Range extender control method, device, vehicle and storage medium

Abstract

The present application relates to the field of vehicle control, and discloses a range extender control method, device, vehicle and storage medium. The method obtains the closed scenario category, closed value and operation information of the target vehicle, and the operation information includes gear information, vehicle speed information, remaining battery power and remaining travel distance; inputs the closed scenario category, closed value and operation information into a preset policy control model to determine the target control strategy of the range extender in the current closed scenario in the target vehicle. The preset policy control model is trained by a genetic algorithm to determine the optimal control strategy of the range extender under the closed value and operation information for each closed scenario category; in response to the target control strategy, controls the range extender. A linkage ecosystem is constructed based on the closed scenario category, closed value, operation information and range extender, enabling intelligent switching of multiple control strategies, thereby improving driving comfort and user experience.

Description

Technical Field

[0001] This application relates to the technical field of vehicle control, and particularly to a control method, device, vehicle and storage medium for a range extender. Background Art

[0002] With the continuous development of new energy vehicle technology, range-extended electric vehicles, as an important transitional solution, have an increasing market demand. Such electric vehicles enable the vehicle to have a longer cruising range and lower energy consumption through the collaborative work between electric energy and fuel.

[0003] In related technologies, since the control strategy of the range extender of electric vehicles is usually set based on preset working conditions or preset driving modes and lacks refined control for closed scenarios, when the electric vehicle enters a closed environment, if the range extender still operates, the exhaust gas emitted due to incomplete combustion of gasoline or diesel will affect the air quality in the environment and also increase noise pollution, thereby reducing the experience of surrounding users. Summary of the Invention

[0004] Embodiments of this application provide a control method, device, vehicle and storage medium for a range extender to solve the technical problems of noise pollution and energy efficiency utilization caused by the operation of the vehicle range extender in a closed environment in related technologies.

[0005] Embodiments of this application provide a control method for a range extender, including: obtaining the closed scenario category, closed value and operation information of a target vehicle, where the operation information includes gear information, vehicle speed information, remaining battery power and remaining travel distance; inputting the closed scenario category, closed value and operation information into a preset policy control model to determine the target control policy of the range extender in the current closed scenario in the target vehicle, where the preset policy control model is trained by a genetic algorithm to determine the optimal control policy of the range extender under the closed value and operation information for each closed scenario category; and controlling the range extender in response to the target control policy.

[0006] In an embodiment of this application, determining the preset policy control model includes: using the closed scenario category, closed value, gear information, vehicle speed information, remaining battery power and remaining travel distance as input parameters to determine an individual, where the individual is a control policy of the range extender, and the control policy includes a range extender shutdown instruction, or a range extender startup instruction and a corresponding power adjustment instruction after starting the range extender; randomly generating an initial population composed of a number of individuals; calculating the fitness of each individual in the initial population according to a preset fitness function; performing iterative optimization calculations using the genetic algorithm based on the initial population and fitness until a preset iteration termination condition is reached; and outputting the optimal individual in the iterated new population.

[0007] In an embodiment of the present application, the preset fitness function is obtained by weighted calculation of energy efficiency, driving experience, safety, and environmental protection; the second weight coefficient corresponding to driving experience and the fourth weight coefficient corresponding to environmental protection are respectively greater than the first weight coefficient corresponding to energy efficiency and the third weight coefficient corresponding to safety. Among them, energy efficiency represents the battery charging efficiency corresponding to the range extender at different energy consumption levels, and the energy consumption of the range extender is negatively correlated with energy efficiency; driving experience represents the impact of the start-up frequency or shutdown frequency of the range extender on driving comfort; safety represents the adequacy of power supply in a closed scenario; environmental protection represents the reduction of noise pollution and air pollution due to the reduction of the use of the range extender in a closed scenario.

[0008] In an embodiment of the present application, each iteration in the genetic algorithm generates a new population based on selection, crossover, and mutation.

[0009] In an embodiment of the present application, it is determined that the individual satisfies the following constraints: if the closing value of the closed scenario is larger, the degree of starting the range extender is smaller; if the closing value is determined to be the maximum value, the range extender is turned off; if the gear position information is in reverse or forward gear, the endurance of the target vehicle is determined according to the vehicle speed information and the remaining journey; if the gear position information is in the parking gear, the range extender is not started, and the target vehicle is driven by electric energy.

[0010] In an embodiment of the present application, the closed scenario categories include driving in a tunnel, driving on a restricted road, open-air parking, indoor parking, obstacle blocking the view, and vehicle covered with a car wrap; the value range of the closing value is 0 to 1, where 0 represents not closed and 1 represents completely closed.

[0011] In an embodiment of the present application, after determining the target control strategy corresponding to the range extender in the target vehicle in the current closed scenario, it further includes: if the closed scenario category, closing value, and operation information of the target vehicle are different from the preset conditions, the target control strategy is corrected using the preset personalized plan, and the control strategy corresponding to the preset personalized plan is output as the final control strategy for the current closed scenario; if the closed scenario category, closing value, and operation information of the target vehicle are the same as the preset specific conditions, the target control strategy corresponding to the range extender in the target vehicle is used as the final control strategy for the current closed scenario. Among them, the preset personalized plan is the range extender control strategy preset by the user according to the requirements under the closed scenario category, closing value, and operation information.

[0012] In an embodiment of the present application, obtaining the closing value corresponding to the current closed scenario of the vehicle includes: obtaining the first point cloud data and the first video data representing the vehicle's surrounding environment, as well as the position information of the vehicle; performing object detection on the first point cloud data and the first video data to determine the first target object and the second target object; inputting the first target object, the second target object, and the position information into a preset scenario recognition model to determine the closed scenario category of the closed scenario, and determining the closing value corresponding to the current closed scenario based on the closed scenario category.

[0013] In an embodiment of the present application, the method further includes: if the closed scenario category and the closing value of the target vehicle are received, sending the closed scenario category and the closing value to the display device, and constructing a three-dimensional environment to simulate and display the current closed scenario; if the range extender status of the target vehicle is received, sending the range extender status to the display device for display, and the range extender status includes the range extender startup status, the power status, the remaining battery ratio, and the additional mileage increased by the operation of the range extender.

[0014] An embodiment of the present application further provides a range extender control device, which includes: an acquisition module for acquiring the closed scenario category, the closing value, and the operation information of the target vehicle, and the operation information includes the gear information, the vehicle speed information, the remaining battery of the battery, and the remaining journey; a strategy determination module for inputting the closed scenario category, the closing value, and the operation information into a preset strategy control model to determine the target control strategy corresponding to the range extender in the current closed scenario of the target vehicle, wherein the preset strategy control model is trained by a genetic algorithm to determine the optimal control strategy of the range extender under the closing value and the operation information for each closed scenario category; a control response module for controlling the range extender in response to the target control strategy.

[0015] An embodiment of the present application further provides a vehicle that adopts the method of any of the above embodiments.

[0016] An embodiment of the present application further provides a computer-readable storage medium that stores a computer program, and when the computer program is executed by a processor, the method of any of the above embodiments is implemented.

[0017] In the solution implemented by the above-provided range extender control method, device, vehicle, and storage medium, the range extender control method obtains the closed scenario category, closed value, and operation information of the target vehicle. The operation information includes gear information, vehicle speed information, remaining battery power, and remaining travel distance. The closed scenario category, closed value, and operation information are input into a preset policy control model to determine the target control policy of the range extender in the current closed scenario for the target vehicle. In response to the target control policy, the range extender is controlled. On the one hand, a linkage ecosystem is constructed based on the closed scenario category, closed value, operation information, and range extender, enabling intelligent switching of multiple control strategies, thereby improving driving comfort and user experience. On the other hand, it ensures that the vehicle preferentially uses the pure electric mode in the closed scenario, reducing exhaust gas pollution and noise pollution in the closed environment and avoiding exhaust gas accumulation of the range extender in a poorly ventilated environment. At the same time, the engine speed is optimized in the non-closed environment to keep emissions always within the optimal range of regulations. Additionally, by combining gear information, vehicle speed information, remaining battery power, and remaining travel distance, the range extender control policy is dynamically adjusted to ensure normal endurance of the vehicle in D gear and R gear and avoid power exhaustion. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 FIG. is an exemplary system architecture diagram to which the range extender control method provided by an embodiment of the present application can be applied;

[0020] Figure 2 FIG. is a flowchart of the range extender control method provided by an embodiment of the present application;

[0021] Figure 3 FIG. is an overall process timing diagram of the range extender control method provided by an embodiment of the present application;

[0022] Figure 4 FIG. is a schematic diagram of a specific implementation of a genetic algorithm for the range extender control method provided by an embodiment of the present application;

[0023] Figure 5 FIG. is a structural diagram of the range extender control device provided by an embodiment of the present application;

[0024] Figure 6 FIG. is a structural diagram of an electronic device in an embodiment of the present application;

[0025] Figure 7Another structural schematic diagram of an electronic device in an embodiment of the present application. Detailed implementation manners

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0027] To enable those skilled in the art to better understand the improvements in the technical solutions provided by the present disclosure, the present disclosure briefly introduces the implementation scenarios and related information of the range extender control method in the related art.

[0028] Figure 1 This is a functional block diagram of a vehicle 100 provided by an embodiment of the present application. The vehicle 100 includes, but is not limited to, a range-extended electric vehicle. The vehicle 100 may include a perception system, a display device, and a computing platform. Among them, the perception system may include several sensors for sensing information about the environment around the vehicle 100. For example, the perception system may include a positioning system, which may be a global positioning system (GPS), or a Beidou system or other positioning systems, an inertial measurement unit (IMU), a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device, either alone or in combination.

[0029] Some or all functions of vehicle 100 can be controlled by a computing platform. The computing platform may include multiple processors. A processor is a circuit with signal processing capabilities. In one implementation, a processor can be a circuit with the ability to read and execute instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a type of microprocessor), or a digital signal processor (DSP), etc.; In another implementation, a processor can achieve certain functions through the logical relationship of a hardware circuit, and the logical relationship of this hardware circuit is fixed or can be reconfigured. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of a processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of a processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as a type of ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform may also include a memory for storing instructions, and some or all of the multiple processors can call the instructions in the memory to achieve corresponding functions.

[0030] Vehicle 100 may include an advanced driving assistant system (ADAS). The ADAS uses a variety of sensors on the vehicle (including but not limited to: lidar, millimeter-wave radar, camera devices, ultrasonic sensors, global positioning system, inertial measurement unit) to obtain information from around the vehicle, and analyzes and processes the obtained information to achieve functions such as obstacle perception, target recognition, vehicle positioning, path planning, driver monitoring / reminder, etc., thereby improving the safety, automation level and comfort of vehicle driving.

[0031] The sensors can include lidar, millimeter-wave radar, camera devices, and ultrasonic sensors. Among them, millimeter-wave radar can be divided into long-range radar and medium / short-range radar. Currently, the sensing range of lidar is about 80 - 150 meters, the sensing range of long-range millimeter-wave radar is about 1 - 250 meters, the sensing range of medium / short-range millimeter-wave radar is about 30 - 120 meters, the sensing range of the camera is about 50 - 200 meters, and the sensing range of ultrasonic radar is about 0 - 5 meters.

[0032] Logically speaking, the ADAS system generally includes three main functional modules: a perception module, a decision-making module, and an execution module. The perception module senses the surrounding environment of the vehicle body through sensors and inputs corresponding real-time data to the decision-making layer processing center. The perception module mainly includes on-vehicle cameras / ultrasonic radars / millimeter-wave radars / lidar, etc.; the decision-making module makes corresponding decisions using computing devices and algorithms based on the information obtained by the perception module; after receiving the decision signal from the decision-making module, the execution module takes corresponding actions, such as driving, lane-changing, steering, braking, warning, etc.

[0033] As mentioned above, in current range-extended electric vehicles, when the battery power drops to a certain threshold, the range extender starts to generate electricity to charge the battery, thereby extending the vehicle's cruising range; the range extender is used to provide additional power support when the battery power is insufficient to ensure the continuous operation of the vehicle. However, when the above vehicle travels to a closed scenario, since the range extender or the range extender burns gasoline or diesel, it will produce pollutants such as carbon dioxide, carbon monoxide, and nitrogen oxides. Especially in urban congestion areas or closed environments, these emissions will have a negative impact on air quality; in addition, the range extender will generate obvious mechanical noise during operation, especially at low speeds or in an idle state, and this noise has a particularly significant impact on the surrounding environment and people.

[0034] In view of this, the embodiments of the present application provide a range extender control method, device, vehicle, and storage medium, which can determine whether the vehicle is in a closed scenario according to the environment where the vehicle is located, detect the category of the current closed scenario, and then determine the best control strategy of the current range extender under different closed values and different operating information according to the closed scenario category, so as to achieve intelligent control of the vehicle with low noise and low energy consumption in the closed scenario.

[0035] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of the range extender control method provided by the embodiments of the present application. The method includes the following steps:

[0036] Step S201, obtain the closed scenario category, closed value, and operating information of the target vehicle. The operating information includes gear information, vehicle speed information, remaining battery power, and remaining travel. The target vehicle includes a range-extended electric vehicle;

[0037] Exemplarily, the closed scenario category, closed value, and operation information of the target vehicle are obtained through ADAS. Among them, the remaining travel distance is the mileage that the remaining battery power can travel according to the current gear information and vehicle speed information, which will not be elaborated here.

[0038] Step S202: Input the closed scenario category, closed value, and operation information into a preset policy control model to determine the target control strategy of the range extender in the target vehicle for the current closed scenario. The preset policy control model is trained by a genetic algorithm to determine the optimal control strategy of the range extender for each closed scenario category under different closed values and different operation information.

[0039] Exemplarily, the optimal control strategy of the range extender under the current conditions is determined by invoking the preset policy control model trained in advance. In addition to training with the genetic algorithm, it may also include replacing it with a convolutional neural network algorithm, bidirectional long short-term memory network, evolutionary algorithm class, swarm intelligence algorithm, and Bayesian optimization algorithm.

[0040] Step S203: Control the range extender in response to the target control strategy.

[0041] Exemplarily, convert the control parameters output by the model into specific control instructions, such as starting the range extender and adjusting the power of the range extender; or, shutting down the range extender. The electronic control unit adjusts the torque output of the range extender by responding to the specific control instructions to determine the output power of the range extender.

