CN111038485A - Hybrid electric vehicle control method and system based on driving style recognition - Google Patents
Hybrid electric vehicle control method and system based on driving style recognition Download PDFInfo
- Publication number
- CN111038485A CN111038485A CN201911394636.8A CN201911394636A CN111038485A CN 111038485 A CN111038485 A CN 111038485A CN 201911394636 A CN201911394636 A CN 201911394636A CN 111038485 A CN111038485 A CN 111038485A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driving style
- engine
- parameters
- driving
- 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.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W20/00—Control systems specially adapted for hybrid vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
- B60W40/105—Speed
Abstract
The invention discloses a hybrid electric vehicle control method and a system based on driving style recognition, which comprises the following steps: the method comprises the steps of collecting driving data to be identified, processing the driving data to be identified to obtain parameters to be identified, collecting the driving data, and extracting characteristic parameters according to the collected data, wherein the characteristic parameters comprise speed, accelerator pedal opening change rate and brake pedal opening change rate; establishing an S4VM driving style recognition model based on genetic algorithm optimization, inputting parameters to be recognized into the model to obtain a driving style recognition result, and obtaining optimal control parameters of the vehicle according to the driving style recognition result; obtaining optimal vehicle control parameters according to the recognition result of the driving style of the driver; and establishing a control strategy by taking the minimum energy consumption of the whole vehicle as an optimization target, and adaptively adjusting the control strategy of the vehicle according to the driving style. The control parameters of the vehicle are identified and adjusted through the driving style, so that the engine works in a high-efficiency area, and the fuel economy of the whole vehicle is greatly improved.
Description
Technical Field
The disclosure relates to the technical field of hybrid electric vehicle control, in particular to a hybrid electric vehicle control method and system based on driving style recognition.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The driving style refers to a driving style that one person is accustomed to. The driving of the vehicle is a process of operating the vehicle by a driver, and different driving states of the vehicle can be caused by different people driving the same vehicle under the same road condition, because different people operate the vehicle differently, the driving styles of the vehicle are different, namely, the driver operates a steering wheel, a clutch, an accelerator pedal, a brake pedal and the like to enable the vehicle to present different running states under the current road condition. Existing research has shown that driver driving style plays an important role in vehicle energy management and driving safety, and in addition, it is critical to the development of advanced driver assistance systems. Therefore, to promote the development of the automobile industry, accurate recognition of the driving style of the driver is required.
In recent years, driving style recognition has been widely studied at home and abroad, for example: classifying and identifying the driving style by applying a principal component analysis and clustering analysis method; designing a fuzzy reasoning system to realize driving style identification; identifying the style of the driver by using methods such as a K nearest neighbor algorithm, a neural network, a decision tree, a random forest and the like; a support vector machine and hidden markov are combined to perform style recognition and a support vector machine using particle swarm optimization parameters is used to perform recognition, and different methods are used to improve recognition accuracy.
Supervised learning methods are widely used for driving style classification; however, they require a large amount of labeled training data, and manual identification of samples is a relatively cumbersome process in practical applications, and is difficult to implement. Unsupervised learning does not have this process, but the classification accuracy is often not high. Under the development of the Machine learning field, many optimized and improved Semi-Supervised learning methods are derived, wherein the optimized and improved Semi-Supervised learning methods comprise a Safe Semi-Supervised support vector Machine (S4 VM). The method for identifying by using semi-supervised learning can reduce sample marks and improve identification precision, and is a method gradually popularized in the field of pattern identification at present.
The control strategy is an important content of the research of the hybrid electric vehicle, which directly influences the fuel economy of the vehicle, and the control strategy is how to distribute energy during the operation of the hybrid electric vehicle with multiple power sources. The current control strategy is formulated under standard working conditions, and the driving style factor is not considered.
Disclosure of Invention
In order to overcome the defects of the prior art, the disclosure provides a hybrid electric vehicle control method and system based on driving style recognition; the method aims to classify and identify the driving style, improve the driving style identification precision and overcome the difficulty of manually marking a large number of samples. When S4VM is used, the selection of parameters is critical to the accuracy, and the invention uses genetic algorithm to optimally select S4VM parameters. And a vehicle control strategy is formulated based on the driving style to distribute energy, so that the distribution is more reasonable, and the fuel economy of the automobile is improved.
In a first aspect, the present disclosure provides a hybrid vehicle control method based on driving style recognition;
the control method of the hybrid electric vehicle based on the driving style recognition comprises the following steps:
collecting driving data of a vehicle to be controlled, and extracting characteristic parameters according to the driving data, wherein the characteristic parameters comprise speed, accelerator pedal opening change rate and brake pedal opening change rate;
establishing an S4VM driving style recognition model based on genetic algorithm optimization, inputting characteristic parameters into the model to obtain a driving style recognition result, and obtaining optimal vehicle control parameters according to the driving style recognition result of a driver;
and establishing a control strategy by taking the minimum energy consumption of the whole vehicle as an optimization target, and enabling the vehicle to be in a self-adaptive adjustment control mode according to the optimal vehicle control parameters.
