Energy management method, device and equipment based on hybrid electric vehicle and medium

Abstract

The invention relates to the technical field of energy management of automobiles, and discloses a vehicle energy management method, device and equipment of a hybrid electric vehicle and a medium, and the method comprises the following steps: obtaining historical driving data of a target type of hybrid electric vehicle, and carrying out driving style classification; constructing an equivalent fuel energy consumption factor set of the generator; based on historical driving data corresponding to different driving styles, a mapping relation table of the vehicle control signals and the equivalent fuel energy consumption factor sets is constructed, and the optimal equivalent fuel energy consumption factor sets corresponding to the different driving styles are solved with the minimum fuel consumption as the target; determining a corresponding current equivalent fuel energy consumption factor set and a corresponding current driving style based on the current driving data of the target vehicle, and obtaining a predicted equivalent fuel energy consumption factor set; and determining a target vehicle control signal corresponding to the predicted equivalent fuel energy consumption factor set so as to control the target vehicle based on the target vehicle control signal. The acceptability of the user to the scheme is improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile energy management, and in particular to a vehicle energy management method, device, equipment and medium for a hybrid electric vehicle. Background Art

[0002] A hybrid electric vehicle (HEV) is a vehicle whose power comes from two or more drive systems. The so-called hybrid power can be simply understood as a combination of an internal combustion engine and a generator. A hybrid electric vehicle is a type of vehicle between pure electric vehicles and fuel vehicles. As today's environmental protection measures become more and more stringent, hybrid electric vehicles have become a focus of automotive research and development due to their energy-saving and low-emission characteristics. The power system used in hybrid electric vehicles mainly includes an internal combustion engine and a generator. In the hybrid drive mode, the inefficient starting and low-speed conditions of the internal combustion engine are handed over to the generator, while the high-speed conditions that are difficult for the motor to control are handed over to the internal combustion engine.

[0003] Energy management strategy is the core of hybrid electric vehicles and can directly affect their power and economy. The purpose of energy management strategy is to reduce the consumption of internal combustion engine as much as possible and maintain the power battery at a high power state during the driving of hybrid electric vehicles. With reasonable control logic and specific mechanical structure, the two power systems are timely intervened to provide power to the vehicle under the most suitable and efficient working conditions, and improve the energy utilization efficiency of the whole vehicle under the premise of ensuring the use demand.

[0004] Common hybrid vehicle energy management strategies are all aimed at pure fuel economy, without considering the driving habits of different drivers. This may result in the optimized energy management strategy not meeting the driver's preferences, causing the driver to have a poor user experience and give up using the energy management strategy optimization function. Summary of the invention

[0005] In view of this, the present invention provides a vehicle energy management method, device, equipment and medium for hybrid vehicles to solve the problem that the energy management strategies of hybrid vehicles in related technologies are all aimed at pure fuel economy, without considering the driving habits of different drivers, which may result in the optimized energy management strategy not meeting the driver's preferences, causing the driver to have a poor user experience and give up using the energy management strategy optimization function.

[0006] In a first aspect, the present invention provides a vehicle energy management method for a hybrid electric vehicle, the method comprising:

[0007] Obtain historical driving data of a target type of hybrid vehicle;

[0008] The historical driving data is classified into driving style categories according to driving scenarios and driving methods, and the historical driving data corresponding to different driving styles are obtained;

[0009] Based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption, a set of equivalent fuel energy consumption factors of the generator is constructed;

[0010] Based on the historical driving data corresponding to different driving styles, a mapping relationship table between vehicle control signals of different driving styles and a set of equivalent fuel energy consumption factors is constructed, and the optimal set of equivalent fuel energy consumption factors corresponding to different driving styles is solved with the goal of minimizing fuel consumption;

[0011] Based on the current driving data of the target vehicle, a current equivalent fuel energy consumption factor set and a corresponding current driving style are determined, the current equivalent fuel energy consumption factor set is input into the time series prediction model, and the best equivalent fuel energy consumption factor set corresponding to the current driving style is used as the label of the time series prediction model during gradient update to obtain a predicted equivalent fuel energy consumption factor set, wherein the target vehicle is a target type hybrid vehicle;

[0012] Based on the mapping relationship table between the vehicle control signal of the current driving style and the equivalent fuel energy consumption factor set, a target vehicle control signal corresponding to the predicted equivalent fuel energy consumption factor set is determined to control the target vehicle based on the target vehicle control signal.

[0013] Therefore, by classifying driving styles, the final vehicle energy management optimization decision plan can be made more in line with the user's individual driving habits, improve the user's acceptance of the energy management optimization plan, and improve the user's usage experience; and by using the best equivalent fuel energy consumption factor set corresponding to the current driving style and its corresponding best vehicle control signal as the label of the time series prediction model during gradient update, the specific value of the vehicle's equivalent fuel energy consumption factor set can be dynamically optimized in real time, so as to dynamically optimize the vehicle's control signal in real time, so that the vehicle's control signal adjustment is in line with the vehicle's actual driving conditions, while improving the fuel economy of hybrid vehicles, ensuring the stability of vehicle driving, and further improving the user's driving experience.

