiple output fuzzy subsets can be {[0,40,80]; S: [70,100,130]; M: [120,140,160]; B: [150,170,190]; VB: [180,195,200]}.

[0061] Step 402: Based on the first input variable, the second input variable corresponding to each preset operating condition, and the corresponding output variable, construct the fuzzy controller corresponding to each preset operating condition using the fuzzy rule table corresponding to each preset operating condition.

[0062] The fuzzy rule tables differ for different operating conditions. During short-term operation, the priority is to reduce fuel cell start-ups and shutdowns > maintain stable state of charge (SCC) parameters > reduce hydrogen consumption. When SCC parameters are low, to avoid over-discharge of the battery, priority is given to increasing fuel cell output power; when SCC parameters are high, battery energy is used first, reducing fuel cell output and minimizing start-ups, shutdowns, and inefficient operation; when power demand is low, fuel cells are shut down as much as possible, with the battery meeting the power demand; when power demand is high, fuel cells serve as the primary output, with the battery assisting in responding to transient demands. During high-speed operation, the priority is to maintain stable SCC parameters > reduce hydrogen consumption > reduce fuel cell start-ups and shutdowns. During high-speed operation, fuel cells are kept in the high-efficiency range. When SCC parameters are low, fuel cell output is appropriately increased while stabilizing SCC parameters; when SCC parameters are close to the ideal value, fuel cell output is maintained in the high-efficiency range, with the battery providing auxiliary adjustment; when SCC parameters are high, fuel cell output is appropriately reduced, prioritizing the use of battery energy; when power demand fluctuations are small, fuel cell output is stable, avoiding frequent load changes.

[0063] Optionally, if the preset operating condition is reverse short operating condition, the corresponding fuzzy rule table for reverse short operating condition is as follows:

[0064] For example, if the fuzzy subset corresponding to the state of charge parameter is B, the fuzzy subset corresponding to the demand power is M, and the fuzzy subset corresponding to the output power is S.

[0065] Optionally, if the preset operating condition is high-speed operating condition, the corresponding fuzzy rule table for high-speed operating condition is as follows:

[0066] For example, if the fuzzy subset corresponding to the state of charge parameter is B, the fuzzy subset corresponding to the demand power is M, and the fuzzy subset corresponding to the output power is M.

[0067] Optionally, multiple first input fuzzy subsets within the preset battery charge state interval corresponding to different operating conditions are the same, and multiple second input fuzzy subsets, multiple output fuzzy subsets, and fuzzy rule tables are determined according to the operating conditions.

[0068] For example, if the operating condition is a reverse short-circuit operating condition, and the state of charge parameter is 45%, the required power is 75 kW. Taking the fuzzy subset of the distance mentioned above as an example, the first input fuzzy subset of the state of charge parameter is L with a membership degree of 1.0, and the second input fuzzy subset of the required power is M with a membership degree of 0.833. According to the fuzzy rule table of the reverse short-circuit operating condition, the output fuzzy subset of the output power can be determined as B. Based on the output fuzzy subset as B and the smaller membership degree of 0.833, the output power is 150 kW.

[0069] In this embodiment, by defining targeted membership functions and fuzzy subsets for different operating conditions, the constructed fuzzy controller can differentiate energy management strategies, enabling the controller to have inherent operating condition adaptive capabilities. This allows the controller to determine multiple objectives such as fuel cell start-up and shutdown, battery state of charge adoption rate maintenance, and system hydrogen consumption in actual operation, thereby improving the efficiency and accuracy of energy control.

[0070] Based on the above embodiments, this application also provides a process for determining variables in the energy control method of a hybrid vehicle. Figure 5 This is a flowchart illustrating the determination of variables in an energy control method for a hybrid vehicle provided in an embodiment of this application, as shown below. Figure 5 As shown, in step 401 above, based on the preset battery state of charge range, preset power demand range, and preset output power range of the power battery, a first input variable, a second input variable, and an output variable are constructed respectively, including: Step 501: Divide the preset battery state of charge interval into multiple intervals to obtain multiple sets of first input variables.

[0071] The division of the first input fuzzy subset in the first input variable differs for different groups. The preset battery state of charge range is fixed data.

[0072] Optionally, multiple sets of first input variables can be obtained by dividing the preset battery state of charge interval multiple times according to the first input fuzzy subset.

