CN110936949A

CN110936949A - Energy control method, equipment, storage medium and device based on driving condition

Info

Publication number: CN110936949A
Application number: CN201911280471.1A
Authority: CN
Inventors: 石大排; 刘康杰; 刘瑞军; 向立明; 郭建华; 景文倩; 张远进
Original assignee: Hubei University of Arts and Science
Current assignee: Hubei University of Arts and Science
Priority date: 2019-12-12
Filing date: 2019-12-12
Publication date: 2020-03-31
Anticipated expiration: 2039-12-12
Also published as: CN110936949B

Abstract

The invention relates to the technical field of hybrid electric vehicles, and discloses an energy control method, equipment, a storage medium and a device based on a driving condition. The method comprises the steps of acquiring current running characteristic information of the hybrid electric vehicle; analyzing the current running characteristic information to obtain running condition category information; determining a preset target relation function according to the driving condition category information; searching a corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relation function; and determining the use proportion information of an engine and a motor in the hybrid electric vehicle according to the target equivalent factor, and realizing the control of the energy of the hybrid electric vehicle according to the use proportion information, so that the target equivalent factor is used for real-time adjustment according to different driving conditions, the instantaneous and global optimization of energy management is realized, and the energy-saving potential of the PHEV is fully exerted.

Description

Energy control method, equipment, storage medium and device based on driving condition

Technical Field

The invention relates to the technical field of hybrid electric vehicles, in particular to an energy control method, equipment, a storage medium and a device based on a driving condition.

Background

At present, a Plug-in Hybrid Electric Vehicle (PHEV) energy management strategy includes a Rule-based threshold control strategy (RB), which is designed mainly according to engineering experience Of a designer and operating characteristics Of each key power component, and a working process Of the strategy is to divide a Hybrid power system into working modes according to a series Of fixed thresholds according to a plurality Of control variables such as a steady-State efficiency Map Of each key power component, a current Vehicle speed and an accelerator pedal opening, and a remaining battery capacity (State Of Charge, SOC) value Of a power battery. The strategy has the advantages of simple design, fast reaction, good robustness and the like. However, the control threshold of the RB strategy is often a fixed set of thresholds, and the adaptability to the operating condition is poor, which may cause the battery power to "consume light" in advance, or the battery power is not used completely at the end of the trip, and both of these two cases may increase the fuel consumption of the parallel PHEV and deteriorate the fuel economy.

At present, many scholars propose a PHEV energy consumption strategy based on an optimal control theory, such as a Dynamic Programming algorithm (DP) of global optimization and a pointryagin's minimum principal, PMP, and the like, the DP control strategy mainly obtains a global optimal solution for power system control on the premise of a known driving condition, but a large amount of calculation and long solution time are required, so that the DP control strategy cannot be directly used in real-time control, the PMP algorithm belongs to an instantaneous optimal control algorithm, instantaneous optimization can be realized, but the working condition is not globally optimal when changed.

The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.

Disclosure of Invention

The invention mainly aims to provide an energy control method, equipment, a storage medium and a device based on driving conditions, and aims to provide an instantaneous and global optimal control strategy for energy management, so that the performance of an automobile is improved.

In order to achieve the above object, the present invention provides an energy control method based on driving conditions, comprising the steps of:

acquiring current running characteristic information of the hybrid electric vehicle;

analyzing the current running characteristic information to obtain running condition category information;

determining a preset target relation function according to the driving condition category information;

searching a corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relation function;

and determining the use proportion information of an engine and a motor in the hybrid electric vehicle according to the target equivalent factor, and controlling the energy of the hybrid electric vehicle according to the use proportion information.

Preferably, the acquiring of the current running characteristic information of the hybrid vehicle includes:

acquiring current driving data of the hybrid electric vehicle;

obtaining current driving parameter information according to the current driving data;

segmenting the current driving data according to the current driving parameter information to obtain current driving fragment information;

and taking the current running parameter information in the current running section information as the current running characteristic information.

Preferably, the analyzing the current driving characteristic information to obtain the driving condition type information includes:

carrying out normalization processing on the current driving characteristic information to obtain target driving characteristic information;

identifying the target running characteristic information by adopting a working condition type identification model to obtain running working condition coding information;

obtaining corresponding running condition type information according to the running condition coding information;

correspondingly, before the target driving characteristic information is identified by adopting the working condition type identification model to obtain the driving condition coding information, the method further comprises the following steps:

acquiring historical driving characteristic information, and dividing an initial clustering center according to the historical driving characteristic information;

respectively calculating distance information from the historical driving feature information to the initial clustering center;

dividing the historical driving feature information according to the distance information to obtain corresponding reference clusters;

dividing the reference cluster according to average value information of historical driving feature information in the reference cluster to obtain a target cluster;

when the target cluster center corresponding to the target cluster meets a preset condition, obtaining running condition coding information of historical running characteristic information according to the target cluster;

generating historical driving feature vector information from the historical driving feature information;

training through a preset neural network model according to the historical driving feature vector information and the corresponding driving condition coding information to obtain a working condition type recognition model.