In a second aspect, the present disclosure also provides a hybrid vehicle control system based on driving style recognition;
hybrid vehicle control system based on driving style recognition includes:
an acquisition module configured to: collecting driving data of a vehicle to be controlled, and extracting characteristic parameters according to the driving data, wherein the characteristic parameters comprise speed, accelerator pedal opening change rate and brake pedal opening change rate;
a driving style identification module configured to: establishing an S4VM driving style recognition model based on genetic algorithm optimization, inputting characteristic parameters into the model to obtain a driving style recognition result, and obtaining optimal vehicle control parameters according to the driving style recognition result of a driver;
a vehicle control module configured to: and establishing a control strategy by taking the minimum energy consumption of the whole vehicle as an optimization target, and enabling the vehicle to be in a self-adaptive adjustment control mode according to the optimal vehicle control parameters.
In a third aspect, the present disclosure also provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method of the first aspect.
In a fourth aspect, the present disclosure also provides a computer-readable storage medium for storing computer instructions which, when executed by a processor, perform the steps of the method of the first aspect.
Compared with the prior art, the beneficial effect of this disclosure is:
1. the control strategy of the hybrid electric vehicle is adaptively adjusted according to the driving style, so that the energy distribution is more reasonable, and the fuel economy of the vehicle is improved.
2. And S4VM is adopted to identify different driving styles of drivers, and semi-supervised learning can also effectively identify different driving styles of drivers, and the problem that a large amount of data needs to be labeled in the identification of the actual driving styles of the drivers is solved.
3. The S4VM parameter is optimized by using a genetic algorithm, so that the S4VM classifier has better performance and the identification result is more accurate.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a control method of a hybrid electric vehicle based on driving style recognition according to a first embodiment of the present application;
FIG. 2 is a flowchart illustrating a control strategy according to a first embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating driving style recognition according to a first embodiment of the present application;
FIG. 4 is a flowchart of the optimization parameters of the genetic algorithm according to the first embodiment of the present application;
fig. 5 is a flowchart of the S4VM algorithm according to the first embodiment of the present application.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
First embodiment, as shown in fig. 1, the present embodiment provides a control method for a hybrid vehicle based on driving style recognition;
the hybrid electric vehicle control method based on driving style recognition comprises the following steps:
s1: collecting driving data of a vehicle to be controlled, and extracting characteristic parameters according to the driving data, wherein the characteristic parameters comprise speed, accelerator pedal opening change rate and brake pedal opening change rate;
s2: establishing an S4VM driving style recognition model based on genetic algorithm optimization, inputting characteristic parameters into the model to obtain a driving style recognition result, and obtaining optimal vehicle control parameters according to the driving style recognition result of a driver;
s3: and establishing a control strategy by taking the minimum energy consumption of the whole vehicle as an optimization target, and enabling the vehicle to be in a self-adaptive adjustment control mode according to the optimal vehicle control parameters.
Further, in S1, the driving data of the vehicle to be controlled includes: the vehicle speed, the accelerator pedal opening and the brake pedal opening in the running working condition.
Further, in S1, extracting the characteristic parameter according to the driving data includes: and calculating to obtain the accelerator pedal opening change rate and the brake pedal opening change rate according to the vehicle speed, the accelerator pedal opening and the brake pedal opening of the vehicle in the running working condition.
Further, in S1, the calculation formula of the accelerator pedal opening change rate is:
wherein, apedalIs the accelerator opening.
Brake pedal opening change rate:
wherein, bpedalIs the brake pedal opening.
Further, in S1, after the step of collecting driving data of the vehicle to be controlled, before the step of extracting characteristic parameters from the driving data and performing normalization processing, the method further includes: carrying out normalization processing on the driving data by adopting a min-max standardization mode;
min-max normalization:
wherein x isiRepresenting the values before and after the normalization of the data,representing the values before and after normalization of the data, xminRepresents the minimum value in the sample data; x is the number ofmaxRepresenting the maximum value in the sample data. The normalization function for MATLAB is mapminmax.
Further, in S2, an S4VM driving style recognition model based on genetic algorithm optimization is established, the characteristic parameters are input into the model to obtain a driving style recognition result, and the optimal vehicle control parameters are obtained according to the driving style recognition result of the driver; the method comprises the following specific steps:
and inputting the extracted characteristic parameters into an S4VM driving style recognition model optimized based on a genetic algorithm, quantizing the driving style recognition result of the driver, taking the driving style recognition result (Dr) and the battery state of charge (SOC) as the input of a fuzzy controller, and taking an Equivalent Factor (EF) as the output of the fuzzy controller to obtain the optimal control parameters of the vehicle.
Further, in S2, designing a fuzzy controller; the method comprises the following specific steps:
the input membership function of the fuzzy controller adopts a triangular membership function and a trapezoidal membership function;
the output membership function of the fuzzy controller adopts a triangular membership function;
the input quantity SOC, the input quantity Dr and the output quantity EF of the fuzzy controller are divided into 3 fuzzy subsets, and the fuzzy subsets are defined as follows and have the following value ranges:
SOC: value range, [0, 1], fuzzy subset, { S, M, B };
dr: value range, [0, 3], fuzzy subset, { S, M, B };
EF: value range, [0.5, 2.5], fuzzy subset, { S, M, B }.
Wherein S represents small; m represents in; b represents large.
The control rules are shown in table 1;
TABLE 1 control rules
When SOC is S, Dr is S, EF is S; when SOC is S, Dr is M, EF is S; when SOC is S, Dr is B, EF is M;
when SOC is M, Dr is S, EF is S; when SOC is M, Dr is M, EF is M; when SOC is M, Dr is B, EF is B;
when SOC is B, Dr is S, EF is M; when SOC is S, Dr is S, EF is B; when SOC is S, Dr is S, EF is B.
