Vehicle control method, device and equipment and storage medium

Abstract

The invention provides a vehicle control method and device, equipment and a storage medium, and the method comprises the steps: determining the predicted driving condition data of a hybrid vehicle in a first future time period according to the current driving environment data and current driving state data of the hybrid vehicle; determining a target driving mode of the hybrid vehicle in the first future time period according to the predicted driving condition data; the target driving mode is one of a plurality of driving modes of the hybrid vehicle; and in the first future time period, the hybrid vehicle is controlled to be driven in the target driving mode. According to the method, the driving condition data of the hybrid vehicle in the future time period is predicted based on the current driving environment data and the current driving state data of the hybrid vehicle, and the driving mode of the hybrid vehicle in the future time period is determined based on the predicted driving condition data; the accuracy of determining the driving mode of the hybrid vehicle in the future time period can be improved, frequent switching of the driving mode of the hybrid vehicle can be avoided, and therefore the energy management effect of the hybrid vehicle can be improved.

Description

Technical Field

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

[0002] Hybrid Electric Vehicles (HEVs) have significant advantages in reducing fuel consumption and emissions by working in cooperation with internal combustion engines and electric motors. However, currently, the energy management strategy (EMS) is mostly determined based on the current driving state data of hybrid vehicles, such as the current battery power, current driving speed, and current throttle opening. Although this method can quickly respond to the current driving demands of hybrid vehicles, it cannot obtain the optimal energy management strategy, resulting in poor energy management effects for current hybrid vehicles. Summary of the Invention

[0003] The main purpose of the embodiments of this application is to propose a vehicle control method, device, equipment and storage medium, aiming to improve the energy management effect of hybrid vehicles.

[0004] The embodiments of this application provide a vehicle control method, including: determining the predicted driving condition data of the hybrid vehicle in a first future period according to the current driving environment data and current driving state data of the hybrid vehicle; wherein, the predicted driving condition data includes at least one of predicted driving speed and predicted demand power; determining the target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data; wherein, the target driving mode is one of multiple driving modes of the hybrid vehicle; and controlling the hybrid vehicle to be driven in the target driving mode in the first future period.

[0005] In an embodiment, the determining the target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data includes: determining the first equivalent fuel consumption of the hybrid vehicle in each of the multiple driving modes according to the predicted driving condition data; and determining the driving mode with the minimum first equivalent fuel consumption among the multiple driving modes as the target driving mode.

[0006] In one embodiment, determining the first equivalent fuel consumption of the hybrid vehicle in each of the multiple driving modes according to the predicted driving condition data includes: for each of the driving modes, determining the second equivalent fuel consumption of the hybrid vehicle in the driving mode according to the predicted driving condition data; determining an equivalent factor corresponding to the driving mode according to the driving characteristic data of the hybrid vehicle; wherein the driving characteristic data includes at least one of the following: the current battery power of the hybrid vehicle, the predicted engine thermal efficiency corresponding to the first future time period, the predicted driving scenario corresponding to the first future time period, and the predicted driving scenario corresponding to the second future time period; the second future time period is after the first future time period; determining the first equivalent fuel consumption according to the product of the equivalent factor and the second equivalent fuel consumption.

[0007] In one embodiment, the multiple driving modes include a pure electric driving mode and a parallel hybrid driving mode; before controlling the hybrid vehicle to drive in the target driving mode, the vehicle control method further includes any one of the following: when the target driving mode is the pure electric driving mode, if the current battery power of the hybrid vehicle is lower than the power threshold, controlling the engine of the hybrid vehicle to start in advance or stop delaying; when the target driving mode is the parallel hybrid driving mode, if the engine thermal state of the hybrid vehicle does not meet the preset thermal state, controlling the engine of the hybrid vehicle to start in advance or stop delaying.

[0008] In one embodiment, the multiple driving modes include a parallel hybrid driving mode; when the target driving mode is the parallel hybrid driving mode, controlling the hybrid vehicle to drive in the target driving mode includes: obtaining the actual required power of the hybrid vehicle in the first future time period and the predicted required power of the hybrid vehicle in the second future time period; wherein the second future time period is after the first future time period; using the golden section search algorithm, determining the high-efficiency working range of the engine of the hybrid vehicle according to the actual required power and the engine thermal efficiency distribution map of the hybrid vehicle; selecting a target working point from the high-efficiency working range according to the first deviation between the predicted required power and the actual required power; in the parallel hybrid driving mode, controlling the engine of the hybrid vehicle to drive with the working parameters corresponding to the target working point.

[0009] In one embodiment, selecting a target operating point from the high-efficiency operating range according to a first deviation between the predicted demand power and the actual demand power includes: when the first deviation is within a second preset range, determining the operating point with the highest thermal efficiency in the high-efficiency operating range as the target operating point; when the first deviation exceeds the second preset range, determining a target operating range in the high-efficiency operating range according to the first deviation; and determining the operating point with the highest thermal efficiency in the target operating range as the target operating point.

[0010] In one embodiment, after determining the predicted driving condition data of the hybrid vehicle in a first future period according to the current driving environment data and the current driving state data of the hybrid vehicle, the vehicle control method further includes: obtaining a second deviation between the actual driving condition data and the predicted driving condition data of the hybrid vehicle in the first future period; wherein, the predicted driving condition data is obtained by inputting the current driving environment data and the current driving state data into a trained long short-term memory neural network model; and when the second deviation exceeds a third preset range, updating the long short-term memory neural network model according to the second deviation.

[0011] An embodiment of the present application further provides a vehicle control device, including a driving condition prediction module, a driving mode determination module, and a driving control module; the driving condition prediction module is configured to determine the predicted driving condition data of the hybrid vehicle in a first future period according to the current driving environment data and the current driving state data of the hybrid vehicle; wherein, the predicted driving condition data includes at least one of a predicted driving speed and a predicted demand power; the driving mode determination module is configured to determine a target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data; wherein, the target driving mode is one of multiple driving modes included in the hybrid vehicle; and the driving control module is configured to control the hybrid vehicle to drive in the target driving mode in the first future period.

[0012] An embodiment of the present application further provides a vehicle control device, the vehicle control device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the above vehicle control method is implemented.

[0013] An embodiment of the present application further provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above vehicle control method is implemented.

[0014] A vehicle control method, device, equipment and storage medium provided by an embodiment of the present application can predict the driving condition data of a hybrid vehicle in a future period based on the current driving environment data and current driving state data of the hybrid vehicle, and determine the driving mode of the hybrid vehicle in the future period based on the predicted driving condition data, which can improve the accuracy of determining the driving mode of the hybrid vehicle in the future period and avoid frequent switching of the driving mode of the hybrid vehicle, thereby improving the energy management effect of the hybrid vehicle. Description of the Drawings

[0015] Figure 1 is a flowchart of the vehicle control method provided by an embodiment of the present application;

[0016] Figure 2 is a flowchart of determining the equivalent fuel consumption provided by an embodiment of the present application;

[0017] Figure 3 is another flowchart of the vehicle control method provided by an embodiment of the present application;

[0018] Figure 4 is a structural diagram of the vehicle control device provided by an embodiment of the present application;

[0019] Figure 5 is the structural schematic of the vehicle control equipment provided by an embodiment of the present application Figure 1 ;

[0020] Figure 6 is the structural schematic of the vehicle control equipment provided by an embodiment of the present application Figure 2 . Detailed Embodiments

[0021] Next, the technical solutions in the embodiments of the present application will be clearly described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0022] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / ", generally represents an "or" relationship between the associated objects before and after.

[0023] The vehicle control method provided by the embodiments of the present application can be applied to a vehicle control device or the software of a vehicle control device. The vehicle control device can be an electronic device or a vehicle. Among them, the electronic device can be a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server can be configured as an independent physical server or a server cluster or a distributed system composed of multiple physical servers. The software can be an application for implementing the vehicle control method, etc., but is not limited to the above forms.

[0024] The following will combine the accompanying drawings and elaborate on the vehicle control method provided by the embodiments of the present application through specific embodiments.

[0025] Please refer to Figure 1 , a vehicle control method provided by the embodiments of the present application may include:

[0026] Step S101: Determine the predicted driving condition data of the hybrid vehicle in the first future period according to the current driving environment data and the current driving state data of the hybrid vehicle; wherein, the predicted driving condition data includes at least one of the predicted driving speed and the predicted required power.

[0027] Optionally, the current driving environment data includes at least one of the following: the road surface characteristics of the driving section where the hybrid vehicle is currently located, the current traffic information of the driving section, and the current driving state data of the target vehicle within the first preset range of the hybrid vehicle. The road surface characteristics of the driving section where the hybrid vehicle is currently located may include at least one of the slope and curvature of the driving section; the current traffic information of the driving section may include at least one of the speed limit information of the driving section, the traffic signal position, the congestion information, the traffic flow speed, and the traffic flow density; the current driving state data of the hybrid vehicle may include at least one of the current battery power, the current driving speed, and the current throttle opening of the hybrid vehicle; the current driving state data of the target vehicle may include at least one of the current position of the target vehicle relative to the hybrid vehicle, the current longitudinal and lateral speeds, and the current longitudinal and lateral accelerations.

[0028] In actual implementation, the road surface characteristics and the current traffic information of the driving section where the hybrid vehicle is currently located, and the current driving state data of the target vehicle within the first preset range of the hybrid vehicle can be obtained according to the positioning and navigation path of the hybrid vehicle, in combination with navigation big data and map data; or the road surface characteristics and the current traffic information of the driving section where the hybrid vehicle is currently located, and the current driving state data of the target vehicle within the first preset range of the hybrid vehicle can be obtained according to the detection information of the on-vehicle radar and / or on-vehicle camera of the hybrid vehicle for the current driving environment.

[0029] In actual implementation, based on the current driving environment data and current driving state data of the hybrid vehicle, the mapping relationship between the current driving environment data, current driving state data, and future driving condition data can be queried to determine the predicted driving condition data of the hybrid vehicle in the first future period; alternatively, the current driving environment data and current driving state data of the hybrid vehicle can be input into a model that has learned the relationship between the current driving environment data, current driving state data, and future driving condition data to obtain the predicted driving condition data of the hybrid vehicle in the first future period. The embodiments of the present application do not limit the specific manner of determining the predicted driving condition data of the hybrid vehicle in the first future period based on the current driving environment data and current driving state data of the hybrid vehicle.

[0030] Step S102: Determine the target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data; wherein, the target driving mode is one of multiple driving modes of the hybrid vehicle.

[0031] Optionally, multiple driving modes of the hybrid vehicle include at least two of an all-electric driving mode, a series hybrid driving mode, and a parallel hybrid driving mode; the all-electric driving mode can be a mode in which the hybrid vehicle only relies on the battery to drive the wheels and the engine does not work; the series hybrid driving mode can be a mode in which the hybrid vehicle only relies on the battery to drive the wheels and the engine supplies power to the battery; the parallel hybrid driving mode can be a mode in which the hybrid vehicle relies on both the battery and the engine to drive the wheels.

[0032] In actual implementation, based on the predicted driving condition data, the mapping relationship between the driving condition data and the driving mode can be queried to obtain the target driving mode of the hybrid vehicle in the first future period; alternatively, first, based on the predicted driving condition data, the first equivalent fuel consumption of the hybrid vehicle in each driving mode can be determined, and then, based on the relationship between the first equivalent fuel consumptions in each driving mode, the target driving mode can be selected from each driving mode. The specific implementation can refer to the following related descriptions and will not be described here. The embodiments of the present application do not limit the specific manner of determining the target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data.

[0033] Optionally, the above parallel hybrid driving mode can include at least two parallel gear driving modes, and the available driving speed ranges corresponding to each parallel gear driving mode are different; in actual implementation, when it is determined that the preferred driving mode of the hybrid vehicle in the first future period is the parallel hybrid driving mode according to the predicted driving condition data, further based on the relationship between the predicted driving speed of the hybrid vehicle in the first future period and the available driving speed ranges corresponding to each parallel gear driving mode, the target gear parallel driving mode can be selected from at least two parallel gear driving modes as the above target driving mode.

[0034] Step S103: Control the hybrid vehicle to drive in the target driving mode during the first future time period.

[0035] In actual implementation, the driving mode of the hybrid vehicle during the first future time period can be set in advance as the target driving mode. When the current driving time period of the hybrid vehicle reaches the first future time period, automatically control the hybrid vehicle to drive in the target driving mode; alternatively, when the current driving time period of the hybrid vehicle reaches the first future time period, query the target driving mode of the first future time period and control the hybrid vehicle to drive in the target driving mode. The embodiments of the present application do not limit the specific manner of S103.

[0036] Based on the current driving environment data and current driving state data of the hybrid vehicle, the embodiments of the present application predict the driving condition data of the hybrid vehicle in the future time period, and determine the driving mode of the hybrid vehicle in the future time period based on the predicted driving condition data, which can improve the accuracy of determining the driving mode of the hybrid vehicle in the future time period and avoid frequent switching of the driving mode of the hybrid vehicle, thereby improving the energy management effect of the hybrid vehicle.

[0037] In one embodiment, determining the target driving mode of the hybrid vehicle in the first future time period according to the predicted driving condition data in the above step S102 includes:

[0038] Determine the first equivalent fuel consumption of the hybrid vehicle in multiple driving modes respectively according to the predicted driving condition data;

[0039] Determine the driving mode with the minimum first equivalent fuel consumption among the multiple driving modes as the target driving mode.

[0040] In actual implementation, according to the predicted driving condition data, the mapping relationship between the driving condition data and the equivalent fuel consumption of the hybrid vehicle in different driving modes can be queried to determine the first equivalent fuel consumption of the hybrid vehicle in multiple driving modes respectively; alternatively, the second equivalent fuel consumption of the hybrid vehicle in multiple driving modes can be determined first according to the predicted driving condition data, and then the first equivalent fuel consumption can be determined according to the driving characteristic data and the second equivalent fuel consumption of the hybrid vehicle. For specific implementation, reference can be made to the following relevant descriptions and will not be described here. The embodiments of the present application do not limit the specific manner of determining the first equivalent fuel consumption of the hybrid vehicle in multiple driving modes according to the predicted driving condition data.

[0041] Furthermore, the first equivalent fuel consumption of the hybrid vehicle in multiple driving modes can be compared, and the driving mode with the minimum first equivalent fuel consumption is selected from the multiple driving modes as the target driving mode.

[0042] In an embodiment of the present application, by determining the first equivalent fuel consumption of the hybrid vehicle in multiple driving modes respectively according to the predicted driving condition data of the hybrid vehicle in the first future period, and determining the driving mode with the minimum first equivalent fuel consumption among the multiple driving modes as the target driving mode of the hybrid vehicle in the first future period, it can not only ensure that the hybrid vehicle can obtain the effect of the minimum equivalent fuel consumption when driving in the target driving mode in the first future period, but also avoid the frequent switching of the driving mode of the hybrid vehicle, thereby improving the energy management effect of the hybrid vehicle.

[0043] In one embodiment, the determining of the first equivalent fuel consumption of the hybrid vehicle in multiple driving modes respectively according to the predicted driving condition data includes:

[0044] For each driving mode, according to the predicted driving condition data, determine the second equivalent fuel consumption of the hybrid vehicle in the driving mode;

[0045] According to the driving characteristic data of the hybrid vehicle and the second equivalent fuel consumption, determine the first equivalent fuel consumption; wherein, the driving characteristic data includes at least one of the following: the current battery power of the hybrid vehicle, the predicted engine thermal efficiency corresponding to the first future period, the predicted driving scenario corresponding to the first future period, and the predicted driving scenario corresponding to the second future period; the second future period is after the first future period.

[0046] Optionally, the predicted engine thermal efficiency corresponding to the first future period can be obtained by querying the engine thermal efficiency distribution map based on the predicted engine speed of the hybrid vehicle in the first future period; the predicted engine speed of the hybrid vehicle in the first future period can be determined based on the predicted driving speed of the hybrid vehicle in the first future period. Optionally, the predicted driving scenario corresponding to the first future period can be determined based on the preset driving condition data of the hybrid vehicle in the first future period. For example, if the predicted driving speed and the predicted required power of the hybrid vehicle in the first future period are both low, it can be determined that the hybrid vehicle will be in a congestion scenario in the first future period; if the predicted driving speed of the hybrid vehicle in the first future period frequently switches to 0, it can be determined that the hybrid vehicle will be in a frequent start-stop scenario in the first future period.

[0047] Optionally, the driving section where the hybrid vehicle is currently located may include the section intervals that the hybrid vehicle will drive to in multiple future periods; optionally, the predicted driving scenario corresponding to the first future period can also be determined based on the preset driving condition data of the hybrid vehicle in the first future period, combined with the current driving environment data of the hybrid vehicle. For example, if the predicted required power of the hybrid vehicle in the first future period is 50kW, and it is obtained from the current driving environment data of the hybrid vehicle that there is a long uphill with a slope of 5% in the section interval that the hybrid vehicle will drive to in the first future period, it can be determined that the hybrid vehicle will be in a climbing scenario in the first future period.

[0048] Optionally, the predicted driving scenario corresponding to the second future period can be determined according to the predicted driving condition data of the hybrid vehicle in the second future period. Specifically, reference can be made to the determination process of the predicted driving scenario corresponding to the first future period, which will not be elaborated here. Optionally, the predicted driving condition data of the hybrid vehicle in the second future period can be determined according to the current driving environment data and the current driving state data of the hybrid vehicle. It can be understood that based on the fact that the current driving section where the hybrid vehicle is located can include the section intervals that the hybrid vehicle will drive to in multiple future periods, the vehicle control method provided in the embodiments of the present application can predict the driving condition data of the hybrid vehicle in multiple future periods according to the current driving environment data and the current driving state data of the hybrid vehicle.

[0049] For each driving mode, the predicted driving condition data can be respectively substituted into the relationship between the driving condition data and the equivalent fuel consumption of the hybrid vehicle in different driving modes to obtain the second equivalent fuel consumption of the hybrid vehicle in multiple driving modes respectively; or the predicted driving condition data can be input into a model that has learned the relationship between the driving condition data and the equivalent fuel consumption of the hybrid vehicle in different driving modes to obtain the second equivalent fuel consumption of the hybrid vehicle in multiple driving modes respectively. The embodiments of the present application do not limit the specific manner of determining the second equivalent fuel consumption of the hybrid vehicle in multiple driving modes according to the predicted driving condition data.

[0050] Further, for each driving mode, the mapping relationship between the driving characteristic data, the equivalent fuel consumption and the equivalent amplitude can be queried according to the driving characteristic data and the second equivalent fuel consumption of the hybrid vehicle to obtain the equivalent amplitude corresponding to the driving mode. Then, the first equivalent fuel consumption can be determined according to the sum of the second equivalent fuel consumption and the equivalent amplitude; or the equivalent factor corresponding to the driving mode can be determined first according to the driving characteristic data of the hybrid vehicle, and then the first equivalent fuel consumption can be determined according to the product of the equivalent factor and the second equivalent fuel consumption. The specific implementation can be seen in the following related description and will not be described here.

[0051] In actual implementation, the determination of the first equivalent fuel consumption according to the sum of the second equivalent fuel consumption and the equivalent amplitude can include at least one of the following: determining the sum of the second equivalent fuel consumption and the equivalent amplitude as the first equivalent fuel consumption; further adding a coefficient on the basis of the sum of the second equivalent fuel consumption and the equivalent amplitude to obtain the first equivalent fuel consumption, so as to further improve the accuracy of determining the first equivalent fuel consumption.

[0052] In the embodiments of the present application, for each driving mode, according to the predicted driving condition data of the hybrid vehicle in the first future period, the second equivalent fuel consumption of the hybrid vehicle in the driving mode is determined, and according to the driving characteristic data and the second equivalent fuel consumption of the hybrid vehicle, the first equivalent fuel consumption is determined, which can make full use of the driving characteristic data of the hybrid vehicle, improve the accuracy of determining the first equivalent fuel consumption of the hybrid vehicle in each driving mode, so that based on the first equivalent fuel consumption in each driving mode, the target driving mode that can minimize the equivalent fuel consumption of the hybrid vehicle in the first future period can be accurately determined, and the hybrid vehicle can be prevented from frequently switching driving modes, thereby improving the energy management effect of the hybrid vehicle.

[0053] Please refer to Figure 2 , in one embodiment, the above-mentioned determination of the first equivalent fuel consumption of the hybrid vehicle in multiple driving modes respectively according to the predicted driving condition data includes:

[0054] Step S201: For each driving mode, according to the predicted driving condition data, determine the second equivalent fuel consumption of the hybrid vehicle in the driving mode;

[0055] Step S202: According to the driving characteristic data of the hybrid vehicle, determine the equivalent factor corresponding to the driving mode; wherein, the driving characteristic data includes at least one of the following: the current battery power of the hybrid vehicle, the predicted engine thermal efficiency corresponding to the first future period, the predicted driving scenario corresponding to the first future period, and the predicted driving scenario corresponding to the second future period; the second future period is after the first future period;

[0056] Step S203: Determine the first equivalent fuel consumption according to the product of the equivalent factor and the second equivalent fuel consumption.

[0057] In actual implementation, for each driving mode, the mapping relationship between the driving characteristic data and the equivalent factor can be queried according to the driving characteristic data of the hybrid vehicle to obtain the equivalent factor corresponding to the driving mode; or the driving characteristic data of the hybrid vehicle can be substituted into the relational expression between the driving characteristic data and the equivalent factor to obtain the equivalent factor corresponding to the driving mode. The embodiments of the present application do not limit the specific manner of determining the equivalent factor corresponding to the driving mode according to the driving characteristic data of the hybrid vehicle.

[0058] Furthermore, the product of the second equivalent fuel consumption and the equivalent factor can be determined as the first equivalent fuel consumption; or a coefficient can be further added on the basis of the product of the second equivalent fuel consumption and the equivalent factor to obtain the first equivalent fuel consumption, so as to further improve the accuracy of determining the first equivalent fuel consumption.

[0059] In addition, for the specific implementation of determining the second equivalent fuel consumption of the hybrid vehicle in the driving mode based on the predicted driving condition data, reference can be made to the description in the above embodiments, which will not be elaborated here.

[0060] Optionally, when the multiple driving modes of the hybrid vehicle include a pure electric driving mode, a series hybrid driving mode, and a parallel hybrid driving mode, for the pure electric driving mode, the equivalent factor corresponding to the pure electric driving mode is negatively correlated with the current battery power of the hybrid vehicle; for the parallel hybrid driving mode, the equivalent factor corresponding to the parallel hybrid driving mode is negatively correlated with the predicted engine thermal efficiency of the hybrid vehicle in the first future period.

[0061] Optionally, when the predicted driving scenario corresponding to the first future period is the above-mentioned climbing scenario, the order of the equivalent factors corresponding to the multiple driving modes from small to large can be: the equivalent factor corresponding to the parallel hybrid driving mode, the equivalent factor corresponding to the series hybrid driving mode, the equivalent factor corresponding to the pure electric driving mode; when the predicted driving scenario corresponding to the first future period is the above-mentioned frequent start-stop scenario or the above-mentioned congestion scenario, the order of the equivalent factors corresponding to the multiple driving modes from small to large can be: the equivalent factor corresponding to the pure electric driving mode, the equivalent factor corresponding to the series hybrid driving mode, the equivalent factor corresponding to the parallel hybrid driving mode.

[0062] Optionally, when the predicted driving scenario corresponding to the second future period is the above-mentioned frequent start-stop scenario or the above-mentioned congestion scenario, the order of the equivalent factors corresponding to the multiple driving modes from small to large can be: the equivalent factor corresponding to the parallel hybrid driving mode, the equivalent factor corresponding to the series hybrid driving mode, the equivalent factor corresponding to the pure electric driving mode.

[0063] When the above-mentioned driving characteristic data includes multiple items of data, for each driving mode, the equivalent factors corresponding to the driving mode and each driving characteristic data can be weighted to obtain the target equivalent factor corresponding to the driving mode. Then, based on the product of the target equivalent factor and the second equivalent fuel consumption of the hybrid vehicle in the driving mode, the first equivalent fuel consumption of the hybrid vehicle in the driving mode can be determined; alternatively, the products of the multiple equivalent factors corresponding to the driving mode and the second equivalent fuel consumption of the hybrid vehicle in the driving mode can be accumulated to obtain the first equivalent fuel consumption of the hybrid vehicle in the driving mode.

[0064] In the embodiments of the present application, for each driving mode, according to the predicted driving condition data, the second equivalent fuel consumption of the hybrid vehicle in the driving mode is determined, and according to the driving characteristic data of the hybrid vehicle, the equivalent factor corresponding to the driving mode is determined, and according to the product of the equivalent factor and the second equivalent fuel consumption, the first equivalent fuel consumption is determined, which can make full use of the driving characteristic data of the hybrid vehicle, improve the accuracy of determining the first equivalent fuel consumption of the hybrid vehicle in each driving mode, so that based on the first equivalent fuel consumption in each driving mode, the target driving mode that can minimize the equivalent fuel consumption of the hybrid vehicle in the first future period can be accurately determined, and the hybrid vehicle can be prevented from frequently switching driving modes, thereby improving the energy management effect of the hybrid vehicle.

[0065] Optionally, the multiple driving modes of the hybrid vehicle include a pure electric driving mode and a parallel hybrid driving mode; in an implementation manner, before controlling the hybrid vehicle to drive in the target driving mode, the vehicle control method provided by the embodiments of the present application further includes any one of the following:

[0066] When the target driving mode is a pure electric driving mode, if the current battery power of the hybrid vehicle is lower than the power threshold, the engine of the hybrid vehicle is controlled to start in advance or stop late.

[0067] When the target driving mode is a parallel hybrid driving mode, if the engine thermal state of the hybrid vehicle does not meet the preset thermal state, the engine of the hybrid vehicle is controlled to start in advance or stop late.

[0068] In actual implementation, when it is determined that the target driving mode of the hybrid vehicle in the first future period is a pure electric driving mode, the start-stop strategy of the engine can be determined based on the comparison result between the current battery power of the hybrid vehicle and the power threshold, and the current working state of the engine of the hybrid vehicle. Optionally, if the current battery power of the hybrid vehicle is lower than the power threshold and the engine of the hybrid vehicle is in the start state, the engine of the hybrid vehicle can be controlled to stop late to charge the battery to meet the pure electric driving demand of the hybrid vehicle in the first future period; if the current battery power of the hybrid vehicle is lower than the power threshold and the engine of the hybrid vehicle is in the stop state, the engine of the hybrid vehicle can be controlled to start in advance to charge the battery to meet the pure electric driving demand of the hybrid vehicle in the first future period.

[0069] In actual implementation, when it is determined that the target driving mode of the hybrid vehicle in the first future period is the parallel hybrid driving mode, the start-stop strategy of the engine can be determined based on the comparison result between the engine thermal state of the hybrid vehicle and the preset thermal state, and the current working state of the engine of the hybrid vehicle. Optionally, if the engine thermal state of the hybrid vehicle does not meet the preset thermal state and the engine of the hybrid vehicle is in the starting state, the engine of the hybrid vehicle can be controlled to delay shutdown to fully preheat the engine to meet the parallel hybrid driving demand of the hybrid vehicle in the first future period; if the engine thermal state of the hybrid vehicle does not meet the preset thermal state and the engine of the hybrid vehicle is in the shutdown state, the engine of the hybrid vehicle can be controlled to start in advance to preheat the engine in advance to meet the parallel hybrid driving demand of the hybrid vehicle in the first future period.

[0070] The above power threshold can be an empirical value preset regardless of the future period; optionally, when the current battery power of the hybrid vehicle reaches the power threshold, the duration of pure electric driving of the hybrid vehicle is greater than the first preset duration; the above power threshold can also be determined based on the power demand for pure electric driving of the hybrid vehicle in the first future period. The above preset thermal state can be an empirical state preset regardless of the future period; optionally, under the preset thermal state, the duration for the thermal efficiency of the engine to change from the current value to the maximum value is less than the second preset duration; the above preset thermal state can also be determined based on the thermal state demand for parallel hybrid driving of the hybrid vehicle in the first future period.

[0071] In the embodiment of the present application, before controlling the hybrid vehicle to drive in the target driving mode, when the target driving mode is the pure electric driving mode, if the current battery power of the hybrid vehicle is lower than the power threshold, the engine of the hybrid vehicle is controlled to start in advance or delay shutdown, and when the target driving mode is the parallel hybrid driving mode, if the engine thermal state of the hybrid vehicle does not meet the preset thermal state, the engine of the hybrid vehicle is controlled to start in advance or delay shutdown, which can ensure that the hybrid vehicle can drive in the target driving mode in the first future period, thereby avoiding frequent switching of the driving mode of the hybrid vehicle, and further improving the energy management effect of the hybrid vehicle.

[0072] Optionally, the multiple driving modes of the hybrid vehicle include the parallel hybrid driving mode; in one embodiment, when the target driving mode is the parallel hybrid driving mode, the control of the hybrid vehicle to drive in the target driving mode in step S103 includes:

[0073] Obtain the actual demand power of the hybrid vehicle in the first future period and the predicted demand power of the hybrid vehicle in the second future period; wherein, the second future period is after the first future period;

[0074] Adopt the golden section search algorithm, and determine the high-efficiency working range of the engine of the hybrid vehicle according to the actual required power and the engine thermal efficiency distribution map of the hybrid vehicle;

[0075] Select a target operating point from the high-efficiency working range according to the first deviation between the predicted required power and the actual required power;

[0076] In the fuel-electric parallel drive mode, control the engine of the hybrid vehicle to drive with the operating parameters corresponding to the target operating point.

[0077] Optionally, on the basis that the current driving section where the hybrid vehicle is located can include the section intervals that the hybrid vehicle will drive to in multiple future time periods, the predicted required power of the hybrid vehicle in the second future time period can be determined based on the above current driving environment data and the above current driving state data of the hybrid vehicle; the actual required power of the hybrid vehicle in the first future time period can be obtained by real-time acquiring the required power during the driving process of the hybrid vehicle in the first future time period in the target driving mode.

[0078] In actual implementation, when controlling the hybrid vehicle to drive in the fuel-electric parallel drive mode in the first future time period, the golden section search algorithm can be adopted according to the actual required power of the hybrid vehicle to determine the high-efficiency working range of the engine of the hybrid vehicle from the engine thermal distribution map of the hybrid vehicle; optionally, the thermal efficiency of the engine corresponding to each operating point in the high-efficiency working range of the engine is higher than the thermal efficiency threshold; further, a target operating point can be selected from the high-efficiency working range based on the first deviation between the actual required power of the hybrid vehicle in the first future time period and the predicted required power of the hybrid vehicle in the second future time period. The specific implementation can be referred to the following description and will not be described here; then, the operating point of the engine of the hybrid vehicle in the first future time period can be set as the target operating point to control the engine of the hybrid vehicle to participate in the fuel-electric parallel drive with the operating parameters corresponding to the target operating point in the first future time period.

[0079] In the case where the target driving mode of the hybrid vehicle in the first future time period is the fuel-electric parallel drive mode, the embodiments of the present application adopt the golden section search algorithm to determine the high-efficiency working range of the engine of the hybrid vehicle according to the actual required power and the engine thermal efficiency distribution map of the hybrid vehicle, and select a target operating point from the high-efficiency working range according to the first deviation between the actual required power of the hybrid vehicle in the first future time period and the predicted required power of the hybrid vehicle in the second future time period, and in the first future time period, control the engine of the hybrid vehicle to participate in the fuel-electric parallel drive with the operating parameters corresponding to the target operating point, which can enable the engine of the hybrid vehicle to operate in the high-efficiency working area in the fuel-electric parallel drive mode, thereby further improving the energy management effect of the hybrid vehicle.

[0080] In one embodiment, selecting a target operating point from the high-efficiency operating range according to the first deviation between the predicted demand power and the actual demand power includes:

[0081] When the first deviation is within the second preset range, determining the operating point with the highest thermal efficiency in the high-efficiency operating range as the target operating point;

[0082] When the first deviation exceeds the second preset range, determining a target operating range in the high-efficiency operating range according to the first deviation; and determining the operating point with the highest thermal efficiency in the target operating range as the target operating point.

[0083] Optionally, when the first deviation is within the second preset range, it can be characterized that the predicted demand power of the hybrid vehicle in the second future period has no sudden change relative to the actual demand power of the hybrid vehicle in the first future period; when the first deviation exceeds the second preset range, it can be characterized that the predicted demand power of the hybrid vehicle in the second future period has a sudden change relative to the actual demand power of the hybrid vehicle in the first future period. Further, when the first deviation is equal to the difference between the predicted demand power of the hybrid vehicle in the second future period and the actual demand power of the hybrid vehicle in the first future period, if the first deviation exceeds the second preset range and the first deviation is less than 0, it can be determined that the sudden change in the predicted demand power of the hybrid vehicle in the second future period relative to the actual demand power of the hybrid vehicle in the first future period is a sudden decrease; if the first deviation exceeds the second preset range and the first deviation is greater than 0, it can be determined that the sudden change in the predicted demand power of the hybrid vehicle in the second future period relative to the actual demand power of the hybrid vehicle in the first future period is a sudden increase.

[0084] Optionally, the high-efficiency operating range may include at least two sub-operating ranges, and the average engine speeds corresponding to the at least two sub-operating ranges are different; in actual implementation, when the first deviation is equal to the difference between the predicted demand power of the hybrid vehicle in the second future period and the actual demand power of the hybrid vehicle in the first future period, for the case where the first deviation exceeds the second preset range, determining the target operating range in the high-efficiency operating range according to the first deviation may include the following steps: if the first deviation is less than 0, the sub-operating range with a lower average engine speed in the high-efficiency operating range can be determined as the target operating range; if the first deviation is greater than 0, the sub-operating range with a higher average engine speed in the high-efficiency operating range can be determined as the target operating range; then, the thermal efficiencies of the operating points corresponding to each operating point in the target operating range can be compared, and the operating point with the highest thermal efficiency in the target operating range can be determined as the target operating point.

[0085] In an embodiment of the present application, when the first deviation between the actual required power of the hybrid vehicle in the first future period and the predicted required power of the hybrid vehicle in the second future period is within the second preset range, the highest thermal efficiency operating point in the high-efficiency operating range is determined as the target operating point. And when the first deviation exceeds the second preset range, according to the first deviation, a target operating range in the high-efficiency operating range is determined, and the highest thermal efficiency operating point of the target operating range is determined as the target operating point. This can not only make the engine of the hybrid vehicle operate at a working point with a relatively high thermal efficiency in the high-efficiency operating range in the fuel-electric parallel drive mode, but also be able to reserve the engine speed margin in advance by predicting the mutation of the required power from the first future period to the second future period, so as to better meet the power demand in the second future period, thereby further improving the power management effect of the hybrid vehicle.

[0086] In an embodiment, after determining the predicted driving condition data of the hybrid vehicle in the first future period according to the current driving environment data and the current driving state data of the hybrid vehicle in step S101 above, the vehicle control method provided by the embodiment of the present application further includes:

[0087] Obtain a second deviation between the actual driving condition data and the predicted driving condition data of the hybrid vehicle in the first future period; wherein, the predicted driving condition data is obtained by inputting the current driving environment data and the current driving state data into the trained long short-term memory neural network model;

[0088] When the second deviation exceeds the third preset range, update the long short-term memory neural network model according to the second deviation.

[0089] Optionally, the trained long short-term memory (LSTM) network model has learned the relationship between the current driving environment data, the current driving state data and the future driving condition data; in actual implementation, the current driving environment data and the current driving state data of the hybrid vehicle can be input into the trained long short-term memory neural network model to obtain the predicted driving condition data of the hybrid vehicle in the first future period.

[0090] In the process of controlling a hybrid vehicle to drive in a target driving mode in a first future period, the actual driving condition data of the hybrid vehicle in the first future period can be obtained in real time; then, the second deviation between the actual driving condition data of the hybrid vehicle in the first future period and the predicted driving condition data of the hybrid vehicle in the first future period can be calculated; if the second deviation exceeds a third preset range, the model parameters of the LSTM network model can be adjusted according to the second deviation to update the LSTM network model; if the second deviation does not exceed the third preset range, the LSTM network model can remain unchanged. Optionally, the third preset range is obtained through experimental calibration and is used to limit that the predicted driving condition data output by the LSTM network model is relatively close to the actual driving condition data.

[0091] After the current driving environment data and current driving state data of the hybrid vehicle are input into the trained LSTM network model in the embodiment of the present application to obtain the predicted driving condition data of the hybrid vehicle in the first future period, by obtaining the second deviation between the actual driving condition data and the predicted driving condition data of the hybrid vehicle in the first future period, and updating the LSTM network model according to the second deviation when the second deviation exceeds the third preset range, a feedback mechanism for correcting the prediction error of the LSTM is established, which can improve the accuracy of predicting the driving condition data of the hybrid vehicle in the future period by using the LSTM network model, thereby improving the accuracy of determining the driving mode of the hybrid vehicle in the future period based on the predicted driving condition data of the hybrid vehicle in the future period, and avoiding frequent switching of the driving mode of the hybrid vehicle, thus improving the energy management effect of the hybrid vehicle.

[0092] Please refer to Figure 3 , in a specific embodiment, the vehicle control method provided by the embodiment of the present application may but is not limited to include the following steps:

[0093] 1. Receive driving environment data and driving state data: Obtain the training data set of the LSTM network model. The training data set includes the driving environment data and driving state data of the hybrid vehicle at a first historical moment, and the driving condition data of the first historical period. The first historical period is the future period of the first historical moment; use the data in the training data set to train the preset LSTM network model. The LSTM network model can synchronize all the data in the training data set by using timestamps, and can map the data in the training data set after timestamp synchronization to the map coordinate system by using the Simultaneous Localization and Mapping (SLAM) technology to learn the relationship between the driving environment data and driving state data at the first historical moment and the driving condition data of the first historical period, and finally obtain the trained LSTM network model.

[0094] 2. Predicted driving speed and predicted required power: The road surface characteristics of the driving section where the hybrid vehicle is currently located, the current traffic information of the driving section, and the current driving state data of the target vehicle are input into the trained LSTM network model to obtain the predicted driving speed and predicted required power of the hybrid vehicle in the first future time period. Among them, the road surface characteristics of the driving section where the hybrid vehicle is currently located can be obtained by integrating map data such as road slope and curvature; the current traffic information of the driving section where the hybrid vehicle is currently located can be obtained by integrating navigation path information such as traffic signal positions, congestion predictions, speed limits, and real-time traffic flow data such as traffic flow speed and traffic flow density; the current driving state data of the target vehicle (which can also be called the dynamic parameters of surrounding vehicles) can be obtained by acquiring the relative position of the target vehicle relative to the hybrid vehicle within the first preset range of the hybrid vehicle, as well as the longitudinal and lateral speeds and / or accelerations of the target vehicle.

[0095] 3. Multiple driving mode switching judgment: The equivalent fuel consumption can be calculated by the Equivalent Consumption Minimization Strategy (ECMS) to convert the electric energy consumption into equivalent fuel consumption. For each driving mode of the hybrid vehicle: pure electric drive mode (which can also be called the EV mode), series hybrid drive mode (which can also be called the series mode), and parallel drive mode (which can also be called the parallel mode), calculate its second equivalent fuel consumption corresponding to the predicted driving speed and predicted required power; further, combined with constraints such as the current battery charge of the hybrid vehicle (which can also be called the real-time battery SOC), the predicted engine thermal efficiency corresponding to the first future time period (which can be obtained by querying the engine thermal efficiency distribution map, and the engine thermal efficiency distribution map can also be called the engine efficiency MAP), and the predicted driving scenario corresponding to the first future time period, etc., dynamically adjust the second equivalent fuel consumption of the hybrid vehicle in each driving mode to obtain the first equivalent fuel consumption of the hybrid vehicle in each driving mode, and the driving mode with the minimum first equivalent fuel consumption can be selected as the target driving mode of the hybrid vehicle in the first future time period.

[0096] Optionally, the dynamic adjustment strategy of the real-time battery SOC for the equivalent fuel consumption of the hybrid vehicle in each driving mode can include: the higher the real-time battery SOC, the greater the weight of the equivalent fuel consumption of the EV mode (it can be understood that the equivalent fuel consumption of the hybrid vehicle in the EV mode is smaller), and the lower the SOC, the greater the weight of the equivalent fuel consumption of the series mode and the parallel mode (it can be understood that the equivalent fuel consumption of the hybrid vehicle in the series mode and the parallel mode is smaller);

[0097] Optionally, the dynamic adjustment strategy for the equivalent fuel consumption of the hybrid vehicle in each driving mode corresponding to the first future time period may include: when it is predicted that the driving scenario of the hybrid vehicle in the first future time period is an urban congestion scenario, the equivalent factor corresponding to the EV mode is negatively correlated with the real-time battery SOC;

[0098] Exemplarily, if it is predicted at the first moment that the driving speed of the hybrid vehicle in the first future time period is within the range of 0-30 km / h and the duration is 5 minutes, and the predicted demand power is 15 kW (low load), it can be determined that the predicted driving scenario of the hybrid vehicle in the first future time period is an urban congestion scenario; if the real-time battery SOC (also referred to as the current SOC) of the hybrid vehicle at the first moment is 45%, the equivalent factor \(\lambda\) corresponding to the EV mode can be assigned as \(\lambda = 1.8\). Based on the equivalent factor 1.8, the second equivalent fuel consumption of the EV mode is adjusted to obtain the first equivalent fuel consumption of the EV mode as 0.68 g / s. Compared with the first equivalent fuel consumption of other driving modes, if the first equivalent fuel consumption of the EV mode, 0.68 g / s, is the smallest, the EV mode can be determined as the target driving mode of the hybrid vehicle corresponding to the first moment in the first future time period; further, if it is predicted at the next moment (which can be referred to as the second moment) after the first moment that the predicted driving scenario of the hybrid vehicle in the first future time period is still an urban congestion scenario (it can be understood that the congestion in the first future time period continues), the equivalent factor \(\lambda\) corresponding to the EV mode can be increased from 1.8 to 2.0, and the second equivalent fuel consumption of the EV mode can be adjusted based on the increased equivalent factor 2.0 to obtain the first equivalent fuel consumption of the EV mode. By comparing the first equivalent fuel consumption of the EV mode with the first equivalent fuel consumption of other driving modes, the driving mode with the smallest first equivalent fuel consumption can be re-determined as the target driving mode of the hybrid vehicle corresponding to the second moment in the second future time period, so as to reserve power for the next calculation for correction.

[0099] In actual implementation, when it is determined that the equivalent fuel consumption of the hybrid vehicle in the parallel mode is minimized, the target gear of the parallel mode can be further selected according to the predicted vehicle speed of the hybrid vehicle in the first future period, and the parallel mode of the target gear can be determined as the target driving mode of the hybrid vehicle in the first future period. Exemplarily, the parallel mode includes parallel gears 1, 2, and 3, and the drivable speed ranges corresponding to parallel gears 1, 2, and 3 are respectively between 0 km / h and 40 km / h, between 40 km / h and 80 km / h, and greater than 80 km / h. The switching of each gear is strongly coupled with the predicted driving speed. When the predicted driving speed is between 0 km / h and 40 km / h (the predicted required torque will be greater than 150 Nm), parallel gear 1 can be selected as the target gear of the parallel mode. When the predicted driving speed is between 40 km / h and 80 km / h, parallel gear 2 can be selected as the target gear of the parallel mode. When the predicted driving speed is greater than 80 km / h, parallel gear 3 can be selected as the target gear of the parallel mode.

[0100] 4. Engine operating point selection: During the process of controlling a hybrid vehicle to drive in a target driving mode in the first future period, based on the engine efficiency MAP and the actual required power of the hybrid vehicle in the first future period, the golden section search algorithm can be used to quickly locate the high-efficiency operating range of the engine. When there is no sudden change between the actual required power of the hybrid vehicle in the first future period and the predicted required power of the hybrid vehicle in the second future period, the highest thermal efficiency operating point (also known as the lowest specific fuel consumption point) in the high-efficiency operating range of the engine can be determined as the target operating point of the engine; when there is a sudden change between the actual required power of the hybrid vehicle in the first future period and the predicted required power of the hybrid vehicle in the second future period, the target operating point of the engine in the high-efficiency operating range can be dynamically adjusted according to the deviation between the actual required power of the hybrid vehicle in the first future period and the predicted required power of the hybrid vehicle in the second future period. For example, when the predicted required power of the hybrid vehicle in the second future period suddenly increases relative to the actual required power of the hybrid vehicle in the first future period, the target operating point of the engine in the high-efficiency operating range can be adjusted from the lowest specific fuel consumption point to the midpoint of the high-efficiency operating range to reserve a rotational speed margin in advance. Exemplarily, the target operating point determined based on the golden section search algorithm can be: n = 2200 rpm, T = 217 Nm (BSFC = 215 g / kWh). When the engine drives at the target operating point, it can maintain high thermal efficiency operation at the beginning of an uphill. If the real-time SOC of the hybrid vehicle drops to 25% during the uphill, it is necessary to switch to the series mode and increase the power generation power of the engine to the battery.

[0101] In addition, before controlling the hybrid vehicle to drive in a target driving mode in the first future period, considering the real-time battery SOC and the engine thermal state of the hybrid vehicle, it can be decided whether to control the engine of the hybrid vehicle to delay shutdown or start in advance, so as to reduce the number of ineffective start and stop operations of the engine and reduce fuel consumption. For example, if it is predicted that there is a long uphill (gradient 5%, predicted continuous power 50 kW) in the 3-kilometer road section ahead of the current driving section where the hybrid vehicle is located, and the current SOC of the hybrid vehicle is 35% and the current temperature of the engine is 85°C, considering that the current SOC is low and high power is required in the future period, the engine can be started 1 kilometer in advance for preheating.

[0102] In the embodiments of the present application, by fusing multi-source environmental information including map data, navigation path information, real-time traffic flow data, and real-time dynamic parameters of surrounding vehicles, and constructing an LSTM network model for predicting the predicted driving speed and predicted demand power of a hybrid vehicle in a future time period, it is possible to reduce the prediction calculation load while ensuring the prediction accuracy, and quickly and accurately determine the predicted vehicle speed and predicted demand power of the hybrid vehicle in the future time period; further, by using the predicted vehicle speed and predicted demand power, the start-stop of the engine, the selection of the operating point, and the drive mode switching strategy are optimized in real time, and the prediction error of the LSTM is corrected by combining a feedback mechanism, so that the optimal drive mode and the optimal engine operating point of the hybrid vehicle in the future time period can be obtained based on the LSTM network model, achieving the purpose of reducing fuel consumption. Using the vehicle control method provided by the embodiments of the present application to globally optimize the start-stop of the engine, the selection of the operating point, and the drive mode switching strategy can effectively reduce the inefficient operation time of the engine, reduce the fuel consumption and mechanical wear of the engine, and the measured fuel consumption is reduced by 10%-15%.

[0103] Please refer to Figure 4 , the embodiments of the present application also provide a vehicle control device 400, which can implement the above vehicle control method. The device 400 includes: a driving condition prediction module 401, a driving mode determination module 402, and a driving control module 403.

[0104] Among them, the driving condition prediction module 401 is used to determine the predicted driving condition data of the hybrid vehicle in the first future time period according to the current driving environment data and current driving state data of the hybrid vehicle; among them, the predicted driving condition data includes at least one of the predicted driving speed and the predicted demand power;

[0105] The driving mode determination module 402 is used to determine the target driving mode of the hybrid vehicle in the first future time period according to the predicted driving condition data; among them, the target driving mode is one of the multiple driving modes included in the hybrid vehicle;

[0106] The driving control module 403 is used to control the hybrid vehicle to drive in the target driving mode in the first future time period.

[0107] The vehicle control device provided by the embodiments of the present application can implement each step of the above vehicle control method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0108] Please refer to Figure 5, The embodiments of the present application further provide a vehicle control device 500, which includes a processor 501 and a memory 502. A program or instruction that can run on the processor 501 is stored on the memory 502. When the program or instruction is executed by the processor 501, each step of the vehicle control method embodiment described above is implemented, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here. It should be noted that the vehicle control device 500 in the embodiments of the present application includes a mobile vehicle control device and a non-mobile vehicle control device.

[0109] Figure 6 The following is a schematic hardware structure diagram of the vehicle control device according to the embodiments of the present application. The vehicle control device includes:

[0110] A processor 601, which can be implemented by using a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present application;

[0111] A memory 602, which can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 602 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 602, and the processor 601 is called to execute the vehicle control method of the embodiments of the present application;

[0112] An input / output interface 603, which is used to implement information input and output;

[0113] A communication interface 604, which is used to implement communication and interaction between this device and other devices. Communication can be achieved through a wired method (such as USB, network cable, etc.) or through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.);

[0114] A bus 605, which transmits information between various components of the device (such as the processor 601, the memory 602, the input / output interface 603, and the communication interface 604);

[0115] Among them, the processor 601, the memory 602, the input / output interface 603, and the communication interface 604 are communicatively connected to each other inside the device through the bus 605.

[0116] The vehicle control device provided by the embodiments of the present application can implement each step of the above-mentioned vehicle control method embodiments and achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0117] The embodiments of the present application further provide a computer-readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each step of the above-mentioned vehicle control method embodiments is implemented, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0118] Among them, the processor is the processor in the vehicle control device described in the above embodiments. The computer-readable storage medium includes computer-readable storage media such as computer read-only memory ROM, random access memory RAM, magnetic disks or optical discs.

[0119] The embodiments of the present application further provide a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run a program or instruction to implement each step of the above-mentioned vehicle control method embodiments, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0120] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-on-chip, system chip, chip system or system-on-chip.

[0121] The embodiments of the present application provide a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement each step of the vehicle control method embodiments as described above, and the same technical effects can be achieved. To avoid repetition, it will not be elaborated here.

[0122] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including one..." does not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the methods and devices in the embodiments of the present application are not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0123] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods 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 method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0124] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A vehicle control method, characterized in that, Including: Determine the predicted driving condition data of the hybrid vehicle in a first future period according to the current driving environment data and current driving state data of the hybrid vehicle; wherein, the predicted driving condition data includes at least one of a predicted driving speed and a predicted required power; Determine the target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data; wherein, the target driving mode is one of multiple driving modes of the hybrid vehicle; In the first future period, control the hybrid vehicle to be driven in the target driving mode.

2. The vehicle control method according to claim 1, characterized in that, The determining the target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data includes: Determine the first equivalent fuel consumption of the hybrid vehicle in each of the multiple driving modes according to the predicted driving condition data; Determine the driving mode with the minimum first equivalent fuel consumption among the multiple driving modes as the target driving mode.

3. The vehicle control method according to claim 2, wherein The determining the first equivalent fuel consumption of the hybrid vehicle in each of the multiple driving modes according to the predicted driving condition data includes: For each of the driving modes, determine the second equivalent fuel consumption of the hybrid vehicle in the driving mode according to the predicted driving condition data; Determine the equivalent factor corresponding to the driving mode according to the driving characteristic data of the hybrid vehicle; wherein, the driving characteristic data includes at least one of the following: the current battery power of the hybrid vehicle, the predicted engine thermal efficiency corresponding to the first future period, the predicted driving scenario corresponding to the first future period, and the predicted driving scenario corresponding to a second future period; the second future period is after the first future period; Determine the first equivalent fuel consumption according to the product of the equivalent factor and the second equivalent fuel consumption.

4. The vehicle control method according to claim 1, characterized in that, The multiple driving modes include a pure electric driving mode and a parallel hybrid driving mode; Before controlling the hybrid vehicle to be driven in the target driving mode, the vehicle control method further includes any one of the following: When the target driving mode is the pure electric driving mode, if the current battery power of the hybrid vehicle is lower than the power threshold, control the engine of the hybrid vehicle to start in advance or stop late; When the target driving mode is the parallel hybrid driving mode, if the engine thermal state of the hybrid vehicle does not meet the preset thermal state, control the engine of the hybrid vehicle to start in advance or stop late.

5. The vehicle control method according to claim 1, characterized in that The multiple driving modes include a parallel hybrid driving mode; When the target driving mode is the parallel hybrid driving mode, the controlling the hybrid vehicle to be driven in the target driving mode includes: Obtain the actual required power of the hybrid vehicle in the first future period and the predicted required power of the hybrid vehicle in a second future period; wherein, the second future period is after the first future period; Adopt the golden section search algorithm to determine the high-efficiency working range of the engine of the hybrid vehicle according to the actual required power and the engine thermal efficiency distribution map of the hybrid vehicle; Select a target operating point from the high-efficiency operating range according to the first deviation between the predicted required power and the actual required power; Under the gasoline-electric parallel drive mode, control the engine of the hybrid vehicle to drive with the operating parameters corresponding to the target operating point.

6. The vehicle control method according to claim 5, characterized in that, The step of selecting a target operating point from the high-efficiency operating range according to the first deviation between the predicted required power and the actual required power includes: When the first deviation is within a second preset range, determine the operating point with the highest thermal efficiency in the high-efficiency operating range as the target operating point; When the first deviation exceeds the second preset range, determine a target operating range in the high-efficiency operating range according to the first deviation; and determine the operating point with the highest thermal efficiency in the target operating range as the target operating point.

7. The vehicle control method according to claim 1, wherein, After determining the predicted driving condition data of the hybrid vehicle in a first future period according to the current driving environment data and current driving state data of the hybrid vehicle, the vehicle control method further includes: Obtain a second deviation between the actual driving condition data and the predicted driving condition data of the hybrid vehicle in the first future period; wherein, the predicted driving condition data is obtained by inputting the current driving environment data and the current driving state data into a trained long short-term memory neural network model; When the second deviation exceeds a third preset range, update the long short-term memory neural network model according to the second deviation.

8. A vehicle control device, characterized in that, It includes a driving condition prediction module, a driving mode determination module and a driving control module; The driving condition prediction module is used to determine the predicted driving condition data of the hybrid vehicle in a first future period according to the current driving environment data and current driving state data of the hybrid vehicle; wherein, the predicted driving condition data includes at least one of a predicted driving speed and a predicted required power; The driving mode determination module is used to determine the target driving mode of the hybrid vehicle in the first future period according to the predicted driving condition data; wherein, the target driving mode is one of multiple driving modes included in the hybrid vehicle; The driving control module is used to control the hybrid vehicle to drive in the target driving mode in the first future period.

9. A vehicle control device, characterized in that, The vehicle control device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the vehicle control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle control method according to any one of claims 1 to 7.

Images