Preferably, the determining a preset target relationship function according to the driving condition category information includes:

acquiring the required torque of a motor and the current state of charge information of a power battery;

establishing an instantaneous change value function of the state of charge of the power battery according to the motor demand torque and the current state of charge information of the power battery, and establishing an instantaneous fuel consumption function of the engine according to the motor demand torque;

establishing an instantaneous Hamilton function according to the instantaneous change value function of the state of charge of the power battery, the instantaneous fuel consumption function of the engine and the current equivalent factor function;

and obtaining a preset target relation function among the torque instantaneously required by the whole vehicle, the optimal distribution torque of the engine and the optimal distribution torque of the motor according to the instantaneous Hamilton function and the type information of the running conditions.

Preferably, before searching for the corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relationship function, the method further includes:

acquiring the instantaneous fuel consumption of a historical engine, and acquiring historical fitness function information according to the instantaneous fuel consumption of the historical engine;

acquiring historical driving condition information, the charge state information of a historical power battery, a preset range of an equivalent factor and genetic iteration frequency information;

obtaining equivalent factor information corresponding to target fitness function information in the historical fitness function information through a preset genetic algorithm according to the historical driving condition information, the charge state information of the historical power battery, the preset range of the equivalent factor and the genetic iteration frequency information;

and establishing a preset equivalent factor comparison table according to the equivalent factor information.

Preferably, before acquiring the historical driving condition information, the state of charge information of the historical power battery, the preset range of the equivalent factor and the information of the number of genetic iterations, the method further includes:

acquiring historical driving mileage and average vehicle speed information, and searching a preset charge state offset table according to the historical driving mileage and the average vehicle speed information to determine target charge state offset information;

acquiring initial charge state information, and acquiring the charge state information of a historical power battery according to the initial charge state information and target charge state offset information;

correspondingly, before the historical driving mileage and the average vehicle speed information are acquired, and the preset state of charge offset table is searched according to the historical driving mileage and the average vehicle speed information to determine the target state of charge offset information, the method further comprises the following steps:

selecting historical combined working condition information, and obtaining change path information of the state of charge according to the historical combined working condition information;

respectively obtaining historical offset information of each working condition according to the changed path information;

determining corresponding historical driving mileage information and average vehicle speed information according to the historical offset information;

and establishing a preset state of charge deviation table according to the historical deviation information, the historical mileage information and the average speed information.

Preferably, before the determining the usage proportion of the engine and the motor in the hybrid vehicle according to the target equivalence factor, the method further comprises:

acquiring current state-of-charge information and reference state-of-charge information of a power battery;

obtaining a power battery punishment factor according to the current state of charge information and the reference state of charge information;

acquiring current vehicle speed information and average vehicle speed information;

obtaining a speed penalty factor according to the current speed information and the average speed information;

and adjusting the current equivalent factor according to the power battery penalty factor and the speed penalty factor to obtain a target equivalent factor.

In addition, to achieve the above object, the present invention also provides a running condition-based energy control apparatus including: the energy control method comprises a memory, a processor and an energy control program stored on the memory and capable of running based on the running condition on the processor, wherein the energy control program based on the running condition realizes the steps of the energy control method based on the running condition when being executed by the processor.

In addition, to achieve the above object, the present invention further provides a storage medium having an energy control program based on driving conditions stored thereon, wherein the energy control program based on driving conditions, when executed by a processor, implements the steps of the energy control method based on driving conditions as described above.

In addition, in order to achieve the above object, the present invention further provides an energy control device based on a driving condition, including:

the acquisition module is used for acquiring the current running characteristic information of the hybrid electric vehicle;

the analysis module is used for analyzing the current running characteristic information to obtain running condition type information;

the determining module is used for determining a preset target relation function according to the driving condition category information;

the searching module is used for searching a corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relation function;

and the control module is used for determining the use proportion information of an engine and a motor in the hybrid electric vehicle according to the target equivalent factor and realizing the control of the energy of the hybrid electric vehicle according to the use proportion information.

According to the technical scheme provided by the invention, the current running characteristic information of the hybrid electric vehicle is obtained; analyzing the current running characteristic information to obtain running condition category information; determining a preset target relation function according to the driving condition category information; searching a corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relation function; and determining the use proportion information of an engine and a motor in the hybrid electric vehicle according to the target equivalent factor, and realizing the control of the energy of the hybrid electric vehicle according to the use proportion information, so that the target equivalent factor is used for real-time adjustment according to different driving conditions, the instantaneous and global optimization of energy management is realized, and the energy-saving potential of the PHEV is fully exerted.