Further, in step S3, a control strategy is established with the minimum energy consumption of the entire vehicle as an optimization objective, and a vehicle is adaptively adjusted according to the optimal vehicle control parameters; the method comprises the following specific steps:
and establishing a control strategy objective function by taking the minimum energy consumption of the whole vehicle as an optimization objective, and taking the optimal control parameter of the vehicle obtained in the step S2 as the input of the control strategy objective function, so that the vehicle can adaptively distribute the torque of the engine and the motor according to EF.
Further, in S3, the formula of the optimization objective function is:
the control variables and state variables are:
the constraint conditions are as follows:
wherein the content of the first and second substances,is the fuel consumption quality of the engine per unit time,is the equivalent power consumption, EF is the equivalent factor, PmIs the motor power, QLHVIs the low heat value of the fuel oil,is the optimized engine and motor torque, SOC is the battery state of charge, TeIs the engine torque, TmIs the motor torque, Tm_minIs the minimum torque, T, of the motor at the current rotational speedm_maxIs the maximum torque, T, of the motor at the current rotational speede_maxIs the maximum torque of the engine at the current speed, omegamIs the motor speed, ωm_maxIs the maximum rotational speed, omega, of the motoreIs the engine speed, ωe_minIs the minimum engine speed, ωe_maxIs the maximum engine speed, SOCminIs the minimum state of charge, SOC, of the batterymaxIs the battery maximum state of charge.
Further, in S3, as shown in fig. 2, the specific flow of the control strategy is as follows:
s31: the external characteristics of the engine torque are represented by T, the specific fuel consumption, the external characteristics of the motor torque and the motor efficiency are knowne_max=f1(ne) The specific fuel consumption is represented by be=f2(ne,Te) The external characteristic of the motor torque is represented as Tm_max=f3(nm) Motor efficiency is shown as ηm=(nm,Tm);
S32: determining constraint conditions, and respectively determining the rotating speed ranges of the engine and the motor, wherein the rotating speed range of the engine is 800<ne<2300, motor rotation speed range of 0<nm<3500;
Correspondingly, the characteristic parameters of the engine and the motor are obtained through tests, so that the characteristic parameters of the engine and the motor corresponding to the current rotating speed point are obtained through an interpolation method;
s33: determining launchFeasible range of machine torque [0, Te_lim_max]And divided into N equal parts, [0, T ]e_i,Te_lim_max]. The selection of N is required to ensure that an optimized solution is obtained and reduce the calculation amount. If N is too small, an optimal solution may not be obtained; if N is too large, the amount of computation is large. And comprehensively selecting N to be 200 according to the torque range of the engine. Then, a corresponding possible value T of the engine torque is obtainedm_i=Treq-Te_i,(TreqTorque demand for driving);
S35: calculating the equivalent fuel consumptionAnd solving for the minimum equivalent fuel consumptionObtaining a corresponding optimized engine torque TeoptAnd then according to Tmopt=Treq-TeoptAnd solving the optimized motor torque.
Further, as shown in fig. 3, the training step of the S4VM classifier based on genetic algorithm optimization includes:
s11: constructing an S4VM classifier based on genetic algorithm optimization;
s12: inputting characteristic parameters into an S4VM classifier based on genetic algorithm optimization; determining the type of the driving style of the driver: dividing the driving style of a driver into an aggressive type, a steady type and a cautious type;
s13: and training the S4VM classifier based on genetic algorithm optimization by using the types of the driving styles of the driver and the characteristic parameters to obtain the trained S4VM classifier based on genetic algorithm optimization.
Further, in the S11, as shown in fig. 4, an S4VM classifier based on genetic algorithm optimization is established; the method comprises the following specific steps:
s1111: and (3) encoding: the parameters needing to be optimized by the S4VM algorithm have penalty coefficients C1,C2And kernel function parameter g, because the three parameters selected are all real values, all adopt floating point number to encode;
s1112: generation of initial population: randomly generating a plurality of groups of parameter values with large differences as initial candidate solutions;
s1113: and (3) fitness evaluation: the fitness indicates the superiority and inferiority of the individual or the solution; the fitness criterion is defined as the accuracy of the classification, i.e.: number of correctly sorted samples/total number of samples;
s1114: selecting: selecting a solution with the highest fitness from the current candidate solutions to enter the next generation by adopting an optimal reservation selection method so as to achieve the aim of continuously optimizing parameters;
s1115: and (3) crossing: using an arithmetic crossover method for two individuals xaAnd xbCross-generated new individuals:
x'a=βxa+(1-β)xb(8)
x'b=(1-β)xa+βxb(9)
wherein β is a random number between 0 and 1;
s1116: mutation: carrying out random disturbance variation on three parameters to be optimized by adopting a non-uniform variation method:
x′i=xi+μ(y) (10)
wherein y represents an upper limit of the random number; mu (y) is a random number taken from [0, y ];
and y is selected as follows:
y=Imax-xi,if rand(0,1)=0 (11)
y=xi-Imax,if rand(0,1)=1 (12)
wherein [ I ]min,Imax]Is xiThe value range of (a);
s1117: and (4) ending: the maximum number of iterations is set to 20 and the maximum number of iterations is set as the termination condition of the algorithm.
