CN117984983B - Hybrid vehicle energy real-time control method, vehicle controller and hybrid vehicle - Google Patents
Hybrid vehicle energy real-time control method, vehicle controller and hybrid vehicle Download PDFInfo
- Publication number
- CN117984983B CN117984983B CN202410398059.4A CN202410398059A CN117984983B CN 117984983 B CN117984983 B CN 117984983B CN 202410398059 A CN202410398059 A CN 202410398059A CN 117984983 B CN117984983 B CN 117984983B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- sequence
- speed
- function
- energy consumption
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000005265 energy consumption Methods 0.000 claims description 54
- 230000001133 acceleration Effects 0.000 claims description 15
- 230000005611 electricity Effects 0.000 claims description 15
- 239000000446 fuel Substances 0.000 claims description 14
- 230000009471 action Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 230000006855 networking Effects 0.000 claims description 3
- 238000007726 management method Methods 0.000 abstract description 10
- 230000006870 function Effects 0.000 description 51
- 238000005457 optimization Methods 0.000 description 5
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a hybrid vehicle energy real-time control method, a vehicle controller and a hybrid vehicle. The method for controlling the energy of the hybrid electric vehicle in real time comprises the following steps: training the dual-delay depth deterministic strategy gradient neural network model to obtain an optimal reference speed planning model; inputting the acquired real-time model into an optimal reference speed planning model for processing to obtain an optimal reference speed of the vehicle at each moment in a future period of time, and obtaining an optimal reference speed sequence; based on the optimal reference speed sequence, calculating the total required torque of the vehicle at each moment in a period of time in the future to obtain a total required torque sequence; determining an engine torque sequence and a motor torque sequence of the vehicle based on the total demand torque sequence; the vehicle is controlled based on the engine torque sequence and the motor torque sequence. The invention can better control the hybrid electric vehicle to carry out energy control management.
Description
Technical Field
The invention relates to the technical field of energy management of hybrid vehicles, in particular to a hybrid vehicle energy real-time control method, a vehicle controller and a hybrid vehicle.
Background
In recent years, a main goal of the automotive industry has been to develop toward environmental friendliness. Because road transportation is a significant part of fossil fuel consumption and carbon dioxide production, energy conservation and emission reduction have become priority in the automotive industry. In this context, hybrid vehicles are considered as solutions with wide application prospects. The method can effectively solve the problem of the endurance mileage of the pure electric vehicle while realizing low emission, low cost and high efficiency. Hybrid vehicles have received extensive attention and research. In hybrid vehicles, energy management is a key factor affecting the overall vehicle economy. The energy-saving mechanism of the hybrid electric vehicle is to optimize the working point of the engine in a high-efficiency range and compensate the gap between the output power of the engine and the current driving demand power by utilizing the motor. Therefore, it is important to formulate an energy management strategy for a hybrid electric vehicle and improve the adaptability of the hybrid electric vehicle in different road environments. This means that there is a need to optimize the energy utilization so that the cooperation of the engine and the motor under different conditions is more efficient. Through a reasonable energy management strategy, the optimal power output and the optimal fuel utilization rate are ensured to be provided under different driving conditions, so that the economy of the whole vehicle is improved.
Many current energy management strategies are designed based on standard driving conditions, and have less attention to real driving data; the vehicle is used as a part of a traffic environment, and the working condition of the vehicle is closely related to the environment; therefore, how to combine the real driving data and the real working condition optimizes the energy management strategy so that the optimized strategy can adapt to various working conditions to realize the optimization of the energy management of the automobile, and has important significance.
Disclosure of Invention
The invention aims to overcome the defects and the shortcomings of the prior art and provide a hybrid vehicle energy real-time control method, a vehicle controller and a hybrid vehicle.