Drawings

Fig. 1 is a schematic structural diagram of a gateway device in a hardware operating environment according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a first embodiment of an energy control method based on driving conditions according to the present invention;

FIG. 3 is a block diagram of a power system of a parallel PHEV according to an embodiment of the energy control method based on driving conditions;

FIG. 4 is a block diagram of a PHEV adaptive control strategy architecture based on driving condition recognition according to an embodiment of the energy control method based on driving conditions;

FIG. 5 is a flowchart illustrating a second embodiment of a driving condition based energy control method according to the present invention;

FIG. 6 is a schematic flow chart of a third embodiment of an energy control method based on driving conditions according to the present invention;

FIG. 7 is a schematic flow chart of Hamilton function solution according to an embodiment of the energy control method based on driving conditions of the present invention;

FIG. 8 is a three-dimensional MAP graph of HWFET driving condition equivalence factors for one embodiment of a driving condition-based energy control method of the present invention;

FIG. 9 is a three-dimensional MAP graph of NurembergR36 driving condition equivalent factors according to an embodiment of the driving condition-based energy control method of the present invention;

FIG. 10 is a three-dimensional MAP of NYCC driving condition equivalent factors according to an embodiment of the driving condition-based energy control method of the present invention;

FIG. 11 is a three-dimensional MAP graph of the US06 driving condition equivalent factor of an embodiment of the driving condition-based energy control method of the present invention;

FIG. 12 is a schematic diagram of a variation curve of the SOC of the power battery and a reference SOC according to an embodiment of the energy control method based on the driving condition;

fig. 13 is a block diagram showing the configuration of the first embodiment of the energy control apparatus according to the present invention.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to fig. 1, fig. 1 is a schematic structural diagram of a driving condition-based energy control device of a hardware operating environment according to an embodiment of the present invention.

As shown in fig. 1, the driving condition-based energy control apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), the optional user interface 1003 may also include a standard wired interface and a wireless interface, and the wired interface of the user interface 1003 may be a Universal Serial Bus (USB) interface in the present invention. The network interface 1004 may optionally include a standard wired interface as well as a wireless interface (e.g., WI-FI interface). The Memory 1005 may be a high speed Random Access Memory (RAM); or a stable Memory, such as a Non-volatile Memory (Non-volatile Memory), and may be a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.

Those skilled in the art will appreciate that the configuration shown in FIG. 1 does not constitute a limitation of a driving-condition-based energy control apparatus, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.

As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a driving condition-based energy control program.

In the energy control device based on the driving condition shown in fig. 1, the network interface 1004 is mainly used for connecting a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting peripheral equipment; the energy control device based on the driving condition calls an energy control program based on the driving condition stored in the memory 1005 through the processor 1001 and executes the energy control method based on the driving condition provided by the embodiment of the invention.

Based on the hardware structure, the embodiment of the energy control method based on the driving condition is provided.

Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the energy control method based on the driving condition according to the present invention.

In a first embodiment, the energy control method based on the driving condition comprises the following steps:

step S10: and acquiring the current running characteristic information of the hybrid electric vehicle.

It should be noted that, an execution main body of the embodiment is an energy control device based on a driving condition, and may also be other devices that can achieve the same or similar functions, such as a hybrid electric vehicle, which is not limited in this embodiment, in the embodiment, a parallel configuration PHEV is taken as an example for description, as shown in a structural block diagram of a power system of the parallel configuration PHEV shown in fig. 3, the PHEV in the embodiment adopts a coaxial parallel structure, in which a motor is coaxially installed on an input shaft of an automatic transmission, an engine and the motor can drive the vehicle to run separately or together, a battery can be charged by an external charger, fig. 4 is a structural block diagram of a PHEV adaptive control strategy based on driving condition recognition, the PHEV adaptive control strategy based on driving condition recognition includes a condition information acquisition module, after a driver inputs a destination in a vehicle-mounted navigation system, the vehicle-mounted navigation system plans a driving route, and obtaining the trip working condition information and the total trip mileage of the vehicle, then obtaining the road traffic state by the intelligent transportation system according to the trip route, and establishing a vehicle driving history database by recording the vehicle driving information.

The characteristic parameter calculation module is configured to process the operating condition information to obtain characteristic parameters of the operating condition information, that is, the maximum speed, the maximum acceleration, the average acceleration, and the average deceleration, and may further include other parameter information, which is not limited in this embodiment.

And the driving condition identification module is used for providing parameters for the equivalent factor calculation module, inputting the driving mileage and the initial residual electric quantity of the power battery into the equivalent factor calculation module according to the driving mileage and the initial residual electric quantity of the power battery obtained by the self-adaptive energy control module to obtain a target equivalent factor, obtaining a reference SOC following module according to the vehicle speed, the driven mileage and the actual SOC, and obtaining a corrected oil-electricity equivalent factor according to the reference SOC following module.

It should be noted that, when the battery is full, the PHEV is in a Charge Depletion (CD) mode, and the vehicle is mainly driven by the motor, so that the PHEV has the advantages of low oil consumption and low emission; when the battery capacity is low, the PHEV is in a Charge Sustaining mode (CS), the engine is used as a main power source to drive the vehicle, the driving range is the same as that of a traditional automobile and an HEV, the PHEV comprises brake control and drive control, the brake control comprises mechanical brake and regenerative brake, the drive control comprises a CD mode and a CS mode, so that an optimal motor and engine torque distribution scheme is obtained, wherein the distribution comprises a transmitter required torque, a motor required torque, an engine switch command, a motor switch command and a mechanical brake required pressure to perform an underlying controller, and the vehicle speed, the engine torque and rotating speed, the motor torque and rotating speed, the power battery, the brake pedal opening, the accelerator pedal opening, the gear speed ratio and the clutch state are monitored through a vehicle state information processing module.