Further, in S12, the type of the driver' S driving style is determined: dividing the driving style of a driver into an aggressive type, a steady type and a cautious type; the method comprises the following specific steps:
the amplitude of the accelerator pedal opening degree change rate and the brake pedal opening degree change rate of the aggressive driver is larger than a first maximum set threshold value F1The speed is greater than a second maximum set threshold value V1;
The magnitude of the change rate of the accelerator pedal and the change rate of the brake pedal of the robust driver is more than or equal to F2And is less than or equal to F1In the range of V or more, and a speed of V or more2And is less than or equal to V1Within the range of (1);
the magnitude of the rate of change of the accelerator pedal and the rate of change of the brake pedal of a cautious driver is less than a first minimum set threshold F2The speed is less than a second minimum set threshold value V2。
Quantizing the driving style of the driver, namely { aggressive } - < 1; { robust } ═ 2; { discreet } ═ 3.
Further, in S13, as shown in fig. 5, the driver driving style category and the feature parameters are used to train the genetic algorithm optimization-based S4VM classifier, so as to obtain a trained genetic algorithm optimization-based S4VM classifier; the method comprises the following specific steps:
determining the number of classifiers to be 3 according to the driving style types; and dividing the data processed in the S12 into marked samples, corresponding labels and unmarked samples as input quantities, importing the marked samples into an S4VM classifier based on genetic algorithm optimization, completing optimization and training of the S4VM classifier based on the genetic algorithm optimization, and finally outputting the driving style types.
Further, training an S4VM classifier based on genetic algorithm optimization by using the type of the driving style of the driver and the characteristic parameters to obtain a trained S4VM classifier based on genetic algorithm optimization; as shown in fig. 4, the specific steps include:
s1321: let the input dataset be S:
wherein S is(l)Representing n sets of label data, S(u)Representing m unmarked data, xiDenotes the identification parameter, yiRepresenting the corresponding label;
s1322: the radial basis kernel function is selected to map the driving style data to a high-dimensional space to solve the problem of linear inseparability in the original space, and the form is as follows:
wherein v isi,vjExpressed as driving style data, and i<j,i,j∈[1,8];σ=cov(vi,vj);
S1323: suppose ftIs a linear function:
ft(x)=w′tφ(x)+b (15)
where φ (x) is a feature map caused by kernel K;
the optimization problem solved is then expressed as:
s.t.yi(w′tφ(xi)+bt)≥1-ξi,ξi≥0,
wherein, T is the number of boundary lines, and Ω is a penalty function for measuring the differentiation of the boundary lines; i is an indicator function; ε is a constant value between 0 and 1; m is a large constant to ensure variability;is thatItem j of (1).
S1324: and in the concrete solving process, a sampling mode is used to realize classification, namely the identification of the driving style is completed.
According to the invention, a man-vehicle-road system is constructed, the speed of the vehicle, the opening degree of an accelerator pedal and the opening degree of a brake pedal are collected, and an S4VM model optimized by a genetic algorithm is utilized, so that the driving style identification precision is improved, the difficulty of manually marking a large number of samples is overcome, and the fuel economy of the vehicle is improved.
The second embodiment also provides a hybrid electric vehicle control system based on driving style recognition;
hybrid vehicle control system based on driving style recognition includes:
an acquisition module configured to: collecting driving data of a vehicle to be controlled, and extracting characteristic parameters according to the driving data, wherein the characteristic parameters comprise speed, accelerator pedal opening change rate and brake pedal opening change rate;
a driving style identification module configured to: establishing an S4VM driving style recognition model based on genetic algorithm optimization, inputting characteristic parameters into the model to obtain a driving style recognition result, and obtaining optimal vehicle control parameters according to the driving style recognition result of a driver;
a vehicle control module configured to: and establishing a control strategy by taking the minimum energy consumption of the whole vehicle as an optimization target, and enabling the vehicle to be in a self-adaptive adjustment control mode according to the optimal vehicle control parameters.
In a third embodiment, the present embodiment further provides an electronic device, which includes a memory, a processor, and computer instructions stored in the memory and executed on the processor, where the computer instructions, when executed by the processor, implement the steps of the method in the first embodiment.
In a fourth embodiment, the present embodiment further provides a computer-readable storage medium for storing computer instructions, and the computer instructions, when executed by a processor, perform the steps of the method in the first embodiment.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. The hybrid electric vehicle control method based on driving style recognition is characterized by comprising the following steps of:
collecting driving data of a vehicle to be controlled, and extracting characteristic parameters according to the driving data, wherein the characteristic parameters comprise speed, accelerator pedal opening change rate and brake pedal opening change rate;
establishing an S4VM driving style recognition model based on genetic algorithm optimization, inputting characteristic parameters into the model to obtain a driving style recognition result, and obtaining optimal vehicle control parameters according to the driving style recognition result of a driver;
and establishing a control strategy by taking the minimum energy consumption of the whole vehicle as an optimization target, and enabling the vehicle to be in a self-adaptive adjustment control mode according to the optimal vehicle control parameters.
2. The method as claimed in claim 1, wherein the driving data of the vehicle to be controlled comprises: the method comprises the following steps that the vehicle speed, the accelerator pedal opening and the brake pedal opening of a vehicle are measured in the running working condition;
extracting characteristic parameters according to the driving data, comprising: calculating to obtain an accelerator pedal opening change rate and a brake pedal opening change rate according to the speed, the accelerator pedal opening and the brake pedal opening of the vehicle in the running working condition;
after the step of collecting the driving data of the vehicle to be controlled, before the step of extracting characteristic parameters according to the driving data and performing normalization processing, the method further comprises the following steps of: and (5) carrying out normalization processing on the driving data by adopting a min-max standardization mode.
3. The method according to claim 1, wherein a genetic algorithm optimization based S4VM driving style recognition model is established, the characteristic parameters are inputted to the model to obtain driving style recognition results, and optimal vehicle control parameters are obtained based on the driving style recognition results of the driver; the method comprises the following specific steps:
and inputting the extracted characteristic parameters into an S4VM driving style recognition model optimized based on a genetic algorithm, quantizing the driving style recognition result of the driver, taking the driving style recognition result Dr and the battery state of charge SOC as the input of a fuzzy controller, and taking the equivalent factor EF as the output of the fuzzy controller to obtain the optimal control parameters of the vehicle.
4. The method of claim 1, wherein the design of the fuzzy controller; the method comprises the following specific steps:
the input membership function of the fuzzy controller adopts a triangular membership function and a trapezoidal membership function;
the output membership function of the fuzzy controller adopts a triangular membership function;
the input quantity SOC, the input quantity Dr and the output quantity EF of the fuzzy controller are divided into 3 fuzzy subsets, and the fuzzy subsets are defined as follows and have the following value ranges:
SOC: value range, [0, 1], fuzzy subset, { S, M, B };
dr: value range, [0, 3], fuzzy subset, { S, M, B };
EF: value range, [0.5, 2.5], fuzzy subset, { S, M, B };
wherein S represents small; m represents in; b represents large;
when SOC is S, Dr is S, EF is S; when SOC is S, Dr is M, EF is S; when SOC is S, Dr is B, EF is M;
when SOC is M, Dr is S, EF is S; when SOC is M, Dr is M, EF is M; when SOC is M, Dr is B, EF is B;
when SOC is B, Dr is S, EF is M; when SOC is S, Dr is S, EF is B; when SOC is S, Dr is S, EF is B.
5. The method as claimed in claim 1, wherein a control strategy is established with the aim of minimizing the energy consumption of the whole vehicle as an optimization target, and the vehicle is adaptively adjusted in a control mode according to the optimal vehicle control parameters; the method comprises the following specific steps:
and establishing a control strategy objective function by taking the minimum energy consumption of the whole vehicle as an optimization objective, and taking the obtained optimal control parameters of the vehicle as the input of the control strategy objective function to enable the vehicle to adaptively distribute the torque of the engine and the motor according to EF.
6. The method of claim 5, wherein the objective function is formulated as:
the control variables and state variables are:
the constraint conditions are as follows:
wherein the content of the first and second substances,is the fuel consumption quality of the engine per unit time,is the equivalent power consumption, EF is the equivalent factor, PmIs the motor power, QLHVIs the low heat value of the fuel oil,is optimized engine and motor torque, and SOC is battery charge stateState, TeIs the engine torque, TmIs the motor torque, Tm_minIs the minimum torque, T, of the motor at the current rotational speedm_maxIs the maximum torque, T, of the motor at the current rotational speede_maxIs the maximum torque of the engine at the current speed, omegamIs the motor speed, ωm_maxIs the maximum rotational speed, omega, of the motoreIs the engine speed, ωe_minIs the minimum engine speed, ωe_maxIs the maximum engine speed, SOCminIs the minimum state of charge, SOC, of the batterymaxIs the battery maximum state of charge;
the specific flow of the control strategy is as follows:
s31: the external characteristics of the engine torque are represented by T, the specific fuel consumption, the external characteristics of the motor torque and the motor efficiency are knowne_max=f1(ne) The specific fuel consumption is represented by be=f2(ne,Te) The external characteristic of the motor torque is represented as Tm_max=f3(nm) Motor efficiency is shown as ηm=(nm,Tm);
S32: determining constraint conditions, and respectively determining the rotating speed ranges of the engine and the motor, wherein the rotating speed range of the engine is 800<ne<2300, motor rotation speed range of 0<nm<3500;
Correspondingly, the characteristic parameters of the engine and the motor are obtained through tests, so that the characteristic parameters of the engine and the motor corresponding to the current rotating speed point are obtained through an interpolation method;
s33: determining a feasible region [0, T ] of engine torquee_lim_max]And divided into N equal parts, [0, T ]e_i,Te_lim_max](ii) a Then, a corresponding possible value T of the engine torque is obtainedm_i=Treq-Te_i,TreqTorque demand for driving;
7. The method of claim 1, wherein a genetic algorithm optimization based S4VM driving style recognition model is established; the method comprises the following specific steps:
s1111: and (3) encoding: the parameters needing to be optimized by the S4VM algorithm have penalty coefficients C1,C2And kernel function parameter g, because the three parameters selected are all real values, all adopt floating point number to encode;
s1112: generation of initial population: randomly generating a plurality of groups of parameter values with large differences as initial candidate solutions;
s1113: and (3) fitness evaluation: the fitness indicates the superiority and inferiority of the individual or the solution; the fitness criterion is defined as the accuracy of the classification, i.e.: number of correctly sorted samples/total number of samples;
s1114: selecting: selecting a solution with the highest fitness from the current candidate solutions to enter the next generation by adopting an optimal reservation selection method so as to achieve the aim of continuously optimizing parameters;
s1115: and (3) crossing: using an arithmetic crossover method for two individuals xaAnd xbCross-generated new individuals:
x′a=βxa+(1-β)xb(8)
x′b=(1-β)xa+βxb(9)
wherein β is a random number between 0 and 1;
s1116: mutation: carrying out random disturbance variation on three parameters to be optimized by adopting a non-uniform variation method:
x′i=xi+μ(y) (10)
wherein y represents an upper limit of the random number; mu (y) is a random number taken from [0, y ];
and y is selected as follows:
y=Imax-xi,ifrand(0,1)=0 (11)
y=xi-Imax,ifrand(0,1)=1 (12)
wherein [ I ]min,Imax]Is xiThe value range of (a);
s1117: and (4) ending: the maximum number of iterations is set to 20 and the maximum number of iterations is set as the termination condition of the algorithm.
8. Hybrid vehicle control system based on driving style recognition includes:
an acquisition module configured to: collecting driving data of a vehicle to be controlled, and extracting characteristic parameters according to the driving data, wherein the characteristic parameters comprise speed, accelerator pedal opening change rate and brake pedal opening change rate;
a driving style identification module configured to: establishing an S4VM driving style recognition model based on genetic algorithm optimization, inputting characteristic parameters into the model to obtain a driving style recognition result, and obtaining optimal vehicle control parameters according to the driving style recognition result of a driver;
a vehicle control module configured to: and establishing a control strategy by taking the minimum energy consumption of the whole vehicle as an optimization target, and enabling the vehicle to be in a self-adaptive adjustment control mode according to the optimal vehicle control parameters.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions, when executed by the processor, performing the steps of the method of any of claims 1-7.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911394636.8A CN111038485B (en) | 2019-12-30 | 2019-12-30 | Hybrid electric vehicle control method and system based on driving style recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911394636.8A CN111038485B (en) | 2019-12-30 | 2019-12-30 | Hybrid electric vehicle control method and system based on driving style recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111038485A true CN111038485A (en) | 2020-04-21 |
CN111038485B CN111038485B (en) | 2021-02-19 |
Family
ID=70241974
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911394636.8A Active CN111038485B (en) | 2019-12-30 | 2019-12-30 | Hybrid electric vehicle control method and system based on driving style recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111038485B (en) |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111474934A (en) * | 2020-04-26 | 2020-07-31 | 东风汽车集团有限公司 | Personalized cruise control system based on high-precision map |
CN111775943A (en) * | 2020-05-18 | 2020-10-16 | 中汽数据有限公司 | Method for reducing engine emissions by predictive control of driving behaviour |
CN111783826A (en) * | 2020-05-27 | 2020-10-16 | 西华大学 | Driving style classification method based on pre-classification and ensemble learning |
CN111775925A (en) * | 2020-06-09 | 2020-10-16 | 同济大学 | Working mode decision method and device for power split hybrid electric vehicle |
CN112046489A (en) * | 2020-08-31 | 2020-12-08 | 吉林大学 | Driving style identification algorithm based on factor analysis and machine learning |
CN112124224A (en) * | 2020-08-28 | 2020-12-25 | 珠海格力电器股份有限公司 | Electric vehicle control system, electric vehicle control method, storage medium, and electric vehicle |
CN112373458A (en) * | 2020-11-26 | 2021-02-19 | 同济大学 | Hybrid electric vehicle energy management method based on self-adaptive fuzzy control |
CN112651443A (en) * | 2020-12-28 | 2021-04-13 | 华北科技学院 | Driving style identification model evaluation method, device, medium and equipment based on machine learning |
CN112744088A (en) * | 2020-06-09 | 2021-05-04 | 长城汽车股份有限公司 | Driving mode control method and device |
CN112776815A (en) * | 2021-02-23 | 2021-05-11 | 东风汽车集团股份有限公司 | Driving style judgment and identification method |
CN112829758A (en) * | 2021-01-08 | 2021-05-25 | 广西宁达汽车科技有限公司 | Automobile driving style self-learning method, device, equipment and storage medium |
CN113085813A (en) * | 2021-03-29 | 2021-07-09 | 南京航空航天大学 | Electric automobile braking feeling consistency control method based on I-Booster and driving personality |
CN113173154A (en) * | 2020-08-21 | 2021-07-27 | 长城汽车股份有限公司 | Power distribution management method and device for hybrid vehicle |
CN113264032A (en) * | 2021-04-16 | 2021-08-17 | 中国重汽集团济南动力有限公司 | Energy management method, device and system for hybrid vehicle |
CN113386779A (en) * | 2021-06-23 | 2021-09-14 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method, device and storage medium |
CN113386768A (en) * | 2021-08-02 | 2021-09-14 | 合肥工业大学 | Single-pedal nonlinear model prediction control method for pure electric vehicle |
CN113619558A (en) * | 2020-05-06 | 2021-11-09 | 上海汽车集团股份有限公司 | Torque distribution method and system for hybrid system vehicle |
CN114347812A (en) * | 2022-01-12 | 2022-04-15 | 河南科技大学 | Driving style-based fuel cell hybrid electric vehicle energy management method |
CN114435364A (en) * | 2022-01-27 | 2022-05-06 | 东风汽车集团股份有限公司 | Vehicle accelerator pedal control method and related equipment |
CN115158451A (en) * | 2022-07-25 | 2022-10-11 | 克诺尔制动系统(大连)有限公司 | Control device, steering system, vehicle, and steering control method |
DE102022205981A1 (en) | 2022-06-13 | 2023-12-14 | Volkswagen Aktiengesellschaft | Method for classifying driving style and adapting the control of a motor vehicle |
CN117261904A (en) * | 2023-11-21 | 2023-12-22 | 北京航空航天大学 | Driving mode decision method of hybrid electric vehicle with self-adaptive scene and style |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102883912A (en) * | 2009-10-30 | 2013-01-16 | 福特全球技术公司 | Vehicle with identification system |
FR2975958B1 (en) * | 2011-06-03 | 2013-05-31 | Renault Sa | SPEED CONTROL CONTROL FOR A VEHICLE |
CN107035560A (en) * | 2017-05-18 | 2017-08-11 | 吉林大学 | Engine control system based on driver's type ONLINE RECOGNITION |
CN107161140A (en) * | 2017-05-09 | 2017-09-15 | 南京航空航天大学 | A kind of plug-in hybrid-power automobile system and its energy control method |
CN109229108A (en) * | 2018-08-07 | 2019-01-18 | 武汉理工大学 | A kind of driving behavior safe evaluation method based on driving fingerprint |
CN110254417A (en) * | 2019-06-27 | 2019-09-20 | 清华大学苏州汽车研究院(吴江) | Method for controlling hybrid power vehicle based on actual condition and the double identifications of driving style |
-
2019
- 2019-12-30 CN CN201911394636.8A patent/CN111038485B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102883912A (en) * | 2009-10-30 | 2013-01-16 | 福特全球技术公司 | Vehicle with identification system |
FR2975958B1 (en) * | 2011-06-03 | 2013-05-31 | Renault Sa | SPEED CONTROL CONTROL FOR A VEHICLE |
CN107161140A (en) * | 2017-05-09 | 2017-09-15 | 南京航空航天大学 | A kind of plug-in hybrid-power automobile system and its energy control method |
CN107035560A (en) * | 2017-05-18 | 2017-08-11 | 吉林大学 | Engine control system based on driver's type ONLINE RECOGNITION |
CN109229108A (en) * | 2018-08-07 | 2019-01-18 | 武汉理工大学 | A kind of driving behavior safe evaluation method based on driving fingerprint |
CN110254417A (en) * | 2019-06-27 | 2019-09-20 | 清华大学苏州汽车研究院(吴江) | Method for controlling hybrid power vehicle based on actual condition and the double identifications of driving style |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111474934A (en) * | 2020-04-26 | 2020-07-31 | 东风汽车集团有限公司 | Personalized cruise control system based on high-precision map |
CN113619558A (en) * | 2020-05-06 | 2021-11-09 | 上海汽车集团股份有限公司 | Torque distribution method and system for hybrid system vehicle |
CN111775943A (en) * | 2020-05-18 | 2020-10-16 | 中汽数据有限公司 | Method for reducing engine emissions by predictive control of driving behaviour |
CN111783826A (en) * | 2020-05-27 | 2020-10-16 | 西华大学 | Driving style classification method based on pre-classification and ensemble learning |
CN111783826B (en) * | 2020-05-27 | 2022-07-01 | 西华大学 | Driving style classification method based on pre-classification and ensemble learning |
CN112744088A (en) * | 2020-06-09 | 2021-05-04 | 长城汽车股份有限公司 | Driving mode control method and device |
CN111775925A (en) * | 2020-06-09 | 2020-10-16 | 同济大学 | Working mode decision method and device for power split hybrid electric vehicle |
CN113173154B (en) * | 2020-08-21 | 2022-04-22 | 长城汽车股份有限公司 | Power distribution management method and device for hybrid vehicle |
CN113173154A (en) * | 2020-08-21 | 2021-07-27 | 长城汽车股份有限公司 | Power distribution management method and device for hybrid vehicle |
CN112124224A (en) * | 2020-08-28 | 2020-12-25 | 珠海格力电器股份有限公司 | Electric vehicle control system, electric vehicle control method, storage medium, and electric vehicle |
CN112124224B (en) * | 2020-08-28 | 2021-11-23 | 珠海格力电器股份有限公司 | Electric vehicle control system, electric vehicle control method, storage medium, and electric vehicle |
CN112046489B (en) * | 2020-08-31 | 2021-03-16 | 吉林大学 | Driving style identification algorithm based on factor analysis and machine learning |
CN112046489A (en) * | 2020-08-31 | 2020-12-08 | 吉林大学 | Driving style identification algorithm based on factor analysis and machine learning |
CN112373458A (en) * | 2020-11-26 | 2021-02-19 | 同济大学 | Hybrid electric vehicle energy management method based on self-adaptive fuzzy control |
CN112373458B (en) * | 2020-11-26 | 2021-10-08 | 同济大学 | Hybrid electric vehicle energy management method based on self-adaptive fuzzy control |
CN112651443A (en) * | 2020-12-28 | 2021-04-13 | 华北科技学院 | Driving style identification model evaluation method, device, medium and equipment based on machine learning |
CN112829758A (en) * | 2021-01-08 | 2021-05-25 | 广西宁达汽车科技有限公司 | Automobile driving style self-learning method, device, equipment and storage medium |
CN112776815A (en) * | 2021-02-23 | 2021-05-11 | 东风汽车集团股份有限公司 | Driving style judgment and identification method |
CN113085813A (en) * | 2021-03-29 | 2021-07-09 | 南京航空航天大学 | Electric automobile braking feeling consistency control method based on I-Booster and driving personality |
CN113264032A (en) * | 2021-04-16 | 2021-08-17 | 中国重汽集团济南动力有限公司 | Energy management method, device and system for hybrid vehicle |
CN113264032B (en) * | 2021-04-16 | 2022-05-03 | 中国重汽集团济南动力有限公司 | Energy management method, device and system for hybrid vehicle |
CN113386779A (en) * | 2021-06-23 | 2021-09-14 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method, device and storage medium |
CN113386779B (en) * | 2021-06-23 | 2022-10-18 | 华人运通(江苏)动力电池系统有限公司 | Driving style recognition method, device and storage medium |
CN113386768A (en) * | 2021-08-02 | 2021-09-14 | 合肥工业大学 | Single-pedal nonlinear model prediction control method for pure electric vehicle |
CN114347812A (en) * | 2022-01-12 | 2022-04-15 | 河南科技大学 | Driving style-based fuel cell hybrid electric vehicle energy management method |
CN114347812B (en) * | 2022-01-12 | 2024-01-16 | 河南科技大学 | Driving style-based energy management method for fuel cell hybrid electric vehicle |
CN114435364A (en) * | 2022-01-27 | 2022-05-06 | 东风汽车集团股份有限公司 | Vehicle accelerator pedal control method and related equipment |
CN114435364B (en) * | 2022-01-27 | 2023-08-04 | 东风汽车集团股份有限公司 | Vehicle accelerator pedal control method and related equipment |
DE102022205981A1 (en) | 2022-06-13 | 2023-12-14 | Volkswagen Aktiengesellschaft | Method for classifying driving style and adapting the control of a motor vehicle |
CN115158451A (en) * | 2022-07-25 | 2022-10-11 | 克诺尔制动系统(大连)有限公司 | Control device, steering system, vehicle, and steering control method |
CN117261904A (en) * | 2023-11-21 | 2023-12-22 | 北京航空航天大学 | Driving mode decision method of hybrid electric vehicle with self-adaptive scene and style |
CN117261904B (en) * | 2023-11-21 | 2024-01-30 | 北京航空航天大学 | Driving mode decision method of hybrid electric vehicle with self-adaptive scene and style |
Also Published As
Publication number | Publication date |
---|---|
CN111038485B (en) | 2021-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111038485B (en) | Hybrid electric vehicle control method and system based on driving style recognition | |
Tian et al. | An adaptive ECMS with driving style recognition for energy optimization of parallel hybrid electric buses | |
Huang et al. | An intelligent multifeature statistical approach for the discrimination of driving conditions of a hybrid electric vehicle | |
Li et al. | Dual-loop online intelligent programming for driver-oriented predict energy management of plug-in hybrid electric vehicles | |
CN107909179B (en) | Method for constructing prediction model of running condition of plug-in hybrid vehicle and vehicle energy management method | |
Liu et al. | Research on classification and recognition of driving styles based on feature engineering | |
CN109255094B (en) | Commercial truck quality estimation method based on SVR-Adaboost improved algorithm | |
CN110929920A (en) | Hybrid power train energy management method based on working condition identification | |
CN112046489B (en) | Driving style identification algorithm based on factor analysis and machine learning | |
CN110386144B (en) | GHMM/GGAP-RBF hybrid model for identifying driver braking intention and identification method | |
CN112327168A (en) | XGboost-based electric vehicle battery consumption prediction method | |
Hou et al. | Machine learning and whale optimization algorithm based design of energy management strategy for plug‐in hybrid electric vehicle | |
CN111198501B (en) | Method for determining fuel equivalent factor by RBF neural network | |
CN114912195B (en) | Aerodynamic sequence optimization method for commercial vehicle | |
Montazeri-Gh et al. | Driving condition recognition for genetic-fuzzy HEV control | |
Yang et al. | A time-efficient approach for decision-making style recognition in lane-changing behavior | |
Shi et al. | RETRACTED ARTICLE: The energy management strategy for parallel hybrid electric vehicles based on MNN | |
Deng et al. | Dual threshold based unsupervised face image clustering | |
CN107886130A (en) | A kind of kNN rapid classification methods based on cluster and Similarity-Weighted | |
CN113401123B (en) | Automobile prediction cruise parameter self-tuning control system fusing driving mode information | |
Li et al. | Dp and ds-lcd: A new lane change decision model coupling driver’s psychology and driving style | |
CN101702172A (en) | Data discretization method based on category-attribute relation dependency | |
CN107909090A (en) | Learn semi-supervised music-book on pianoforte difficulty recognition methods based on estimating | |
Xie et al. | Real-time driving pattern prediction based on KPCA and neural network | |
YuanTong | Research of intrusion detection method based on IL-FSVM |
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 |