In a first aspect of the present invention, there is provided a method for controlling energy of a hybrid vehicle in real time, comprising the steps of:
S1, training a dual-delay depth deterministic strategy gradient neural network model to obtain an optimal reference speed planning model; constructing a state space by the dual-delay depth deterministic strategy gradient neural network model according to the current road slope of the own vehicle, the charge state of the battery of the own vehicle, the speed of the own vehicle, the relative distance between the own vehicle and the front vehicle, the acceleration of the front vehicle and the speed of the front vehicle, and constructing an action space by the acceleration of the own vehicle; the rewarding function is constructed by an own vehicle oil consumption and electricity consumption assembly energy consumption rewarding function, an own vehicle and front vehicle relative distance energy consumption rewarding function, an own vehicle speed energy consumption rewarding function and a front vehicle speed energy consumption rewarding function; after training, taking an Actor target network as an optimal reference speed planning model;
s2, inputting data based on a real-time model acquired by an intelligent traffic system and/or a vehicle networking, inputting an optimal reference speed planning model for processing, and obtaining an optimal reference speed sequence at each moment of the vehicle in a future period of time;
S3, calculating total required torque of the vehicle at each moment in a future period of time based on the optimal reference speed sequence to obtain a total required torque sequence;
S4, determining an engine torque sequence and a motor torque sequence of the vehicle based on the total required torque sequence and with minimum vehicle energy consumption as a target; wherein the sum of the engine torque and the motor torque at each moment in time of the vehicle in the future is equal to the total torque required;
S5, controlling the vehicle based on the engine torque sequence and the motor torque sequence of the vehicle.
The expression of the dual-delay depth deterministic strategy gradient neural network model is as follows:
,
wherein S represents a state space, A represents an action space, and R represents a reward function;
Indicating the state of charge of the battery of the own vehicle at the current moment, Indicating the gradient of the current moment under the current road surface where the own vehicle is located,Indicating the relative distance between the own vehicle and the front vehicle at the current moment,Indicating the acceleration of the front vehicle at the current moment,Indicating the speed of the preceding vehicle at the current moment,Representing the speed of the vehicle at the current moment;
Representing the self-vehicle acceleration at the current moment;
a weight factor representing the energy consumption rewarding function of the self-vehicle fuel consumption and the electricity consumption assembly in unit time, A weight factor representing the energy consumption rewarding function of the relative distance between the own vehicle and the front vehicle in unit time,A weight factor representing a motor vehicle speed energy consumption rewarding function in unit time,A weight factor representing a preceding vehicle speed energy consumption rewarding function per unit time,Is the energy consumption rewarding function of the own vehicle oil consumption and electricity consumption assembly in unit time,Is the energy consumption rewarding function of the relative distance between the own vehicle and the front vehicle in unit time,Is a self-vehicle speed energy consumption rewarding function in unit time,Is a function of the energy consumption rewarding of the speed of the front vehicle in unit time.
Wherein, the fuel consumption and the electricity consumption of the bicycle in unit time are combined into the cost energy consumption rewarding functionThe total sum of the fuel consumption and the electricity consumption of the vehicle in the unit time step is shown.
Wherein the relative distance energy consumption rewarding function between the own vehicle and the front vehicle in unit timeThe expression of (2) is as follows:
,
In the method, in the process of the invention, ,Respectively represents the maximum relative distance and the minimum relative distance between the front vehicle and the own vehicle,Representing an exponential function.
Wherein the self-vehicle speed energy consumption rewarding function in unit timeThe expression of (2) is as follows:
,
In the method, in the process of the invention, ,Representing the maximum and minimum speeds that can be reached by the vehicle, respectively.
Wherein, the preceding vehicle speed energy consumption rewarding function in unit timeThe expression of (2) is as follows:
。
in step S3, based on the optimal reference speed sequence, calculating a total required torque at each moment in a period of time in the future of the vehicle, to obtain a total required torque sequence, including:
The own vehicle obtains a speed difference sequence according to the speed difference value of the optimal reference speed of each future moment and the vehicle speed obtained by predicting traffic conditions of the own vehicle;
based on the speed difference in the speed difference sequence, outputting total required torque at each moment in a future period from a PI driver model in the vehicle to form a total required torque sequence.
In step S4, based on the total required torque sequence, with the minimum energy consumption of the vehicle as a target, determining an engine torque sequence and a motor torque sequence of the vehicle, and implementing the following cost function control:
,
,,
In the method, in the process of the invention, For the instantaneous fuel consumption of the engine,As an equivalent factor to the number of the elements,For the sequence of engine torques,For the motor torque of the vehicle,Is the calorific value of the gasoline,Representing the power cell's electrical quantity value at the initial moment of the cycle,For a sequence of engine torques over a period of time in the future,The function of the optimization objective is represented as,Representing a cost function.