[0042] Through the above method, by obtaining the closed scenario category, closed value, and operation information of the target vehicle, where the operation information includes gear information, vehicle speed information, remaining battery power, and remaining travel distance; inputting the closed scenario category, closed value, and operation information into the preset policy control model to determine the target control strategy of the range extender in the target vehicle for the current closed scenario; and controlling the range extender in response to the target control strategy. On the one hand, a linkage ecosystem is constructed based on the closed scenario category, closed value, operation information, and range extender, enabling intelligent switching of multiple control strategies, improving driving comfort and user experience; on the other hand, it ensures that the vehicle preferentially uses the pure electric mode in the closed scenario, reducing exhaust gas pollution and noise pollution in the closed environment, and avoiding the accumulation of exhaust gas of the range extender in a poorly ventilated environment; at the same time, optimizing the engine speed in the non-closed environment to keep the emissions always within the optimal range of regulations; and on the other hand, dynamically adjusting the range extender control strategy in combination with gear information, vehicle speed information, remaining battery power, and remaining travel distance to ensure the normal endurance of the vehicle in D gear and R gear and avoid running out of power.

[0043] In this embodiment, the CAN (Controller Area Network) signal is adopted as the bus type. The CAN bus has high real-time performance and can complete data transmission in an extremely short time. The CAN bus adopts a multiple control method, and any node can send information to other nodes on the network at any time. At the same time, it also has a non-destructive bus arbitration mechanism and error detection and processing functions, which can ensure the reliability of data transmission.

[0044] As Figure 3 shown, it is a schematic diagram of the overall process timing of the range extender control method provided by the embodiment of the present application, which is described in detail as follows:

[0045] The intelligent driving system comprehensively senses the environment around the vehicle, completes the recognition of the closed scene and the judgment of the closed value, and obtains the scene category C and the closed value V_closed. The corresponding signals are ADS_ClosedScene (closed scene category) and ADS_ClosedValue (closed value) respectively.

[0046] The intelligent driving system sends ADS_ClosedScene (closed scene category) and ADS_ClosedValue (closed value) to the VCU (vehicle controller).

[0047] The VCU obtains the optimal range extender adjustment strategy under the current closed scene category and closed value through the intelligent adjustment of the range extender based on the evolutionary algorithm. This strategy includes VCU_engStopCmd (stop the range extender) / VCU_engStartCmd (start the range extender), VCU_REPowerAdjust (range extender output power).

[0048] The VCU sends VCU_engStopCmd (stop the range extender) / VCU_engStartCmd (start the range extender), VCU_REPowerAdjust (range extender output power) to the EMS (engine management system), and the EMS executes the range extender adjustment strategy.

[0049] The EMS feeds back the EMS_engine_status (range extender status) to the VCU in real time to facilitate subsequent dynamic adjustment of the range extender.

[0050] In some other embodiments, the following specific signals and the corresponding 0Xn signal values are involved:

[0051] If the advanced driving assistance system recognizes that the vehicle is currently in a closed scene, the closed scene category, and the signal description values include at least one of the following:

[0052] 0x0:NO_INFOMATION No information

[0053] 0x1: Driving within a tunnel

[0054] 0x2: Driving on restricted roads

[0055] 0x3: Open Air Parking

[0056] 0x4: Indoor Parking

[0057] 0x5: obscure the view

[0058] 0x6: Covering a vehicle with a car cover

[0059] 0x7: Reserved

[0060] The advanced driver assistance system sends the signal description value to the vehicle control unit through CAN communication.

[0061] If the advanced driver assistance system recognizes the enclosure value of the vehicle, and the signal description value of the enclosure value is [0, 1], where 0 represents non-enclosed and 1 represents enclosed, the advanced driver assistance system sends its corresponding signal description value to the vehicle control unit through CAN communication.

[0062] If the vehicle control unit receives an engine stop request, and its signal description values include 0x0: NO_STOP (i.e., the engine does not stop) and 0x1: STOP (i.e., the engine stops), the vehicle control unit sends its corresponding signal description value to the engine management system through CAN communication. [[ID=z31]]

[0063] If the vehicle control unit receives an engine start request, and its signal description values specifically include 0x0: NO_START (i.e., the engine does not start) and 0x1: START (i.e., the engine starts), the vehicle control unit sends its corresponding signal description value to the engine management system through CAN communication.

[0064] If the vehicle control unit receives a range extender start request, and its signal description value includes kilowatts (kW) with a range of [10, 100], the vehicle control unit sends its corresponding signal description value to the engine management system through CAN communication.

[0065] If the engine management system receives the engine operating status, its signal description values include:

[0066] 0x1: Initial; 0x2: Stop; 0x3: Cranking;

[0067] 0x4: Running Low Power (10 - 30% power);

[0068] 0x5: Running Medium Power (30 - 70% power);

[0069] 0x6: Running High Power (70 - 100% power);

[0070] 0x7: Stopping; 0x8: Fault; 0x9: Reserved;

[0071] 0xA: Pre - start Check (Ensure all systems are properly prepared for startup);

[0072] 0xB: Cranking Low Power;

[0073] 0xC: Cranking Medium Power;

[0074] 0xD: Cranking High Power;

[0075] 0xE: Post - start Adjustment (Stabilize power output);

[0076] 0xF: Reserved;

[0077] Then the engine management system sends its corresponding signal description value to the vehicle controller via CAN communication.

[0078] If the electronic stability program (ESP) receives the vehicle speed information and its signal description value includes Km / h, then the ESP sends its corresponding signal description value to the advanced driver assistance system via CAN communication.

[0079] If the ESP receives the valid bit of the vehicle speed signal and its signal description value includes 0x0: Invalid (vehicle speed signal is invalid), 0x1: Valid (vehicle speed signal is valid), then the ESP sends its corresponding signal description value to the advanced driver assistance system via CAN communication.

[0080] If the vehicle control unit receives the actual gear position, its signal description values include 0x0: Park gear, 0x1: Reverse gear,

[0081] 0x2: Neutral gear, 0x3: Drive gear; then the vehicle control unit sends the corresponding signal description value to the advanced driver assistance system via CAN communication.

[0082] If the vehicle control unit receives the gear position validity bit, its signal description values include 0x0: Invalid (i.e., the gear position is invalid), 0x1: Valid (i.e., the gear position is valid); then the vehicle control unit sends the corresponding signal description value to the advanced driver assistance system via CAN communication.

[0083] If the battery management system receives the current battery charge percentage, its signal description value includes the percentage %, with a range of [0, 1]; then the battery management system sends the corresponding signal description value to the vehicle control unit via CAN communication.

[0084] If the body control module receives the outside rearview mirror folding state, its signal description values include 0x0: invalid (i.e., the state is invalid), 0x1: ON (i.e., the state is on), 0x2: OFF (i.e., the state is off), 0x3: Reserved (i.e., the state is maintained); then the body control module sends the corresponding signal description value to the advanced driver assistance system via CAN communication.

[0085] In some embodiments, in order to find the optimal range extender control strategy under the current closed scenario and closed value, so that the range extender can operate intelligently and energy-efficiently under different closed scenarios, while reducing noise and air pollution, and ensuring normal vehicle endurance.

[0086] Exemplarily, determining a preset policy control model includes:

[0087] Taking the closed scenario category, closed value, gear position information, vehicle speed information, remaining battery charge and remaining travel distance as input parameters to determine an individual, where the individual is a control strategy for the range extender, and the control strategy includes a range extender shutdown instruction, or a range extender startup instruction and the corresponding power adjustment instruction after starting the range extender;

[0088] Randomly generating an initial population composed of several individuals; calculating the fitness of each individual in the initial population according to a preset fitness function; based on the initial population and fitness, using a genetic algorithm for iterative optimization calculation until the preset iteration termination condition is reached; outputting the optimal individual in the iterated new population.

[0089] Exemplarily, a fitness algorithm is an algorithm used to evaluate the performance or quality of each individual. For each individual in the initial population, the fitness algorithm calculates a fitness value based on the individual parameters. The fitness value is a quantitative representation of the individual's performance and is usually a numerical value used to guide the retention and elimination of individuals in the selection process of the genetic algorithm.

[0090] Exemplarily, the initial population and fitness are used as the initial input variables of the genetic algorithm, and the genetic algorithm is used for iterative optimization calculations. By simulating natural selection and genetic mechanisms, the genetic algorithm gradually selects individuals with higher fitness and generates a new population. This process continues until the preset iterative termination condition is reached, and the algorithm stops iterating. When the iterative termination condition is met, the algorithm stops iterating and outputs the individual with the highest fitness as the optimal solution. This optimal solution represents the optimized best control strategy and can be used to guide the operation of the range extender.

[0091] In some embodiments, the closed scene categories include driving within a tunnel, driving on restricted roads, open air parking, indoor parking, obstructed view, and vehicle covered with car wrap; the closed value ranges from 0 to 1, where 0 represents not closed and 1 represents fully closed; the gear information includes reverse gear, forward gear, and parking gear; the remaining battery power includes low power, medium power, and high power, and the remaining travel distance includes long remaining travel distance and short remaining travel distance.

[0092] For example, the input parameters are as follows:

[0093] Scene category C, the type of closed scene recognized by the ADAS system, corresponding to the signal ADAS_Closed Scene;

[0094] Specifically, the closed scene categories are as follows (when implementing, a scene recognition dataset can be made according to the actual project requirements, and the types can be added or reduced by oneself):

[0095] 0x1: Driving within a tunnel

[0096] [ 0x2: Driving on restricted roads

[0097] 0x3: Open Air Parking

[0098] 0x4: Indoor Parking

[0099] 0x5: obscure the view

[0100] 0x6:Covering a vehicle with a car cover

[0101] Closed value : Range [0, 1], representing the degree of environmental enclosure, corresponding to the signal ADAS_Closed Value; where 0 represents completely unenclosed (open), and 1 represents completely enclosed.

[0102] Current battery level : Percentage %, range [0, 1], representing the remaining battery level of the current battery, corresponding to the signal BMS_Battery SOC.

[0103] Current vehicle speed : Unit is km / h, corresponding to the signal ESP_Vehicle Speed.

[0104] Current gear position : P (parking), D (driving), R (reverse), N (neutral), corresponding to the signal VCU_actual Gear.

[0105] Remaining range : Unit is km, representing the remaining travel distance, obtained in real-time based on the navigation target destination.

[0106] For example, the output parameters are as follows:

[0107] Range extender start / stop command S: Range extender start corresponds to the signal VCU_engStartCmd, and range extender stop corresponds to the signal VCU_engStopCmd;

[0108] Range extender power adjustment command P: Kilowatt (kW), range [10, 100], representing the output power of the range extender, corresponding to the signal VCU_REPower Adjust.

[0109] In summary, each individual corresponds to a set of input parameters and a set of output parameters, forming individual parameters.

[0110] In some embodiments, to solve the core contradiction of multi-objective optimization control of hybrid / extended-range vehicles in closed scenarios. For example, the traditional control strategy to improve battery charging efficiency will frequently start and stop the range extender, resulting in a degraded driving experience; another example is that the priority of performance requirements dynamically changes in different driving scenarios, and it is necessary to adaptively adjust the optimization target. The specific implementation method is as follows:

[0111] The preset fitness function is obtained by weighted calculation of energy efficiency, driving experience, safety, and environmental friendliness; the second weight coefficient corresponding to driving experience and the fourth weight coefficient corresponding to environmental friendliness are respectively greater than the first weight coefficient corresponding to energy efficiency and the third weight coefficient corresponding to safety. Among them, energy efficiency represents the battery charging efficiency of the range extender at different energy consumption levels, and the energy consumption of the range extender is negatively correlated with energy efficiency, that is, the lower the energy consumption, the higher the energy efficiency; driving experience represents the impact of the startup frequency or shutdown frequency of the range extender on driving comfort; safety represents the sufficiency of power supply in a closed scenario; environmental friendliness represents the reduction of noise pollution and air pollution due to the reduction of the use of the range extender in a closed scenario.

[0112] Specifically, a fitness function formula in a closed scenario is constructed:

[0113]

[0114] Among them, in formula (1) , , , are the weight coefficients corresponding to energy efficiency, driving experience, safety, and environmental friendliness respectively, corresponding to the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight coefficient respectively. Since in this embodiment, more attention is paid to the noise and exhaust gas of the range extender in a closed scenario and the user experience is improved. Therefore, for and higher weights are given. For example, = 0.2, = 0.3, = 0.2, = 0.3. In specific implementation, higher weights can be given to the parts that are valued according to project requirements, which will not be elaborated here.

[0115] Through the above method, by systematically optimizing multiple objectives, the performance balance problem of the hybrid power system under complex working conditions is effectively solved; the quantitative mapping from multiple physical quantities to a single fitness is realized, and driving experience and environmental friendliness are guaranteed to be prioritized through weight constraints; the start-stop times of the range extender are greatly reduced; at the same time, the noise level of the vehicle is reduced.

[0116] In an embodiment of the present application, the preset iteration termination conditions include: the number of iterations meets a preset threshold; based on the initial population and fitness, iterative optimization calculation is performed using the genetic algorithm until the preset iteration termination conditions are reached, including: using the initial population and fitness as initial parameters and inputting them into the genetic algorithm for calculation; performing iterative optimization processing on the initial population, where each iteration generates a new population based on selection, crossover, and mutation; until the number of iterative optimization processing times meets the preset iteration termination conditions.

[0117] Exemplarily, the initial population and the fitness corresponding to each individual are input as initial parameters into the genetic algorithm for calculation, and the initial population is iteratively optimized. In this stage, each iteration will sequentially perform three core operations: selection, crossover, and mutation to generate a new population.

[0118] Specifically, according to the fitness values of the individuals, a certain number of excellent individuals are selected from the current population as the parents for generating the new population. The selected parent individuals are paired, and new offspring individuals are generated by exchanging some of their genes. Random small-scale gene changes are made to the newly generated offspring individuals to introduce new genetic information. By continuously repeating the above three operations, the genetic algorithm will generate a series of new populations and gradually approach the optimal solution to the problem. When the number of iterations of the iterative optimization process reaches the preset iteration termination condition, the genetic algorithm stops iterating.

[0119] Exemplarily, in the selection stage, the roulette wheel selection strategy is adopted. This strategy assigns selection probabilities according to the fitness values of the individuals, such that individuals with higher fitness values have a greater chance of being selected as parents. In each selection process, two individuals are randomly selected as a pair of parents for subsequent crossover operations. In the crossover stage, the single-point crossover operation is adopted. For each pair of selected parents, crossover is performed at a random position of a certain continuous control variable, that is, the partial control variables before and after this position of the two parents are exchanged, thereby generating two new individuals. This step aims to generate offspring with potentially better performance by combining the excellent genes of different individuals. To increase the diversity of the population and prevent the algorithm from falling into local optimal solutions, mutation operations are performed on the newly generated individuals in the mutation stage. At a certain mutation rate, each control variable has the opportunity to be randomly perturbed. For continuous variables, a random fluctuation value is added to its current value to introduce new genetic information. By continuously repeating the above selection, crossover, and mutation operations, the genetic algorithm will generate a series of new populations and gradually approach the optimal solution to the problem. When the number of iterations reaches the preset termination condition, the genetic algorithm stops iterating.

[0120] Through the above method, through the iterative optimization of the genetic algorithm, the optimal or approximately optimal individual parameter combination can be efficiently searched. This optimization process avoids the cumbersome and time-consuming nature of the traditional trial-and-error method and significantly improves the optimization efficiency.

[0121] Specifically, after each iteration, the genetic algorithm checks whether the iteration counter has reached a preset threshold. If so, the algorithm stops and outputs the currently found optimal solution (i.e., individual parameter combination). By setting an upper limit on the number of iterations, the algorithm avoids performing a large number of inefficient calculations even when it is nearing the optimal solution, thereby saving computing resources and time. For example, setting the preset threshold to 100, i.e., the maximum number of iterations is 100, ensuring that the iterations complete within 1-2 seconds.

[0122] In summary, according to the technical solution provided by the embodiments of the present disclosure, by setting an upper limit on the number of iterations, the genetic algorithm can stop iterating when a preset threshold is reached, thereby avoiding a large amount of ineffective calculations. This helps save computing resources.

[0123] See also Figure 4 , which is a schematic diagram of a genetic algorithm for implementing the range extender control method provided in an embodiment of the present application, is described in detail as follows:

[0124] (1) Initialize the population

[0125] Generate initial population , each individual Is a range extender control strategy, which includes a set of parameters ,in, Indicates the start / stop status of the range extender (0: off, 1: on). Indicates the range extender power setting.

[0126]

[0127] At this point, each individual's performance varies, and each individual's understanding and completion of the task are also different.

[0128] (2) Define the fitness function

[0129] A closed-scene adaptability function was designed to consider multiple factors in the range extender strategy under closed scenarios, including the following aspects:

[0130] Energy efficiency : The greater the power, the higher the energy consumption, and the corresponding battery charging efficiency is also higher.

[0131] Driving Experience : The impact of the frequency of starting and shutting down the range extender on driving comfort.

[0132] Security : Ensure that there is enough power to provide power in closed scenarios.

[0133] Environmental protection :The environmental friendliness characterizes that the greater the power of the range extender in a closed scenario, the greater the corresponding noise pollution and air pollution.

[0134] The formula of the fitness function in a closed scenario is shown in Equation (1).

[0135] (3)Selection operation

[0136] ① For the environment (scenario category C, closed value V_closed, current battery level B, current vehicle speed V, current gear G, remaining travel distance D_remaining), each individual in the initial population will make a decision (range extender start / stop command Si and range extender power adjustment command Pi), generating parameters

[0137] ② Input the parameters generated by each individual into the fitness function formula This function will evaluate the adaptability of each individual to the current environment

[0138] ③ Arrange from largest to smallest. The larger the value, the higher the adaptability.

[0139] ④ Select 5% of the individuals in the initial population in descending order of adaptability to enter the next generation population.

[0140] ⑤ The selection operation finally outputs the next generation population .

[0141] (4)Crossover operation based on a closed scenario

[0142] The crossover operation refers to selecting a part of the genes from two parent individuals for exchange to generate new offspring individuals.

[0143] Advantages: ① Through the crossover operation, the advantages of different individuals can be combined to generate a better range extender control strategy.

[0144] ② The crossover operation can generate new gene combinations, helping the algorithm explore a wider space and avoid falling into local optimal solutions.

[0145] The crossover operation formula is as follows:

[0146]

[0147] In this embodiment, for the range extender control strategy , the crossover operation can combine different start / stop states S and power settings P to find a better control strategy. The crossover operation in this embodiment is as follows:

[0148] Parent individual

[0149] Parent individual

[0150] New individual generated after crossover

[0151] (5) Mutation operation based on closed scenario

[0152] The mutation operation refers to randomly changing the genes of an individual with a certain probability, introducing new gene combinations to prevent the algorithm from converging to the local optimal solution prematurely.

[0153] In this embodiment, in the range extender control strategy under a closed scenario, the mutation operation can help explore high-quality control strategies that have not been discovered yet. Especially when the fitness improvement is slow, the mutation operation is as follows:

[0154] ① For the start / stop state S of the range extender, which is a binary encoding, binary mutation is adopted, that is, a certain gene bit is flipped with a certain probability:

[0155] If S = 1, this embodiment considers that there is a probability of e to change it to S = 0.

[0156] ② For the power setting P of the range extender, the gene value is slightly perturbed with a certain probability. In this embodiment, a random perturbation within a small range is added to the current power, and the formula is as follows:

[0157]

[0158] where ϵ is the perturbation coefficient, and N(0,σ 2 ) is a normal distribution with a mean of 0 and a variance of σ 2 .

[0159] (6) Output the optimal individual I_opt

[0160] ① Assume that the number of individuals in P_(t + 1) is n, and rank them in descending order according to adaptability

[0161] ② Select the top 10% of the individuals directly to ensure that excellent genes are not lost

[0162] ③ Select the individuals from the top 10% to the top 60% for crossover operation

[0163] ④ Select the individuals after 60% for mutation operation

[0164] ⑤ After completing the crossover operation and the mutation operation, pass the n individuals through the fitness function again and rank them.

[0165] ⑥ Continuously repeat the above iteration, and finally select the top 10 individuals for output, that is, output the optimal individual I_opt.

[0166] Through the above method, the range extender control method of the present application has the following technical effects:

[0167] First, build a linkage ecosystem between ADAS and the range extender, establish a range extender adjustment strategy in a closed scenario, and improve the intelligence level of the range extension strategy.

[0168] Second, in a high-closure value scenario, give priority to air quality and quietness effect, reduce noise and air pollution, and improve driving comfort and user experience.

[0169] Third, combine factors such as battery power, gear position, speed, and remaining travel distance, and dynamically adjust the range extender strategy to ensure the normal endurance of the vehicle in D gear and R gear, and avoid power exhaustion.

[0170] Fourth, through the IVI system, provide real-time display of the closed scenario and the status of the range extender, so that users can intuitively understand the current environment and the working conditions of the range extender, and enhance driving confidence.

[0171] In some embodiments, it aims to solve the intelligent control problems of the start-stop logic and energy distribution of the range extender in different driving scenarios, specifically including: how to dynamically adjust the intervention degree of the range extender according to the closure value of the closed scenario to achieve the balance between energy consumption and power demand; how to optimize the endurance prediction and energy management by combining the gear position state and vehicle operation information (vehicle speed, remaining travel distance); how to completely rely on electric energy to drive in the parking scenario to reduce the ineffective energy consumption and emissions of the range extender.

[0172] To solve the above problems, it is determined that the individual meets the following constraints:

[0173] If the closure value of the closed scenario is larger, the degree of starting the range extender is smaller; if the closure value is determined to be the maximum value, the range extender is turned off; if the gear information is in reverse gear or forward gear, the endurance of the target vehicle is determined according to the vehicle speed information and the remaining travel distance; if the gear information is in parking gear, the range extender is not started, and the target vehicle is driven by electric energy.

[0174] Exemplarily, the closure value is quantified, and it is quantified with 0~1. As the closure value increases → the output power of the range extender decreases or the start-stop frequency decreases. For example, when the closure value reaches the maximum value, the range extender is forced to turn off; through the look-up table method or function model, such as linear interpolation, the dynamic binding of the closure value and the start-stop parameters of the range extender is realized.

[0175] Specifically, the closed value of the closed scenario category is determined by ADAS. For example, the image data and the point cloud data are combined with the navigation system for comprehensive judgment, and the closed value is dynamically updated according to the sensor data (such as reducing the closed value level when sudden congestion is detected). For example, the gear signal is obtained through the CAN bus, the real-time vehicle speed is obtained through the wheel speed sensor, and the remaining journey is predicted based on the energy consumption of the navigation path. The remaining driving range is predicted based on the current battery SOC, vehicle speed, and road conditions (such as highway / urban area). For example, the output power or start-stop strategy of the range extender is adjusted to meet the driving range requirements. For example, the power generation efficiency of the range extender is increased when the battery is low. The remaining journey energy consumption prediction is dynamically corrected according to the current vehicle speed and road slope. For example, the energy consumption compensation is increased when going uphill.

[0176] Through the above methods, by linking the closed value grading with the gear state, precise control of the start and stop of the range extender is achieved; by combining dynamic driving range prediction with real-time road conditions, the pure electric / hybrid mode switching logic is optimized to achieve energy closed-loop management; by dynamically adjusting the intervention degree of the range extender through the closed value, the ineffective energy consumption in high-closed scenarios is reduced; when the closed value reaches the threshold, the range extender is turned off, reducing the tail gas pollution in specific scenarios, avoiding the risk of breakdown caused by misjudgment of the driving range, and enhancing user trust.

[0177] In some embodiments, in order to optimize in specific closed scenarios, a supplementary strategy is based on rules to further optimize and refine the control logic of the range extender, which is described in detail as follows:

[0178] After determining the target control strategy corresponding to the range extender in the current closed scenario of the target vehicle, it further includes:

[0179] If the closed scenario category, closed value, and operation information of the target vehicle are different from the preset conditions, the target control strategy is corrected using the preset personalized plan, and the control strategy corresponding to the preset personalized plan is output as the final control strategy for the current closed scenario; if the closed scenario category, closed value, and operation information of the target vehicle are the same as the preset specific conditions, the target control strategy corresponding to the range extender in the target vehicle is used as the final control strategy for the current closed scenario, where the preset personalized plan is the range extender control strategy preset by the user according to requirements under the closed scenario category, closed value, and operation information.

[0180] Exemplarily, according to the closed value Vclosed, the start threshold and power setting of the range extender are dynamically adjusted:

[0181] ① For a high closed value (Vclosed > 0.8), the range extender is turned off (S = 0), unless the battery power is extremely low (B < 5%) and the remaining journey is long (Dremaining > 5 km).

[0182] If it must be started, the power setting is the lowest ( )

[0183] ② Medium closed value (0.5 < Vclosed ≤ 0.8), the power setting for the range extender to start is medium ( ). Combine speed and remaining travel distance to ensure sufficient endurance.

[0184] ③ Low closed value (Vclosed ≤ 0.5): The range extender starts normally (S = 1), and the power setting is maximum ( ).

[0185] Exemplarily, the gear affects the start strategy of the range extender by adjusting it according to the current gear:

[0186] ① P gear (parking), prioritize quietness and air quality, and try not to start the range extender (S = 0).

[0187] If the battery power is extremely low (B < 5%), allow the range extender to start for a short time to charge ( ).

[0188] ② D gear (driving), dynamically adjust the start and power setting of the range extender according to the speed V and the remaining travel distance Dremaining. When driving at high speed (V > 60 km / h), the range extender starts normally (S = 1, P = Pmax). When driving at low speed (V ≤ 60 km / h), appropriately reduce the power in combination with the closed value and battery power.

[0189] ③ R gear (reverse), prioritize quietness and air quality, and try not to start the range extender (S = 0).

[0190] If the battery power is extremely low (B < 5%), allow the range extender to start for a short time to charge ( ).

[0191] Exemplarily, the battery power and remaining travel distance affect the start strategy of the range extender by further optimizing it according to the current battery power B and the remaining travel distance Dremaining:

[0192] ① Low battery power (B < 10%) and long remaining travel distance (Dremaining > 10 km):

[0193] The range extender is forced to start (S = 1), and the power setting is maximum ( ).

[0194] ② Medium battery power (B > 15%) and short remaining travel distance (Dremaining < 3 km):

[0195] Try not to start the range extender (S = 0), and rely on the battery for power supply.

[0196] For example, a combined approach is used to achieve intelligent adjustment of the range extender in closed scenarios. In actual application, the optimization strategy is used after the evolutionary algorithm for fine-tuning:

[0197] ① In the training phase, an evolutionary algorithm is used to generate a set of candidate range extender control strategies. These strategies are obtained through global search and their effectiveness is verified through fitness evaluation.

[0198] ② In the actual application stage, in actual operation, the strategy generated by the evolutionary algorithm is fine-tuned by applying a specific scenario optimization strategy based on input parameters such as the current closed value, power, gear, speed, and remaining range.

[0199] For example, when the closure value is very high, even if the evolutionary algorithm recommends activating the range extender, the scenario-specific optimization strategy may prioritize quietness and air quality and choose not to activate the range extender. Another example is when the battery is extremely low and the remaining range is long, the scenario-specific optimization strategy may override the evolutionary algorithm's recommendation and force the range extender to activate to ensure range.

[0200] Through the above methods, the optimal control strategy is provided for specific scenarios; multi-dimensional parameter optimization is achieved through a personalized solution library to enhance user experience.

[0201] In some embodiments, the method aims to solve how to obtain the closure value corresponding to the vehicle in the current closure scene, including:

[0202] Acquire first point cloud data and first video data representing the environment surrounding the vehicle, as well as location information of the vehicle;

[0203] Preprocessing the first point cloud data and the first video data respectively to determine second point cloud data and second video data;

[0204] Segmenting the second point cloud data and the second video data respectively to determine the first target feature and the second target feature;

[0205] Detecting the first target feature and the second target feature respectively to determine the first target object and the second target object;

[0206] Inputting the first target object, the second target object, and the position information into a preset scene recognition model to determine the closed scene category of the closed scene, wherein the preset scene recognition model is trained based on a convolutional neural network;

[0207] The closure value corresponding to the current closure scene is determined based on the closure scene category.

[0208] Exemplarily, a lidar (LiDAR) scans for obstacles around the vehicle in 360°, generating a three-dimensional point cloud, e.g., with a resolution of 0.1°×0.1°; RGB (red, green, blue) images are collected through a front view / surround view camera, e.g., with a resolution of 1920×1080@30fps; the position information (accuracy ±10 cm) is determined through the fusion positioning of the global navigation satellite system / inertial measurement unit. Through timestamp alignment and spatial calibration, the external parameter calibration error is <0.5°, generating a multi-modal data packet in a unified coordinate system.

[0209] The point cloud preprocessing includes denoising filtering: statistical filtering removes outliers, e.g., with a threshold of σ = 3; ground segmentation: the RANSAC (Random Sample Consensus) algorithm extracts the ground plane, e.g., with an error <5 cm.

[0210] The video preprocessing includes adaptive exposure: dynamically adjusting the camera exposure parameters according to the light intensity, e.g., with an adjustment range of 1 / 1000s~1 / 30s; feature enhancement: an image optimization algorithm enhances the image contrast to highlight the features of lane lines / traffic signs.

