CN115675099A - Pure electric vehicle braking energy recovery method based on driver style recognition - Google Patents
Pure electric vehicle braking energy recovery method based on driver style recognition Download PDFInfo
- Publication number
- CN115675099A CN115675099A CN202211436587.1A CN202211436587A CN115675099A CN 115675099 A CN115675099 A CN 115675099A CN 202211436587 A CN202211436587 A CN 202211436587A CN 115675099 A CN115675099 A CN 115675099A
- Authority
- CN
- China
- Prior art keywords
- driver
- braking force
- style
- energy recovery
- braking
- 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.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/72—Electric energy management in electromobility
Landscapes
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a pure electric vehicle braking energy recovery method based on driver style recognition, and belongs to the field of unmanned vehicles. The method comprises the following steps: s101: classifying the driver style by preprocessing the NGSIM data set and extracting and optimizing the characteristic parameters of the driver style; s102: training the sample data by adopting a convolutional neural network, and establishing a driver style identification model; s103: and analyzing the braking intention of the driver through the style type of the driver, distributing the braking force according to the proposed energy recovery strategy, and controlling the motor to recover the energy. The invention can identify different driving styles of drivers, match the optimal braking energy recovery mode according to the driving styles of the drivers, increase the driving mileage of the pure electric vehicle, improve the experience feeling of the drivers and realize the energy consumption economy of the pure electric vehicle.
Description
Technical Field
The invention relates to the technical field of pure electric vehicle control, in particular to a pure electric vehicle braking energy recovery method based on driver style recognition.
Background
Along with the intelligent starting of the automobile, people meet the requirements of good experience of the automobile, so that people hope that the automobile can customize corresponding service content and assistant driving according to own state and requirements, the style of the automobile is accurately adapted to the style of the driver, and more humanized service and safer and more comfortable assistant driving are provided for the driver, and the automobile intelligent starting system has an extremely important function. The braking energy recovery is an important means for improving the energy utilization efficiency of the electric automobile, when the motor runs in a power generation state, the braking torque can be generated, the speed of the automobile is reduced, meanwhile, part of braking energy of the automobile is converted into electric energy, and the electric energy is charged for a power battery, so that the driving range of the automobile is improved.
Chinese patent No. CN 108081961B, discloses "a brake energy recovery control method, device and electric vehicle", the method includes: and determining the total required braking force of the driver according to the displacement of the brake pedal, and determining the required braking force of the motor by combining the maximum braking force which can be provided by the motor and the judgment threshold of the braking force distribution, so as to control the motor to recover the braking energy. The method can realize higher energy recovery efficiency by recovering the electric brake to the maximum extent on the premise of not changing the total braking force required by a driver.
Chinese patent No. CN 109278566B discloses a method and a device for controlling the recovery of braking energy of a rear wheel drive pure electric vehicle, the method comprising: in the braking process of the automobile, the mechanical braking force and the regenerative braking force are controlled to be distributed, on the basis of ensuring the braking safety and the braking efficiency, the distribution coefficient of the regenerative braking force is improved to the maximum extent, the power battery is charged by fully utilizing the feed capacity of the motor to recover the energy lost in the braking process, the recovery efficiency of the braking energy is improved, the loss of the braking energy is reduced, and the driving range of the automobile is optimized.
Although the effect of increasing the driving range of the pure electric vehicle is achieved from the aspect of recovering the braking energy in the prior art, the regenerative braking energy recovery method in the prior art does not consider factors of different driver styles, and the requirements of the driver on comfort and driving experience feeling cannot be met.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention aims to provide a pure electric vehicle braking energy recovery method and system based on driver style identification, which can identify different driving styles of drivers, match the optimal braking energy recovery mode according to the driving styles of the drivers, increase the driving mileage of a pure electric vehicle, improve the experience feeling of the drivers and realize the energy consumption economy of the pure electric vehicle.
The purpose of the invention is realized by the following technical scheme:
a pure electric vehicle braking energy recovery method and system based on driver style recognition comprises the following steps:
s101: classifying the driver styles by preprocessing the NGSIM data set and selecting and optimizing driver style characteristic parameters;
s102: training the sample data by adopting a convolutional neural network, and establishing a driver style identification model;
s103: and analyzing the braking intention of the driver through the style type of the driver, distributing the braking force according to the proposed energy recovery strategy, and controlling the motor to recover the energy.
Further, the step S101 specifically includes the following steps:
s1011: and removing abnormal data in the NGSIM data set, performing smooth denoising processing on the data stream by adopting a Savitzky-Golay filtering algorithm, and standardizing by using a max-min method. The Savitzky-Golay filter algorithm function is as follows:
wherein
The coefficients are found by a least squares fit for smoothing.
S1012: selecting the average speed v mean Maximum vehicle speed v max Minimum vehicle speed v min Speed standard deviation σ v Average acceleration a mean Maximum acceleration a max Minimum acceleration a min Acceleration standard deviation sigma a And the leading vehicle distance l is the style characteristic of the driver, specific parameters of the driver are calculated and optimized, and the Factor Analysis method is adopted to perform dimension reduction processing on the characteristic parameters. The factor analysis model expression form is as follows:
x i ＝a 1 F 1 +a 2 F 2 +...+a p F p +η i
wherein x i Is the ith observable variable (i =1,2, 3.., k), F j Is a common factor (j =1,2,3,. Cndot., p), and p < k; a is a p Is a factor load.
S1013: selecting the average vehicle speed v according to the index that the sum of squares of the extracted loads is greater than 75% mean Maximum vehicle speed v max Minimum vehicle speed v min Standard deviation of velocity σ v And (4) clustering the common factors by adopting a K-means + + clustering algorithm to minimize the loss function, and analyzing the result. The loss function is defined as:
wherein x i Represents the ith sample, c i Is x i Cluster of which, mu ci Represents the corresponding center point of each cluster, and M is the total number of samples.
Further, the step S102 specifically includes the following steps:
s1021: giving an input driving data set, setting a penalty function L (y, y ^) to judge the error between an output predicted value and an actual value, and utilizing an Adam optimizer to adjust the learning rate and correct the gradient estimation;
s1022: selecting convolution kernel size of 3 and number of (16, 64, 128), selecting Relu as an activation function for acceleration, setting the number of neurons in a full connection layer to be 5, and constructing a driver style recognition model based on a CNN convolution neural network;
s1023: and (3) carrying out effectiveness evaluation and verification by adopting a cross entropy (cross entropy) form penalty function and accuracy (accuracy), wherein the cross entropy form penalty function formula is as follows:
wherein N is the total amount of data, K is the number of target tasks, y i，k Is the value of a certain sample data in class K, p i，k Representing the possible probability of predicting it as class K.
The accuracy (accuracy) formula is:
further, the step S103 specifically includes the following steps:
s1031: inputting driving data of a driver into a driver style recognition model to obtain the style of the current driver;
s1032: analyzing the braking intention of the driver according to the recognized style type of the driver, and acquiring a target braking force;
s1033: under the condition of meeting an I curve and an ECE (engineering environmental engineering) regulation, a maximum energy recovery control strategy is adopted, and front and rear axle braking force and mechanical and friction braking force are distributed, wherein the I curve expression is as follows:
wherein F br For rear axle braking force, F bf Is the braking force of the front axle, m is the mass of the whole vehicle, g is the gravity coefficient, h g Is the height of the center of mass, b is the distance from the center of mass to the rear axle, and L is the distance between the front axle and the rear axle;
the ECE regulation expression is as follows:
where z is the braking intensity.
S1034: and controlling the motor to recover braking energy.
The invention has the beneficial effects that: compared with the prior art:
(1) The invention refers to NGSIM data set information to select the characteristic information, preprocesses the driver data, selects the strong association data, and classifies the driver style by using the strong association characteristic data, thereby reducing the model calculation amount and improving the identification speed of the method.
(2) The method classifies the characteristic information of the driver by using a clustering algorithm, trains sample data by using a convolutional neural network, establishes a driver style recognition model, and improves the recognition precision of the driver style.
(3) The invention can identify different driving styles of drivers and analyze the braking intention of the drivers according to the driving styles, thereby greatly improving the integration of the system and the driving experience.
According to the invention, on the premise of ensuring the comfort of a driver, the maximum braking energy recovery control strategy is adopted for energy recovery, the travel mileage of the pure electric vehicle is increased, and the energy consumption economy of the pure electric vehicle is realized.
Drawings
The above and/or additional aspects and advantages of embodiments of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flowchart of a pure electric vehicle braking energy recovery method based on driver style recognition according to an embodiment of the present invention;
FIG. 2 is a detailed flowchart of step S101;
FIG. 3 is a diagram showing the result of the distribution of driving style characteristic parameters;
FIG. 4 is a graph of the variation of the accuracy of the training set and the validation set;
FIG. 5 is a graphical illustration of vehicle demand braking force versus brake pedal displacement for different driving styles;
FIG. 6 is a graph illustrating a vehicle braking force distribution according to one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a pure electric vehicle braking energy recovery method based on driver style identification, and FIG. 1 is a flow chart of the method in the embodiment of the invention.
A pure electric vehicle braking energy recovery method based on driver style recognition comprises the following steps:
s101: classifying the driver style by preprocessing the NGSIM data set and selecting and optimizing the driver style characteristic parameters;
s102: training the sample data by adopting a convolutional neural network, and establishing a driver style identification model;
s103: and analyzing the braking intention of the driver through the style type of the driver, distributing the braking force according to the proposed energy recovery strategy, and controlling the motor to recover the energy.
Further, as a preferred implementation manner, as shown in fig. 2, the step S101 specifically includes the following steps:
s1011: and removing abnormal data in the NGSIM data set, performing smooth denoising treatment on local x and local y values in the data set by adopting a Savitzky-Golay filtering algorithm, recalculating speed and acceleration, and optimizing by using a matrix expression. The Savitzky-Golay filter algorithm function is as follows:
wherein
The smoothing coefficient was obtained by least squares fitting.
Further, the dimension and the unit of different characteristic parameters in the data set are matched by using a mix-max standardization method. The functional formula is:
where max (x) is the maximum value of vector x and min (x) is the minimum value of vector x.
S1012: selecting an average vehicle speed v mean Maximum vehicle speed v max Minimum vehicle speed v min Standard deviation of velocity σ v Average acceleration a mean Maximum acceleration a max Minimum acceleration a min Acceleration standard deviation sigma a And the leading vehicle distance l is the style characteristic of the driver, specific parameters of the driver are calculated and optimized, and the Factor Analysis method is adopted to perform dimension reduction processing on the characteristic parameters. The factor analysis model expression form is as follows:
x i ＝a 1 F 1 +a 2 F 2 +...+a p F p +η i
wherein x is i Is the ith observable variable (i =1,2, 3.., k), F j Is a common factor (j =1,2, 3.., p), and p < k; a is a p Is a factor load.
Further, assuming that the influence of each common factor on each characteristic variable is a linear relation, a Z-score standardization method is adopted to carry out standardization processing on sample data:
x * ＝(x-μ)/σ
wherein x is * For the value of the normalized access travel data x, μ is the average value of the travel data to be normalized, and σ denotes the standard deviation of the travel data to be normalized.
Further, derived, the common factor can be expressed as:
F j ＝b j1 x 1 +b j2 x 2 +...+b jp x p ，j＝1，2，...，m
the calculated common factors are normalized data with a mean of 0 and a standard deviation of 1.
S1013: selecting the average vehicle speed v according to the index that the sum of squares of the extracted loads is greater than 75% mean Maximum vehicle speed v max Minimum vehicle speed v min Speed standard deviation σ v And (4) clustering the common factors by adopting a K-means + + clustering algorithm to minimize the loss function, and analyzing the result. The loss function is defined as:
wherein x i Represents the ith sample, c i Is x i Cluster of which, mu ci Represents the center point for each cluster, and M is the total number of samples.
Further, taking the sample data set and the initial clustering number k as input, randomly selecting an initial clustering center point (c) in the sample set 1 (1) ，c 2 (1) ，...，c k (1) ) (ii) a Calculating Euclidean distance between each data and each clustering center
Dividing each data into the nearest clustering centers, and updating the clustering centers once every time iterative computation is performed to obtain
When the calculation process meets a certain condition, calculating a cost function
And judging whether the driver style clustering model is good or bad, wherein the smaller the target function is, the better the clustering model is.
As is clear from the driving style characteristic parameter distribution results, as shown in fig. 3, the driving style of category 1 is a cautious style, the driving style of category 2 is a normal style, and the driving style of category 3 is an aggressive style.
S1014: and analyzing the clustering result by using SPSS software to obtain a driver style classification result.
Further, the step S102 specifically includes the following steps:
s1021: given an input driving data set, setting a penalty function L (y, y ^) to judge the error between an output predicted value and an actual value, and respectively calculating a net input value z of each layer l And an activation value a l Output to the last layer, and then output the error term delta of each layer l And (4) performing inverse propagation, namely propagating the initial layer to the initial layer by layer, and updating all parameters by calculating parameter partial derivatives. And adjusting the learning rate and estimating and correcting the gradient by using an Adam optimizer, wherein the Adam algorithm calculates the square g of the gradient n 2 And gradient g n Is calculated by an exponentially weighted average of (a). The parameter updating difference is as follows:
wherein
And
the learning rate α is set to 0.001 to obtain a weighted average value after correction.
S1022: selecting convolution kernel size as 3 and number as (16, 64, 128), selecting Relu as an activation function for acceleration, setting the number of neurons in a full connection layer as 5, and constructing a driver style recognition model based on a CNN convolution neural network;
s1023: carrying out effectiveness evaluation and verification by adopting a penalty function in the form of cross entropy (lateral entropy) and accuracy (accuracy) when p is i，k ＝1，y i，k If y is not less than 1, the prediction is correct i，k And logp i，k If the value of (2) is a negative value, the prediction result is false, the penalty function becomes larger, the adjustment is continuously carried out according to the penalty function, the Adam optimizer optimizes the gradient descent algorithm, and the minimum penalty function is ensured. The cross entropy form penalty function formula is:
wherein N is the total amount of data, K is the target task number, y i，k Is the value of a certain sample data in class K, p i，k Representing the possible probability of predicting it as class K.
The accuracy (accuracycacy) formula is:
further, as shown in fig. 4, the more the number of iterations is, the more the training accuracy and the verification accuracy are over 90%, so that the validity of the driver style identification model is proved.
The step S103 specifically includes the following steps:
s1031: inputting driving data of a driver into a driver style recognition model to obtain the style of the current driver;
it should be noted that the preset corresponding relationship between the brake pedal displacement and the required braking force corresponding to the results of different driving styles is established in advance. When the automobile brakes, the brake pedal pushes the master cylinder push rod to change in displacement, the master cylinder push rod pushes the hydraulic cavity piston to change, so that the master cylinder pressure and the front and rear wheel cylinder pressure (namely the 'p-V characteristic' of the wheel cylinders) are changed, and the front and rear wheel cylinder pressure changes directly cause the braking force to change. Therefore, the embodiment of the invention establishes the corresponding relation between the brake pedal displacement and the total braking force required by the driver, and as shown in fig. 5, the actual required pressure needs to be calibrated according to the actual vehicle.
S1032: analyzing the braking intention of the driver according to the recognized style type of the driver, acquiring target braking force, and judging whether the vehicle meets the condition requirement of entering a braking energy recovery mode or not by the vehicle control unit according to the received battery state signal, vehicle speed signal and braking strength demand signal;
it should be noted that, if the battery SOC signal is greater than the maximum SOC value that allows energy recovery max Or when the vehicle speed signal is less than the lowest vehicle speed allowing energy recovery, or the braking intensity demand signal is greater than the maximum braking intensity allowed by the whole vehicle, judging that the vehicle cannot enter a regenerative braking mode, and judging that the regenerative braking force F is m And =0, the braking demand is completely provided by the friction braking forces of the front and rear axles according to an ideal front and rear axle braking force distribution curve I curve.
S1033: when the vehicle meets the condition requirement of entering a braking energy recovery mode, under the condition of meeting an I curve and an ECE regulation, a maximum energy recovery control strategy is adopted, and the braking force of a front axle and a rear axle and the braking force of a machine and friction are distributed, as shown in FIG. 6, the specific braking force distribution strategy is as follows:
when z is more than 0 and less than or equal to 0.2 (the intersection of the lower ECE boundary line and the horizontal axis), the total braking force is completely provided by the front axle electric braking force:
when z is more than 0.2 and less than or equal to 0.35 (the intersection point of the lower ECE boundary line and the corresponding f line when the braking strength z = 0.5), the total braking force is distributed according to the lower ECE regulation boundary line:
when z is more than 0.35 and less than or equal to 0.5, the total braking force is distributed along the f line:
when z > 0.5, the total braking force is distributed along the I-curve:
wherein F br For rear axle braking force, F bf Is the braking force of the front axle, m is the mass of the whole vehicle, g is the gravity coefficient, h g Is the height of the center of mass, b is the distance from the center of mass to the rear axle, L is the distance between the front axle and the rear axle, L r Is the distance from the front axle to the center of mass, z is the brake strength, and μ is the coefficient of friction.
It should be noted that, in the braking force distribution, the following constraints are mainly considered in the present invention:
1) In order to prevent dangerous side slipping due to wheel locking, the actual front and rear brake force distribution lines of the vehicle should always be below the ideal brake force distribution curve (I curve);
2) In order to maximize the recovery of braking energy, the embodiment of the invention distributes as much braking force as possible to the front wheels under the premise of meeting the I curve and the ECE regulation, namely the total braking force distribution is along the lower boundary curve of the ECE regulation.
S1034: and controlling the motor to recover braking energy.