In a second aspect of the present invention, a vehicle controller is provided for performing real-time control on a hybrid vehicle by using the hybrid vehicle energy real-time control method according to the first aspect of the present invention.
In a third aspect of the present invention, there is provided a hybrid vehicle comprising the vehicle controller according to the second aspect of the present invention.
The invention fully considers the influence of the real-time change of the environmental information of the vehicle and the information of the vehicle on the energy consumption of the hybrid electric vehicle, and can obtain a more accurate energy-saving speed sequence by combining an intelligent traffic system, thereby obtaining a more accurate economic speed prediction, and further better controlling the hybrid electric vehicle to carry out energy control management.
Drawings
Fig. 1 is a flowchart of a method for controlling energy of a hybrid vehicle in real time according to the present invention.
Fig. 2 is a schematic diagram of an optimal reference speed planning model (Actor target network) according to the present invention.
FIG. 3 is a data processing flow chart of the optimal reference speed planning model of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and the specific examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, in a first aspect of the embodiment of the present invention, a method for controlling energy of a hybrid vehicle in real time is provided, including the steps of:
S1, training a dual-delay depth deterministic strategy gradient neural network model to obtain an optimal reference speed planning model;
The dual-delay depth deterministic strategy gradient neural network model constructs a state space according to the current road surface gradient of the own vehicle, the charge state of a battery of the own vehicle, the speed of the own vehicle, the relative distance between the own vehicle and a front vehicle, the acceleration of the front vehicle and the speed of the front vehicle, and constructs an action space according to the acceleration of the own vehicle; the rewarding function is constructed by an energy consumption rewarding function of the fuel consumption and electricity consumption assembly of the own vehicle, a relative distance energy consumption rewarding function of the own vehicle and the front vehicle, a speed energy consumption rewarding function of the own vehicle and a speed energy consumption rewarding function of the front vehicle; after training, taking an Actor target network as an optimal reference speed planning model;
S2, inputting real-time model input data acquired based on an intelligent traffic system and/or a vehicle networking, and inputting the real-time model input data into the optimal reference speed planning model for processing to obtain optimal reference speeds of vehicles at each moment in a future period of time, so as to obtain an optimal reference speed sequence;
S3, calculating total required torque of the vehicle at each moment in a future period of time based on the optimal reference speed sequence to obtain a total required torque sequence;
S4, determining an engine torque sequence and a motor torque sequence of the vehicle by taking the minimum energy consumption of the vehicle as a target based on the total required torque sequence; wherein the sum of the engine torque and the motor torque at each moment in time of the vehicle in the future is equal to the total torque required;
S5, controlling the vehicle based on the engine torque sequence and the motor torque sequence of the vehicle.
In step S2, the real-time model input data obtained based on the intelligent traffic system and/or the internet of vehicles includes data such as a gradient of the current road surface where the vehicle is located, a battery charge state of the vehicle, a speed of the vehicle, a relative distance between the vehicle and the front vehicle, an acceleration of the front vehicle, a speed of the front vehicle, and SOC information of the battery of the vehicle, etc., which may be obtained in real time from the intelligent traffic system and/or the internet of vehicles or related devices, and after obtaining the required real-time data, the data is used as parameters of a state space, the optimal reference speed planning model is input, and finally, a corresponding acceleration value is output from an action space, and a speed is calculated according to the acceleration, thereby obtaining an optimal reference speed sequence, see fig. 2.
In a specific vehicle running process, the vehicle management system continuously and repeatedly executes the steps, calculates an optimal strategy of energy distribution, and distributes the energy of the vehicle.
The expression of the dual-delay depth deterministic strategy gradient neural network model is as follows:
,
wherein S represents a state space, A represents an action space, and R represents a reward function;
Indicating the state of charge of the battery of the own vehicle at the current moment, Indicating the gradient of the current moment under the current road surface where the own vehicle is located,Indicating the relative distance between the own vehicle and the front vehicle at the current moment,Indicating the acceleration of the front vehicle at the current moment,Indicating the speed of the preceding vehicle at the current moment,Representing the speed of the vehicle at the current moment;
Representing the self-vehicle acceleration at the current moment;
a weight factor representing the energy consumption rewarding function of the self-vehicle fuel consumption and the electricity consumption assembly in unit time, A weight factor representing the energy consumption rewarding function of the relative distance between the own vehicle and the front vehicle in unit time,A weight factor representing a motor vehicle speed energy consumption rewarding function in unit time,A weight factor representing a forward speed energy reward function per unit time,Is the energy consumption rewarding function of the own vehicle oil consumption and electricity consumption assembly in unit time,Is the energy consumption rewarding function of the relative distance between the own vehicle and the front vehicle in unit time,Is a self-vehicle speed energy consumption rewarding function in unit time,Is a function of the energy consumption rewarding of the speed of the front vehicle in unit time.