Step S20: and analyzing the current running characteristic information to obtain running condition category information.

It should be noted that the traveling condition category information includes a congestion condition, an urban condition, a suburban condition, a high-speed condition, and the like, and may also include other types of conditions.

Step S30: and determining a preset target relation function according to the driving condition category information.

It can be understood that the preset target relation function is a relation between the instantaneous equivalent fuel consumption rate of the PHEV at the time t and the fuel consumption of the engine and the fuel consumption when the instantaneous consumed electric quantity of the motor is equivalent to the consumed fuel quantity.

Step S40: and searching a corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relation function.

In specific implementation, firstly, checking the SOC value of the power battery and determining the driving mileage of the vehicle; secondly, solving an optimal cooperative state value of a Hamilton function under a driving condition by using an offline control optimization method and a genetic optimization algorithm, and establishing an equivalent factor MAP (MAP) under different SOC initial values and driving mileage conditions; then, the intelligent running condition recognizer recognizes the current working condition, selects a proper equivalent factor MAP, calculates the equivalent factor of the vehicle under the actual running working condition by using an interpolation method, and distributes the power output of the engine and the motor according to an ECMS energy control strategy to achieve the purpose of reducing the fuel consumption of the whole vehicle.

Step S50: and determining the use proportion information of an engine and a motor in the hybrid electric vehicle according to the target equivalent factor, and realizing the control of the energy of the hybrid electric vehicle according to the use proportion information.

According to the scheme, the current running characteristic information of the hybrid electric vehicle is obtained; analyzing the current running characteristic information to obtain running condition category information; determining a preset target relation function according to the driving condition category information; searching a corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relation function; and determining the use proportion information of an engine and a motor in the hybrid electric vehicle according to the target equivalent factor, and realizing the control of the energy of the hybrid electric vehicle according to the use proportion information, so that the target equivalent factor is used for real-time adjustment according to different driving conditions, the instantaneous and global optimization of energy management is realized, and the energy-saving potential of the PHEV is fully exerted.

Referring to fig. 5, fig. 5 is a flowchart illustrating a second embodiment of the energy control method based on driving conditions according to the present invention, and the second embodiment of the energy control method based on driving conditions according to the present invention is provided based on the first embodiment shown in fig. 2.

In the second embodiment, the step S10 includes:

step S101, acquiring current running data of the hybrid electric vehicle.

And step S102, obtaining current running parameter information according to the current running data.

It should be noted that the current driving parameter information includes information that the vehicle driving speed is ν, the acceleration is α, the absolute value of the acceleration is | α |, and other information<1km/h&|α|<0.1m/s²The vehicle running process is expressed as an idling state, and v is not equal to 0&α>0.1m/s²The running process of the vehicle is expressed as an acceleration state, v is>1km/h&|α|≤0.1m/s²The running process of the vehicle is expressed as a constant speed state, and v is not equal to 0&α≤-0.1m/s²Is indicated as a decelerating state.

And step S103, segmenting the current driving data according to the current driving parameter information to obtain current driving fragment information.

In this embodiment, the vehicle driving data is automatically cut into micro-travel segments, and the micro-travel segments are automatically cut according to the above state by importing a mat file recording the driving speed and time of the vehicle, and then the cut micro-travel segments are sorted and stored in a newly-built mat file, so that 1020 micro-travel segments are cut out in total.

And step S104, taking the current running parameter information in the current running section information as the current running characteristic information.

In a specific embodiment, the maximum driving speed v of the vehicle in the kinematic segment_maxComprises the following steps:

ν_max＝max{ν_i,i＝1,2,3,...,k}； (1)

in the above formula, v_iRepresenting the current speed, k is the number of sample points in km/h of non-0 vehicle speed over a certain period of time.

In the embodiment, the vehicle running recorder is adopted to acquire the speed and time of the running condition to obtain the acceleration characteristic value. Because the frequency of collecting the driving condition is set to be 5Hz, the acceleration of the driving condition is obtained through deduction:

in the above formula, acceleration α_i,i+1Is the acceleration value of the running condition from the ith point to the (i + 1) th point, and the unit is m/s²；v_iAnd v_i+1Respectively the driving speed values of the ith second and the (i + 1) th second in the driving working condition in the unit of km/h; t is t_iAnd t_i+1Respectively at the moment of collecting a sample point of the non-0 vehicle speed, and the unit is s; k is the number of sample points at a vehicle speed other than 0 for a certain period of time.

In the kinematic segment, the maximum acceleration α_maxComprises the following steps:

α_max＝max{α₁，α₂，...，α_i，i＝1,2,3,..k}； (3)

in the above formula, α₁，α₂，...，α_iRespectively the vehicle acceleration at each acquisition point during a sampling period; k is the number of sample points at a vehicle speed other than 0 for a certain period of time.

In the kinematic segment, the maximum deceleration α of the vehicle travel_min；

α_min＝min{α₁，α₂，...，α_i，i＝1,2,3,..k}； (4)

In the kinematic segment, the average acceleration α of all the running vehicles during the sampling time_{acc_avg}：

In the kinematic segment, the average α of the negative accelerations of all the running vehicles over the sampling time_{dcc_avg}；

In the above formula, the unit of each acceleration is m/s²。

The characteristic parameters of the driving conditions can be calculated through the formula, and the characteristic parameters of a certain kinematic segment are calculated. Table 1 shows the data of the characteristic parameters of a certain kinematic segment in the collection experiment.

TABLE 1

Further, the step S20 includes:

carrying out normalization processing on the current driving characteristic information to obtain target driving characteristic information; identifying the target running characteristic information by adopting a working condition type identification model to obtain running working condition coding information; and obtaining corresponding running condition type information according to the running condition coding information.

It should be noted that the working condition type identification model may be a Back Propagation (BP) neural network identification model, and the working condition identification module firstly imports driving working condition data; calculating corresponding characteristic parameters through a characteristic parameter calculation module; then inputting the characteristic parameters of the driving working condition into a BP neural network identification model; and finally, identifying the type of the current running working condition of the vehicle through a BP neural network identification module.

acquiring historical driving characteristic information, and dividing an initial clustering center according to the historical driving characteristic information; respectively calculating distance information from the historical driving feature information to the initial clustering center; dividing the historical driving feature information according to the distance information to obtain corresponding reference clusters; dividing the reference cluster according to average value information of historical driving feature information in the reference cluster to obtain a target cluster; when the target cluster center corresponding to the target cluster meets a preset condition, obtaining running condition coding information of historical running characteristic information according to the target cluster; generating historical driving feature vector information from the historical driving feature information; training through a preset neural network model according to the historical driving feature vector information and the corresponding driving condition coding information to obtain a working condition type recognition model.

In the specific implementation, n sample data are selected, 4 characteristic parameters corresponding to each sample are solved, and k initial clustering centers (z) are selected according to k classes of division₁,z₂,z₃,...z_k) And calculating Euclidean distances between each characteristic parameter and each cluster center according to a formula, and dividing the characteristic parameter closest to the cluster center into own cluster clusters.

The specific calculation formula of the Euclidean distance is as follows:

in the above formula, P (i, j) represents the Euclidean distance, x_imThe m characteristic parameter value of the ith sample; x is the number of_jmAnd calculating the average value of all samples in each cluster for the mth characteristic parameter value of the jth sample, taking the average value of the samples as a new clustering center of the cluster, and continuously performing iterative calculation until the clustering center is not changed, thereby obtaining the working condition type identification model.

It should be noted that the working condition classes include a first class, a second class, a third class and a fourth class, the first class is congestion working condition including CBDTRUCK, MANHATTAN and NYCC, the second class is city working condition including JPN1015, ARTERIAL, numberr 36WVUCITY and WVUSUB, the third class is fast working condition including FTP, UDDS, communicator, SC03, NYCCOMP, HWFET, LA92 and WVUINTER, and the fourth class is high speed working condition including ARB02, ECE _ EUDC, HL07, NEDC and US 06.

In the embodiment, the accuracy of the BP neural network identification is mainly influenced by the training algebra, the learning rate and the number of training samples. In order to obtain a suitable training sample, the embodiment respectively generates 100 sample sets for each type of driving condition in 120s duration, there are 400 driving condition information in total, then calculates 400 sets of characteristic parameters of the driving condition information, and performs normalization processing on the characteristic parameters, because the selected driving condition characteristic parameters are 4, the input of the neural network is 4, the output is 4 type numbers representing typical driving conditions, the number "1" represents the working condition congestion, the number "2" represents the urban working condition, the number "3" represents the suburban working condition, and the number "4" represents the high-speed working condition.

In order to create the BP neural network, after sample data of training is prepared, the characteristic parameters of 400 groups of driving condition samples are calculated, a vector form of 400x4 is used as input, the BP neural network is created by using a newff function, the BP neural network established in the last step is trained by using a train function, and the trained BP neural network is stored in a Simulink module form by using a genim function. And establishing a corresponding characteristic parameter calculation module in Simulink, connecting the characteristic parameter calculation module with a BP neural network module, and finally establishing an intelligent driving condition identification model.

According to the scheme, the characteristic parameters of the running working condition are input into the BP neural network identification module, and the type of the current running working condition of the vehicle is identified through the BP neural network identification module, so that the type of the working condition is accurately identified.

Referring to fig. 6, fig. 6 is a flow chart illustrating a third embodiment of the energy control method based on driving conditions according to the present invention, and the third embodiment of the energy control method based on driving conditions according to the present invention is proposed based on the first embodiment or the second embodiment, and in this embodiment, explained based on the first embodiment,

in the third embodiment, the step S30 includes:

step S301, obtaining the torque required by the motor and the current state of charge information of the power battery.

In an ECMS energy control strategy, an equivalent fuel consumption factor determines the fuel-electricity conversion efficiency of a power system of the PHEV, and the fuel economy of the whole vehicle is controlled. Because the electric energy consumed by the vehicle is converted into fuel consumption through a certain coefficient, the instantaneous equivalent fuel consumption rate of the PHEV at the time t is as follows:

in the above formula, the first and second carbon atoms are,

is the instantaneous fuel consumption of the engine;

the instantaneous electricity consumption for the motor is equivalent to the fuel consumption.

According to the PMP control theory and the ECMS energy control thought, an ECMS optimization energy control objective function is established, and the expression is as follows:

in the process of solving the energy control optimization problem offline by using the PMP control strategy, the variation amplitude of the cooperative state variable is very small, and the cooperative state variable can be regarded as a constant, that is:

and step S302, establishing a transient variation value function of the charge state of the power battery according to the motor demand torque and the current charge state information of the power battery, and establishing a transient fuel consumption function of the engine according to the motor demand torque.

And step S303, establishing an instantaneous Hamilton function according to the instantaneous change value function of the state of charge of the power battery, the instantaneous fuel consumption function of the engine and the current equivalent factor function.

The required torque of the motor is a control variable u (t), the SOC value of the power battery is a state variable x (t), and the instantaneous change value of the SOC of the power battery is f (x (t), u (t), namely

In the case of a constant equivalent factorThen, establishing a Hamiltonian of the ECMS, wherein the expression is as follows:

in the above equation, the coordinated state variable λ will be equivalent to an oil-electric equivalent factor, which is set to a constant value throughout the running condition.

The equivalence factor is constantly changing during the actual driving of the vehicle. Thus, the ECMS-based instantaneous hamiltonian can be expressed as;

and step S304, obtaining a preset target relation function among the torque instantaneously required by the whole vehicle, the optimal distribution torque of the engine and the optimal distribution torque of the motor according to the instantaneous Hamilton function and the type information of the running condition.

Under the condition that the required torque of the whole vehicle is known, the optimal output torque of the motor is calculated according to the relation among the engine, the motor and the total required torque

And the sequence is that the optimal output torque of the engine is obtained as follows:

in the above formula, T_req(t)、

The torque required by the whole vehicle instantaneously, the optimal distribution torque of the engine and the optimal distribution torque of the motor are respectively.

The method comprises the steps of calculating the required torque and the rotating speed of the whole vehicle at any moment, solving the output torque combinations of all engines and motors under the constraint condition of meeting an objective function, calculating the equivalent fuel consumption rates of all the combinations according to a motor working efficiency characteristic diagram, an engine working efficiency characteristic diagram and a fuel consumption MAP, selecting control variables to enable the engines to work in a high efficiency region and enable the objective function to be minimum, and enabling the combinations to be the optimal power distribution of the current motors. Therefore, the hammerton function solving process is shown in fig. 7, and the specific steps are as follows:

(1) determining a range of a controlled variable

In the current PHEV driving state and the working state of each power component, the total required power T of the whole vehicle at the current moment is obtained according to the values of the parameters of the whole vehicle driving speed, the power battery SOC, the engine output power and the like_req(t), the range of the cooperative control variable is: [ u ] of_min(t),u_max(t)]

T_m(t)＝T_m,nmax:ΔT:T_m,pmax(14)

In the above formula, T_m,nmaxThe maximum generating torque which can be achieved by the current motor is obtained; delta T is the step length of the motor control variable; t is_m,pmaxThe maximum driving torque which can be output by the motor at present.

When the motor is used as a generator, the torque of the motor is as follows:

in the above formula, T_bat,chamaxThe maximum power generation torque allowed by the power battery under the current SOC; t is_m,chamaxThe maximum allowable generating torque of the motor at the current rotating speed; t is_emax(w_e) The maximum charging torque provided by the motor at the current rotating speed is provided.

When the motor is used as a motor, the maximum output torque is as follows:

in the above formula, T_bat,dismaxThe maximum output torque allowed by the power battery under the current SOC; t is_m,dismaxThe maximum output torque allowed by the motor at the current required rotating speed is the maximum.

Through the above analysis, the magnitude of the corresponding engine working output torque is as follows:

(2) determining all alternative engine working points in the current total vehicle required torque and constraint conditions, and obtaining instantaneous engine fuel consumption m by combining with an engine fuel consumption MAP (MAP) table look-up_e。

(3) Calculating the equivalent oil consumption m of the power battery consumed electric energy at the current moment according to the total required torque of the whole vehicle and all the alternative motor working points by combining the equivalent factor lambda and the motor working efficiency MAP_batt。

(4) Calculating the instantaneous total oil consumption of the whole vehicle

Repeating the steps (2) and (3), and selecting the minimum instantaneous total equivalent fuel consumption at the current moment

The corresponding control variable is used as the optimal solution of the control variable at the current moment, namely the optimal output torque of the motor

Further, before the step S40, the method further includes:

acquiring the instantaneous fuel consumption of a historical engine, and acquiring historical fitness function information according to the instantaneous fuel consumption of the historical engine; acquiring historical driving condition information, the charge state information of a historical power battery, a preset range of an equivalent factor and genetic iteration frequency information; obtaining equivalent factor information corresponding to target fitness function information in the historical fitness function information through a preset genetic algorithm according to the historical driving condition information, the charge state information of the historical power battery, the preset range of the equivalent factor and the genetic iteration frequency information; and establishing a preset equivalent factor comparison table according to the equivalent factor information.

The fitness function expression of an individual is as follows:

the invention selects the HWFET running conditions of different multiples as the road condition effect of different running mileage. In the simulation experiment, HWFET driving conditions of 1 time, 2 times, 3 times, 4 times and 5 times are selected as different driving ranges, and initial SOC values of the power battery are set to 0.4, 0.5, 0.6, 0.7, 0.8 and 0.9, respectively, so that the solution of the oil-electricity equivalent factor needs to be performed under 30 conditions in total.

The process of solving the equivalent factor is explained by using a genetic calculation, wherein 5 times of WLTC is taken as a driving condition, the initial SOC value of the power battery is set to be 0.9. To increase the solving speed, an approximate range of solving equivalence factors is set to [1, 4%]And the maximum genetic iteration number is 15, thereby reducing the range of the optimized variable size of the genetic algorithm. Solving procedure based on the equivalence factor as shown in FIG. 7, by Hamiltonian

And a function u^*Solving the argminH (x (t), u (t), lambda (t) and t) to obtain the optimal output torque sequence of the engine and the motor

And

according to

Determining the final value of the equivalence factor lambda at optimum fuel consumption and emissions^*Calling the GA function and writing a genetic algorithm program, thereby calculating the equivalent factor corresponding to the minimum value of the fitness function, and obtaining a final result of-1.98 kg. At the beginning of 30 differencesThe values of the oil-electricity equivalent factors solved under the starting SOC and the driving cycle working condition are shown in Table 2. And drawing a three-dimensional MAP (MAP) graph of the equivalent factors according to the data of the table 2 by taking the initial SOC (state of charge) of the power battery and different driving mileage as an x axis and a y axis of the three-dimensional MAP graph and taking the size of the equivalent factors as a z axis, as shown in figure 8.

TABLE 2

According to the steps of solving the equivalent factors and establishing the equivalent factor MAP, corresponding equivalent factors are solved and an equivalent factor MAP is established for three other representative working conditions of NumbergR 36, NYCC and US06 respectively, so that the equivalent factors can be rapidly calculated off line. Under the three typical driving conditions, corresponding MAP MAPs are established, which are respectively shown in fig. 9, 10 and 11.

Further, before obtaining the historical driving condition information, the state of charge information of the historical power battery, the preset range of the equivalent factor and the genetic iteration number information, the method further comprises:

the energy control system can acquire information of different types of circulation conditions and traffic flow speed through the GIS and the ITS, the modulation conditions can reflect the actual condition of the road surface, the linear reference SOC can be further divided, and a broken-line reference SOC is generated, as shown in fig. 12. The city working condition of the section is divided into 3 sections of branch road-main road-secondary main road, the system identifies the driving mileage of each section, and the information such as the average speed of each section is calculated according to the modulation working condition. The calculation process is briefly described as follows:

(1) first, a straight reference SOC is generated, as indicated by the red line in the figure, anFind S₁And S₂SOC value SOC of_dref1And soc_dref2；

(2) Under the branch working condition, the motor drive is mainly adopted on the premise that the electric quantity of the battery is allowed due to the low efficiency of the engine. The ROS system tends to distribute more battery power, and determines the offset delta SOC through table lookup according to the branch driving mileage and the average speed₁Then S is₁Adjusted soc_end1Comprises the following steps:

soc_end1＝soc_drf1-Δsoc₁(19)

(3) the same process S₂And the SOC value is taken care of ensuring that the allowed electric quantity of the battery can be completely used by the end of the travel, and the charging condition does not occur in any section of urban working condition.

(1) Selecting a specific combination working condition, and simulating by adopting dynamic programming to obtain an optimal battery SOC change path;

(2) and fitting the optimal broken line reference SOC by adopting a broken line, solving the delta SOC of each section of working condition, and filling the delta SOC into a table with a fixed format according to the driving mileage and the average speed as variables.

(3) The above process is repeated to form a complete Δ SOC table. And programming according to a polygonal line reference SOC generation algorithm to realize generation of the polygonal line reference SOC.

Further, before the step S50, the method further includes:

acquiring current state-of-charge information and reference state-of-charge information of a power battery; obtaining a power battery punishment factor according to the current state of charge information and the reference state of charge information; acquiring current vehicle speed information and average vehicle speed information; obtaining a speed penalty factor according to the current speed information and the average speed information; and adjusting the current equivalent factor according to the power battery penalty factor and the speed penalty factor to obtain a target equivalent factor.

In order to make the actual SOC of the power battery move towards the reference SOC, the average speed of the whole trip mileage and the initial value lambda of the cooperative state are required to be adjusted₀Considering the entering, adding a power battery SOC penalty factor and a speed penalty factor to a correction collaborative state formula, and calculating an expression as follows:

λ(t)＝λ₀+λ(ΔSOC,t)+λ(ΔV,t) (20)

in order to realize the self-adaptation of the self-adaptive ECMS control strategy to the running condition, the equivalent factor lambda (t) value determines the use ratio of the engine and the motor of the vehicle, if the lambda (t) value is larger, the probability of using the engine of the vehicle is increased, otherwise, the motor is used more. Thus, this parameter can be used to adjust the ratio of the engine to the electric machine. From the above equation, it can be seen that the magnitude of λ (t) is determined by the difference between the actual SOC of the power battery and the reference value SOC, Δ SOC-SOC_refAnd the actual vehicle speed V and the average vehicle speed

The difference Δ V of (a) is determined by two parameters. If the vehicle runs on a congested road section, the real-time vehicle running speed is lower than the average speed of the vehicle in the whole journey, namely delta V is V_m-V>0. Therefore, the lambda (t) value is reduced, so that the motor drive is additionally used in the whole vehicle power system, the fuel economy of the whole vehicle is improved, and vice versa.

During the actual running of the vehicle, the change curve edge of the power battery SOC does not change completely according to the reference SOC curve, and as can be seen from FIG. 12The thick line represents the power battery reference SOC curve, and the thin line represents the actual power battery SOC variation curve. For example: at a vehicle running distance S₁Time, delta SOC of power battery>0, the actual SOC value at the time of power is relatively small, and the use of the motor needs to be reduced, that is, the electric quantity output of the power battery needs to be reduced. This requires an increase in the λ (t) value, which increases the use of the engine in the power system.

In addition, an embodiment of the present invention further provides a storage medium, where an energy control program based on a driving condition is stored on the storage medium, and the energy control program based on the driving condition is executed by a processor to implement the steps of the terminal network access method described above.

Since the storage medium adopts all technical solutions of all the embodiments, at least all the beneficial effects brought by the technical solutions of the embodiments are achieved, and no further description is given here.

In addition, referring to fig. 13, an embodiment of the present invention further provides an energy control device based on a driving condition, where the energy control device based on a driving condition includes:

the obtaining module 10 is used for obtaining the current running characteristic information of the hybrid electric vehicle.

In the present embodiment, a parallel-configuration PHEV is taken as an example, and as shown in the block diagram of the power system of the parallel-configuration PHEV shown in fig. 3, the PHEV in the present embodiment adopts a coaxial parallel-configuration, wherein the motor is coaxially arranged on an input shaft of the automatic transmission, the engine and the motor can drive the automobile to run independently or together, the battery can be charged by an external charger, FIG. 4 is a block diagram of a PHEV adaptive control strategy based on driving condition recognition, which includes a condition information collection module, after a driver inputs a destination in a vehicle navigation system, the vehicle-mounted navigation system plans a travel route to obtain vehicle travel condition information and total travel mileage, then the intelligent transportation system can obtain the road traffic state according to the travel route, and a vehicle driving history database is established by recording vehicle driving information.

And the analysis module 20 is configured to analyze the current driving characteristic information to obtain driving condition category information.

And the determining module 30 is configured to determine a preset target relationship function according to the driving condition category information.

And the searching module 40 is configured to search for a corresponding target equivalent factor through a preset equivalent factor comparison table according to the preset target relationship function.

And the control module 50 is used for determining the use proportion information of the engine and the motor in the hybrid electric vehicle according to the target equivalent factor and realizing the control of the energy of the hybrid electric vehicle according to the use proportion information.

The energy control device based on the driving condition of the invention adopts all technical schemes of all the embodiments, so that the energy control device at least has all the beneficial effects brought by the technical schemes of the embodiments, and is not repeated herein.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. A running condition-based energy control method is characterized by comprising the following steps of:

2. The energy control method based on the running condition according to claim 1, wherein the acquiring the current running characteristic information of the hybrid electric vehicle comprises:

acquiring current driving data of the hybrid electric vehicle;

3. The energy control method based on driving conditions according to claim 1, wherein the analyzing the current driving characteristic information to obtain the driving condition category information comprises:

4. The energy control method based on running conditions according to any one of claims 1 to 3, wherein the determining a preset target relation function according to the running condition category information comprises:

5. A method as claimed in any one of claims 1 to 3, wherein before looking up the corresponding target equivalence factor from a preset equivalence factor comparison table according to the preset target relationship function, the method further comprises:

6. The energy control method based on the driving condition according to claim 5, wherein before acquiring the historical driving condition information, the state of charge information of the historical power battery, the preset range of the equivalent factor and the genetic iteration number information, the method further comprises:

7. The running condition-based energy control method according to any one of claims 1 to 3, wherein before determining the usage ratio of the engine and the motor in the hybrid vehicle based on the target equivalence factor, the method further comprises:

8. An energy control apparatus based on a running condition, characterized by comprising: a memory, a processor and a driving condition based energy control program stored on the memory and executable on the processor, the driving condition based energy control program when executed by the processor implementing the steps of the driving condition based energy control method according to any one of claims 1 to 7.

9. A storage medium having a driving condition-based energy control program stored thereon, wherein the driving condition-based energy control program, when executed by a processor, implements the steps of the driving condition-based energy control method according to any one of claims 1 to 7.

10. An energy control apparatus based on a driving condition, characterized in that the energy control apparatus based on a driving condition comprises: