Energy Management Method, Device, Storage Medium and Apparatus

Abstract

The present invention belongs to the technical field of vehicles, and discloses an energy management method, device, storage medium and device. The present invention predicts the driving road conditions corresponding to the target vehicle based on the visually acquired information in real time to obtain the predicted driving road conditions; adjusts the SOC threshold value of the target battery according to the predicted driving road conditions and the preset ECMS control strategy to obtain the adjusted SOC threshold value; corrects the vehicle demand power according to the adjusted SOC threshold value and the preset ECMS control strategy, and controls the target range extender to generate electricity according to the corrected demand power. The present invention predicts the future driving road conditions through the real-time visual information of the vehicle, and dynamically regulates the battery SOC threshold value and the demand power according to the predicted driving road conditions and the preset ECMS control strategy, so as to achieve energy conservation and emission reduction while meeting the driving requirements of multiple scenarios, thereby improving the user experience.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular, to an energy management method, device, storage medium and apparatus. Background Art

[0002] At present, new energy vehicles have become the main development direction of the automotive industry. Among them, pure electric vehicles have advantages such as energy conservation, environmental protection, comfort and convenience. However, due to factors such as battery energy density and low-temperature power retention, the driving range has become the main limiting factor. At the same time, factors such as the number of charging piles, grid load, and long charging time also limit the rapid development of pure electric vehicles.

[0003] Currently, range-extended electric vehicles (REEV) can effectively solve the problems of the driving range of electric vehicles and the shortage of charging pile hardware. At the same time, a high-voltage charging port is reserved, so more energy replenishment options are provided for customers. Therefore, range-extended electric vehicles have become one of the main technical paths of current new energy vehicles. The existing energy management strategies of range-extended electric vehicles are mainly based on the collected vehicle driving speed and the overall vehicle demand power, and are targeted at the upper and lower limits of the driving motor speed, the torque constraints of the engine / generator, the state of charge (SOC) of the power battery, etc. Based on the pre-cured range extender power generation map, fixed-point or power-following power generation is performed. The above management strategies have problems such as poor adaptability, inability to fully utilize the vehicle performance under different usage conditions, and low energy utilization efficiency. Therefore, they cannot cover complex and changeable road conditions and driving conditions in real time, resulting in low energy utilization efficiency of the current REEV range extender and poor adaptation to road conditions, and unable to achieve the predetermined energy-saving and emission-reduction effects during actual use. Summary of the Invention

[0004] The main purpose of the present invention is to provide an energy management method, device, storage medium and apparatus, aiming to solve the technical problems that the current REEV range extender has low energy utilization efficiency and poor adaptation to road conditions, and cannot achieve the predetermined energy-saving and emission-reduction effects during actual use.

[0005] To achieve the above object, the present invention provides an energy management method, and the energy management method includes the following steps:

[0006] Predict the driving road conditions corresponding to the target vehicle based on the real-time collected visual information to obtain the predicted driving road conditions;

[0007] Adjust the SOC threshold value of the target battery according to the predicted driving road conditions and the preset ECMS control strategy to obtain the adjusted SOC threshold value;

[0008] Modify the vehicle's required power according to the adjusted SOC threshold value and the preset ECMS control strategy, and control the range extender to generate electricity according to the modified required power target.

[0009] Optionally, the step of predicting the driving road conditions corresponding to the target vehicle based on the real-time collected visual information to obtain the predicted driving road conditions includes:

[0010] Detect the number of vehicles and the vehicle distance in the real-time collected visual information to obtain the number of vehicles and the vehicle distance information;

[0011] Perform data denoising and filtering on the vehicle speed information in the historical driving data to obtain the optimized target vehicle speed information;

[0012] Predict the driving road conditions corresponding to the target vehicle based on the number of vehicles, the vehicle distance information, and the target vehicle speed information to obtain the predicted driving road conditions.

[0013] Optionally, the step of predicting the driving road conditions corresponding to the target vehicle based on the number of vehicles, the vehicle distance information, and the target vehicle speed information to obtain the predicted driving road conditions includes:

[0014] Divide the vehicle distance information and the target vehicle speed information into section characteristic parameters based on the preset road condition type to obtain the section characteristic parameters;

[0015] Predict the driving road conditions corresponding to the target vehicle based on the section characteristic parameters, the number of vehicles, and the preset number of vehicles to obtain the predicted driving road conditions.

[0016] Optionally, the preset ECMS control strategy includes a preset SOC threshold optimization strategy and a preset vehicle required power prediction optimization strategy. The step of adjusting the SOC threshold value of the target battery according to the predicted driving road conditions and the preset ECMS control strategy to obtain the adjusted SOC threshold value includes:

[0017] Adjust the SOC threshold value of the target battery according to the predicted driving road conditions and the preset SOC threshold optimization strategy to obtain the adjusted SOC threshold value;

[0018] The step of modifying the vehicle's required power according to the adjusted SOC threshold value and the preset ECMS control strategy, and controlling the target range extender to generate electricity according to the modified required power includes:

[0019] Modify the vehicle's required power according to the adjusted SOC threshold value and the preset vehicle required power prediction optimization strategy, and control the target range extender to generate electricity according to the modified required power.

[0020] Optionally, the predicted driving road conditions include smooth road conditions, neutral road conditions, and congested road conditions. The step of adjusting the SOC threshold value of the target battery according to the predicted driving road conditions and the preset SOC threshold optimization strategy to obtain the adjusted SOC threshold value includes:

[0021] If the predicted driving road condition is a congested road condition and the driver's intention at the current moment is not to accelerate urgently, reduce the SOC of the target battery based on the preset SOC threshold optimization strategy CS-in threshold;

[0022] If the predicted driving road condition is a neutral congested road condition and the driver's intention at the current moment is not to accelerate urgently, increase the SOC of the target battery based on the preset SOC threshold optimization strategy CS-out threshold;

[0023] If the predicted driving road condition is a smooth congested road condition and the driver's intention at the current moment is not to accelerate urgently, increase the SOC of the target battery based on the preset SOC threshold optimization strategy CS-in threshold.

[0024] Optionally, the step of correcting the vehicle demand power according to the adjusted SOC threshold value and the preset vehicle demand power prediction optimization strategy, and controlling the target range extender to generate electricity according to the corrected demand power includes:

[0025] Obtain the driver's acceleration intention information;

[0026] Correct the input value of the vehicle demand power according to the adjusted SOC threshold value, the driver's acceleration intention information, and the preset vehicle demand power prediction optimization strategy to obtain the corrected demand power;

[0027] Control the target range extender to generate electricity according to the corrected demand power.