Wherein, the fuel consumption and the electricity consumption of the bicycle in unit time are combined into the cost energy consumption rewarding functionThe total sum of the fuel consumption and the electricity consumption of the own vehicle in a unit time step.
Wherein the relative distance energy consumption rewarding function between the own vehicle and the front vehicle in unit timeThe expression of (2) is as follows:
,
In the method, in the process of the invention, ,Respectively represents the maximum relative distance and the minimum relative distance between the front vehicle and the own vehicle,Representing an exponential function.
Wherein the self-vehicle speed energy consumption rewarding function in unit timeThe expression of (2) is as follows:
,
In the method, in the process of the invention, ,Representing the maximum and minimum speeds that can be reached by the vehicle, respectively.
Wherein, the preceding vehicle speed energy consumption rewarding function in unit timeThe expression of (2) is as follows:
。
in one embodiment of the present application, in step S3, the calculating the total required torque at each moment in a period of time in the future of the vehicle based on the optimal reference speed sequence to obtain the total required torque sequence includes:
The own vehicle obtains a speed difference sequence according to the speed difference value of the optimal reference speed of each future moment and the vehicle speed obtained by predicting traffic conditions of the own vehicle;
based on the speed difference in the speed difference sequence, outputting total required torque at each moment in a future period from a PI driver model in the vehicle to form a total required torque sequence.
The corresponding expression is as follows:
,
In the method, in the process of the invention, In order to achieve the total required torque,Is a coefficient of proportionality and is used for the control of the power supply,For the optimal reference speed to be achieved,In order to achieve the speed of the vehicle,Is an integral coefficient.
In one embodiment, in step S4, based on the total required torque sequence, the engine torque sequence and the motor torque sequence of the vehicle are determined with the minimum energy consumption of the vehicle as a target, and the following cost function control is adopted to realize:
,
,,
In the method, in the process of the invention, For the instantaneous fuel consumption of the engine,For the sequence of engine torques,As an equivalent factor to the number of the elements,For the motor torque of the vehicle,Is the calorific value of the gasoline,Representing the charge value of the power battery of the vehicle,Representing the power cell's electrical quantity value at the initial moment of the cycle,For a sequence of engine torques over a period of time in the future,The function of the optimization objective is represented as,Representing a cost function.
In step S4, in determining an engine torque sequence and a motor torque of the vehicleBased on the total required torque in a period of time in the future of the vehicleSequence, constructing an optimal control problem, solving an optimal action sequence, and determining engine torque in a future period of timeSequence and motor torqueA sequence;
The specific processing process comprises the following steps:
state variable selection ;
Control variable selection;
;
For the capacity of the power battery,Is the internal impedance of the power battery,Is the power supply voltage of the power battery,Is the power of the power battery;
the optimal control expression is established as follows:
;
Simultaneously satisfies the constraint:
;
In the method, in the process of the invention, ,,,,Representing the minimum torque of the engine, the maximum torque of the engine, the torque of the motor, the maximum torque of the motor and the total required torque of the bicycle respectively;
Allowing the sum of the engine torque and the motor torque of the vehicle in the future for this period of time to be equal to the total required torque, i.e ;
Minimizing cost functionMinimizing energy consumption of the hybrid vehicle in a future period of time;
When solving, the values of the engine torque, the motor torque and the power battery must meet respective ranges;
,
the above problems are converted into the following general form:
;
Optimizing an objective function And state transition equationBoth atypical quadratic forms, but satisfying the second order is differentiable and includes both inequality constraint functions with respect to control quantity and state quantityAnd;
When solving, the objective function is optimizedPerforming Taylor expansion, linearizing a state transfer equation, and converting an inequality constraint function into a new optimization objective function by using an obstacle function methodThe problem is converted into a linear secondary adjustment problem, and the optimal action sequences of the engine and the motor in the future period are solved in an iterative mode: barrier function,Q1, q2, q3 and q4 are a first preset parameter, a second preset parameter, a third preset parameter and a fourth preset parameter, respectively; thus, the following new optimized objective function is obtained:
。
Specifically, when solving, the engine torque is optimized through the new optimization objective functionAndThe desired engine torque sequence and motor torque sequence are obtained.
When the optimal reference speed planning model shown in fig. 2 is adopted and output action is performed according to the input state space parameters, the steps are as follows:
Under any initial action sequence, generating initial state quantity according to a forward recursion equation of a model to obtain an initial objective function J_old in a loop, and setting an iteration step lamada and a regularization coefficient Obtaining a new series of control rates through a backward pass (forward pass) of the model, calculating a new state quantity according to the control rates, calculating a new J_new value, and if the new J_new value is greater than or equal to J_old, increasing a regularization coefficient appropriately to enable J_old=J_new, and repeatedly executing the backward pass and the forward pass; if the NEW value of j_new is smaller than j_old, updating the state space sequence, the action space sequence and the objective function value, so that x=x_new, u=u_new, j_old=j_new, (x_new, u_new represent the NEW state space sequence and the action space sequence calculated through NEW circulation), increasing the regularization coefficient, and then judging whether the absolute value difference of j_old-j_new is smaller than a preset difference tol, and if so, outputting the action sequence and the state sequence; if not, repeating the backward pushing method and the forward pushing method. The specific algorithm flow is shown in fig. 3.
In a second aspect of the embodiment of the present invention, a vehicle controller is provided, where the hybrid vehicle is controlled in real time by using the method for controlling energy of the hybrid vehicle in real time according to the first aspect of the embodiment of the present invention.
In a third aspect of the embodiment of the present invention, a hybrid vehicle is provided, including the vehicle controller according to the second aspect of the embodiment of the present invention.
While the fundamental and principal features of the invention and advantages of the invention have been shown and described, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but may be embodied in other specific forms without departing from the spirit or essential characteristics thereof;
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (9)
1. The method for controlling the energy of the hybrid electric vehicle in real time is characterized by comprising the following steps:
s1, training a dual-delay depth deterministic strategy gradient neural network model to obtain an optimal reference speed planning model; constructing a state space by the dual-delay depth deterministic strategy gradient neural network model according to the current road slope of the own vehicle, the charge state of the battery of the own vehicle, the speed of the own vehicle, the relative distance between the own vehicle and the front vehicle, the acceleration of the front vehicle and the speed of the front vehicle, and constructing an action space by the acceleration of the own vehicle; the rewarding function is constructed by an own vehicle oil consumption and electricity consumption assembly energy consumption rewarding function, an own vehicle and front vehicle relative distance energy consumption rewarding function, an own vehicle speed energy consumption rewarding function and a front vehicle speed energy consumption rewarding function; after training, taking an Actor target network as an optimal reference speed planning model;
s2, inputting data based on a real-time model acquired by an intelligent traffic system and/or a vehicle networking, inputting an optimal reference speed planning model for processing, and obtaining an optimal reference speed sequence at each moment of the vehicle in a future period of time;
S3, calculating total required torque of the vehicle at each moment in a future period of time based on the optimal reference speed sequence to obtain a total required torque sequence;
S4, determining an engine torque sequence and a motor torque sequence of the vehicle based on the total required torque sequence and with minimum vehicle energy consumption as a target; wherein the sum of the engine torque and the motor torque at each moment in time of the vehicle in the future is equal to the total torque required;
s5, controlling the vehicle based on an engine torque sequence and a motor torque sequence of the vehicle;
the expression of the dual-delay depth deterministic strategy gradient neural network model is as follows:
,
wherein S represents a state space, A represents an action space, and R represents a reward function;
Representing the state of charge of a battery of a self-vehicle at the current moment,/> Representing the gradient of the current road surface where the own vehicle is located at the current moment,/>Representing the relative distance between the own vehicle and the front vehicle at the current moment,/>Indicating the acceleration of the front vehicle at the current moment,Representing the speed of the front vehicle at the current moment,/>Representing the speed of the vehicle at the current moment;
Representing the self-vehicle acceleration at the current moment;
weight factor representing energy consumption rewarding function of own vehicle fuel consumption and electricity consumption assembly in unit time,/> Weight factor representing energy consumption rewarding function of relative distance between own vehicle and front vehicle,/>, and method for generating weight factorWeight factor representing energy consumption rewarding function of speed of bicycle in unit time,/>Weight factor representing a preceding vehicle speed energy consumption rewarding function per unit time,/>Is the energy consumption rewarding function of the own vehicle oil consumption and electricity consumption assembly in unit time,/>Is the energy consumption rewarding function of the relative distance between the own vehicle and the front vehicle in unit time,Is a speed energy consumption rewarding function of a vehicle per unit time,/>Is a function of the energy consumption rewarding of the speed of the front vehicle in unit time.