[0014] In an optional implementation, the historical driving data is classified into driving styles according to the driving scene and the driving mode to obtain the historical driving data corresponding to different driving styles, including:

[0015] Classify the historical driving data into driving scenarios to obtain driving data classified into different scenarios;

[0016] Extracting driving features of driving data corresponding to different driving scenarios respectively, where the driving features are features used to characterize driving styles;

[0017] The driving characteristics of the driving data corresponding to different driving scenarios are classified to obtain historical driving data corresponding to different driving styles composed of different driving scenario-driving mode combinations.

[0018] Therefore, by extracting driving features, features used to characterize driving methods are obtained, and this is combined with driving scenarios to determine the driving styles of different users, making the classification of driving styles more refined, thereby improving the accuracy of providing vehicle energy management optimization solutions for users with the same driving style, and further enhancing the user experience.

[0019] In an optional implementation, the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption is expressed by the following formula:

[0020] P=P 1 +P 4 -P 2 -P 3 ,

[0021] Among them, P is the equivalent fuel consumption, P 1 The power consumption of the battery is P 2 is the power consumption of the converter, P 3 Power consumption for thermal management system, P 4 The amount of electricity generated by the generator.

[0022] Therefore, by converting the consumed / recovered electric energy of the generator into the fuel consumption, the influencing parameters related to the generator and fuel consumption can be extracted, providing a data basis for the follow-up.

[0023] In an optional implementation, based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption, a set of equivalent fuel energy consumption factors of the generator is constructed, including:

[0024] The equivalent fuel energy consumption factor set of the generator is determined based on the influencing parameters of battery power consumption, inverter power consumption, thermal management system power consumption and generator power generation, wherein the equivalent fuel energy consumption factors of the equivalent fuel energy consumption factor set include: total battery voltage, total battery current, inverter output voltage, inverter output current, thermal management system power consumption, actual power consumption of the thermal management system, generator voltage, and generator current.

[0025] Therefore, each equivalent fuel energy consumption factor of the equivalent fuel energy consumption factor set is determined according to the influencing parameters of the electric energy consumed / recovered by the generator, so that the equivalent fuel consumption can be directly calculated through the specific values ​​of each equivalent fuel energy consumption factor, so as to formulate an energy management optimization plan for the vehicle.

[0026] In an optional implementation, based on historical driving data corresponding to different driving styles, a mapping relationship table between vehicle control signals of different driving styles and equivalent fuel consumption factor sets is constructed, and with the goal of minimizing fuel consumption, the optimal equivalent fuel consumption factor set corresponding to different driving styles is solved, including:

[0027] Based on the historical driving data corresponding to different driving styles, a mapping relationship table between vehicle control signals of different driving styles and a set of equivalent fuel energy consumption factors is constructed using a global dynamic programming method.

[0028] With the goal of minimizing fuel consumption, a global dynamic programming method is used to input historical driving data corresponding to different driving styles, and a simulated annealing particle swarm optimization algorithm is used to solve the global optimal solution, thus obtaining the best equivalent fuel energy consumption factor set corresponding to different driving styles.

[0029] Therefore, by establishing a mapping relationship table between vehicle control signals of different driving styles and equivalent fuel energy consumption factor sets, it is convenient to subsequently determine the vehicle control signals, and by solving the optimal equivalent fuel energy consumption factor sets corresponding to different driving styles, a reference direction is provided for the subsequent adjustment of the equivalent fuel energy consumption factor sets of the vehicles, so that the subsequent predicted equivalent fuel energy consumption factor sets can increase fuel economy while ensuring the stability of vehicle driving, further improving the user's driving experience.

[0030] In an optional implementation, determining the current driving style corresponding to the target vehicle based on the current driving data of the target vehicle includes:

[0031] determining a current driving scenario based on current driving data;

[0032] Extracting current driving features from current driving data;

[0033] A current driving manner is determined based on the current driving characteristics, and a current driving style is determined based on the current driving manner and the current driving scene.

[0034] By analyzing the driving style of the target vehicle, it is helpful to provide the target vehicle with a vehicle energy management strategy that suits the user's driving style, further improving the user experience.

[0035] In an optional implementation, controlling the target vehicle based on the target vehicle control signal includes:

[0036] Obtain the current control signal of the target vehicle;

[0037] Comparing the difference between the target vehicle control signal and the current control signal;

[0038] A control parameter of a power system of the target vehicle is generated based on the difference, and the target vehicle is controlled based on the control parameter.

[0039] Therefore, by comparing the current control signal of the target vehicle with the control signal of the target vehicle, the control parameters of the vehicle power system, such as the adjustment amount of the engine and generator output torque, are obtained, which facilitates precise control of the target vehicle to improve fuel economy.

[0040] In a second aspect, the present invention provides a vehicle energy management device for a hybrid electric vehicle, the device comprising:

[0041] An acquisition module, used for acquiring historical driving data of a target type of hybrid vehicle;

[0042] The first processing module is used to classify the historical driving data into driving styles according to the driving scenes and driving methods, and obtain the historical driving data corresponding to different driving styles;

[0043] The second processing module is used to construct an equivalent fuel energy consumption factor set of the generator based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption;

[0044] The third processing module is used to construct a mapping relationship table between vehicle control signals of different driving styles and equivalent fuel energy consumption factor sets based on historical driving data corresponding to different driving styles, and to solve the optimal equivalent fuel energy consumption factor sets corresponding to different driving styles with the goal of minimizing fuel consumption;

[0045] a fourth processing module, for determining a current equivalent fuel energy consumption factor set and a corresponding current driving style corresponding to the target vehicle based on the current driving data thereof, inputting the current equivalent fuel energy consumption factor set into the time series prediction model, and using the best equivalent fuel energy consumption factor set corresponding to the current driving style as a label of the time series prediction model during gradient update, to obtain a predicted equivalent fuel energy consumption factor set, wherein the target vehicle is a target type hybrid vehicle;

[0046] The fifth processing module is used to determine the target vehicle control signal corresponding to the predicted equivalent fuel consumption factor set based on the mapping relationship table between the vehicle control signal of the current driving style and the equivalent fuel consumption factor set, so as to control the target vehicle based on the target vehicle control signal.

[0047] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0048] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to execute the method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 is a flow chart of a vehicle energy management method for a hybrid electric vehicle according to an embodiment of the present invention;

[0051] Figure 2 is a flow chart of another vehicle energy management method for a hybrid vehicle according to an embodiment of the present invention;

[0052] Figure 3 is a schematic diagram of a specific working process of vehicle energy management of a hybrid vehicle according to an embodiment of the present invention;

[0053] Figure 4 is a structural block diagram of a vehicle energy management device for a hybrid vehicle according to an embodiment of the present invention;

[0054] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0056] Energy management strategy is the core of hybrid electric vehicles and can directly affect their power and economy. The purpose of energy management strategy is to reduce the consumption of internal combustion engine as much as possible and maintain the power battery at a high power state during the driving of hybrid electric vehicles. With reasonable control logic and specific mechanical structure, the two power systems are timely intervened to provide power to the vehicle under the most suitable and efficient working conditions, and improve the energy utilization efficiency of the whole vehicle under the premise of ensuring the use demand.

[0057] Common hybrid vehicle energy management strategies are all aimed at pure fuel economy, without considering the driving habits of different drivers. This may result in the optimized energy management strategy not meeting the driver's preferences, causing the driver to have a poor user experience and give up using the energy management strategy optimization function.

[0058] The present invention mainly sets a vehicle energy management program in a computer device such as a vehicle computer installed on a hybrid vehicle to optimize the vehicle's energy management strategy and improve the user experience. By proposing an adaptive management strategy for driving energy consumption, not only the optimal energy consumption is considered, but also the impact of different driving styles of different drivers on vehicle energy consumption is considered. The driving style category is used as the first element to divide the data into different driving styles. Based on each driving style data, an equivalent fuel consumption factor set is constructed. First, a dynamic programming algorithm is used to find the optimal energy consumption factor for the entire process as a comparison benchmark. Then, based on a machine learning algorithm, a real-time optimal solution of the adaptive equivalent fuel consumption factor set is obtained. Then, the vehicle-related hardware system is optimized and adjusted, and the power system is adjusted to the optimal state suitable for the driver.

[0059] According to an embodiment of the present invention, an embodiment of a vehicle energy management method for a hybrid vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0060] In this embodiment, a vehicle energy management method for a hybrid electric vehicle is provided, which can be used for the above-mentioned computer device such as a vehicle computer deployed on a vehicle. Figure 1 is a flow chart of a vehicle energy management method for a hybrid vehicle according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0061] Step S101, obtaining historical driving data of a target type of hybrid electric vehicle.

[0062] Specifically, by obtaining the vehicle sensor data of a certain model, the vehicle sensor signals required for driving style classification can be determined based on expert experience and the vehicle CAN matrix query table, and the historical data of all vehicle-related signals are extracted from the data cloud server platform according to the signal name and frame number to form the above-mentioned historical driving data.

[0063] Exemplarily, the vehicle sensor signals include total current, total voltage, power battery SOC, DCDC output current, DCDC output voltage, actual power consumption of thermal management system, generator current, generator voltage, vehicle speed, longitudinal acceleration, motor speed, motor torque, engine speed, engine torque, etc., totaling 153 signal quantities, by extracting the frame numbers of 1,000 extended-range hybrid vehicles of S model, and the historical data of sensor signals of each vehicle for six months and their corresponding time data. This is just an example, and the present invention is not limited to this.

[0064] Step S102: classify the historical driving data into driving styles according to the driving scene and the driving method, and obtain the historical driving data corresponding to different driving styles.

[0065] Specifically, when classifying driving styles, data preprocessing operations such as data cleaning are also required on historical driving data to ensure the accuracy of subsequent classification results.

[0066] Step S103: constructing a set of equivalent fuel energy consumption factors of the generator based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption.

[0067] Specifically, the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption is expressed by the following formula (1):

[0068] P=P 1 +P 4 -P 2 -P 3 (1)

[0069] Among them, P is the equivalent fuel consumption, P 1 The power consumption of the battery is P 2 is the power consumption of the converter, P 3 Power consumption for thermal management system, P 4 The equivalent fuel consumption P refers to the power consumption of the vehicle due to various factors such as vehicle speed, acceleration, braking, and environment.

[0070] Therefore, by converting the consumed / recovered electric energy of the generator into the fuel consumption, the influencing parameters related to the generator and fuel consumption can be extracted, providing a data basis for the follow-up.

[0071] Step S104, based on the historical driving data corresponding to different driving styles, a mapping relationship table between vehicle control signals of different driving styles and a set of equivalent fuel consumption factors is constructed, and with the goal of minimizing fuel consumption, an optimal set of equivalent fuel consumption factors corresponding to different driving styles is solved.

[0072] Step S105, based on the current driving data of the target vehicle, determine its corresponding current equivalent fuel energy consumption factor set and the corresponding current driving style, input the current equivalent fuel energy consumption factor set into the time series prediction model, and use the best equivalent fuel energy consumption factor set corresponding to the current driving style as the label of the time series prediction model during gradient update to obtain the predicted equivalent fuel energy consumption factor set.

[0073] Among them, the target vehicle is a target type hybrid electric vehicle.

[0074] Specifically, the current driving style of the vehicle is first divided based on the vehicle sensor signals in the vehicle's historical driving data, and then a prediction model with good time series data prediction capabilities, such as an LSTM network, is used. Under the current driving style, the current energy consumption equivalent fuel energy consumption factor set obtained from the vehicle's historical driving data and the global optimal energy consumption equivalent factor value obtained from the above-mentioned driving styles, that is, the above-mentioned optimal equivalent fuel energy consumption factor set, are used as labels in the gradient update stage and are transmitted back to correct the prediction results, and the instantaneous optimal energy consumption equivalent factor value of the real-time data, that is, the above-mentioned predicted equivalent fuel energy consumption factor set, is predicted.

[0075] Step S106, based on the mapping relationship table between the vehicle control signal of the current driving style and the equivalent fuel consumption factor set, determine the target vehicle control signal corresponding to the predicted equivalent fuel consumption factor set, so as to control the target vehicle based on the target vehicle control signal.

[0076] Specifically, by inputting the instantaneous optimal energy consumption equivalent factor value obtained in the above step S105 into the above mapping relationship table, an instantaneous control signal value based on the global optimum, i.e., the target vehicle control signal, is obtained, so that the vehicle control system can reduce the vehicle's energy consumption by adjusting the signal.

[0077] Therefore, by classifying driving styles, the final vehicle energy management optimization decision plan can be made more in line with the user's individual driving habits, improve the user's acceptance of the energy management optimization plan, and improve the user's usage experience; and by using the best equivalent fuel energy consumption factor set corresponding to the current driving style and its corresponding best vehicle control signal as the label of the time series prediction model during gradient update, the specific value of the vehicle's equivalent fuel energy consumption factor set can be dynamically optimized in real time, so as to dynamically optimize the vehicle's control signal in real time, so that the vehicle's control signal adjustment is in line with the vehicle's actual driving conditions, while improving the fuel economy of hybrid vehicles, ensuring the stability of vehicle driving, and further improving the user's driving experience.

[0078] Figure 2 is a flow chart of another vehicle energy management method for a hybrid vehicle according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0079] Step S201, obtaining historical driving data of the target type of hybrid vehicle. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0080] Step S202: classify the historical driving data into driving styles according to the driving scene and the driving method, and obtain the historical driving data corresponding to different driving styles.

[0081] Specifically, the above step S202 includes:

[0082] Step S2021, classify the historical driving data into driving scenarios to obtain driving data classified into different scenarios.

[0083] Specifically, by using the k-means clustering algorithm to identify driving scenes from a large amount of real vehicle sensor data in historical driving data, different driving scene categories such as high speed, congestion, etc. are obtained.

[0084] Step S2022: extract driving features of driving data corresponding to different driving scenarios respectively, where the driving features are features used to characterize the driving style.

[0085] The extracted driving style features include: multiple characteristic values ​​composed of multiple signal quantities such as vehicle speed and lateral acceleration.

[0086] Step S2023, classifying the driving characteristics of the driving data corresponding to different driving scenarios to obtain historical driving data corresponding to different driving styles composed of different driving scenario-driving mode combinations.

[0087] Different driving styles are identified by deep embedding clustering of the above extracted features, such as aggressive, cautious, etc. Then, M*N driving styles are formed by combining the categories of driving scenes and driving styles through matrix multiplication, where M and N represent the number of driving scene and driving style classifications, respectively. The specific values ​​of M and N are determined by the accuracy of driving style classification, and the present invention is not limited thereto.

[0088] Therefore, by extracting driving features, features used to characterize driving methods are obtained, and this is combined with driving scenarios to determine the driving styles of different users, making the classification of driving styles more refined, thereby improving the accuracy of providing vehicle energy management optimization solutions for users with the same driving style, and further enhancing the user experience.

[0089] Step S203: constructing a set of equivalent fuel energy consumption factors of the generator based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption.

[0090] Specifically, the above step S203 includes:

[0091] Step S2031, determining a set of equivalent fuel energy consumption factors of the generator based on the influencing parameters of the battery power consumption, the converter power consumption, the thermal management system power consumption and the generator power generation.

[0092] The equivalent fuel energy consumption factors of the equivalent fuel energy consumption factor set include: total battery voltage, total battery current, converter output voltage, converter output current, power consumption of thermal management system, actual power consumption of thermal management system, generator voltage, and generator current.

[0093] Specifically, the above P 1 The specific explanation is the total energy consumption of the battery, that is, the amount of electricity consumed by the battery. The mathematical expression is shown in formula (2):

[0094]

[0095] Where: P 1 is the battery power consumption, in kWh; t is the time, in s; U is the total battery voltage, in V; I is the total battery current, in A; that is, P 1 It is obtained by integrating the total battery current and the total battery voltage over time t.

[0096] Among them, P 2 The specific explanation is the power consumed by high and low voltage electrical appliances during vehicle discharge, and its calculation is shown in formula (3):

[0097]

[0098] Where: P 2 is the power consumption of the converter, i.e. DCDC, in kWh; t is the time, in s; U′ is the DCDC output voltage, in V; I′ is the DCDC output current, in A; i.e. P 2 It is obtained by integrating the DCDC output current and the DCDC output voltage within the time t.

[0099] Among them, P 3 The specific explanation is the power consumption of the vehicle thermal management system, which is calculated as shown in formula (4):

[0100]

[0101] Where: P 3 The power consumption of the thermal management system (TMS) is in kWh; P wrAct is the actual power consumption of TMS, in W; t is the time, in s; that is, P 3The actual power consumed by the thermal management system is obtained by integrating it over time t.

[0102] Among them, P 4 The specific explanation of is the power generation of the generator during the vehicle discharge process, which is calculated as shown in formula (5):

[0103]

[0104] Where: P 4 is the power generation of the generator, in kWh; t is the time, in s; GERU is the generator voltage, in V; GERI is the generator current, in A; that is, P 4 It is obtained by integrating the generator output current and the generator output voltage over time t.

[0105] The fuel consumption factor set factors is defined as follows: factors = {total battery voltage, total battery current, DCDC output voltage, DCDC output current, TMS power consumption, TMS actual power consumption, generator voltage, generator current}.

[0106] Therefore, each equivalent fuel energy consumption factor of the equivalent fuel energy consumption factor set is determined according to the influencing parameters of the electric energy consumed / recovered by the generator, so that the equivalent fuel consumption can be directly calculated through the specific values ​​of each equivalent fuel energy consumption factor, so as to formulate an energy management optimization plan for the vehicle.

[0107] Step S204, based on the historical driving data corresponding to different driving styles, a mapping relationship table between vehicle control signals of different driving styles and equivalent fuel consumption factor sets is constructed, and the optimal equivalent fuel consumption factor sets corresponding to different driving styles are solved with the goal of minimizing fuel consumption.

[0108] Specifically, the above step S204 includes:

[0109] Step S2041, based on the historical driving data corresponding to different driving styles, a mapping relationship table between vehicle control signals of different driving styles and a set of equivalent fuel consumption factors is constructed by using a global dynamic programming method.

[0110] Step S2042, with the goal of minimizing fuel consumption, using a global dynamic programming method, inputting historical driving data corresponding to different driving styles, and using a simulated annealing particle swarm optimization algorithm to solve the global optimal solution, thereby obtaining a set of optimal equivalent fuel energy consumption factors corresponding to different driving styles.

[0111] Specifically, for each driving style, based on the idea of ​​global dynamic programming, a particle swarm optimization algorithm with simulated annealing is used to construct a unique equivalent fuel consumption factor-control signal mapping relationship table for each vehicle according to historical driving data. The current optimal equivalent fuel factor output by the subsequent machine learning network will be used to obtain the current optimal control signal by looking up the table, so that the control system can adjust the output torque of the engine and generator, etc., so that its operating point falls within the high efficiency range of energy utilization.

[0112] In this embodiment, the input signal of the mapping relationship table is the historical driving data of all factors of the equivalent fuel energy consumption factor set, and the output control signal includes the historical driving data of speed, acceleration, generator speed, generator torque, engine speed, engine torque, battery SOC, accelerator pedal depth and brake depth, among which the acceleration is calculated by the vehicle speed under adjacent operating conditions.

[0113] For each driving style, based on the idea of ​​global dynamic programming, the historical data of the energy consumption equivalent factor is input, and the simulated annealing particle swarm optimization (SA-PSO) algorithm is used to solve the global optimal solution. The global optimal energy consumption equivalent factor value under each driving style is obtained as the input data for the subsequent machine learning algorithm.

[0114] Therefore, by establishing a mapping relationship table between vehicle control signals of different driving styles and equivalent fuel energy consumption factor sets, it is convenient to subsequently determine the vehicle control signals, and by solving the optimal equivalent fuel energy consumption factor sets corresponding to different driving styles, a reference direction is provided for the subsequent adjustment of the equivalent fuel energy consumption factor sets of the vehicles, so that the subsequent predicted equivalent fuel energy consumption factor sets can increase fuel economy while ensuring the stability of vehicle driving, further improving the user's driving experience.

[0115] Step S205, based on the current driving data of the target vehicle, determine its corresponding current equivalent fuel energy consumption factor set and the corresponding current driving style, input the current equivalent fuel energy consumption factor set into the time series prediction model, and use the best equivalent fuel energy consumption factor set corresponding to the current driving style as the label of the time series prediction model during gradient update to obtain the predicted equivalent fuel energy consumption factor set, wherein the target vehicle is a target type hybrid vehicle.

[0116] Specifically, the current driving style corresponding to the target vehicle is determined based on the current driving data of the target vehicle in the above step S205, including:

[0117] Step a1, determining the current driving scene based on the current driving data.

[0118] Step a2: extracting current driving features from current driving data.

[0119] Step a3, determining the current driving mode based on the current driving characteristics, and determining the current driving style based on the current driving mode and the current driving scene.

[0120] For details about the process of determining the current driving style of the target vehicle, please refer to the relevant description of the driving style classification in the above step S202. The implementation method is similar and will not be repeated here.

[0121] By analyzing the driving style of the target vehicle, it is helpful to provide the target vehicle with a vehicle energy management strategy that suits the user's driving style, further improving the user experience.

[0122] Step S206, based on the mapping relationship table between the vehicle control signal of the current driving style and the equivalent fuel consumption factor set, determine the target vehicle control signal corresponding to the predicted equivalent fuel consumption factor set, so as to control the target vehicle based on the target vehicle control signal.

[0123] Specifically, the target vehicle is controlled based on the target vehicle control signal in the above step S206, including:

[0124] Step b1, obtaining the current control signal of the target vehicle.

[0125] Step b2, comparing the difference between the target vehicle control signal and the current control signal.

[0126] Step b3, generating control parameters of the target vehicle power system based on the difference, and controlling the target vehicle based on the control parameters.

[0127] Among them, the control signal includes: speed, acceleration, generator speed, generator torque, engine speed, engine torque, battery SOC, accelerator pedal depth and brake depth, etc. By calculating the difference between the current control signal and the target vehicle control signal in the above parameters, it is finally converted into the adjustment amount of control parameters such as accelerator pedal depth and brake depth, and the relevant control parameters of the vehicle power system are adjusted on the basis of the current control signal according to the specific adjustment amount. The specific control parameter adjustment method is the existing technology and will not be repeated here.

[0128] Therefore, by comparing the current control signal of the target vehicle with the control signal of the target vehicle, the control parameters of the vehicle power system, such as the adjustment amount of the engine and generator output torque, are obtained, which facilitates precise control of the target vehicle to improve fuel economy.

[0129] For example, the specific working process of the vehicle energy management of a hybrid vehicle is as follows: Figure 3As shown, the present invention provides such an adaptive management strategy for driving energy consumption, which provides optimization decisions for hardware logic based on the real sensor data of the vehicle and by analyzing the driver's driving style factors, which is more in line with the driver's driving habits under the driving style, and the driver has a higher acceptance of the energy management; by constructing an equivalent fuel consumption factor set, the common influencing factors of the energy consumption of hybrid vehicles of different models can be extracted in the future, and the parameter conversion matrix of different models can be extracted through the migration algorithm, and directly input into the trained basic model to obtain an algorithm model that is more suitable for each model, which can effectively shorten the training cycle of the energy management strategy of hybrid vehicles of different models; based on the machine learning algorithm, the real-time optimal solution of the adaptive equivalent fuel consumption factor set is obtained, and the control logic parameters of the power system are optimized in real time and dynamically, which is conducive to improving the fuel economy of hybrid vehicles.

[0130] In this embodiment, a vehicle energy management device for a hybrid electric vehicle is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0131] This embodiment provides a vehicle energy management device for a hybrid vehicle, such as Figure 4 As shown, including:

[0132] The acquisition module 401 is used to acquire historical driving data of a target type of hybrid electric vehicle.

[0133] The first processing module 402 is used to classify the historical driving data into driving styles according to the driving scenes and driving methods, and obtain the historical driving data corresponding to different driving styles.

[0134] The second processing module 403 is used to construct an equivalent fuel energy consumption factor set of the generator based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption.

[0135] The third processing module 404 is used to construct a mapping relationship table between vehicle control signals of different driving styles and a set of equivalent fuel energy consumption factors based on historical driving data corresponding to different driving styles, and to solve the optimal set of equivalent fuel energy consumption factors corresponding to different driving styles with the goal of minimizing fuel consumption.

[0136] The fourth processing module 405 is used to determine the current equivalent fuel energy consumption factor set and the corresponding current driving style based on the current driving data of the target vehicle, input the current equivalent fuel energy consumption factor set into the time series prediction model, and use the best equivalent fuel energy consumption factor set corresponding to the current driving style as the label of the time series prediction model during gradient update to obtain the predicted equivalent fuel energy consumption factor set, wherein the target vehicle is a target type hybrid vehicle.

[0137] The fifth processing module 406 is used to determine the target vehicle control signal corresponding to the predicted equivalent fuel consumption factor set based on the mapping relationship table between the vehicle control signal of the current driving style and the equivalent fuel consumption factor set, so as to control the target vehicle based on the target vehicle control signal.

[0138] In some optional implementations, the first processing module 402 includes:

[0139] A first processing unit is used to classify the historical driving data into driving scenarios to obtain driving data classified into different scenarios;

[0140] A second processing unit is used to extract driving features of driving data corresponding to different driving scenarios, where the driving features are features used to characterize driving styles;

[0141] The third processing unit is used to classify the driving characteristics of the driving data corresponding to different driving scenarios to obtain historical driving data corresponding to different driving styles composed of different driving scenario-driving methods.

[0142] In some optional implementations, the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption is expressed by the following formula:

[0143] P=P 1 +P 4 -P 2 -P 3 ,

[0144] Among them, P is the equivalent fuel consumption, P 1 The power consumption of the battery is P 2 is the power consumption of the converter, P 3 Power consumption for thermal management system, P 4 The amount of electricity generated by the generator.

[0145] In some optional implementations, the second processing module 403 includes:

[0146] The fourth processing unit is used to determine an equivalent fuel energy consumption factor set of the generator based on the influencing parameters of the battery power consumption, the inverter power consumption, the thermal management system power consumption and the generator power generation, wherein the equivalent fuel energy consumption factors of the equivalent fuel energy consumption factor set include: battery total voltage, battery total current, inverter output voltage, inverter output current, thermal management system power consumption, thermal management system actual power consumption, generator voltage, generator current.

[0147] In some optional implementations, the third processing module 404 includes:

[0148] The fifth processing unit is used to construct a mapping relationship table between vehicle control signals of different driving styles and a set of equivalent fuel energy consumption factors based on historical driving data corresponding to different driving styles by using a global dynamic programming method.

[0149] The sixth processing unit is used to take the lowest fuel consumption as the goal, use the global dynamic programming method, input the historical driving data corresponding to different driving styles, adopt the simulated annealing particle swarm optimization algorithm to solve the global optimal solution, and obtain the best equivalent fuel energy consumption factor set corresponding to different driving styles.

[0150] In some optional implementations, the fourth processing module 405 determines the current driving style corresponding to the target vehicle based on the current driving data of the target vehicle, including:

[0151] a seventh processing unit, configured to determine a current driving scene based on current driving data;

[0152] an eighth processing unit, configured to extract current driving characteristics from current driving data;

[0153] The ninth processing unit is used to determine the current driving mode based on the current driving characteristics, and determine the current driving style based on the current driving mode and the current driving scene.

[0154] In some optional implementations, the fifth processing module 406 controls the target vehicle based on the target vehicle control signal, including:

[0155] a tenth processing unit, configured to obtain a current control signal of the target vehicle;

[0156] an eleventh processing unit, for comparing the difference between the target vehicle control signal and the current control signal;

[0157] The twelfth processing unit is used to generate control parameters of a power system of the target vehicle based on the difference, and control the target vehicle based on the control parameters.

[0158] The vehicle energy management device of the hybrid vehicle in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0159] The further functional description of each of the above modules and units is the same as that of the above corresponding method embodiments and will not be repeated here.

[0160] The embodiment of the present invention also provides a computer device having the above Figure 4 The vehicle energy management device of the hybrid vehicle is shown.

[0161] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0162] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0163] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0164] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0165] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0166] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0167] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0168] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A vehicle energy management method for a hybrid electric vehicle, characterized in that: The method comprises: Obtain historical driving data of a target type of hybrid vehicle; Classifying the historical driving data into driving styles according to driving scenarios and driving methods to obtain historical driving data corresponding to different driving styles; Based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption, a set of equivalent fuel energy consumption factors of the generator is constructed; Based on the historical driving data corresponding to different driving styles, a mapping relationship table between the vehicle control signals of different driving styles and the equivalent fuel energy consumption factor set is constructed, and the optimal equivalent fuel energy consumption factor set corresponding to different driving styles is solved with the goal of minimizing fuel consumption; Determine a current equivalent fuel energy consumption factor set and a current driving style corresponding to the target vehicle based on current driving data, input the current equivalent fuel energy consumption factor set into a time series prediction model, and use the best equivalent fuel energy consumption factor set corresponding to the current driving style as a label of the time series prediction model during gradient update to obtain a predicted equivalent fuel energy consumption factor set, wherein the target vehicle is a target type hybrid vehicle; Based on the mapping relationship table between the vehicle control signal of the current driving style and the equivalent fuel energy consumption factor set, a target vehicle control signal corresponding to the predicted equivalent fuel energy consumption factor set is determined to control the target vehicle based on the target vehicle control signal.

2. The method according to claim 1, characterized in that The driving style classification of the historical driving data according to the driving scene and the driving mode to obtain the historical driving data corresponding to different driving styles includes: Classifying the historical driving data according to driving scenarios to obtain driving data classified according to different scenarios; Extracting driving features of driving data corresponding to different driving scenarios respectively, wherein the driving features are features used to characterize driving styles; The driving characteristics of the driving data corresponding to different driving scenarios are classified to obtain historical driving data corresponding to different driving styles composed of different driving scenario-driving mode combinations.

3. The method according to claim 1, characterized in that The conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption is expressed by the following formula: p=P l 10 P4-P2-P3, Among them, P is the equivalent fuel consumption, P1 is the battery power consumption, P2 is the inverter power consumption, P3 is the thermal management system power consumption, and P4 is the generator power consumption.

4. The method according to claim 3, characterized in that: The equivalent fuel energy consumption factor set of the generator is constructed based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption, including: The equivalent fuel energy consumption factor set of the generator is determined based on the influencing parameters of battery power consumption, inverter power consumption, thermal management system power consumption and generator power generation, wherein the equivalent fuel energy consumption factors of the equivalent fuel energy consumption factor set include: total battery voltage, total battery current, inverter output voltage, inverter output current, thermal management system power consumption, actual power consumption of the thermal management system, generator voltage, and generator current.

5. The method according to claim 1, characterized in that The mapping relationship table between the vehicle control signals of different driving styles and the equivalent fuel energy consumption factor set is constructed based on the historical driving data corresponding to different driving styles, and the optimal equivalent fuel energy consumption factor set corresponding to different driving styles is solved with the goal of minimizing fuel consumption, including: Based on the historical driving data corresponding to different driving styles, a mapping relationship table between the vehicle control signals of different driving styles and the equivalent fuel energy consumption factor set is constructed by using a global dynamic programming method; With the goal of minimizing fuel consumption, a global dynamic programming method is used to input historical driving data corresponding to different driving styles, and a simulated annealing particle swarm optimization algorithm is used to solve the global optimal solution, thus obtaining the best equivalent fuel energy consumption factor set corresponding to different driving styles.

6. The method according to claim 1, characterized in that The determining the current driving style corresponding to the target vehicle based on the current driving data of the target vehicle includes: determining a current driving scene based on the current driving data; extracting current driving characteristics from the current driving data; A current driving manner is determined based on the current driving characteristics, and a current driving style is determined based on the current driving manner and the current driving scene.

7. The method according to claim 1, characterized in that The controlling the target vehicle based on the target vehicle control signal includes: Acquiring a current control signal of the target vehicle; comparing the target vehicle control signal with the current control signal; A control parameter of the target vehicle power system is generated based on the difference, and the target vehicle is controlled based on the control parameter.

8. A vehicle energy management device for a hybrid vehicle, characterized in that: The device comprises: An acquisition module, used for acquiring historical driving data of a target type of hybrid vehicle; A first processing module, configured to classify the historical driving data into driving styles according to driving scenarios and driving methods, and obtain historical driving data corresponding to different driving styles; The second processing module is used to construct an equivalent fuel energy consumption factor set of the generator based on the conversion relationship between the electric energy consumed / recovered by the generator and the fuel consumption; The third processing module is used to construct a mapping relationship table between the vehicle control signals of different driving styles and the equivalent fuel energy consumption factor set based on the historical driving data corresponding to different driving styles, and solve the optimal equivalent fuel energy consumption factor set corresponding to different driving styles with the goal of minimizing fuel consumption; a fourth processing module, for determining a current equivalent fuel energy consumption factor set and a current driving style corresponding to the target vehicle based on the current driving data thereof, inputting the current equivalent fuel energy consumption factor set into a time series prediction model, and using the best equivalent fuel energy consumption factor set corresponding to the current driving style as a label of the time series prediction model during gradient update, to obtain a predicted equivalent fuel energy consumption factor set, wherein the target vehicle is a target type hybrid vehicle; The fifth processing module is used to determine the target vehicle control signal corresponding to the predicted equivalent fuel energy consumption factor set based on the mapping relationship table between the vehicle control signal of the current driving style and the equivalent fuel energy consumption factor set, so as to control the target vehicle based on the target vehicle control signal.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images