[0028] Optionally, the step of correcting the input value of the vehicle demand power according to the adjusted SOC threshold value, the driver's acceleration intention information, and the preset vehicle demand power prediction optimization strategy to obtain the corrected demand power includes:

[0029] If the adjusted SOC threshold value is lower than the preset threshold value and the driver has an acceleration demand, it is determined to enable the preset vehicle demand power prediction optimization strategy;

[0030] Predict the correction ratio coefficient according to the acceleration demand, urgent acceleration demand, deceleration demand, and urgent deceleration demand in the driver's acceleration intention information and the preset vehicle demand power prediction optimization strategy to obtain the predicted ratio coefficient;

[0031] The input value of the vehicle's required power is corrected according to the predicted proportionality coefficient to obtain the corrected required power.

[0032] In addition, to achieve the above object, the present invention also provides an energy management device, which includes a memory, a processor, and an energy management program stored on the memory and executable on the processor. The energy management program is configured to implement the steps of the energy management as described above.

[0033] In addition, to achieve the above object, the present invention also provides a storage medium with an energy management program stored thereon. When the energy management program is executed by a processor, it implements the steps of the energy management method as described above.

[0034] In addition, to achieve the above object, the present invention also provides an energy management device, which includes:

[0035] A road condition prediction module, configured to predict the driving road condition corresponding to the target vehicle based on the visually acquired information in real time, and obtain the predicted driving road condition;

[0036] A threshold adjustment module, configured to adjust the SOC threshold of the target battery according to the predicted driving road condition and a preset ECMS control strategy, and obtain the adjusted SOC threshold;

[0037] A power correction module, configured to correct the vehicle's required power according to the adjusted SOC threshold and the preset ECMS control strategy, and control the target range extender to generate electricity according to the corrected required power.

[0038] Based on the visually acquired information in real time, the present invention predicts the driving road condition corresponding to the target vehicle to obtain the predicted driving road condition; adjusts the SOC threshold of the target battery according to the predicted driving road condition and a preset ECMS control strategy to obtain the adjusted SOC threshold; corrects the vehicle's required power according to the adjusted SOC threshold and the preset ECMS control strategy, and controls the target range extender to generate electricity according to the corrected required power. Compared with the current low energy utilization rate of the REEV range extender and poor adaptability to road conditions, and the inability to achieve the predetermined energy conservation and emission reduction effect during actual use, the present invention predicts the future driving road condition through the vehicle's real-time visual information, and dynamically adjusts the battery SOC threshold and required power according to the predicted driving road condition and the preset ECMS control strategy, so as to achieve energy conservation and emission reduction while meeting the driving requirements of multiple scenarios, thereby improving the user experience. Description of the Drawings

[0039] Figure 1It is a schematic structural diagram of an energy management device in the hardware operating environment related to the embodiment solution of the present invention;

[0040] Figure 2 It is a schematic flowchart of the first embodiment of the energy management method of the present invention;

[0041] Figure 3 It is a schematic diagram of the working condition prediction energy management strategy of the first embodiment of the energy management method of the present invention;

[0042] Figure 4 It is a schematic flowchart of the second embodiment of the energy management method of the present invention;

[0043] Figure 5 It is a structural block diagram of the first embodiment of the energy management device of the present invention.

[0044] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0045] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] Referring to Figure 1 , Figure 1 It is a schematic structural diagram of an energy management device in the hardware operating environment related to the embodiment solution of the present invention.

[0047] As Figure 1 shown, the energy management device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), and optionally, the user interface 1003 may further include a standard wired interface and a wireless interface. For the wired interface of the user interface 1003, it may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable memory (Non-volatile Memory, NVM), such as a disk memory. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0048] Those skilled in the art can understand that Figure 1The structure shown does not constitute a limitation on the energy management device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0049] As Figure 1 shown, the memory 1005, which is identified as a data processing storage medium, may include an operating system, a network communication module, a user interface module, and an energy management program.

[0050] In Figure 1 the energy management device shown, the network interface 1004 is mainly used to connect to the background server and communicate data with the background server; the user interface 1003 is mainly used to connect to user devices; the energy management device calls the energy management program stored in the memory 1005 through the processor 1001 and executes the energy management method provided by the embodiments of the present invention.

[0051] Based on the above hardware structure, embodiments of the energy management method of the present invention are proposed.

[0052] Referring to Figure 2 , Figure 2 which is a schematic flowchart of the first embodiment of the energy management method of the present invention, the first embodiment of the energy management method of the present invention is proposed.

[0053] In this embodiment, the energy management method includes the following steps:

[0054] Step S10: Predict the driving road condition corresponding to the target vehicle based on the visually acquired real-time information, and obtain the predicted driving road condition.

[0055] It should be noted that the execution subject in this embodiment can be a device that includes an ECMS control system, such as: a vehicle-mounted computer, a computer, a tablet, a mobile phone or a notebook, and can also be other devices that can achieve the same or similar functions. The engine speed control system includes an energy management function. In this embodiment and the following embodiments, the energy management method of the present invention is explained using a computer as an example. This solution uses REEV extended-range electric vehicles as the target vehicle, predicts the operating conditions of the forward visual information identified based on the vehicle's camera / recording equipment, and uses open source algorithms to complete vehicle number recognition and front vehicle ranging through road condition video stream data, constructs a cycle operating condition with environmental information and compares it with all driving data and typical operating conditions NEDC / WLTC, and optimizes and fits the equivalent fuel minimum control strategy ECMS (Equivalent Consumption Minimization Strategy) based on the predicted future driving conditions of the vehicle. At the same time, based on the power battery SOC threshold and real-time optimization method, an improved equivalent fuel minimum control strategy based on operating condition prediction is designed, and the SOC threshold and the vehicle's required power input value are optimized and adjusted according to different road conditions and driver intentions. Finally, the constructed energy management strategy is solidified on the whole vehicle to achieve the optimal REEV vehicle energy management path and strategy.

[0056] It is understandable that the vehicle has complex and changeable working conditions when driving, including objective road facilities and real-time traffic conditions. From the perspective of optimizing vehicle control strategy, if the vehicle is in a congested section, the road traffic flow is large, the speed is slow and the start and stop are frequent, the economy of the vehicle should be considered, the engine should not be operated at low speed for a long time, the engine should not be started and stopped frequently, and pure electric driving should be used as much as possible; if the vehicle is in a smooth section for a long time, the road traffic flow is small, and the speed is high, the vehicle's driving range should be considered, so that the engine can work at high efficiency and provide sufficient backup power for the whole vehicle. However, the actual road conditions have great uncertainty, and it is difficult for traditional methods to obtain the driving conditions of the vehicle. Therefore, most of the existing energy management strategies for automobiles cannot achieve the expected energy-saving and emission reduction effects during actual use. However, this solution can more reasonably control various components such as the engine, generator, motor, and power battery through road condition identification and prediction of automobile driving conditions, which can effectively reduce automobile exhaust emissions and reduce vehicle energy losses.

[0057] It should be understood that visual information may refer to images and video information collected by cameras configured on the vehicle, including information about the vehicle ahead and road conditions.

[0058] In a specific implementation, this solution predicts the driving conditions in a future time period by using the real-time collected vehicle information and road condition information to obtain the predicted driving conditions.

[0059] Further, the step S10 further includes: detecting the number of vehicles and the vehicle distance in the visually acquired information in real time to obtain the number of vehicles and the vehicle distance information; performing data denoising and filtering processing on the vehicle speed information in the historical driving data to obtain the optimized target vehicle speed information; predicting the driving road condition corresponding to the target vehicle based on the number of vehicles, the vehicle distance information, and the target vehicle speed information to obtain the predicted driving road condition.

[0060] It should be noted that it should be understood that predicting the working condition in combination with the driving environment under unknown working conditions of the whole vehicle (the traditional typical driving cycle conditions NEDC / WLTC are not completely applicable). This solution uses the vehicle tracking method for data collection. The GPS carried by the vehicle randomly follows the vehicle in front. If the vehicle in front leaves the specified range, another vehicle will be randomly tracked (this method has driving randomness and conforms to the daily driving situation). Among them, the monocular vision acquisition device of the driving recorder is used for visual ranging (without data fusion, high real-time performance, and low cost), and driving road condition information such as the degree of road congestion ahead and the vehicle distance ahead can be obtained.

[0061] It can be understood that for vehicle target detection, an algorithm is used to realize the detection of the total number of vehicles and depth estimation for the video stream collected by the monocular camera. The detection of the number of vehicles in the visually acquired information in real time can be divided into daytime detection and nighttime detection. Among them, daytime detection: The YOLO algorithm is used based on the deep neural network model for target detection. This algorithm uniformly converts the image into a 448*448 pixel image and divides it into 7*7 grids of equal size. After the trained network, input a picture, and information such as the object category, the box selection range, and the credibility in the picture will be obtained. Nighttime detection: On the basis of enhancing the illuminance of the nighttime image, it is divided into a two-stage detection method of the backbone and the detection head. The backbone part uses attention distillation and convolution to complete the extraction of vehicle contour features. The detection head part focuses on separating the foreground and the environmental background to complete the nighttime vehicle target detection. The upper limit of the number of pictures detected can be set to 6. If the detected value is ≤2, the system judges that the scene is unobstructed. If the detected value ≥3, the system judges that the scene is congested.

[0062] It should be understood that the detection of the vehicle distance can be based on the principle of parallax ranging using a camera or image motion, analyze consecutive pictures, and analyze the image depth based on the object motion speed. The relative depth estimation motion parallax algorithm is carried out based on an unsupervised neural network. When converting the relative depth to the absolute depth, it is realized by combining the unit matrix of the camera internal parameters calibrated in advance by the checkerboard method. After the initial depth convolutional neural network estimation of the current target image, the pose network estimation is carried out using the two images at the current and the next moment, the original image is inferred reversely from the depth map and the pose map, and finally the gray difference of the corresponding pixel points is calculated to construct the loss function Loss of the least squares model for network training.

[0063]

[0064] In the formula, I t (p) is the input target image, is the original image inferred by the pose network. Considering the installation position of the camera and the recognition effect, the lower limit of the following vehicle distance recognition result can be set to 1m, and the upper limit to 60m, and the driving segments with invalid depth estimation are deleted. Combining the above target detection algorithm and the front block diagram corresponding to the same lane of the vehicle, the depth of the front vehicle recognized is the following vehicle distance. Among them, the following vehicle distance data has a certain impact on the subsequent driving decisions of the driver. Subsequently, it is considered to be used for driving intention recognition and then introduced into the energy management strategy for use.

[0065] Among them, in order to accurately obtain the vehicle speed information, it is also necessary to perform data denoising and filtering processing on the vehicle speed information in the historical driving data to obtain the optimized target vehicle speed information; the processing of the driving data specifically includes: interpolation processing for missing data: spline interpolation is used to supplement the speed data with lost GPS signals. Spline function interpolation can be used for the missing part of the speed to solve the continuity and differentiability problems of the intermediate section data, so that the acceleration remains continuous. For data denoising and filtering: for the acceleration threshold greater than 6m / s2 or less than -8m / s2, it is judged as an outlier, and the mean filtering method is used to filter the abnormal noise points. For the long idling condition removal (vehicle speed is 0), the time threshold can be set to 5 minutes, and if it exceeds the threshold, the data of this section will be deleted and optimized.

[0066] In specific implementation, the number of vehicles and the vehicle distance in the visually acquired information in real time are detected to obtain the number of vehicles and the vehicle distance information; the vehicle speed information in the historical driving data is subjected to data noise reduction and filtering processing to obtain the optimized target vehicle speed information; the driving road condition corresponding to the target vehicle is predicted based on the number of vehicles, the vehicle distance information, and the target vehicle speed information to obtain the predicted driving road condition. This solution can combine the number detection and ranging effect of the target vehicle in the above video stream image, screen and splice the road condition segments of the experimental data, and construct a real vehicle loop road condition, so as to facilitate the comparison of the constructed real vehicle loop road condition with the typical working conditions, and then determine the road condition type.

[0067] Further, the step of predicting the driving road condition corresponding to the target vehicle based on the number of vehicles, the vehicle distance information, and the target vehicle speed information to obtain the predicted driving road condition includes: dividing the vehicle distance information and the target vehicle speed information into section characteristic parameters based on a preset road condition type to obtain the section characteristic parameters; predicting the driving road condition corresponding to the target vehicle based on the section characteristic parameters, the number of vehicles, and a preset number of vehicles to obtain the predicted driving road condition.

[0068] It should be noted that when comparing the constructed working condition with the typical working condition, limited by the road speed limit, the duration, the driving distance, and the average vehicle speed are all close to the typical working conditions NEDC / WLTC. Based on the driving historical information, the driving working condition is divided by using the number of vehicles in the field of view with a neural network, so as to determine that the driving working condition in each time period is congested, neutral or unobstructed.

[0069] It can be understood that the preset road condition types include: three road condition types of congestion, neutral, and unobstructed. A certain degree of road condition identification effect is achieved by using ten characteristic parameters, and the statistics are carried out according to the following section characteristic parameters: maximum vehicle speed Vmax (km / h), driving mileage S (m), acceleration time tacc (s), maximum acceleration amax (m / s2), average acceleration a+ (m / s2), minimum deceleration amin (m / s2), average deceleration a- (m / s2), cruise time tcruise (s), average vehicle speed V (km / h), idle time tidle (s).

[0070] It should be understood that the section working condition can be cut into 60s working condition blocks by adopting the composite equal division method, and the start times of each working condition section differ by 10s. 63 sections of congested road conditions, 88 sections of neutral road conditions, and 50 sections of unobstructed road conditions are respectively divided for the three types of working conditions, and the characteristic parameters of each working condition section are respectively obtained.

[0071] In specific implementation, this solution uses a BP (Back Propagation) neural network to identify road conditions in a cyclic driving condition: the neural network establishes a mapping relationship through the input and output parameters provided by the training samples, and performs network training by adjusting the error backpropagation. To verify the rationality of introducing the parameter of the number of vehicles in the field of view into the established network, a neural network with only 10 driving parameters as input parameters is trained respectively, and the obtained results are used to identify the actual vehicle conditions. The method of using a BP neural network to identify road conditions in a cyclic driving condition has strong feasibility. This solution introduces the number of vehicles ahead as a judgment basis, and corresponds the relationship between different road conditions and the number of vehicles in the field of view. For example: (1) In the unobstructed type, the detected number of vehicles in the field of view is set to 0, 1, 2; (2) In the neutral type, the detected number of vehicles in the field of view is set to 2, 3, 4; (3) In the congested type, the detected number of vehicles in the field of view is set to 4 or more.

[0072] Step S20: Adjust the SOC threshold value of the target battery according to the predicted driving road conditions and the preset ECMS control strategy to obtain the adjusted SOC threshold value.

[0073] It should be noted that the realization of the REEV fuel economy depends on a reasonable energy management strategy, which is also the core of the current mainstream research. The design of the control strategy should follow the following principles:

[0074] (1) The principle of maximum battery power consumption: The control strategy should consume the battery power as much as possible during driving, but also prevent the battery from over-discharging.

[0075] (2) The principle of power priority: During driving, sufficient driving force should be ensured, and the operation safety should be guaranteed. Then, the working modes of each power component are determined to improve the economy and reduce emissions;

[0076] (3) The principle of regenerative braking energy recovery; In special driving conditions such as vehicle braking and downhill, the kinetic energy should be converted into electrical energy and stored through the drive motor. On the premise of correct safety, the energy loss of friction braking should be reduced as much as possible.

[0077] It is understandable that the control strategy based on the optimization idea has good dynamics. By using numerical calculation methods to construct functions for optimizing the control of each component, it has strong adaptability and can be improved in combination with specific road conditions and different driving intentions of drivers. The preset ECMS control strategy can be a pre-set equivalent fuel consumption minimization strategy, that is, a typical real-time optimization control strategy with the lowest fuel consumption as the optimization goal based on meeting a series of constraints of internal combustion engines, motors, batteries, etc. In the energy management design process of REEV, the SOC threshold value determines the start and stop of the range extender. The selection of the threshold value includes the following factors: (1) Meeting the pure electric driving range of the vehicle; the vehicle has corresponding driving range requirements at the beginning of design, so the SOC inlet of the power battery in the CS stage should not be too large. (2) Meeting the needs of various driving conditions of the vehicle; the vehicle should be able to provide sufficient power under conditions such as starting and rapid acceleration with high power demand for a short time, so the lower SOC threshold value cannot be too low. In addition, the settings of the SOC inlet and outlet of the power battery in the CS stage should be formulated in combination with specific control strategies to avoid too large a range between the inlet and outlet, excessive charging of the battery, and too small a range, resulting in frequent start-up of the range extender. (3) Meeting the needs of the engineering life of the battery; when using the power battery, attention should be paid to avoiding overcharging and over-discharging, which will damage the battery life. Therefore, the SOC outlet of the power battery in the CS stage should not be too high to prevent overcharging, and the lower SOC threshold value should not be too low to prevent over-discharging. (4) Being in the region with higher charge and discharge efficiency of the battery; the voltage and internal resistance of the power battery are different in different SOC intervals, corresponding to different charge and discharge efficiencies. According to the battery parameter characteristics, the upper SOC threshold value should not be too high, and the lower SOC threshold value should not be too low.

[0078] In specific implementation, according to the above factor limitations, the threshold values related to the state of charge of the power battery initially set are summarized in the following table:

[0079] Symbol Value / % <![CDATA[SOC origin > 30 <![CDATA[SOC CS-in > 30 <![CDATA[SOC CS-out > 35 <![CDATA[SOC lowest > 25

[0080] In the table, SOC origin represents the initial state of charge of the power battery at the beginning of the cycle, and should be adjusted as needed during each specific cycle for simulation and analysis; SOC CS-in represents the SOC inlet of the power battery in the CS mode of the energy management strategy; SOC CS-out represents the SOC outlet of the power battery in the CS mode; SOC lowest represents the lower SOC limit value. When the parameters of the power battery reach this lower limit value, the parking charging mode is forcibly turned on and the power output of the drive motor is restricted. In the subsequent control strategy, the setting of each SOC threshold value can be analyzed and adjusted according to the previously obtained road conditions and driver intentions, and the above initial settings can be adjusted according to the driver's intentions and road conditions.

[0081] It should be understood that the preset ECMS control strategy includes a preset SOC threshold optimization strategy and a preset vehicle demand power prediction optimization strategy. To further illustrate the preset ECMS control strategy in this solution, reference can be made to Figure 3 the schematic diagram of the working condition prediction energy management strategy shown in the figure. The core of the improved equivalent fuel consumption minimization strategy established in this solution is as follows: the obtained working condition prediction results of road condition identification and driving intention recognition are used in the two control links (SOC threshold and vehicle demand power) of the equivalent fuel consumption minimization strategy ECMS, and a SOC threshold optimization strategy (PS-ECMS) is generated based on road conditions + partial driving intentions, and a vehicle demand power prediction optimization strategy (PPR-ECMS) is generated based on driving intentions. The above two strategies are respectively compared with the fixed-point power following strategy FPPF in terms of verification results (using the equivalent fuel consumption per 100 kilometers as the evaluation index) to obtain the optimal energy consumption control strategy.

[0082] It should be noted that the preset SOC threshold optimization strategy can be a preset ECMS strategy optimization control strategy (PS-ECMS) based on working condition prediction. The preset SOC threshold optimization strategy adjusts the threshold value in combination with road identification and driver intention recognition results, so as to accurately adjust the SOC threshold value according to road conditions and driver intentions. Among them, the SOC threshold value includes SOC CS-in 、SOC CS-out adjustments.

[0083] Furthermore, the step of adjusting the SOC threshold value of the target battery according to the predicted driving road conditions and the preset ECMS control strategy to obtain the adjusted SOC threshold value includes: adjusting the SOC threshold value of the target battery according to the predicted driving road conditions and the preset SOC threshold optimization strategy to obtain the adjusted SOC threshold value.

[0084] It should be noted that in this solution, the preset SOC threshold optimization strategy and the predicted driving road conditions are used to perform real-time regulation on SOC CS-in 、SOC CS-out included in the SOC threshold value.

[0085] Step S30: Correct the vehicle demand power according to the adjusted SOC threshold value and the preset ECMS control strategy, and control the target range extender to generate electricity according to the corrected demand power.

[0086] It should be noted that according to the adjusted SOC threshold value and the preset vehicle demand power prediction optimization strategy, the vehicle demand power is corrected, and the target range extender is controlled to generate electricity according to the corrected demand power.

[0087] It can be understood that the preset vehicle demand power prediction optimization strategy in this scheme can be a pre-set optimization control strategy (PPR-ECMS) of the vehicle demand power input value based on the predicted road conditions. The preset vehicle demand power prediction optimization strategy can be based on the driving intention identified by the working condition prediction to correct the future vehicle demand power, thereby optimizing the vehicle demand power input value of the ECMS control strategy, so that the range extender can generate electricity according to the future power demand.

[0088] In the specific implementation, the vehicle power demand is corrected according to the adjusted SOC threshold value and the preset vehicle power demand prediction optimization strategy, and the target range extender is controlled to generate electricity according to the corrected power demand. That is, when facing actual driving, it is necessary to consider that when the range extender is shut down, if the battery power is low but the driver has a sudden acceleration demand, resulting in a hysteresis in the vehicle power output, this solution can correct the vehicle power demand in the ECMS control strategy in combination with the driver's intention, so as to meet user needs.

[0089] This embodiment predicts the driving condition corresponding to the target vehicle based on the real-time collected visual information to obtain the predicted driving condition; adjusts the SOC threshold value of the target battery according to the predicted driving condition and the preset ECMS control strategy to obtain the adjusted SOC threshold value; corrects the vehicle's required power according to the adjusted SOC threshold value and the preset ECMS control strategy, and controls the target range extender to generate electricity according to the corrected required power. Compared with the current REEV range extender, which has low energy utilization and poor adaptability to road conditions and cannot achieve the predetermined energy-saving and emission reduction effects during actual use, this embodiment predicts future driving conditions through real-time visual information of the whole vehicle, and dynamically adjusts the battery SOC threshold value and required power according to the predicted driving condition and the preset ECMS control strategy, so as to achieve energy saving and emission reduction while meeting driving needs in various scenarios, thereby improving user experience.

[0090] Based on the above Figure 2 The first embodiment shown in FIG. 1 is a second embodiment of the energy management method of the present invention, referring to FIG. Figure 4 , Figure 4 FIG. 4 is a flow chart of the second embodiment of the energy management method of the present invention.

[0091] In this embodiment, the predicted driving road conditions include smooth road conditions, neutral road conditions and congested road conditions, and step S20 further includes:

[0092] Step S201: If the predicted driving condition is a congested type of condition and the driver does not intend to accelerate urgently at the current moment, the SOC of the target battery is reduced based on a preset SOC threshold optimization strategy. CS-in Threshold.

[0093] It should be noted that if the vehicle starts and stops frequently under congested conditions but the power demand is not high, and at this time if the SOC reaches the preset SOC CS-in when the CS mode is activated to start the range extender for power generation, the surplus power will be used to charge the power battery, and the battery SOC will quickly reach the SOC CS-out . At the end of the journey, the power battery will have too much surplus power. Driving in congested conditions for a long time will also cause the range extender to start and stop frequently. This situation can be improved by reducing the SOC CS-in threshold. The control strategy is set as follows: when in congested conditions and the driver's intention is not to accelerate suddenly at the current moment, adjust the SOC CS-in to 27%, and adjust the SOC CS-out to 30%. The above values are only for illustrative purposes.

[0094] Step S202: If the predicted driving road condition is a neutral congestion type road condition and the driver's intention is not to accelerate suddenly at the current moment, increase the SOC of the target battery based on the preset SOC threshold optimization strategy CS-out threshold.

[0095] It should be noted that if the predicted driving road condition is a neutral congestion type road condition and the driver's intention is not to accelerate suddenly at the current moment, increase the SOC CS-out threshold of the target battery, and the SOC CS-in remains unchanged at the initial setting. For example: under neutral conditions, the SOC CS-in parameter remains 30% unchanged, and the SOC CS-out is adjusted to 33%. The above values are only for illustrative purposes.

[0096] Step S203: If the predicted driving road condition is a smooth congestion type road condition and the driver's intention is not to accelerate suddenly at the current moment, increase the SOC of the target battery based on the preset SOC threshold optimization strategy CS-in threshold.

[0097] It should be noted that under smooth conditions, the driving speed and power demand are relatively high. At this time, if the SOC has not reached the preset SOC CS-in when the CS mode is activated in advance and the range extender is operated at the point of minimum specific fuel consumption for power generation, it can avoid the engine running in the high-speed and low-efficiency region for a long time to meet the driving demand, improve the overall vehicle economy and also contribute to the improvement of the high-speed cruising range. This situation can be improved by increasing the SOC CS-in threshold. The control strategy is set as follows: for example, when in smooth conditions and the driver's intention is not to decelerate suddenly at the current moment, adjust the SOC CS-in to 33%, and adjust the SOC CS-out to 36%. The above values are only for illustrative purposes.

[0098] In a specific implementation, simulations are carried out under the actual vehicle test conditions, and the results of the Predictive SOC adaptive ECMS strategy (PS-ECMS strategy for short) are compared with the Fixed Point and Power Following strategy (FPPF strategy for short). From the comparison of the battery SOC curves obtained from the FPPF and PS-ECMS strategies, it can be found that the fluctuation speed of the battery SOC curve of the FPPF strategy is faster, and its numerical range is also larger; while for the PS-ECMS, in different working condition sections, the SOC curve is respectively stable near the preset lower limit, and the change of the SOC CS-in value also affects the range of the SOC curve. Although the overall range is also large, in different set working condition sections, its SOC range is maintained within 3.5%. The PS-ECMS strategy is beneficial to the charge and discharge efficiency and service life of the power battery. The SOC at the end of the FPPF strategy may be any value between SOC CS-in and SOC CS-out , while the PS-ECMS strategy can stabilize the SOC at a certain lower target value at the end of the journey, with better economy. The PS-ECMS strategy takes into account the driving requirements of the vehicle at low power and high power at the same time. The curvature of the fuel consumption curve has a certain change, but the slope difference is not large when the curve rises, indicating that the operating point is basically near the minimum specific fuel consumption. The total fuel consumption of the PS-ECMS strategy at the end of the journey is significantly lower than that of the FPPF strategy. Therefore, the strategy in this solution is significantly better than the engine fixed point + power following strategy in the prior art.

[0099] In this embodiment, step S30 further includes:

[0100] Step S301: Obtain the driver's acceleration intention information.

[0101] It should be noted that the driver's acceleration intention information can be demand information such as acceleration, rapid acceleration, deceleration, and rapid deceleration triggered by the driver during the driving process. Among them, the CMS control strategy generates power for the range extender based on the real-time driving demand power, which can improve economy and reduce fuel consumption compared with the traditional control strategy. However, the range extender started multiple times during the simulation process of the above PS-ECMS strategy. When actually driving, it is necessary to consider that when the range extender stops, if the battery power is low but the driver has a rapid acceleration demand, resulting in a lag in the vehicle's power output, this phenomenon is similar to the possible consequences caused by the frequent start and stop of the range extender in the ECMS control strategy. Therefore, it is necessary to correct the future vehicle demand power by combining the driving intention identified based on the working condition prediction, so as to optimize the input value of the vehicle demand power of the ECMS control strategy and enable the range extender to generate power according to the future power demand.

[0102] Step S302: Modify the input value of the vehicle demand power according to the adjusted SOC threshold value, the driver's acceleration intention information, and a preset vehicle demand power prediction optimization strategy to obtain the modified demand power.

[0103] It can be understood that in this solution, the future vehicle demand power is modified by combining the driving intention identified based on the working condition prediction, so as to optimize the input value of the vehicle demand power of the ECMS control strategy, enabling the range extender to generate electricity according to the future power demand. Therefore, compared with the engine fixed-point + power following strategy in the prior art, the PPR-ECMS strategy in this solution can pre-charge the battery based on the larger demand power predicted by the driver's intention, so that the electricity generated by the range extender can be delivered to the drive motor through the high-voltage bus in the first time.

[0104] Further, step S302 further includes: if the adjusted SOC threshold value is lower than the preset threshold value and the driver has an acceleration demand, it is determined to enable the preset vehicle demand power prediction optimization strategy; predict the correction ratio coefficient according to the acceleration demand, rapid acceleration demand, deceleration demand, rapid deceleration demand in the driver's acceleration intention information and the preset vehicle demand power prediction optimization strategy to obtain the predicted ratio coefficient; modify the input value of the vehicle demand power according to the predicted ratio coefficient to obtain the modified demand power.

[0105] It should be noted that the predicted ratio coefficient can determine the target correction ratio coefficient according to the acceleration demand, rapid acceleration demand, deceleration demand, rapid deceleration demand in the driver's acceleration intention information and the adjusted SOC threshold value. If the battery power is low but the driver has a rapid acceleration demand, the PPR-ECMS strategy is triggered, and the predicted ratio coefficient is determined based on the driving intention identified by the working condition prediction, and the future vehicle demand power is modified to facilitate the range extender to generate electricity according to the future power demand.

[0106] In specific implementation, this solution needs to adjust the PS-ECMS control strategy as follows: modify the prediction ratio coefficient of the vehicle demand power in the ECMS control strategy by combining the driver's intention. When the driver's intention is to accelerate or rapidly accelerate, the vehicle demand power is increased; when the driver's intention is to drive at a constant speed, the vehicle demand power remains unchanged; when the driver's intention is to decelerate or rapidly decelerate, the vehicle demand power is decreased. The ratio coefficients can be defined as 1.2, 1.1, 1.0, 0.9, and 0.8. The above values are only used for illustrative purposes.

[0107] Step S303: Control the target range extender to generate electricity according to the modified demand power.

[0108] It should be noted that according to the corrected demand power control target, the range extender generates electricity, so that it can meet the large demand power based on the driver's intention prediction for battery pre-charging, and the electricity generated by the range extender is sent to the drive motor through the high-voltage bus in the first time.

[0109] In the specific implementation, the working condition prediction variable vehicle demand power ECMS strategy (Predictive Power Request adaptive ECMS, referred to as the PPR-ECMS strategy) is compared with the engine fixed-point + power following strategy. The power SOC curve of the improved control strategy is more easily affected by the demand power, and the charging oscillation amplitude of the battery SOC is higher than that of the PS-ECMS. The PPR-ECMS strategy can perform battery pre-charging based on the large demand power predicted by the driver's intention, so that the electricity generated by the range extender is sent to the drive motor through the high-voltage bus in the first time. When the vehicle is driving at a high speed on a smooth road section, the driving intention recognition remains at a constant speed and deceleration for a long time. Therefore, the PPR-ECMS strategy tends to consume more electricity, keeping the battery SOC within a lower range. At the end of the journey, the final value of the battery SOC drops to 31.5%, which is lower than the SOCCS-in normally set in the smooth working condition. The reason is that there are more deceleration and sudden deceleration driving intentions recognized on the smooth road section, and the upper and lower SOC thresholds are adjusted to the original values, indicating that the PPR-ECMS strategy helps to reduce the final value of the battery SOC at the end of the journey. For the total engine fuel consumption curve, the starting time of the PPR-ECMS strategy is similar to that of the PS-ECMS strategy, and the starting fuel consumption is slightly higher than that of the PS-ECMS strategy. The fuel consumption difference in the neutral working condition section is not significant, and the fuel consumption in the smooth working condition is significantly lower than that of the other two strategies. It shows that the PPR-ECMS strategy combined with the driver's driving intention has better economy at medium and high vehicle speeds, avoiding excessive charging of the vehicle at high speeds. And the PPR-ECMS control strategy predicts the future vehicle demand power through the driver's intention, and can significantly reduce the start-stop times of the range extender in the neutral / smooth road working condition section. Moreover, the equivalent fuel consumption of the PPR-ECMS strategy is reduced by 1.08% compared with the PS-ECMS and 5.48% compared with the FPPF.

[0110] In this embodiment, the driving road conditions corresponding to the target vehicle are predicted based on the visually acquired real-time information to obtain the predicted driving road conditions; the SOC threshold value of the target battery is adjusted according to the predicted driving road conditions and the preset ECMS control strategy to obtain the adjusted SOC threshold value; the vehicle demand power is corrected according to the adjusted SOC threshold value and the preset ECMS control strategy, and the target range extender is controlled to generate electricity according to the corrected demand power. Compared with the current REEV range extender with low energy utilization rate and poor adaptability to road conditions, and unable to achieve the predetermined energy conservation and emission reduction effect during actual use, in this embodiment, the future driving road conditions are predicted through the vehicle's real-time visual information, and the battery SOC threshold value and demand power are dynamically regulated according to the predicted driving road conditions and the preset ECMS control strategy, so as to achieve energy conservation and emission reduction while meeting the driving requirements of multiple scenarios, thereby enhancing the user experience.

[0111] In addition, to achieve the above object, the present invention also provides a storage medium, on which an energy management program is stored. When the energy management program is executed by a processor, the steps of the energy management method as described above are implemented.

[0112] Refer to Figure 5 , Figure 5 which is the structural block diagram of the first embodiment of the energy management device of the present invention.

[0113] As Figure 5 shown, the energy management device proposed in the embodiment of the present invention includes:

[0114] A road condition prediction module 10, configured to predict the driving road conditions corresponding to the target vehicle based on the visually acquired real-time information to obtain the predicted driving road conditions;

[0115] A threshold value adjustment module 20, configured to adjust the SOC threshold value of the target battery according to the predicted driving road conditions and the preset ECMS control strategy to obtain the adjusted SOC threshold value;

[0116] A power correction module 30, configured to correct the vehicle demand power according to the adjusted SOC threshold value and the preset ECMS control strategy, and control the target range extender to generate electricity according to the corrected demand power.

[0117] This embodiment predicts the driving condition corresponding to the target vehicle based on the real-time collected visual information to obtain the predicted driving condition; adjusts the SOC threshold value of the target battery according to the predicted driving condition and the preset ECMS control strategy to obtain the adjusted SOC threshold value; corrects the vehicle's required power according to the adjusted SOC threshold value and the preset ECMS control strategy, and controls the target range extender to generate electricity according to the corrected required power. Compared with the current REEV range extender, which has low energy utilization and poor adaptability to road conditions and cannot achieve the predetermined energy-saving and emission reduction effects during actual use, this embodiment predicts future driving conditions through real-time visual information of the whole vehicle, and dynamically adjusts the battery SOC threshold value and required power according to the predicted driving condition and the preset ECMS control strategy, so as to achieve energy saving and emission reduction while meeting driving needs in various scenarios, thereby improving user experience.

[0118] Furthermore, the road condition prediction module 10 is also used to detect the number of vehicles and the distance between vehicles in the visual information collected in real time to obtain the number of vehicles and the distance between vehicles information; perform data noise reduction and filtering on the speed information in the historical driving data to obtain optimized target speed information; predict the driving road condition corresponding to the target vehicle based on the number of vehicles, the distance information and the target speed information to obtain the predicted driving road condition.

[0119] Furthermore, the road condition prediction module 10 is also used to divide the vehicle distance information and the target vehicle speed information into section characteristic parameters based on a preset road condition type to obtain section characteristic parameters; based on the section characteristic parameters, the number of vehicles and a preset number of vehicles, predict the driving condition corresponding to the target vehicle to obtain the predicted driving condition.

[0120] Furthermore, the preset ECMS control strategy includes a preset SOC threshold optimization strategy and a preset vehicle demand power prediction optimization strategy, and the threshold value adjustment module 20 is also used to adjust the SOC threshold value of the target battery according to the predicted driving conditions and the preset SOC threshold optimization strategy to obtain an adjusted SOC threshold value.

[0121] The power correction module 30 is further used to correct the vehicle demand power according to the adjusted SOC threshold value and the preset vehicle demand power prediction optimization strategy, and control the target range extender to generate electricity according to the corrected demand power.

[0122] Further, the predicted driving road conditions include smooth road conditions, neutral road conditions, and congested road conditions. The threshold adjustment module 20 is further configured to, when the predicted driving road conditions are congested road conditions and the driver's intention at the current moment is not to accelerate urgently, reduce the SOCCS-in threshold of the target battery based on a preset SOC threshold optimization strategy; when the predicted driving road conditions are neutral congested road conditions and the driver's intention at the current moment is not to accelerate urgently, increase the SOCCS-out threshold of the target battery based on the preset SOC threshold optimization strategy; when the predicted driving road conditions are smooth congested road conditions and the driver's intention at the current moment is not to accelerate urgently, increase the SOCCS-in threshold of the target battery based on the preset SOC threshold optimization strategy.

[0123] Further, the power correction module 30 is further configured to obtain driver acceleration intention information; correct the input value of the vehicle demand power according to the adjusted SOC threshold value, the driver acceleration intention information, and a preset vehicle demand power prediction optimization strategy to obtain a corrected demand power; and control the target range extender to generate electricity according to the corrected demand power.

[0124] Further, the power correction module 30 is further configured to, if the adjusted SOC threshold value is lower than a preset threshold value and there is a driver acceleration demand, determine to enable a preset vehicle demand power prediction optimization strategy; predict a correction ratio coefficient according to the acceleration demand, urgent acceleration demand, deceleration demand, and urgent deceleration demand in the driver acceleration intention information and the preset vehicle demand power prediction optimization strategy to obtain a predicted ratio coefficient; and correct the input value of the vehicle demand power according to the predicted ratio coefficient to obtain a corrected demand power.

[0125] It should be understood that the above is only an example for illustration and does not impose any limitation on the technical solution of the present invention. In specific applications, those skilled in the art can set according to needs, and the present invention does not make any restrictions in this regard.

[0126] It should be noted that the above-described working process is only illustrative and does not limit the protection scope of the present invention. In actual applications, those skilled in the art can select some or all of them according to actual needs to achieve the purpose of the solution of this embodiment, and no restrictions are imposed here.

[0127] In addition, for the technical details not described in detail in this embodiment, reference can be made to the energy management method provided in any embodiment of the present invention, which will not be elaborated here.

[0128] It should be noted that, in this document, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or system comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or system comprising such element.

[0129] The serial numbers of the embodiments of the present invention above are merely for description and do not represent the superiority or inferiority of the embodiments. In the unit claims listing several devices, several of these devices may be embodied by the same hardware item. The use of the terms first, second, third, etc. does not denote any order and these terms may be construed as names.

[0130] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a Read Only Memory image (ROM) / Random Access Memory (RAM), magnetic disk, optical disc), and includes several instructions for causing a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0131] The above are only the preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or equivalent process transformation made by using the description of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. An energy management method, characterized in that, the energy management method includes the following steps: Predict the driving road conditions corresponding to the target vehicle based on the visually acquired information in real time to obtain the predicted driving road conditions; Adjust the SOC threshold value of the target battery according to the predicted driving road conditions and the preset equivalent fuel minimum control strategy to obtain the adjusted SOC threshold value; Correct the vehicle's total demand power according to the adjusted SOC threshold value and the preset equivalent fuel minimum control strategy, and control the target range extender to generate electricity according to the corrected demand power.

2. The energy management method according to claim 1, characterized in that, the step of predicting the driving road conditions corresponding to the target vehicle based on the visually acquired information in real time to obtain the predicted driving road conditions includes: Detect the number of vehicles and the vehicle distance in the visually acquired information in real time to obtain the number of vehicles and the vehicle distance information; Perform data denoising and filtering on the vehicle speed information in the historical driving data to obtain the optimized target vehicle speed information; Predict the driving road conditions corresponding to the target vehicle based on the number of vehicles, the vehicle distance information, and the target vehicle speed information to obtain the predicted driving road conditions.

3. The energy management method according to claim 2, characterized in that, the step of predicting the driving road conditions corresponding to the target vehicle based on the number of vehicles, the vehicle distance information, and the target vehicle speed information to obtain the predicted driving road conditions includes: Divide the vehicle distance information and the target vehicle speed information into section characteristic parameters based on the preset road condition types to obtain the section characteristic parameters; Predict the driving road conditions corresponding to the target vehicle based on the section characteristic parameters, the number of vehicles, and the preset number of vehicles to obtain the predicted driving road conditions.

4. The energy management method according to claim 1, characterized in that, the preset equivalent fuel minimum control strategy includes a preset SOC threshold optimization strategy and a preset vehicle total demand power prediction optimization strategy. The step of adjusting the SOC threshold value of the target battery according to the predicted driving road conditions and the preset equivalent fuel minimum control strategy to obtain the adjusted SOC threshold value includes: Adjust the SOC threshold value of the target battery according to the predicted driving road conditions and the preset SOC threshold optimization strategy to obtain the adjusted SOC threshold value; The step of correcting the vehicle's total demand power according to the adjusted SOC threshold value and the preset equivalent fuel minimum control strategy, and controlling the target range extender to generate electricity according to the corrected demand power includes: Correct the vehicle's total demand power according to the adjusted SOC threshold value and the preset vehicle total demand power prediction optimization strategy, and control the target range extender to generate electricity according to the corrected demand power.

5. The energy management method according to claim 4, characterized in that, the predicted driving road conditions include smooth type road conditions, neutral type road conditions, and congested type road conditions. The step of adjusting the SOC threshold value of the target battery according to the predicted driving road conditions and the preset SOC threshold optimization strategy to obtain the adjusted SOC threshold value includes: If the predicted driving road condition is a congested type road condition and the driver's intention at the current moment is not to accelerate urgently, the SOC entry threshold of the target battery is reduced based on a preset SOC threshold optimization strategy; If the predicted driving road condition is a neutral type road condition and the driver's intention at the current moment is not to accelerate urgently, the SOC exit threshold of the target battery is increased based on the preset SOC threshold optimization strategy; If the predicted driving road condition is a smooth type road condition and the driver's intention at the current moment is not to accelerate urgently, the SOC entry threshold of the target battery is increased based on the preset SOC threshold optimization strategy.

6. The energy management method according to claim 4, wherein, The step of correcting the vehicle demand power according to the adjusted SOC threshold value and a preset vehicle demand power prediction optimization strategy, and controlling the target range extender to generate power according to the corrected demand power includes: Obtaining driver acceleration intention information; Correcting the input value of the vehicle demand power according to the adjusted SOC threshold value, the driver acceleration intention information, and a preset vehicle demand power prediction optimization strategy to obtain a corrected demand power; Controlling the target range extender to generate power according to the corrected demand power.

7. The energy management method according to claim 6, wherein, The step of correcting the input value of the vehicle demand power according to the adjusted SOC threshold value, the driver acceleration intention information, and a preset vehicle demand power prediction optimization strategy to obtain a corrected demand power includes: If the adjusted SOC threshold value is lower than a preset threshold value and there is a driver's acceleration demand, it is determined to enable a preset vehicle demand power prediction optimization strategy; Predicting a correction proportionality coefficient according to the acceleration demand, urgent acceleration demand, deceleration demand, and urgent deceleration demand in the driver acceleration intention information and the preset vehicle demand power prediction optimization strategy to obtain a predicted proportionality coefficient; Correcting the input value of the vehicle demand power according to the predicted proportionality coefficient to obtain a corrected demand power.

8. An energy management device, wherein, The energy management device includes: a memory, a processor, and an energy management program stored on the memory and executable on the processor. When the energy management program is executed by the processor, it implements the energy management method according to any one of claims 1 to 7.

9. A storage medium, wherein, An energy management program is stored on the storage medium. When the energy management program is executed by a processor, it implements the energy management method according to any one of claims 1 to 7.

10. An energy management device, wherein, The energy management device includes: A road condition prediction module, configured to predict the driving road condition corresponding to the target vehicle based on visually acquired information in real time to obtain a predicted driving road condition; A threshold value adjustment module, configured to adjust the SOC threshold value of the target battery according to the predicted driving road condition and a preset equivalent fuel minimum control strategy to obtain an adjusted SOC threshold value; A power correction module, which is used to correct the vehicle demand power according to the adjusted SOC threshold value and the preset equivalent fuel minimum control strategy, and control the target range extender to generate electricity according to the corrected demand power.

Images