2. The method for controlling energy of a hybrid vehicle according to claim 1, wherein the unit time is a cost-effective energy consumption reward function of the own vehicle fuel consumption and electricity consumption assemblyThe total sum of the fuel consumption and the electricity consumption of the own vehicle in a unit time step.
3. The method for controlling energy of a hybrid vehicle according to claim 2, wherein the energy consumption reward function of the relative distance between the vehicle and the preceding vehicle in unit timeThe expression of (2) is as follows:
,
In the method, in the process of the invention, ,/>Respectively represent the maximum relative distance and the minimum relative distance between the front vehicle and the own vehicle,/>Representing an exponential function.
4. A method for controlling energy of a hybrid vehicle in real time according to claim 3, wherein the vehicle speed per unit time is an energy consumption rewarding functionThe expression of (2) is as follows:
,
In the method, in the process of the invention, ,/>Representing the maximum and minimum speeds that can be reached by the vehicle, respectively.
5. The method for controlling energy of a hybrid vehicle in real time according to claim 4, wherein the speed of the vehicle in a unit time is a power consumption rewarding functionThe expression of (2) is as follows:
。
6. The method according to claim 1, wherein in step S3, based on the optimal reference speed sequence, the total required torque at each time in a future period of time of the vehicle is calculated to obtain a total required torque sequence, including:
The own vehicle obtains a speed difference sequence according to the speed difference value of the optimal reference speed of each future moment and the vehicle speed obtained by predicting traffic conditions of the own vehicle;
based on the speed difference in the speed difference sequence, outputting total required torque at each moment in a future period from a PI driver model in the vehicle to form a total required torque sequence.
7. The method according to claim 1, wherein in step S4, the engine torque sequence and the motor torque sequence of the vehicle are determined based on the total required torque sequence with minimum vehicle energy consumption as a target, and the following cost function control is adopted to implement:
,
,/>,
In the method, in the process of the invention, For instantaneous fuel consumption of engine,/>Is equivalent factor/>For the sequence of engine torques,For motor torque of vehicle,/>Is the heat value of gasoline,/>Representing the power cell's electrical quantity value at the initial moment of the cycle,For engine torque sequences over a period of time in the future,/>Representing an optimized objective function,/>Representing a cost function.
8. A vehicle controller, characterized in that the hybrid vehicle is controlled in real time by using the hybrid vehicle energy real-time control method according to any one of claims 1 to 7.
9. A hybrid vehicle comprising the vehicle controller of claim 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410398059.4A CN117984983B (en) | 2024-04-03 | 2024-04-03 | Hybrid vehicle energy real-time control method, vehicle controller and hybrid vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410398059.4A CN117984983B (en) | 2024-04-03 | 2024-04-03 | Hybrid vehicle energy real-time control method, vehicle controller and hybrid vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117984983A CN117984983A (en) | 2024-05-07 |
CN117984983B true CN117984983B (en) | 2024-06-21 |
Family
ID=90891385
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410398059.4A Active CN117984983B (en) | 2024-04-03 | 2024-04-03 | Hybrid vehicle energy real-time control method, vehicle controller and hybrid vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117984983B (en) |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113525396A (en) * | 2021-08-13 | 2021-10-22 | 北京理工大学 | Hybrid electric vehicle layered prediction energy management method integrating deep reinforcement learning |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023096968A1 (en) * | 2021-11-23 | 2023-06-01 | Strong Force Tp Portfolio 2022, Llc | Intelligent transportation methods and systems |
CN114287193B (en) * | 2022-01-14 | 2023-04-14 | 中国水稻研究所 | Straw returning method suitable for northern cold areas |
CN114969982A (en) * | 2022-06-14 | 2022-08-30 | 南京航空航天大学 | Fuel cell automobile deep reinforcement learning energy management method based on strategy migration |
CN117485318A (en) * | 2022-07-28 | 2024-02-02 | 乾碳国际公司 | Intelligent multimode hybrid assembly and intelligent network-connected electric heavy truck |
CN115495997B (en) * | 2022-10-28 | 2024-01-30 | 东南大学 | New energy automobile ecological driving method based on heterogeneous multi-agent deep reinforcement learning |
CN116811836A (en) * | 2023-05-16 | 2023-09-29 | 昆明理工大学 | Plug-in hybrid electric vehicle energy management method based on double-delay Q learning |
CN116461391A (en) * | 2023-06-06 | 2023-07-21 | 东南大学 | Energy management method for fuel cell hybrid electric vehicle |
CN117131606A (en) * | 2023-10-17 | 2023-11-28 | 北京理工大学 | Hybrid power tracked vehicle energy management method capable of transferring across motion dimension |
-
2024
- 2024-04-03 CN CN202410398059.4A patent/CN117984983B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113525396A (en) * | 2021-08-13 | 2021-10-22 | 北京理工大学 | Hybrid electric vehicle layered prediction energy management method integrating deep reinforcement learning |
Non-Patent Citations (1)
Title |
---|
融合类人驾驶行为的无人驾驶深度强化学习方法;吕迪;徐坤;李慧云;潘仲鸣;;集成技术;20200915(05);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117984983A (en) | 2024-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Salmasi | Control strategies for hybrid electric vehicles: Evolution, classification, comparison, and future trends | |
CN102729987B (en) | Hybrid bus energy management method | |
Liu et al. | Rule-corrected energy management strategy for hybrid electric vehicles based on operation-mode prediction | |
Sarvaiya et al. | Comparative analysis of hybrid vehicle energy management strategies with optimization of fuel economy and battery life | |
CN112810504B (en) | Fuel cell automobile energy management method based on nonlinear prediction model control | |
CN109591659B (en) | Intelligent learning pure electric vehicle energy management control method | |
Huo et al. | Lifespan-consciousness and minimum-consumption coupled energy management strategy for fuel cell hybrid vehicles via deep reinforcement learning | |
Liu et al. | Cooperative optimization of velocity planning and energy management for connected plug-in hybrid electric vehicles | |
WO2021159660A1 (en) | Energy management method and system for hybrid vehicle | |
CN112590760B (en) | Double-motor hybrid electric vehicle energy management system considering mode switching frequency | |
Wang et al. | Control rules extraction and parameters optimization of energy management for bus series-parallel AMT hybrid powertrain | |
CN112319462B (en) | Energy management method for plug-in hybrid electric vehicle | |
CN110509914B (en) | Energy consumption optimization method for parallel hybrid electric vehicle | |
CN111456860A (en) | Online learning method for optimal operation line of series-parallel hybrid electric vehicle engine | |
CN112498334B (en) | Robust energy management method and system for intelligent network-connected hybrid electric vehicle | |
Zhou et al. | A two-term energy management strategy of hybrid electric vehicles for power distribution and gear selection with intelligent state-of-charge reference | |
CN113104023A (en) | Distributed MPC (Multi-media control protocol) network-connected hybrid electric vehicle energy management system and method | |
CN113928182B (en) | Battery thermal management optimization system of hybrid electric vehicle based on global traffic information | |
Pan et al. | Optimal rule extraction-based real-time energy management strategy for series-parallel hybrid electric vehicles | |
Yang et al. | Variable optimization domain-based cooperative energy management strategy for connected plug-in hybrid electric vehicles | |
Yu et al. | Integrated energy and thermal management strategy for extended range electric vehicle based on battery temperature and state-of-charge global planning | |
Huang et al. | A novel data-driven energy management strategy for fuel cell hybrid electric bus based on improved twin delayed deep deterministic policy gradient algorithm | |
Hai et al. | Deep learning-based prediction of lithium-ion batteries state of charge for electric vehicles in standard driving cycle | |
Liu et al. | Computationally efficient energy management for a parallel hybrid electric vehicle using adaptive dynamic programming | |
CN117984983B (en) | Hybrid vehicle energy real-time control method, vehicle controller and hybrid vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |