Energy management method, device and vehicle

Abstract

The application provides an energy management method, device and vehicle. The method determines a target driving mode of the vehicle based on driving data of the vehicle in a first time interval, and outputs a target value of an oil-electricity conversion factor to an energy management control unit based on the target driving mode, so as to trigger the energy management control unit to perform energy management control on the vehicle based on the target value of the oil-electricity conversion factor in a second time interval. The first time interval includes a time interval before the current time, and the second time interval includes a time interval after the current time. Therefore, the target value of the oil-electricity conversion factor in the future time interval can be predicted according to the driving mode of the vehicle in the historical time interval, and the energy consumption level of the vehicle can be effectively reduced. Meanwhile, the method does not need to increase hardware devices such as cameras, radars and high-precision maps, and thus the hardware cost of the vehicle is not increased.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and more particularly to an energy management method, device, and vehicle. Background Technology

[0002] As global warming becomes increasingly severe, reducing carbon emissions and improving energy efficiency have become important development directions across various sectors. Automobiles, as crucial modes of transportation, consume enormous amounts of energy; therefore, strengthening vehicle energy management and improving fuel economy and electrical energy efficiency are of great significance for reducing greenhouse gas emissions. With the rise of new energy vehicles such as electric vehicles and hybrid vehicles, effectively managing the energy of onboard batteries has become a key technology for improving vehicle fuel economy and electrical energy efficiency.

[0003] Currently, vehicles typically employ rule-based energy management strategies. However, this strategy has reached a bottleneck, failing to further improve fuel economy and electrical energy efficiency, thus hindering the effective reduction of overall vehicle energy consumption. Furthermore, existing energy management methods also utilize cameras, radar, and high-precision maps to acquire road condition information and perform predictive energy management based on this information. However, this method requires additional hardware such as cameras, radar, and high-precision maps, significantly increasing the overall vehicle hardware cost. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides an energy management method, apparatus, and vehicle to solve the problem that existing technologies cannot effectively reduce the energy consumption level of the entire vehicle without increasing the vehicle's hardware costs.

[0005] To achieve the above technical objectives, the embodiments of this application provide the following technical solutions:

[0006] Firstly, the embodiments of this specification provide an energy management method, including:

[0007] The target driving mode of the vehicle is determined based on the vehicle's driving data within a first time interval; the first time interval includes the time interval before the current moment.

[0008] Based on the target driving mode, a target value for the hybrid power conversion factor is determined, and the target value of the hybrid power conversion factor is output to the energy management control unit to trigger the energy management control unit to perform energy management control on the vehicle based on the target value of the hybrid power conversion factor in a second time interval, the second time interval including the time interval after the current moment.

[0009] In one implementation, the target driving mode includes a target driving condition and the driver's driving style; the driving data includes first data corresponding to driving state parameters and second data corresponding to driving control input parameters.

[0010] The determination of the vehicle's target driving mode based on the vehicle's driving data within a first time interval includes:

[0011] Based on the first statistical information corresponding to the first data, the target driving condition is determined, and based on the second statistical information corresponding to the second data, the driving style is determined.

[0012] In one implementation, determining the target value of the hybrid conversion factor based on the target driving mode includes:

[0013] Based on the target driving conditions and the predetermined correspondence, a preset value space for the oil-electric conversion factor under the target driving conditions is determined and used as the target value space; the predetermined correspondence includes multiple candidate driving conditions and a preset value space for the oil-electric conversion factor under each candidate driving condition.

[0014] Based on the driving style and the target value space, the target value of the oil-electric conversion factor is determined.

[0015] In one embodiment, the process of determining the preset value space of the oil-electric conversion factor under the candidate driving conditions includes:

[0016] Based on vehicle speed test information corresponding to at least one standard driving cycle, determine multiple target vehicle speed sequences for the vehicle under the candidate driving conditions;

[0017] During the vehicle simulation operation based on the physical model of the vehicle controlled by the target vehicle speed sequence, the oil-electric conversion factor is iteratively optimized based on the SOC simulation value output by the physical model to obtain the oil-electric conversion factor correction value corresponding to the target vehicle speed sequence.

[0018] Based on the correction value of the oil-electric conversion factor corresponding to each of the target vehicle speed sequences, the preset value space of the oil-electric conversion factor under the candidate driving conditions is determined.

[0019] In one implementation, the iterative optimization of the oil-electric conversion factor based on the SOC simulation value output by the physical model to obtain the corrected oil-electric conversion factor value corresponding to the target vehicle speed sequence includes:

[0020] In the current iteration, the current value of the oil-electric conversion factor is output to the energy management control unit to trigger the energy management control unit to output an energy distribution control command to the physical model and obtain the SOC simulation value output by the physical model; the current value of the oil-electric conversion factor is the preferred value of the oil-electric conversion factor or the initial oil-electric conversion factor;

[0021] If the deviation between the simulated SOC value and the target SOC value corresponding to the candidate driving condition is less than or equal to a preset deviation threshold, then the current value of the oil-electric conversion factor is used as the correction value of the oil-electric conversion factor corresponding to the target vehicle speed sequence.

[0022] If the deviation value is greater than the preset deviation threshold, the preferred value of the oil-electricity conversion factor in the next iteration is determined based on the SOC simulation value, and the next iteration is executed.

[0023] In one implementation, determining the preferred value of the oil-electricity conversion factor for the next iteration based on the SOC simulation value includes:

[0024] Based on the relationship between the simulated SOC value and the target SOC value, and the predetermined trend of the simulated SOC value with respect to the oil-electric conversion factor, the first endpoint of the candidate value space of the oil-electric conversion factor in the next iteration is determined from the two endpoints of the candidate value space of the oil-electric conversion factor in the current iteration, and the current value of the oil-electric conversion factor in the current iteration is taken as the second endpoint of the candidate value space of the oil-electric conversion factor in the next iteration.

[0025] Based on the candidate value space of the oil-electricity conversion factor in the next iteration, the preferred value of the oil-electricity conversion factor in the next iteration is determined.

[0026] In one implementation, determining multiple target vehicle speed sequences for the vehicle under the candidate driving conditions based on vehicle speed test information corresponding to at least one standard driving cycle includes:

[0027] Based on the vehicle speed range corresponding to the candidate driving conditions, the target data segment in the vehicle speed test information corresponding to each standard driving cycle is obtained respectively.

[0028] The target data segments are spliced ​​together to obtain multiple target vehicle speed sequences under the candidate driving conditions.

[0029] In one implementation, determining the target value of the hybrid power conversion factor based on the driving style and the target value space includes:

[0030] Based on the energy demand level under the driving style, the predetermined trend of the oil-electric conversion factor with the energy demand level, and the target value space, the target value of the oil-electric conversion factor is determined.

[0031] Secondly, embodiments of this specification provide an energy management device, including:

[0032] The first processing module is used to determine the target driving mode of the vehicle based on the vehicle's driving data within a first time interval; the first time interval includes the time interval before the current moment.

[0033] The second processing module is used to determine the target value of the oil-electric conversion factor based on the target driving mode, and output the target value of the oil-electric conversion factor to the energy management control unit, so as to trigger the energy management control unit to perform energy management control on the vehicle based on the target value of the oil-electric conversion factor in a second time interval, the second time interval including the time interval after the current moment.

[0034] Thirdly, embodiments of this specification provide a vehicle including an energy management control unit and an energy management device as described above.

[0035] Fourthly, embodiments of this specification provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the energy management method as described in any of the preceding claims.

[0036] Fifthly, embodiments of this specification provide a computer program product or computer program, the computer program product including a computer program stored in a computer-readable storage medium; a processor of the computer device reads the computer program from the computer-readable storage medium, and when the processor executes the computer program, it implements the energy management method as described in any of the preceding claims.

[0037] As can be seen from the above technical solutions, the embodiments of this application provide an energy management method, device, and vehicle. The method determines the target driving mode of the vehicle based on the vehicle's driving data in a first time interval, determines the target value of the fuel-electric conversion factor based on the target driving mode, and outputs the target value of the fuel-electric conversion factor to the energy management control unit. This triggers the energy management control unit to perform energy management control on the vehicle in a second time interval based on the target value of the fuel-electric conversion factor. The first time interval includes the time interval before the current moment, and the second time interval includes the time interval after the current moment. This allows the target value of the fuel-electric conversion factor in the future time interval to be predicted based on the vehicle's driving mode in the historical time interval, thereby achieving predictive energy management of the vehicle. Furthermore, when the vehicle is running smoothly (i.e., there is no abrupt change in vehicle operating conditions), energy management control based on the predicted target value of the fuel-electric conversion factor can effectively reduce the energy consumption level of the entire vehicle. At the same time, the method of this embodiment does not require the addition of hardware devices such as cameras, radar, and high-precision maps, thus avoiding any increase in the vehicle's hardware costs. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating an energy management method for implementing this specification.

[0040] Figure 2 This is a schematic diagram illustrating the predetermined trend of SOC simulation value with respect to the oil-electricity conversion factor, provided for the implementation of this specification.

[0041] Figure 3 This is a schematic diagram illustrating the extraction of target data segments from vehicle speed test information corresponding to a standard driving cycle, as provided for implementation of this specification.

[0042] Figure 4 This is a schematic diagram of an energy management device provided for embodiments of this specification. Detailed Implementation

[0043] Unless otherwise defined, the technical or scientific terms used in the embodiments of this specification shall have the ordinary meaning understood by one of ordinary skill in the art to which this specification pertains. The terms "first," "second," and similar terms used in the embodiments of this specification do not indicate any order, quantity, or importance, but are merely used to avoid confusion of constituent elements.

[0044] Unless the context otherwise requires, throughout this specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of this specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this specification. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0045] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0046] Overview

[0047] As described in the background section, with the increasingly severe problem of global warming, reducing carbon emissions and improving energy efficiency have become important development directions in various fields. Automobiles, as important means of transportation, consume enormous amounts of energy; therefore, strengthening vehicle energy management and improving fuel economy and electrical energy efficiency are of great significance for reducing greenhouse gas emissions. With the rise of new energy vehicles such as electric vehicles and hybrid vehicles, effectively managing the energy of onboard batteries has become a key technology for improving vehicle fuel economy and electrical energy efficiency. This not only relates to the vehicle's driving range but also directly affects the user experience. For example, with the improvement of living standards, users are paying more attention to driving pleasure, comfort, and economy; effectively managing the energy of onboard batteries can provide a technological foundation for achieving these goals.

[0048] Currently, vehicles typically employ rule-based energy management strategies. However, this strategy has reached a bottleneck, failing to further improve fuel economy and electrical efficiency, thus hindering the overall energy consumption reduction. The inventors have discovered that predictive energy management can proactively predict and optimize vehicle energy usage, thereby effectively improving fuel economy and electrical efficiency. However, existing predictive energy management methods typically rely on cameras, radar, and high-precision maps to acquire road condition information and perform predictive energy management based on this information. This method requires additional hardware such as cameras, radar, and high-precision maps, significantly increasing the overall vehicle hardware cost.

[0049] To address the problem that traditional methods cannot effectively reduce vehicle energy consumption without increasing hardware costs, the energy management method in this application determines the vehicle's target driving mode based on driving data within a first time interval, determines the target value of the fuel-electric conversion factor based on the target driving mode, and outputs the target value of the fuel-electric conversion factor to the energy management control unit. This triggers the energy management control unit to perform energy management control on the vehicle within a second time interval based on the target value of the fuel-electric conversion factor. The first time interval includes the time interval before the current moment, and the second time interval includes the time interval after the current moment. This allows the target value of the fuel-electric conversion factor in the future time interval to be predicted based on the vehicle's driving mode in historical time intervals, enabling predictive energy management. Furthermore, when the vehicle is operating smoothly (i.e., without sudden changes in vehicle operating conditions), energy management control based on the predicted target value of the fuel-electric conversion factor can effectively reduce the vehicle's energy consumption. Simultaneously, this method eliminates the need for additional hardware such as cameras, radar, and high-precision maps, thus avoiding any increase in vehicle hardware costs.

[0050] Based on the above inventive concept, the energy management method provided in the embodiments of this specification will be described exemplarily below.

[0051] Exemplary methods

[0052] This specification provides an energy management method, such as... Figure 1 As shown, it includes:

[0053] S101. Based on the vehicle's driving data within a first time interval, determine the vehicle's target driving mode; the first time interval includes the time interval before the current moment.

[0054] Specifically, the first time interval can include the time interval preceding the current moment. For example, the first time interval can be the time interval immediately adjacent to the current moment and preceding the current moment, or it can be a continuous time interval including the current moment and the time interval preceding the current moment. The length of the first time interval can be set according to actual needs, as long as it can effectively identify the driving mode; for example, it can be set to 100 seconds.

[0055] The target driving mode for a vehicle can be the driving mode of the vehicle within a specific time interval. The driving mode can include driving conditions, as well as the driver's driving style, etc.

[0056] S102. Based on the target driving mode, determine the target value of the oil-electric conversion factor and output the target value of the oil-electric conversion factor to the energy management control unit, so as to trigger the energy management control unit to perform energy management control on the vehicle based on the target value of the oil-electric conversion factor in a second time interval, wherein the second time interval includes the time interval after the current moment.

[0057] Specifically, the oil-to-electricity conversion factor can be used to characterize the cost per unit of energy consumption; that is, the oil-to-electricity conversion factor can be understood as a virtual price factor.

[0058] In implementation, the target value of the hybrid power conversion factor can be determined based on the target driving mode. For example, the target value of the hybrid power conversion factor can be determined based on the target driving mode and the predetermined correspondence between the driving mode and the hybrid power conversion factor. This predetermined correspondence can be determined in advance based on the vehicle's target operating data, which may include the vehicle's historical operating data or vehicle speed test information corresponding to a standard driving cycle. For example, sub-operating data for each operating condition can be determined based on the target operating data, and the vehicle's physical model can be controlled to simulate vehicle operation based on the sub-operating data, thereby optimizing the hybrid power conversion factor corresponding to each driving condition during the vehicle simulation operation.

[0059] After obtaining the target value of the hybrid power conversion factor, this target value can be output to the energy management control unit to trigger the control unit to perform energy management control on the vehicle based on the target value of the hybrid power conversion factor within a second time interval. The second time interval can include the time interval following the current moment; for example, it can be the time interval immediately adjacent to and following the current moment. The length of the second time interval can be set according to actual needs, as long as it meets the vehicle's energy consumption requirements; for example, it can be set to 10 seconds.

[0060] Since the target value of the oil-electric conversion factor is determined based on the driving mode of the vehicle in the first time interval before the current moment, under the condition that the vehicle is running smoothly (i.e., there is no abrupt change in the vehicle's operating condition), the applicability of the target value of the oil-electric conversion factor in the second time interval can be effectively guaranteed. Furthermore, by predicting the driving mode and determining and adjusting the oil-electric conversion factor in advance based on the prediction results, the energy consumption level of the whole vehicle can be effectively reduced.

[0061] In implementation, the energy management control unit, when managing the vehicle's energy based on the target value of the fuel-to-electric conversion factor, can use the target value of the fuel-to-electric conversion factor as the initial value. It then employs ECMS (Equivalent Consumption Minimization Strategy) to control various controlled components of the vehicle, minimizing equivalent fuel consumption and achieving optimal fuel economy, thus realizing energy conservation and emission reduction. These controlled components may include the engine, motor, and transmission.

[0062] At the same time, the oil-electric conversion factor can be corrected in real time based on the SOC (State of Charge) detection value of the on-board battery during the energy management control of the vehicle, so as to realize dynamic closed-loop control of energy management and further reduce the energy consumption level of the whole vehicle.

[0063] Therefore, the method of this embodiment can predict the target value of the oil-electric conversion factor in the future time interval based on the vehicle's driving mode in the historical time interval, so as to realize predictive energy management of the vehicle. Thus, when the vehicle is running smoothly (i.e., there is no abrupt change in the vehicle's operating condition), energy management control of the vehicle based on the predicted target value of the oil-electric conversion factor can effectively reduce the energy consumption level of the entire vehicle. At the same time, the method of this embodiment does not require the addition of hardware equipment such as cameras, radar, and high-precision maps, thereby avoiding any increase in the vehicle's hardware costs.

[0064] In one feasible implementation, the target driving mode includes the target driving condition and the driver's driving style; the driving data includes first data corresponding to the driving state parameters and second data corresponding to the driving control input parameters;

[0065] The determination of the vehicle's target driving mode based on the vehicle's driving data within a first time interval includes:

[0066] Based on the first statistical information corresponding to the first data, the target driving condition is determined, and based on the second statistical information corresponding to the second data, the driving style is determined.

[0067] Specifically, the target driving mode can include the target driving condition and the driver's driving style. The target driving condition can include any one of multiple candidate driving conditions. In implementation, driving conditions can be categorized based on vehicle speed. For example, based on the speed fluctuation range, eight candidate driving conditions can be defined: 0~20 km / h, 20~40 km / h, 40~60 km / h, 60~80 km / h, 80~100 km / h, 100~120 km / h, 120~140 km / h, and above 140 km / h. The driver's driving style can be any one of multiple candidate driving styles, used to characterize the driver's driving habits. For example, candidate driving styles can include aggressive driving, mild driving, and normal driving. Aggressive driving involves frequent and forceful braking and acceleration, mild driving involves slow and smooth braking and acceleration, and normal driving is a driving style between aggressive and mild driving.

[0068] The vehicle's driving data within the first time interval can include first data corresponding to driving state parameters and second data corresponding to driving control input parameters. The driving state parameters characterize the vehicle's driving state and may specifically include vehicle speed, acceleration, and deceleration. The driving control input parameters characterize the parameters input by the driver to control the vehicle's driving state, such as accelerator pedal depth and brake pedal depth.

[0069] In implementation, the driving conditions within a first time interval can be determined based on the first statistical information corresponding to the first data, and this can be used as the target driving conditions. For any driving state parameter, the first statistical information corresponding to that driving state parameter may include the maximum value, minimum value, average value, etc., of that driving state parameter. For example, the first statistical information corresponding to the first data may include maximum vehicle speed, minimum vehicle speed, average vehicle speed, maximum acceleration, minimum acceleration, average acceleration, maximum deceleration, minimum deceleration, and average deceleration. The first statistical information can be weighted and summed based on predetermined weights to obtain a first weighted value. The target driving conditions are then determined based on the first weighted value and the predetermined correspondence between the first weighted value and the driving conditions. It is understood that the first data and / or the first statistical information corresponding to the first data can also be input into a pre-trained driving condition recognition model to output the target driving conditions. The driving condition recognition model can be a machine learning model such as a convolutional neural network.

[0070] Simultaneously, the driver's driving style within the first time interval can be determined based on the second statistical information corresponding to the second data. For any driving control input parameter, the second statistical information corresponding to that driving control input parameter includes the maximum value, minimum value, average value, maximum rate of change, minimum rate of change, and average rate of change of that driving control input parameter within the first time interval. For example, the second statistical information corresponding to the second data may include the maximum accelerator pedal depth, minimum accelerator pedal depth, average accelerator pedal depth, maximum rate of change of accelerator pedal depth, minimum rate of change of accelerator pedal depth, average rate of change of accelerator pedal depth, maximum brake pedal depth, minimum brake pedal depth, average brake pedal depth, maximum rate of change of brake pedal depth, minimum rate of change of brake pedal depth, and average rate of change of brake pedal depth. Furthermore, based on the predetermined weights corresponding to each piece of second statistical information, a weighted sum can be performed to obtain a second weighted value. The driver's driving style can then be determined based on the second weighted value and the predetermined correspondence between the second weighted value and the driving style. It is understandable that the second data and / or the second statistical information corresponding to the second data can also be input into a pre-trained driving style recognition model, so as to output the driver's driving style through the driving style recognition model. The driving style recognition model can be a machine learning model such as a convolutional neural network.

[0071] Therefore, the method of this embodiment can quickly and effectively determine the target driving conditions of the vehicle and the driver's driving style, and then accurately determine the target value of the oil-electric conversion factor based on the target driving conditions and the driver's driving style.

[0072] In one feasible implementation, determining the target value of the hybrid conversion factor based on the target driving mode includes:

[0073] Based on the target driving conditions and the predetermined correspondence, a preset value space for the oil-electric conversion factor under the target driving conditions is determined and used as the target value space; the predetermined correspondence includes multiple candidate driving conditions and a preset value space for the oil-electric conversion factor under each candidate driving condition.

[0074] Based on the driving style and the target value space, the target value of the oil-electric conversion factor is determined.

[0075] Specifically, the predetermined correspondence may include multiple candidate driving conditions and a preset value space for the fuel-electric conversion factor under each candidate driving condition. The preset value space may include one or more discrete values, and may also include one or more continuous numerical ranges. Therefore, the target driving condition can be matched with each candidate driving condition in the predetermined correspondence, and the preset value space corresponding to the successfully matched candidate driving condition can be used as the target value space for the fuel-electric conversion factor. This allows for the rapid and effective prediction of the target value space for the fuel-electric conversion factor over a future period based on the vehicle's historical driving conditions.

[0076] After determining the target value space of the oil-electric conversion factor, the target value of the oil-electric conversion factor can be further determined based on driving style and the target value space.

[0077] As a preferred embodiment, determining the target value of the hybrid power conversion factor based on the driving style and the target value space includes:

[0078] Based on the energy demand level under the driving style, the predetermined trend of the oil-electric conversion factor with the energy demand level, and the target value space, the target value of the oil-electric conversion factor is determined.

[0079] Specifically, for any given driving style, the energy demand level under that driving style can characterize the level of energy required during driving based on that style. For example, under the same driving conditions, a more aggressive driving style results in a higher energy demand, while a more moderate driving style results in a lower energy demand. In practice, the energy demand levels for aggressive driving, normal driving, and moderate driving can be high, medium, and low, respectively.

[0080] The predetermined trend of the oil-to-electric conversion factor with the degree of energy demand can be that, under the same driving conditions, the higher the degree of energy demand, the larger the oil-to-electric conversion factor, and the lower the degree of energy demand, the smaller the oil-to-electric conversion factor.

[0081] In practice, the target value of the fuel-electric conversion factor can be determined based on the energy demand level under the driving style, the predetermined trend of the fuel-electric conversion factor with the energy demand level, and the target value space of the fuel-electric conversion factor. For example, if the driver's driving style is aggressive, the maximum value in the target value space can be used as the target value of the fuel-electric conversion factor; if the driver's driving style is mild, the minimum value in the target value space can be used as the target value of the fuel-electric conversion factor; and if the driver's driving style is normal, the median or average value in the target value space can be used as the target value of the fuel-electric conversion factor. This can effectively improve the accuracy of the determination of the target value of the fuel-electric conversion factor.

[0082] Furthermore, for any preset value space of the hybrid-electric conversion factor, if the preset value space includes multiple discrete values ​​or one or more continuous numerical segments, the preset value space can be pre-divided into multiple subspaces, which can correspond to multiple candidate driving styles. In practice, the target value of the hybrid-electric conversion factor can also be determined based on the subspace corresponding to the driver's driving style in the target value space. For example, the median or average value of the subspace can be used as the target value of the hybrid-electric conversion factor.

[0083] It is understandable that if the target value space only includes a discrete value, that discrete value can be directly used as the target value of the oil-electricity conversion factor.

[0084] Therefore, the method of this embodiment can quickly and effectively determine the target value of the oil-electric conversion factor, and then effectively reduce the energy consumption level of the vehicle during the energy management control of the vehicle based on the target value of the oil-electric conversion factor in the second time interval.

[0085] In one feasible implementation, the process of determining the preset value space of the oil-electric conversion factor under the candidate driving conditions includes:

[0086] Based on vehicle speed test information corresponding to at least one standard driving cycle, determine multiple target vehicle speed sequences for the vehicle under the candidate driving conditions;

[0087] During the vehicle simulation operation based on the physical model of the vehicle controlled by the target vehicle speed sequence, the oil-electric conversion factor is iteratively optimized based on the SOC simulation value output by the physical model to obtain the oil-electric conversion factor correction value corresponding to the target vehicle speed sequence.

[0088] Based on the correction value of the oil-electric conversion factor corresponding to each of the target vehicle speed sequences, the preset value space of the oil-electric conversion factor under the candidate driving conditions is determined.

[0089] Specifically, a standard driving cycle is a standardized test procedure for evaluating vehicle performance, fuel economy, and emissions. There are various types of standard driving cycles, such as WLTC (Worldwide harmonized Lightvehicles Test Cycles), CLTC (China Light-duty vehicle Test Cycle), NEDC (New European Driving Cycle), FTP (Federal Test Procedure), JC08 (Japanese Test Cycle), US06 (Supplementary Test Procedure), and SCC (Supplementary City Cycle).

[0090] The WLTC (Wheel Threatened Scale) aims to provide new vehicles with fuel consumption and emissions data that more accurately reflect real-world driving conditions. The WLTC comprises four distinct phases, each representing a different driving scenario, ranging from low-speed city driving to highway cruising, covering a wide range of possible road conditions. These phases are conducted sequentially: Low, Medium, High, and Very High, forming a complete test cycle.

[0091] The CLTC was designed to better reflect real-world driving conditions on Chinese roads, aiming to provide a testing methodology that more closely approximates real-world fuel economy and emissions data.

[0092] NEDC includes driving conditions on urban, suburban, and rural roads, consisting of four urban driving cycles and one suburban driving cycle.

[0093] FTP is a standard developed by the U.S. Environmental Protection Agency (EPA) for certifying emissions of light-duty vehicles, including both cold start and hot start scenarios.

[0094] JC08 takes into account more real-world driving conditions, such as frequent acceleration and deceleration.

[0095] US06 is used to simulate vehicle performance under high-speed driving conditions and is usually used in conjunction with FTP.

[0096] SCC, also known as the Los Angeles Cycle, simulates a more demanding urban driving environment and is often used as a supplement to FTP.

[0097] The vehicle speed test information corresponding to a standard driving cycle can include the vehicle speed data of the tested vehicle at various times during the standard driving cycle test, such as a speed change curve over time. In practice, the target vehicle speed sequence under each candidate driving condition can be determined based on the vehicle speed test information corresponding to at least one standard driving cycle. For example, for any standard driving cycle, the vehicle speed test information corresponding to that standard driving cycle can include the vehicle speed test information of any tested vehicle that passed the test under that standard driving cycle.

[0098] For any candidate driving condition, the target vehicle speed sequence under that candidate driving condition may include multiple sequences. The target vehicle speed sequence can be continuous data showing the change of vehicle speed over time, and the range of vehicle speed values ​​in the target vehicle speed sequence is the same as the vehicle speed range corresponding to the candidate driving condition. In practice, based on the vehicle speed range corresponding to the candidate driving condition, target data segments can be extracted from each vehicle speed test information, and the target data segments can be spliced ​​together to obtain multiple target vehicle speed sequences. The duration of the target vehicle speed sequence can be a predetermined duration, for example, 1800 seconds.

[0099] For any target vehicle speed sequence, the correction value of the oil-electric conversion factor corresponding to the target vehicle speed sequence can be the optimal value of the oil-electric conversion factor obtained by optimizing the oil-electric conversion factor during the operation of the vehicle or the vehicle's physical model according to the target vehicle speed sequence.

[0100] The vehicle's physical model can include a powertrain system and an aerodynamic system. The powertrain system can include components such as the engine, transmission, and differential to simulate acceleration performance at different gears. The aerodynamic system is used to simulate air resistance when the vehicle is traveling at high speeds. The power transmission efficiency of each component in the powertrain system can be determined through real-vehicle testing, and the drag coefficient of the aerodynamic system can be obtained through real-vehicle wind tunnel testing or CFD (Computational Fluid Dynamics) simulation, thus ensuring the validity of the predetermined value space for the fuel-electric conversion factor under various candidate driving conditions.

[0101] During vehicle simulation, the SOC (State of Charge) simulated value output by the vehicle's physical model is the SOC of the onboard battery simulated by the physical model during speed following control based on the target vehicle speed sequence and energy management control simulation based on the fuel-electric conversion factor. In practice, the fuel-electric conversion factor can be iteratively optimized based on the simulated SOC value to obtain a corrected value corresponding to the target vehicle speed sequence. For example, if the deviation between the simulated SOC value and the target SOC value for the candidate driving condition is less than or equal to a preset deviation threshold, the optimized result of the fuel-electric conversion factor can be used as the corrected value for the target vehicle speed sequence. Therefore, by repeatedly executing this method under different target vehicle speed sequences, the corrected value of the fuel-electric conversion factor corresponding to each target vehicle speed sequence under the candidate driving condition can be obtained, thus effectively ensuring the validity of the determination results of the corrected values ​​for each target vehicle speed sequence.

[0102] Specifically, the preset value space of the fuel-electric conversion factor under the candidate driving condition can be determined based on the correction values ​​of the fuel-electric conversion factor corresponding to each target vehicle speed sequence under the candidate driving condition. For example, the preset value space may include the correction values ​​of the fuel-electric conversion factor corresponding to each target vehicle speed sequence under the candidate driving condition, and may also include curve segments or straight line segments fitted based on the correction values ​​of the fuel-electric conversion factor corresponding to some or all target vehicle speed sequences under the candidate driving condition. The specific settings can be configured according to actual needs, thereby enabling offline optimization of the value space of the fuel-electric conversion factor under different candidate driving conditions. This ensures the robustness of the determination results of the preset value space of the fuel-electric conversion factor under each candidate driving condition. Furthermore, during actual vehicle operation, predictive energy management control can be performed based on the offline optimization results of the fuel-electric conversion factor under the corresponding driving condition, which can effectively reduce the vehicle's energy consumption level.

[0103] In one feasible implementation, the iterative optimization of the oil-electric conversion factor based on the SOC simulation value output by the physical model to obtain the corrected oil-electric conversion factor value corresponding to the target vehicle speed sequence includes:

[0104] In the current iteration, the current value of the oil-electric conversion factor is output to the energy management control unit to trigger the energy management control unit to output an energy distribution control command to the physical model and obtain the SOC simulation value output by the physical model; the current value of the oil-electric conversion factor is the preferred value of the oil-electric conversion factor or the initial oil-electric conversion factor;

[0105] If the deviation between the simulated SOC value and the target SOC value corresponding to the candidate driving condition is less than or equal to a preset deviation threshold, then the current value of the oil-electric conversion factor is used as the correction value of the oil-electric conversion factor corresponding to the target vehicle speed sequence.

[0106] If the deviation value is greater than the preset deviation threshold, the preferred value of the oil-electricity conversion factor in the next iteration is determined based on the SOC simulation value, and the next iteration is executed.

[0107] Specifically, the current iteration can be any iteration in the iterative optimization process of the oil-electric conversion factor. In the current iteration, the current value of the oil-electric conversion factor can be output to the energy management control unit to trigger the energy management control unit to output energy allocation control commands to the physical model based on the current value of the oil-electric conversion factor. Thus, the physical model can output the SOC simulation value. Specifically, when the current iteration is the first iteration, the current value of the oil-electric conversion factor can be the initial oil-electric conversion factor. The initial oil-electric conversion factor can be a predetermined value; for example, it can be randomly selected within the interval formed by the upper and lower limits of the oil-electric conversion factor, or the median of the interval can be used as the initial oil-electric conversion factor. When the current iteration is not the first iteration, the current value of the oil-electric conversion factor can be the optimal value of the oil-electric conversion factor in the current iteration determined based on the SOC simulation value output by the physical model in the previous iteration.

[0108] After obtaining the SOC simulation value output by the physical model, the deviation between the SOC simulation value and the SOC target value corresponding to the candidate driving condition can be obtained. Based on the comparison between the deviation value and the preset deviation threshold, it is determined whether the condition for ending the iteration is met. The deviation between the SOC simulation value and the SOC target value corresponding to the candidate driving condition is the absolute value of the difference between the SOC simulation value and the SOC target value corresponding to the candidate driving condition.

[0109] When the deviation value is less than or equal to the preset deviation threshold, it can be determined that the condition for ending the iteration is met, and the current value of the oil-electric conversion factor is used as the correction value of the oil-electric conversion factor corresponding to the target vehicle speed sequence.

[0110] When the deviation value exceeds the preset deviation threshold, it can be determined that the condition for ending the iteration is not met. The oil-electric conversion factor is updated based on the SOC simulation value output by the physical model in the current iteration to obtain the optimal value of the oil-electric conversion factor in the next iteration, and the next iteration is executed. This can effectively ensure the validity of the determination result of the oil-electric conversion factor correction value corresponding to each target vehicle speed sequence. Thus, in the process of determining the target value of the oil-electric conversion factor based on the preset value space determined by the oil-electric conversion factor correction value corresponding to each target vehicle speed sequence, and performing predictive energy management control of the vehicle based on the target value of the oil-electric conversion factor, effective energy management of the vehicle battery can be achieved, thereby further improving the vehicle's fuel economy and electric energy utilization rate, and reducing the overall vehicle energy consumption level.

[0111] In one feasible implementation, determining the preferred value of the oil-electricity conversion factor in the next iteration based on the SOC simulation value includes:

[0112] Based on the relationship between the simulated SOC value and the target SOC value, and the predetermined trend of the simulated SOC value with respect to the oil-electric conversion factor, the first endpoint of the candidate value space of the oil-electric conversion factor in the next iteration is determined from the two endpoints of the candidate value space of the oil-electric conversion factor in the current iteration, and the current value of the oil-electric conversion factor in the current iteration is taken as the second endpoint of the candidate value space of the oil-electric conversion factor in the next iteration.

[0113] Based on the candidate value space of the oil-electricity conversion factor in the next iteration, the preferred value of the oil-electricity conversion factor in the next iteration is determined.

[0114] Specifically, the predetermined trend of the SOC simulated value with respect to the oil-electric conversion factor can be that, under the same driving conditions, the larger the oil-electric conversion factor, the larger the SOC simulated value. For example, the predetermined trend of the SOC simulated value with respect to the oil-electric conversion factor can be as follows: Figure 2 As shown, Figure 2 In this context, λ represents the hybrid-electric conversion factor. It is understood that under different driving conditions, the simulated SOC value can exhibit the same predetermined trend of variation with the hybrid-electric conversion factor. In practice, the predetermined trend of variation of the simulated SOC value with the hybrid-electric conversion factor can be determined in advance through experiments. For example, multiple sampling points can be obtained within the threshold range of the hybrid-electric conversion factor, and the simulated SOC value corresponding to each sampling point can be obtained during the simulation of the vehicle's physical model under the same driving conditions to obtain the predetermined trend of variation of the simulated SOC value with the hybrid-electric conversion factor. For any given sampling point, the simulated SOC value corresponding to that sampling point can be the SOC of the on-board battery obtained through the physical model simulation when performing energy management control simulation on the vehicle's physical model based on that sampling point.

[0115] In the iterative optimization of the oil-electricity conversion factor, for any given iteration, in determining the optimal value of the oil-electricity conversion factor for the next iteration, the candidate value space of the oil-electricity conversion factor for the next iteration can be determined first. Specifically, based on the relationship between the simulated SOC value and the target SOC value in the current iteration, and the predetermined trend of the simulated SOC value changing with the oil-electricity conversion factor, the first endpoint of the candidate value space for the oil-electricity conversion factor in the next iteration can be determined from the two endpoints of the candidate value space of the oil-electricity conversion factor in the current iteration, and the current value of the oil-electricity conversion factor in the current iteration can be used as the second endpoint of the candidate value space of the oil-electricity conversion factor in the next iteration. That is, the candidate value space of the oil-electricity conversion factor in the next iteration is one of the two sub-value spaces within the candidate value space of the oil-electricity conversion factor in the current iteration.

[0116] Among them, the two sub-value spaces in the candidate value space of the oil-electric conversion factor in the current iteration can be determined based on the candidate value space of the oil-electric conversion factor in the current iteration and the current value of the oil-electric conversion factor in the current iteration. The first endpoints of the two sub-value spaces can be the two endpoints of the candidate value space of the oil-electric conversion factor in the current iteration, and the first endpoints of the two sub-value spaces can both be the current value of the oil-electric conversion factor in the current iteration.

[0117] In practice, the method for determining the first endpoint of the candidate value space for the oil-electricity conversion factor in the next iteration may include: if the simulated SOC value in the current iteration is greater than the target SOC value, then the endpoint in the decreasing direction of the simulated SOC value in the predetermined trend among the two endpoints of the candidate value space for the oil-electricity conversion factor in the current iteration is taken as the first endpoint of the candidate value space for the oil-electricity conversion factor in the next iteration. For example, the endpoint with the smaller value among the two endpoints of the candidate value space for the oil-electricity conversion factor in the current iteration is taken as the first endpoint of the candidate value space for the oil-electricity conversion factor in the next iteration. If the simulated SOC value in the current iteration is less than the target SOC value, then the endpoint of the candidate value space of the oil-electric conversion factor in the current iteration, which is in the direction of the increase of the simulated SOC value in the predetermined trend, is taken as the first endpoint of the candidate value space of the oil-electric conversion factor in the next iteration. For example, the endpoint with the larger value in the candidate value space of the oil-electric conversion factor in the current iteration is taken as the first endpoint of the candidate value space of the oil-electric conversion factor in the next iteration, thereby effectively ensuring the validity of the determination result of the candidate value space of the oil-electric conversion factor in the next iteration.

[0118] In this approach, the optimal value of the oil-electric conversion factor in the next iteration can be determined based on the candidate value space of the oil-electric conversion factor in the next iteration. For example, any value other than the first and second endpoints in the candidate value space can be used as the optimal value of the oil-electric conversion factor in the next iteration. This effectively reduces the search space for the optimal value of the oil-electric conversion factor in the next iteration compared to the current iteration, thereby ensuring the validity of the determination result of the optimal value of the oil-electric conversion factor in the next iteration while effectively improving the optimization efficiency of the oil-electric conversion factor.

[0119] As a preferred implementation, the median of the candidate value space of the oil-electric conversion factor in the next iteration can be used as the preferred value of the oil-electric conversion factor in the next iteration. This reduces the search space for the preferred value of the oil-electric conversion factor by half compared to the previous iteration in each iteration, maximizing the optimization efficiency of the oil-electric conversion factor. It can be understood that in the first iteration, the candidate value space of the oil-electric conversion factor can be the interval formed by the upper and lower limits of the oil-electric conversion factor, for example, [2,3]. In this case, the initial oil-electric conversion factor can be selected as 2.5.

[0120] In one feasible implementation, determining the vehicle's multiple target speed sequences under the candidate driving conditions based on vehicle speed test information corresponding to at least one standard driving cycle includes:

[0121] Based on the vehicle speed range corresponding to the candidate driving conditions, the target data segment in the vehicle speed test information corresponding to each standard driving cycle is obtained respectively.

[0122] The target data segments are spliced ​​together to obtain multiple target vehicle speed sequences under the candidate driving conditions.

[0123] Specifically, for any candidate driving condition, based on the speed range corresponding to that candidate driving condition, data segments satisfying the speed range corresponding to the candidate driving condition can be extracted from the speed test information corresponding to each standard driving cycle. These extracted data segments are then used as target data segments; that is, the speed value range in each target data segment is the speed range corresponding to the candidate driving condition. Taking a speed range of 20~40 km / h for the candidate driving condition as an example, the target data segments extracted from the speed test information corresponding to the standard driving cycle can be as follows: Figure 3 As shown.

[0124] After obtaining the target data segments corresponding to the candidate driving condition, these segments can be concatenated to obtain multiple target vehicle speed sequences for that candidate driving condition. It is understandable that, to achieve vehicle speed following control based on the vehicle's physical model, the target vehicle speed sequences need to ensure temporal continuity. For example, some target data segments can be mirrored before concatenation to achieve temporal continuity of vehicle speed.

[0125] In practice, during the splicing process of target data segments, multiple target data segments can be randomly arranged and spliced. A target vehicle speed sequence may contain duplicate target data segments or may only include some target data segments, as long as the duration of the target vehicle speed sequence is greater than or equal to the predetermined duration.

[0126] Since the vehicle speed test information corresponding to the standard driving cycle represents the vehicle speed test information under different driving conditions, optimizing the preset value space of the oil-electric conversion factor under the target vehicle speed sequence can meet the energy management control for different driving conditions under this driving condition, and further improve the robustness of the determination result of the preset value space of the oil-electric conversion factor.

[0127] Exemplary device

[0128] In one exemplary embodiment of this specification, an energy management device is also provided, such as Figure 4 As shown, it includes:

[0129] The first processing module 401 is used to determine the target driving mode of the vehicle based on the vehicle's driving data within a first time interval; the first time interval includes the time interval before the current moment.

[0130] The second processing module 402 is used to determine the target value of the oil-electric conversion factor based on the target driving mode, and output the target value of the oil-electric conversion factor to the energy management control unit, so as to trigger the energy management control unit to perform energy management control on the vehicle based on the target value of the oil-electric conversion factor in a second time interval, the second time interval including the time interval after the current moment.

[0131] In one feasible implementation, the target driving mode includes the target driving condition and the driver's driving style; the driving data includes first data corresponding to the driving state parameters and second data corresponding to the driving control input parameters; the first processing module 401 is specifically used for:

[0132] Based on the first statistical information corresponding to the first data, the target driving condition is determined, and based on the second statistical information corresponding to the second data, the driving style is determined.

[0133] In one feasible implementation, the second processing module 402 is specifically used for:

[0134] Based on the target driving conditions and the predetermined correspondence, a preset value space for the oil-electric conversion factor under the target driving conditions is determined and used as the target value space; the predetermined correspondence includes multiple candidate driving conditions and a preset value space for the oil-electric conversion factor under each candidate driving condition.

[0135] Based on the driving style and the target value space, the target value of the oil-electric conversion factor is determined.

[0136] In one feasible implementation, a third processing module is further included, the third processing module being used for:

[0137] Based on vehicle speed test information corresponding to at least one standard driving cycle, determine multiple target vehicle speed sequences for the vehicle under the candidate driving conditions;

[0138] During the vehicle simulation operation based on the physical model of the vehicle controlled by the target vehicle speed sequence, the oil-electric conversion factor is iteratively optimized based on the SOC simulation value output by the physical model to obtain the oil-electric conversion factor correction value corresponding to the target vehicle speed sequence.

[0139] Based on the correction value of the oil-electric conversion factor corresponding to each of the target vehicle speed sequences, the preset value space of the oil-electric conversion factor under the candidate driving conditions is determined.

[0140] In one feasible implementation, the third processing module is specifically used for:

[0141] In the current iteration, the current value of the oil-electric conversion factor is output to the energy management control unit to trigger the energy management control unit to output an energy distribution control command to the physical model and obtain the SOC simulation value output by the physical model; the current value of the oil-electric conversion factor is the preferred value of the oil-electric conversion factor or the initial oil-electric conversion factor;

[0142] If the deviation between the simulated SOC value and the target SOC value corresponding to the candidate driving condition is less than or equal to a preset deviation threshold, then the current value of the oil-electric conversion factor is used as the correction value of the oil-electric conversion factor corresponding to the target vehicle speed sequence.

[0143] If the deviation value is greater than the preset deviation threshold, the preferred value of the oil-electricity conversion factor in the next iteration is determined based on the SOC simulation value, and the next iteration is executed.

[0144] In one feasible implementation, the third processing module is specifically used for:

[0145] Based on the relationship between the simulated SOC value and the target SOC value, and the predetermined trend of the simulated SOC value with respect to the oil-electric conversion factor, the first endpoint of the candidate value space of the oil-electric conversion factor in the next iteration is determined from the two endpoints of the candidate value space of the oil-electric conversion factor in the current iteration, and the current value of the oil-electric conversion factor in the current iteration is taken as the second endpoint of the candidate value space of the oil-electric conversion factor in the next iteration.

[0146] Based on the candidate value space of the oil-electricity conversion factor in the next iteration, the preferred value of the oil-electricity conversion factor in the next iteration is determined.

[0147] In one feasible implementation, the third processing module is specifically used for:

[0148] Based on the vehicle speed range corresponding to the candidate driving conditions, the target data segment in the vehicle speed test information corresponding to each standard driving cycle is obtained respectively.

[0149] The target data segments are spliced ​​together to obtain multiple target vehicle speed sequences under the candidate driving conditions.

[0150] In one feasible implementation, the second processing module 402 is specifically used for:

[0151] Based on the energy demand level under the driving style, the predetermined trend of the oil-electric conversion factor with the energy demand level, and the target value space, the target value of the oil-electric conversion factor is determined.

[0152] The energy management device provided in this embodiment belongs to the same concept as the energy management method provided in the above embodiments of this application. It can execute the energy management method provided in any of the above embodiments of this application and has the corresponding functional modules and beneficial effects for executing the energy management method. Technical details not described in detail in this embodiment can be found in the specific processing content of the energy management method provided in the above embodiments of this application, and will not be repeated here.

[0153] Exemplary vehicle

[0154] In one exemplary embodiment of this specification, a vehicle is also provided, including an energy management control unit and an energy management device as described in any of the above embodiments.

[0155] Exemplary computer program products and storage media

[0156] In addition to the methods and devices described above, the energy management methods provided in the embodiments of this specification can also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the energy management methods according to various embodiments of this specification as described in the "Exemplary Methods" section above.

[0157] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this specification. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages.

[0158] Furthermore, embodiments of this specification also provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor of the steps in the energy management methods according to various embodiments of this specification as described in the "Exemplary Methods" section above.

[0159] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this specification can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0160] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The embodiments described above are merely illustrative of several implementation methods outlined in this specification. While the descriptions are specific and detailed, they should not be construed as limiting the scope of the solutions provided in this specification. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this specification, and these all fall within the scope of protection of this specification. Therefore, the scope of protection for this patent should be determined by the appended claims.

Claims

1. An energy management method, characterized in that, include: Based on the vehicle's driving data within a first time interval, the target driving mode of the vehicle is determined. The target driving mode includes the target driving conditions and the driver's driving style. The first time interval includes the time interval before the current moment. Based on the target driving conditions and the predetermined correspondence, a preset value space for the oil-electric conversion factor under the target driving conditions is determined and used as the target value space. Based on the driving style and the target value space, a target value for the oil-electric conversion factor is determined and output to the energy management control unit to trigger the energy management control unit to perform energy management control on the vehicle based on the target value of the oil-electric conversion factor in a second time interval, wherein the second time interval includes the time interval after the current moment. The predetermined correspondence includes multiple candidate driving conditions and a preset value space for the fuel-electric conversion factor under each candidate driving condition. The process of determining the preset value space for the fuel-electric conversion factor under the candidate driving conditions includes: determining multiple target vehicle speed sequences for the vehicle under the candidate driving conditions based on vehicle speed test information corresponding to at least one standard driving cycle; iteratively optimizing the fuel-electric conversion factor based on the SOC simulation value output by the physical model of the vehicle based on the target vehicle speed sequences to obtain the fuel-electric conversion factor correction value corresponding to the target vehicle speed sequences; and determining the preset value space for the fuel-electric conversion factor under the candidate driving conditions based on the fuel-electric conversion factor correction values ​​corresponding to each target vehicle speed sequence.

2. The method according to claim 1, characterized in that, The driving data includes first data corresponding to driving status parameters and second data corresponding to driving control input parameters; The determination of the vehicle's target driving mode based on the vehicle's driving data within a first time interval includes: Based on the first statistical information corresponding to the first data, the target driving condition is determined, and based on the second statistical information corresponding to the second data, the driving style is determined.

3. The method according to claim 1, characterized in that, The oil-electric conversion factor is iteratively optimized based on the SOC simulation value output by the physical model to obtain the corrected oil-electric conversion factor value corresponding to the target vehicle speed sequence, including: In the current iteration, the current value of the oil-electric conversion factor is output to the energy management control unit to trigger the energy management control unit to output an energy distribution control command to the physical model and obtain the SOC simulation value output by the physical model; the current value of the oil-electric conversion factor is the preferred value of the oil-electric conversion factor or the initial oil-electric conversion factor; If the deviation between the simulated SOC value and the target SOC value corresponding to the candidate driving condition is less than or equal to a preset deviation threshold, then the current value of the oil-electric conversion factor is used as the correction value of the oil-electric conversion factor corresponding to the target vehicle speed sequence. If the deviation value is greater than the preset deviation threshold, the preferred value of the oil-electricity conversion factor in the next iteration is determined based on the SOC simulation value, and the next iteration is executed.

4. The method according to claim 3, characterized in that, The step of determining the preferred value of the oil-electricity conversion factor in the next iteration based on the SOC simulation value includes: Based on the relationship between the simulated SOC value and the target SOC value, and the predetermined trend of the simulated SOC value with respect to the oil-electric conversion factor, the first endpoint of the candidate value space of the oil-electric conversion factor in the next iteration is determined from the two endpoints of the candidate value space of the oil-electric conversion factor in the current iteration, and the current value of the oil-electric conversion factor in the current iteration is taken as the second endpoint of the candidate value space of the oil-electric conversion factor in the next iteration. Based on the candidate value space of the oil-electricity conversion factor in the next iteration, the preferred value of the oil-electricity conversion factor in the next iteration is determined.

5. The method according to claim 1, characterized in that, The determination of multiple target vehicle speed sequences for the vehicle under the candidate driving conditions based on vehicle speed test information corresponding to at least one standard driving cycle includes: Based on the vehicle speed range corresponding to the candidate driving conditions, the target data segment in the vehicle speed test information corresponding to each standard driving cycle is obtained respectively. The target data segments are spliced ​​together to obtain multiple target vehicle speed sequences under the candidate driving conditions.

6. The method according to any one of claims 1 to 5, characterized in that, Determining the target value of the hybrid power conversion factor based on the driving style and the target value space includes: Based on the energy demand level under the driving style, the predetermined trend of the oil-electric conversion factor with the energy demand level, and the target value space, the target value of the oil-electric conversion factor is determined.

7. An energy management device, characterized in that, include: The first processing module is used to determine the target driving mode of the vehicle based on the vehicle's driving data within a first time interval. The target driving mode includes the target driving conditions and the driver's driving style. The first time interval includes the time interval before the current moment. The second processing module is used to determine a preset value space of the oil-electric conversion factor under the target driving condition based on the target driving condition and a predetermined correspondence, and use it as the target value space; and to determine the target value of the oil-electric conversion factor based on the driving style and the target value space, and output the target value of the oil-electric conversion factor to the energy management control unit, so as to trigger the energy management control unit to perform energy management control on the vehicle based on the target value of the oil-electric conversion factor in a second time interval, wherein the second time interval includes the time interval after the current moment; The predetermined correspondence includes multiple candidate driving conditions and a preset value space for the fuel-electric conversion factor under each candidate driving condition. The process of determining the preset value space for the fuel-electric conversion factor under the candidate driving conditions includes: determining multiple target vehicle speed sequences for the vehicle under the candidate driving conditions based on vehicle speed test information corresponding to at least one standard driving cycle; iteratively optimizing the fuel-electric conversion factor based on the SOC simulation value output by the physical model of the vehicle based on the target vehicle speed sequences to obtain the fuel-electric conversion factor correction value corresponding to the target vehicle speed sequences; and determining the preset value space for the fuel-electric conversion factor under the candidate driving conditions based on the fuel-electric conversion factor correction values ​​corresponding to each target vehicle speed sequence.

8. A vehicle, characterized in that, It includes an energy management control unit and an energy management device as described in claim 7.

Images