[0073] For example, if the preset battery state of charge interval is [0.3, 0.8], by linearly dividing the preset battery state of charge interval into five intervals according to the first input fuzzy subset, a set of first input variables can be obtained as follows: {VS: [0.300, 0.300, 0.363]; S: [0.363, 0.425, 0.488]; M: 0.488, 0.550, 0.613]; B: [0.613, 0.675, 0.738] ;VB: [0.738,0.800,0.800]}, according to the asymmetric partitioning, a set of first input variables can be obtained as {VS: [0.3,0.35,0.4]; S: [0.35,0.45,0.55]; M: [0.5,0.6,0.7]; B: [0.65,0.7,0.75]; VB: [0.7,0.75,0.8]}. The partitioning method can also be other methods, and this application embodiment does not limit this.

[0074] Step 502: Divide the preset power demand range into multiple intervals to obtain multiple sets of second input variables.

[0075] The division of the second input fuzzy subset in the second input variables differs for different groups. The preset required power range is a fixed value.

[0076] Optionally, multiple sets of second input variables can be obtained by dividing the preset demand power range into intervals multiple times according to the second input fuzzy subset.

[0077] For example, if the preset power demand range is [0, 190] kW, the preset battery state of charge range is divided into five intervals according to the second input fuzzy subset. One set of second input variables can be {VS: [0, 10, 30]; S: [20, 40, 60]; M: [50, 80, 110]; B: [100, 130, 160]; VB: [150, 170, 190]}, and another set of second input variables can be {VS: [0, 0, 40]; S: [20, 50, 90]; M: [60, 100, 140]; B: [110, 150, 180]; VB: [160, 190, 190]}. There are multiple ways to divide the range, and this application embodiment does not limit this.

[0078] Step 503: Divide the preset output power range of the fuel cell into multiple intervals to obtain multiple sets of output variables.

[0079] The division of the output fuzzy subsets in the output variables of different groups is different. The preset output power range is a fixed value.

[0080] Optionally, multiple sets of output variables can be obtained by dividing the preset output power range into intervals multiple times according to the output fuzzy subset.

[0081] For example, if the preset output power range is [0, 200] kW, by dividing the preset output power range into five intervals according to the output fuzzy subset, one set of output variables can be obtained as {Z[0,0,20]; VS: [10,30,50]; S: [40,60,80]; M: [70,100,130]; B: [120,150,180]; VB: [170,190,200]}, and another set of output variables can be {{Z[0,0,30]; VS: [10,40,70]; S: [50,80,110]; M: [80,120,160]; B: [140,160,180]; VB: [170,190,200]}. There can be multiple ways to divide the range, and this application embodiment does not limit this.

[0082] In this embodiment, multiple sets of fuzzy subset definitions are prepared for battery state, required power, and fuel cell output, respectively, to accurately synthesize a controller adapted to a specific optimization objective or operational scenario. Without modifying the core rule base, the corresponding controller is determined, achieving accuracy in the control logic and precise optimization of the controller.

[0083] Based on the above embodiments, this application also provides a process for determining a fuzzy controller in the energy control method of a hybrid vehicle. Figure 6 This is a flowchart illustrating the determination of a fuzzy controller in an energy control method for a hybrid vehicle provided in this application embodiment. Figure 6 As shown, in step 402 above, based on the first input variable, the second input variable corresponding to each preset operating condition, and the corresponding output variable, a fuzzy controller corresponding to each preset operating condition is constructed using the fuzzy rule table corresponding to each preset operating condition, including: Step 601: Based on multiple sets of first input variables, multiple sets of second input variables, and multiple sets of output variables, obtain multiple sets of variable combinations corresponding to the preset operating conditions.

[0084] The variable combination includes: a first input variable, a second input variable, and an output variable.

[0085] Optionally, multiple sets of first input variables, multiple sets of second input variables, and multiple sets of output variables are traversed and randomly combined to obtain multiple variable combinations.

[0086] Step 602: Using the particle swarm optimization algorithm, determine the target variable combination that satisfies the preset optimization objective function from multiple sets of variable combinations.

[0087] Among them, the particle swarm optimization algorithm is an intelligent optimization algorithm that collaboratively searches for the global optimum in the search space by tracking the current optimal solution and its own historical optimal solutions. If there are multiple operating conditions, the target variable combination corresponding to each operating condition is determined separately.

[0088] Optionally, each variable combination is treated as a particle, and a corresponding fuzzy controller is constructed based on the variable combination. The variable combination of the target fuzzy controller is determined from the multiple fuzzy controllers constructed from multiple variable combinations as the target variable combination.

[0089] Step 603: Based on the first input variable, the second input variable, and the corresponding output variable in the target variable combination, construct the fuzzy controller corresponding to each preset operating condition using the fuzzy rule table.

[0090] Optionally, when the preset operating condition is the reverse short operating condition, the fuzzy controller corresponding to the reverse short operating condition is constructed by using the fuzzy rule table corresponding to the reverse short operating condition based on the first input variable, the second input variable, and the corresponding output variable in the target variable combination in the reverse short operating condition.

[0091] Optionally, when the preset operating condition is the high-speed operating condition, the fuzzy controller corresponding to the high-speed operating condition is constructed by using the fuzzy rule table corresponding to the high-speed operating condition based on the first input variable, the second input variable, and the corresponding output variable in the target variable combination in the high-speed operating condition.

[0092] In this embodiment, by constructing all possible combinations of different partitioning schemes into multiple variable combinations and systematically searching this space using the particle swarm optimization algorithm, the optimal set of input and output variable configurations can be determined. This avoids the traditional trial-and-error parameter tuning that relies on experience, improving design efficiency and the upper limit of controller performance.

[0093] Based on the above embodiments, this application also provides a process for determining the combination of target variables in the energy control method for hybrid vehicles. Figure 7 This is a flowchart illustrating the process of determining a combination of target variables in an energy control method for a hybrid vehicle provided in this application, as shown in the embodiment of the present application. Figure 7 As shown, in step 602 above, the particle swarm optimization algorithm is used to determine the combination of target variables that satisfies the preset optimization objective function from multiple combinations of variables, including: Step 701: Based on each combination of variables, determine the fuel cell energy consumption prediction data, cumulative state of charge deviation data, and cumulative number of fuel cell starts corresponding to the variable combination.

[0094] The fuel cell energy consumption prediction data, cumulative state of charge (SOC) deviation data, and cumulative fuel cell start-up count are all data within a preset operating cycle. If the operating condition is a reverse short operating condition, the corresponding preset operating cycle is 3600 seconds; if the operating condition is a high-speed operating condition, the preset operating cycle is 4 hours. The fuel cell energy consumption prediction data is the predicted energy consumption of the fuel cell within the preset operating cycle. When the fuel cell is a hydrogen fuel cell, the fuel cell energy consumption prediction data is the hydrogen energy consumption prediction data. The cumulative SOC deviation data is determined based on the difference between the SOC parameters within the preset operating cycle and the reference SOC parameters. The cumulative fuel cell start-up count is the fuel cell start-stop data within the preset operating cycle.

[0095] Optionally, based on each combination of variables, the predicted fuel cell energy consumption data corresponding to that combination is determined. Cumulative deviation data of state of charge and the cumulative number of fuel cell starts ,in, For the desired values ​​of the charge state parameters, Let t be the state-of-charge parameters of the power battery at time t.

[0096] Step 702: Based on the corresponding fuel cell energy consumption prediction data, cumulative state of charge deviation data, and cumulative number of fuel cell starts, calculate the target optimization parameters corresponding to the variable combination using a preset optimization objective function.

[0097] Optionally, based on each combination of variables, the predicted fuel cell energy consumption data corresponding to that combination is determined. Cumulative deviation data of state of charge and the cumulative number of fuel cell starts Using a pre-defined optimization objective function + Calculate the target optimization parameters corresponding to the combination of variables. .in, Based on hydrogen consumption, The maximum permissible fluctuation range of the baseline state of charge parameter, The maximum number of startups is the baseline; T is a complete cycle. , , The weighting coefficients for each optimization objective; if the operating condition is a reversible short-run operation condition. =0.4, =0.3, =0.3, =0.55; if the operating condition is high-speed operating condition =0.5, =0.4, =0.1, =0.6.

[0098] Step 703: Based on the target optimization parameters corresponding to multiple sets of variable combinations, use the particle swarm optimization algorithm to determine the target variable combinations.

[0099] Optionally, based on the target optimization parameters corresponding to multiple sets of variable combinations, the variable combination corresponding to the minimum value of the target optimization parameters is determined as the target variable combination.

[0100] In this embodiment, by configuring the parameters for each group of candidate controllers, simulations are performed under standard operating conditions, and their core performance indicators are extracted and converted into a comprehensive score. This clearly demonstrates the advantages and disadvantages of different design schemes, thereby intelligently and efficiently determining the combination of target variables from a vast space of parameter combinations.

[0101] Based on the same inventive concept, this application also provides an energy control device for a hybrid vehicle corresponding to the energy control method for a hybrid vehicle. Since the principle of the device in this application is similar to the energy control method for a hybrid vehicle described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0102] Figure 8 This is a schematic diagram of the structure of an energy control device for a hybrid vehicle provided in an embodiment of this application, as shown below. Figure 8 As shown, the device includes: an acquisition module 801, an identification module 802, a control module 803, and a determination module 804; wherein, the acquisition module 801 is used to acquire vehicle driving information from the real-time data stream of the hybrid vehicle for the preset time window closest to the current time; The identification module 802 is used to identify the operating condition of the hybrid vehicle based on the vehicle driving information in the preset time window, and to obtain the current operating condition of the hybrid vehicle at the current time. The control module 803 is used to perform fuzzy control using a fuzzy controller corresponding to the current operating condition based on the state of charge parameters of the power battery in the hybrid vehicle and the power demand of the hybrid vehicle, so as to obtain the first output power of the fuel cell in the hybrid vehicle. The determining module 804 is used to determine the second output power of the power battery based on the required power and the first output power of the fuel cell; the first output power and the second output power are respectively used to control the energy output of the fuel cell and the power battery in the next time window.

[0103] In one possible implementation, the identification module 802 is specifically used to: extract current driving feature parameters from the vehicle driving data in the preset time window; Based on the current driving characteristic parameters, a preset operating condition identification model is used to identify the operating condition and obtain the current operating condition.

[0104] In one possible implementation, the identification module 802 is further configured to: acquire a database of multiple preset operating conditions; the database stores actual vehicle driving data under the corresponding operating conditions; Feature recognition is performed on the operating condition database of the preset operating conditions to obtain the operating feature library of the preset operating conditions. The operating feature library stores multiple sets of driving feature parameters under the preset operating conditions. The preset operating conditions recognition model is obtained by training the model based on the operating feature library of multiple preset operating conditions.

[0105] In one possible implementation, the control module 803 is further configured to: construct a first input variable, a second input variable, and an output variable based on the preset battery state of charge range, the preset demand power range, and the preset output power range of the fuel cell, respectively, wherein the first input variable includes: multiple first input fuzzy subsets within the preset battery state of charge range, the second input variable includes: multiple second input fuzzy subsets of the preset demand power range under each preset operating condition, and the output variable includes: multiple output fuzzy subsets of the preset output power range under each preset operating condition; Based on the first input variable, the second input variable corresponding to each preset operating condition, and the corresponding output variable, a fuzzy controller corresponding to each preset operating condition is constructed using the fuzzy rule table corresponding to each preset operating condition.

[0106] In one possible implementation, the control module 803 is specifically used to: divide the preset battery state of charge interval multiple times to obtain multiple sets of the first input variables; the division of the first input fuzzy subset in the first input variables of different sets is different; The preset power demand range is divided into multiple intervals to obtain multiple sets of second input variables; the division of the second input fuzzy subset in the second input variables of different sets is different; The preset output power range of the fuel cell is divided into multiple intervals to obtain multiple sets of output variables; the division of the output fuzzy subsets in the output variables of different sets is different.

[0107] In one possible implementation, the control module 803 is specifically configured to: obtain multiple sets of variable combinations corresponding to the preset operating condition based on multiple sets of first input variables, multiple sets of second input variables, and multiple sets of output variables; the variable combination includes: a first input variable, a second input variable, and an output variable; The particle swarm optimization algorithm is used to determine the combination of target variables that satisfies the preset optimization objective function from multiple combinations of the variables. Based on the first input variable, the second input variable, and the corresponding output variable in the target variable combination, a fuzzy controller corresponding to each preset operating condition is constructed using the fuzzy rule table corresponding to each preset operating condition.

[0108] In one possible implementation, the control module 803 is specifically used to: determine the fuel cell energy consumption prediction data, cumulative state of charge deviation data, and cumulative number of fuel cell starts corresponding to each group of variable combinations; Based on the corresponding fuel cell energy consumption prediction data, the cumulative state of charge deviation data, and the cumulative number of fuel cell starts, the target optimization parameters corresponding to the variable combination are calculated using the preset optimization objective function. Based on the target optimization parameters corresponding to multiple sets of variable combinations, the particle swarm optimization algorithm is used to determine the target variable combinations.

[0109] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0110] This application also provides an energy control device. Figure 9 This is a schematic diagram of the structure of an energy control device provided in an embodiment of this application, as shown below. Figure 9 As shown, the energy control device 900 includes a processor 901 and a memory 902, and optionally, a bus 903. The memory 902 stores machine-readable instructions executable by the processor 901. When the energy control device 900 is running, the processor 901 and the memory 902 communicate via the bus 903. When the machine-readable instructions are executed by the processor 901, the steps of the energy control method for the hybrid vehicle described above are performed.

[0111] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the energy control method for the hybrid vehicle described above.

[0112] This application also provides a vehicle control system. Figure 10This is a schematic diagram of the structure of a vehicle control system provided in an embodiment of this application, such as... Figure 10 As shown, the system includes: an energy control device 900, a fuel cell 1001, a power battery 1002, and a vehicle controller 1003; the energy control device 900 is connected to the fuel cell 1001 and the power battery 1002 respectively, and the energy control device 900 and the vehicle controller 1003 are connected in communication to obtain the power demand of the hybrid vehicle and the vehicle driving information of the preset time window. The energy control device 900 is used to execute the energy control method for the hybrid vehicle. The fuel cell 1001 includes a fuel cell control system, a fuel cell system, a fuel storage system, and a bidirectional DC-DC converter. The power battery 1002 also includes a battery management system, which controls the power battery 1002. The energy control device 900 sends the first output power of the fuel cell 1001 to the fuel cell control system. The fuel cell control system controls the output of the fuel cell system and the fuel storage system based on the first output power. The energy control device 900 sends the second output power of the power battery to the battery management system. The battery management system controls the output of the power battery 1001 based on the second output power. The energy control device 900 obtains the required power and vehicle driving information within a preset time window through the vehicle controller 1003. The vehicle controller 1003 is connected to the powertrain of the vehicle, and the powertrain is connected to the drive axle of the vehicle to obtain the required power and vehicle driving information within the preset time window. The vehicle controller 1003 is also connected to a multi-function controller, which is connected to the power battery and the bidirectional DC-DC converter, which is connected to the fuel cell system in the fuel cell 1001.

[0113] This application also provides a vehicle. Figure 11 This application provides a schematic diagram of the structure of a vehicle, as shown in the embodiment of the present application. Figure 11 As shown, the vehicle includes at least: a vehicle body 1101 and the aforementioned vehicle control system 1000.

[0114] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0115] Furthermore, the functional units in the various embodiments of this application 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. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a 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 described in the various embodiments of this invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0116] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. An energy control method for a hybrid vehicle, characterized in that, The method includes: Obtain vehicle driving information from the real-time data stream of hybrid vehicles for the preset time window closest to the current time; Based on the vehicle driving information within the preset time window, the operating condition of the hybrid vehicle is identified to obtain the current operating condition of the hybrid vehicle at the current time. Based on the state of charge parameters of the power battery in the hybrid vehicle and the power demand of the hybrid vehicle, fuzzy control is performed using a fuzzy controller corresponding to the current operating condition to obtain the first output power of the fuel cell in the hybrid vehicle. Based on the required power and the first output power of the fuel cell, the second output power of the power battery is determined; the first output power and the second output power are respectively used to control the energy output of the fuel cell and the power battery in the next time window.

2. The method according to claim 1, characterized in that, The step of identifying the operating condition of the hybrid vehicle based on the vehicle driving information within the preset time window to obtain the current operating condition of the hybrid vehicle at the current time includes: Extract current driving characteristic parameters from the vehicle driving data within the preset time window; Based on the current driving characteristic parameters, a preset operating condition identification model is used to identify the operating condition and obtain the current operating condition.

3. The method according to claim 2, characterized in that, Before obtaining the current operating condition by performing operating condition identification using a preset operating condition identification model based on the current driving characteristic parameters, the method further includes: Obtain a database of operating conditions for multiple preset operating conditions; the database stores actual vehicle driving data under the corresponding operating conditions. Feature recognition is performed on the operating condition database of the preset operating conditions to obtain the operating feature library of the preset operating conditions. The operating feature library stores multiple sets of driving feature parameters under the preset operating conditions. The preset operating conditions recognition model is obtained by training the model based on the operating feature library of multiple preset operating conditions.

4. The method according to claim 1, characterized in that, Before obtaining the first output power of the fuel cell in the hybrid vehicle by performing fuzzy control using a fuzzy controller corresponding to the current operating condition based on the state-of-charge parameters of the power battery in the hybrid vehicle and the power demand of the hybrid vehicle, the method further includes: Based on the preset battery state of charge range, preset power demand range, and preset output power range of the power battery, a first input variable, a second input variable, and an output variable are constructed respectively. The first input variable includes multiple first input fuzzy subsets within the preset battery state of charge range. The second input variable includes multiple second input fuzzy subsets of the preset power demand range under each preset operating condition. The output variable includes multiple output fuzzy subsets of the preset output power range under each preset operating condition. Based on the first input variable, the second input variable corresponding to each preset operating condition, and the corresponding output variable, a fuzzy controller corresponding to each preset operating condition is constructed using the fuzzy rule table corresponding to each preset operating condition.

5. The method according to claim 4, characterized in that, The first input variable, the second input variable, and the output variable are constructed based on the preset battery state of charge range, the preset power demand range, and the preset output power range of the fuel cell, respectively, including: The preset battery state of charge interval is divided into multiple intervals to obtain multiple sets of the first input variables; the division of the first input fuzzy subset in the first input variables of different sets is different; The preset power demand range is divided into multiple intervals to obtain multiple sets of second input variables; the division of the second input fuzzy subset in the second input variables of different sets is different; The preset output power range of the fuel cell is divided into multiple intervals to obtain multiple sets of output variables; the division of the output fuzzy subsets in the output variables of different sets is different.

6. The method according to claim 5, characterized in that, The step of constructing a fuzzy controller corresponding to each preset operating condition based on the first input variable, the second input variable corresponding to each preset operating condition, and the corresponding output variable, using a fuzzy rule table corresponding to each preset operating condition, includes: Based on multiple sets of first input variables, multiple sets of second input variables, and multiple sets of output variables, obtain multiple sets of variable combinations corresponding to the preset operating conditions; the variable combination includes: one first input variable, one second input variable, and one output variable; The particle swarm optimization algorithm is used to determine the combination of target variables that satisfies the preset optimization objective function from multiple combinations of the variables. Based on the first input variable, the second input variable, and the corresponding output variable in the target variable combination, a fuzzy controller corresponding to each preset operating condition is constructed using the fuzzy rule table corresponding to each preset operating condition.

7. The method according to claim 6, characterized in that, The step of employing a particle swarm optimization algorithm to determine the target variable combination that satisfies the preset optimization objective function from multiple sets of variable combinations includes: Based on each set of variable combinations, determine the fuel cell energy consumption prediction data, cumulative state of charge deviation data, and cumulative number of fuel cell starts corresponding to the variable combination; Based on the corresponding fuel cell energy consumption prediction data, the cumulative state of charge deviation data, and the cumulative number of fuel cell starts, the target optimization parameters corresponding to the variable combination are calculated using the preset optimization objective function. Based on the target optimization parameters corresponding to multiple sets of variable combinations, the particle swarm optimization algorithm is used to determine the target variable combinations.

8. An energy control device, characterized in that, The energy control device includes a processor and a memory, the memory storing machine-readable instructions executable by the processor. When the computer device is running, the processor executes the machine-readable instructions to perform the steps of the energy control method for a hybrid vehicle as described in any one of claims 1 to 7.

9. A vehicle control system, characterized in that, The vehicle control system includes: an energy control device, a fuel cell, a power battery, and a vehicle controller; the energy control device is connected to the fuel cell and the power battery respectively, and the energy control device and the vehicle controller are communicatively connected to obtain the power demand of the hybrid vehicle and the vehicle driving information within a preset time window; The energy control device is used to execute the energy control method of the hybrid vehicle according to any one of claims 1 to 7.

10. A hybrid vehicle, characterized in that, The hybrid vehicle includes at least: a vehicle body, and the vehicle control system of claim 9 above.

Images