[0211] The point cloud segmentation includes a semantic segmentation network: PointNet++ (3D point cloud network) clusters the point cloud (DBSCAN algorithm, a density-based clustering algorithm), distinguishing categories such as roads, obstacles, sky, etc.; dynamic object removal: Kalman filtering tracks moving targets, such as pedestrians and vehicles, to exclude interference.

[0212] The video segmentation includes an instance segmentation model: Mask R-CNN (i.e., an object detection and instance segmentation model) identifies the features of closed scenes such as road markings, tunnel entrances, guardrails, etc.; geometric feature extraction: the Hough transform detects straight lines, i.e., lane lines and arcs, i.e., the tunnel vault. The SECOND algorithm (i.e., a 3D detection network) detects objects such as vehicles, pedestrians, traffic cones, etc.;

[0213] Speed estimation: calculates the target speed through the displacement of consecutive frame point clouds.

[0214] Video object detection includes using YOLOv-8 (the 8th version of the object detection algorithm) to detect and identify semantic labels such as "tunnel entrance" and "construction area"; analyzing the target motion trajectory through an LSTM (Long Short-Term Memory) network for intention prediction, such as the intention of a vehicle to merge. Features are extracted through the ResNet-50 backbone network of the deep residual network, and the fully connected layer outputs the closed scene categories, e.g., tunnels / indoor parking lots / open-air parking lots. After feature concatenation of the collected data, it is input into a preset scene recognition model for joint training to determine the preset scene recognition model for identifying closed scene categories. After determining the closed scene category, it is quantified according to the light, humidity, temperature, combined with the position information and identification information to determine the corresponding closed value, and the value range of this closed value is [0, 1].

[0215] Through the above method, the closed scenario category in which the vehicle is located can be quickly and accurately determined, and the closed value corresponding to the currently recognized closed scenario category can be determined.

[0216] In one embodiment, in the related art, due to the lack of intelligence in the range extender control strategy, the working state of the range extender cannot be dynamically adjusted according to the specific scenario category and the degree of enclosure; such a static or preset control strategy cannot adapt to the changing driving environment, resulting in energy waste and increased emissions, and is also not very friendly to the surrounding environment and pedestrians.

[0217] In one embodiment, since the current range extender lacks the visualization support of the in-vehicle infotainment system interface during startup, shutdown or adjustment, the user cannot know the status of the range extender in real time (such as working status, power output, remaining battery power, etc.). In this way, the user's understanding and trust in the vehicle energy management system are reduced; at the same time, it also limits the user's real-time monitoring and adjustment of the energy usage during driving.

[0218] To solve the above problems, the specific implementation methods are as follows:

[0219] If the closed scenario category and the closed value of the target vehicle from the advanced driver assistance system are received, the closed scenario category and the closed value are sent to the display device, and a three-dimensional environment simulation is constructed to display the current closed scenario;

[0220] If the status of the range extender of the target vehicle from the engine management system is received, the status of the range extender is sent to the display device for display. The status of the range extender includes the startup status of the range extender, the power status, the remaining battery power ratio, and the increased mileage during the operation of the range extender.

[0221] Among them, the display device can be an in-vehicle infotainment system (In-Vehicle Infotainment, abbreviated as IVI), which is an in-vehicle integrated information processing system formed by using a vehicle-mounted dedicated central processor based on the vehicle body bus system and Internet services. The human-computer interaction form of IVI can be voice, image, and text. The human-computer interaction media of IVI include the central control screen (display, touch), instrument display, voice, steering wheel, etc.

[0222] Exemplarily, by designing a range extender status display module on the IVI interface to display information such as the working status, power output, and remaining battery power of the range extender in real time, the user can monitor the working strategy of the range extender according to needs in real time.

[0223] For details, see Figure 3, in this embodiment, the ADAS system (intelligent driving system) comprehensively senses the environment around the vehicle to complete the recognition of the closed scene and the judgment of the closed value. After obtaining the scene category C and the closed value V_closed, the corresponding signals are ADAS_Closed Scene (closed scene category) and ADAS_Closed Value (closed value).

[0224] The intelligent driving system sends ADAS_Closed Scene (closed scene category) and ADAS_Closed Value (closed value) to the IVI (in-vehicle infotainment system); the IVI displays the closed scene and the degree of closure, enabling the user to intuitively feel the current environment;

[0225] The EMS (engine management system) sends the EMS_engine_status (range extender status) to the IVI in real time; the IVI displays the real-time status of the range extender, enabling the user to intuitively feel the adjustment process of intelligent range extension.

[0226] Specifically, the engine management system sends the range extender status (i.e., start / stop status S and power setting P) to the IVI in real time; after the IVI receives these signals, it analyzes and processes them into visual elements. For example, it shows whether the range extender is started (blue indicates started, gray indicates stopped) through the range extender status indicator light. The current power setting of the range extender is dynamically displayed through a power bar chart. The current battery level is shown through the percentage of remaining battery power. The working effect of the range extender, such as the increase in cruising range, is graphically shown through a range extension effect chart.

[0227] For another example, a dynamic dashboard is designed in the in-vehicle infotainment system. Combining the closed value Vclosed and the range extender status S, the pointer position on the dashboard is updated in real time. For example, when the closed value is high and the range extender is off, the pointer points to "environmental protection mode"; when the closed value is low and the range extender is on, the pointer points to "efficient mode". By generating a historical record and a trend analysis chart of the range extender status, it helps the user better understand the operation of the range extender. For example, it shows data such as the number of times the range extender has been started and the average power setting in the past week for the user to refer to and optimize driving habits.

[0228] Through the above method, the IVI system provides a real-time display of the closed scene and the range extender status, realizing range extension visualization, intuitively, and enhancing the user experience: the user can intuitively understand the current environment and the working conditions of the range extender, enhancing driving confidence.

[0229] In one embodiment, a range extender control device is provided. The range extender control device is used to execute the range extender control method provided in any of the above embodiments. Please refer to Figure 5 ,Figure 5 This is a schematic structural diagram of the range extender control device provided by an embodiment of the present application. As Figure 5 shown, the range extender control device includes an acquisition module 501, a policy determination module 502, and a control response module 503, where:

[0230] The acquisition module 501 is configured to acquire the closed scenario category, the closed value, and the operation information of the target vehicle. The operation information includes gear information, vehicle speed information, remaining battery power, and remaining travel distance;

[0231] The policy determination module 502 is configured to input the closed scenario category, the closed value, and the operation information into a preset policy control model to determine the target control policy of the range extender in the current closed scenario of the target vehicle. The preset policy control model is trained by a genetic algorithm to determine the optimal control policy of the range extender under different closed scenario categories, different closed values, and different operation information;

[0232] The control response module 503 is configured to control the range extender in response to the target control policy.

[0233] For the specific limitations of the range extender control device, reference can be made to the limitations of the range extender control method in the above text, which will not be elaborated here. Each module in the above range extender control device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the electronic device in hardware form or be independent of the processor, or can be stored in the memory in the electronic device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0234] In this embodiment, the range extender control device essentially sets multiple modules to execute the range extender control method in any of the above embodiments. The specific functions and technical effects can be referred to the above embodiments, which will not be elaborated here.

[0235] In an embodiment, a vehicle is provided. The vehicle includes the range extender control device provided in any of the above embodiments.

[0236] For the specific limitations of the vehicle, reference can be made to the limitations of the range extender control method in the above text, which will not be elaborated here. Each module in the above vehicle can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the electronic device in hardware form or be independent of the processor, or can be stored in the memory in the electronic device in software form, so that the processor can call and execute the operations corresponding to the above modules.

[0237] In an embodiment, an electronic device is provided. The electronic device can be a server, and its internal structure diagram can be as Figure 6As shown in the figure. The electronic device includes a processor, a memory, a network interface, and a database connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the server side of the above method.

[0238] In one embodiment, an electronic device is provided. The electronic device can be a client, and its internal structure diagram can be as Figure 7 As shown in the figure. The electronic device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes non-volatile storage media and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of the above method.

[0239] In one embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are realized:

[0240] Obtain the closed scenario category, closed value, and operation information of the target vehicle. The operation information includes gear information, vehicle speed information, remaining battery power, and remaining travel distance; input the closed scenario category, closed value, and operation information into a preset policy control model to determine the target control policy of the range extender in the current closed scenario of the target vehicle. The preset policy control model is trained by a genetic algorithm to determine the optimal control policy of the range extender under different closed scenario categories, different closed values, and different operation information; in response to the target control policy, control the range extender.

[0241] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are realized:

[0242] Obtain the closed scenario category, closed value, and operating information of the target vehicle. The operating information includes gear information, vehicle speed information, remaining battery power, and remaining mileage. Input the closed scenario category, closed value, and operating information into a preset policy control model to determine the target control strategy of the range extender in the current closed scenario for the target vehicle. The preset policy control model is trained by a genetic algorithm to determine the optimal control strategy of the range extender under different closed scenario categories, different closed values, and different operating information. In response to the target control strategy, control the range extender.

[0243] It should be noted that for the functions or steps that the above computer-readable storage medium or electronic device can achieve, reference can be made to the relevant descriptions on the server side and the client side in the foregoing method embodiments. To avoid repetition, they will not be described in detail here.

[0244] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The above computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to the memory, storage, database, or other media used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. The non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. The volatile memory can include random access memory (RAM) or an external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0245] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the above device and system can be divided into different functional units or modules to complete all or part of the functions described above.

[0246] The embodiments provided above are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included within the protection scope of the present application.

Claims

1. A range extender control method, characterized in that: The method comprises: Obtaining the target vehicle's closed scene category, closed value, and operating information, including gear information, vehicle speed information, remaining battery power, and remaining range; The closed scene category, the closed value, and the operating information are input into a preset strategy control model to determine a target control strategy corresponding to the range extender in the target vehicle in the current closed scene, wherein the preset strategy control model is trained by a genetic algorithm to determine the optimal control strategy of the range extender under the closed value and the operating information for each closed scene category; wherein, if the closed scene category, the closed value, and the operating information of the target vehicle are different from preset conditions, the target control strategy is corrected using a preset personalized solution, and the control strategy corresponding to the preset personalized solution is output as the final control strategy for the current closed scene; if the closed scene category, the closed value, and the operating information of the target vehicle are the same as the preset specific conditions, the target control strategy corresponding to the range extender in the target vehicle is used as the final control strategy for the current closed scene, wherein the preset personalized solution is a range extender control strategy pre-set by the user under the closed scene category, the closed value, and the operating information according to needs; The range extender is controlled in response to the target control strategy.

2. The range extender control method according to claim 1, wherein: Determining the preset strategy control model includes: Determine an individual using the closed scene category, the closed value, the gear information, the vehicle speed information, the remaining battery power, and the remaining range as input parameters, wherein the individual is a control strategy for the range extender, the control strategy including a range extender shutdown instruction, or a range extender startup instruction and a corresponding power adjustment instruction after the range extender is started; An initial population consisting of a number of individuals is randomly generated; the fitness of each individual in the initial population is calculated according to a preset fitness function; and based on the initial population and the fitness, an optimal individual is output using a genetic algorithm.

3. The range extender control method according to claim 2, wherein: The preset fitness function is obtained by weighted calculation of energy efficiency, driving experience, safety and environmental protection; the energy efficiency represents the battery charging efficiency of the range extender corresponding to different energy consumption levels, and the energy consumption of the range extender is negatively correlated with the energy efficiency; the driving experience represents the impact of the start-up or shutdown frequency of the range extender on driving comfort; the safety represents the sufficiency of the power provided by the electricity in a closed scene; and the environmental protection represents the reduction in noise pollution and air pollution in a closed scene due to the reduced use of the range extender.

4. The range extender control method according to claim 3, wherein: Each iteration in the genetic algorithm generates a new population based on selection, crossover, and mutation.

5. The range extender control method according to claim 2, wherein: Determine that the individual satisfies the following constraints: If the closure value of the closure scenario is larger, the degree of activation of the range extender is smaller; if the closure value is determined to be the maximum value, the range extender is turned off; if the gear information is in reverse gear or forward gear, the endurance of the target vehicle is determined based on the vehicle speed information and the remaining range; If the gear information indicates that the vehicle is in the parking gear, the range extender is not started, and the target vehicle is driven by electric energy.

6. The range extender control method according to claim 2, wherein: The closed scene categories include driving in tunnels, driving on restricted roads, open-air parking, indoor parking, obstacles blocking the view, and vehicles covered by car covers; the closed value ranges from 0 to 1, where 0 represents not closed and 1 represents completely closed.

7. The range extender control method according to any one of claims 1 to 6, characterized in that: Get the closure value corresponding to the vehicle in the current closure scene, including: Acquire first point cloud data and first video data representing the environment surrounding the vehicle, as well as location information of the vehicle; Performing target detection on the first point cloud data and the first video data to determine a first target object and a second target object; Inputting the first target object, the second target object and the position information into a preset scene recognition model to determine the closed scene category of the closed scene; A closure value corresponding to the current closure scene is determined based on the closure scene category.

8. The range extender control method according to any one of claims 1 to 6, wherein: Also includes: If the closed scene category and closed value of the target vehicle are received, the closed scene category and closed value are sent to the display device, and a three-dimensional environment simulation is constructed to display the current closed scene; If the range extender status of the target vehicle is received, the range extender status is sent to the display device for display, and the range extender status includes the range extender startup status, power status, remaining power ratio, and mileage increased by the range extender operation.

9. A range extender control device, characterized in that: The range extender control device includes: An acquisition module is used to obtain the closed scene category, closed value and operation information of the target vehicle, wherein the operation information includes gear information, vehicle speed information, remaining battery power and remaining range; a strategy determination module, configured to input the closed scenario category, the closed value, and the operating information into a preset strategy control model to determine a target control strategy corresponding to the range extender in the target vehicle in the current closed scenario, wherein the preset strategy control model is trained by a genetic algorithm to determine the optimal control strategy for the range extender under the closed value and the operating information for each closed scenario category; if the closed scenario category, the closed value, and the operating information of the target vehicle are different from preset conditions, then using a preset personalized solution to perform strategy correction on the target control strategy, and outputting the control strategy corresponding to the preset personalized solution as the final control strategy for the current closed scenario; if the closed scenario category, the closed value, and the operating information of the target vehicle are the same as the preset specific conditions, then using the target control strategy corresponding to the range extender in the target vehicle as the final control strategy for the current closed scenario, wherein the preset personalized solution is a range extender control strategy pre-set by the user under the closed scenario category, the closed value, and the operating information according to needs; A control response module is used to control the range extender in response to the target control strategy.

10. A vehicle, characterized in that: The vehicle adopts the method according to any one of claims 1 to 8.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images