It should be noted that, when the maximum value of the braking force F of the motor is F m_max Greater than the braking force F required by the front axle bf The front axle braking force is totally made of the motor braking force F m Providing, at this time, a motor braking force F m ＝F bf (ii) a If the motor braking force F m Maximum value is less than the braking force F required by the front axle bf Then, the motor braking force F is explained m The total braking force of the front axle cannot be met, and an additional hydraulic braking force F is required hf Compensating for residual required braking force, at which time the motor braking force F m ＝F m_max Extra hydraulic braking force F hf ＝F bf -F m_max 。
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (6)
1. A pure electric vehicle braking energy recovery method based on driver style recognition is characterized by comprising the following steps:
s101: classifying the driver styles by preprocessing the NGSIM data set and selecting and optimizing driver style characteristic parameters;
s102: training the sample data by adopting a convolutional neural network, and establishing a driver style identification model;
s103: and analyzing the braking intention of the driver through the style and the type of the driver, distributing braking force according to the proposed energy recovery strategy, and controlling a motor to recover energy.
2. The pure electric vehicle braking energy recovery method based on driver style recognition of claim 1, wherein step S101 specifically includes:
s1011: removing abnormal data in the NGSIM data set, performing smooth denoising processing on the data stream by adopting a Savitzky-Golay filtering algorithm, and standardizing by using a max-min method;
s1012: selecting average vehicle speed upsilon mean Maximum vehicle speed upsilon max Minimum vehicle speed v min Speed standard deviation σ υ Average acceleration a mean Maximum acceleration a max Minimum acceleration a min Acceleration standard deviation sigma a And the involvement distance l is the style characteristic of the driver, specific parameters of the driver are calculated and optimized, and the dimension reduction processing is carried out on the characteristic parameters by adopting a Factor Analysis method;
s1013: selecting average vehicle speed upsilon according to the index that the sum of squares of extracted loads is larger than 75% mean Maximum vehicle speed v max Minimum vehicle speed v min Speed markTolerance σ υ And (4) clustering the common factors by adopting a K-means + + clustering algorithm to minimize the loss function, and analyzing the result.
3. The pure electric vehicle braking energy recovery method based on driver style recognition of claim 1, wherein step S101 specifically includes:
s1021: giving an input driving data set, setting a penalty function L (y, y ^) to judge the error between an output predicted value and an actual value, and adjusting the learning rate and correcting the gradient estimation by using an Adam algorithm;
s1022: selecting convolution kernel size as 3 and number as (16, 64, 128), selecting Relu as an activation function for acceleration, setting the number of neurons in a full connection layer as 5, and constructing a driver style recognition model based on a CNN convolution neural network;
s1023: and carrying out effectiveness evaluation and verification by adopting a cross entropy form penalty function and accuracy.
4. The pure electric vehicle braking energy recovery method based on driver style identification as claimed in claim 3, wherein in step S1021, the Adam algorithm calculates gradient square g n 2 And gradient g n The parameter update difference is:
wherein
And
the learning rate α is set to 0.001 to obtain a weighted average value after correction.
5. The pure electric vehicle braking energy recovery method based on driver style recognition of claim 1, wherein step S103 specifically includes:
s1031: inputting driving data of a driver into a driver style recognition model to obtain the style of the current driver;
s1032: analyzing the braking intention of the driver according to the recognized style type of the driver, and acquiring a target braking force;
s1033: under the condition of meeting the I curve and ECE regulations, a maximum energy recovery control strategy is adopted, and front and rear axle braking force and mechanical and friction braking force are distributed.
6. The pure electric vehicle braking energy recovery method based on driver style identification as claimed in claim 5, wherein when motor braking force is maximum F m_max Greater than the braking force F required by the front axle bf The front axle braking force is totally made of the motor braking force F m Providing, at this time, a motor braking force F m ＝F bf (ii) a If the motor braking force F m The maximum value of which is less than the braking force F required by the front axle bf Then, the motor braking force F is explained m The total braking force of the front axle cannot be satisfied, and an additional hydraulic braking force F is required hf Compensating for residual required braking force, at which time the motor braking force F m ＝F m_max Extra hydraulic braking force F hf ＝F bf -F m_max 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211436587.1A CN115675099A (en) | 2022-11-16 | 2022-11-16 | Pure electric vehicle braking energy recovery method based on driver style recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211436587.1A CN115675099A (en) | 2022-11-16 | 2022-11-16 | Pure electric vehicle braking energy recovery method based on driver style recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115675099A true CN115675099A (en) | 2023-02-03 |
Family
ID=85053408
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211436587.1A Pending CN115675099A (en) | 2022-11-16 | 2022-11-16 | Pure electric vehicle braking energy recovery method based on driver style recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115675099A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116811894A (en) * | 2023-08-30 | 2023-09-29 | 北京理工大学 | Continuous driving style identification method, system and equipment |
| CN117021959A (en) * | 2023-10-10 | 2023-11-10 | 北京航空航天大学 | Method for acquiring coasting recovery torque based on driving style identification |
| CN118457248A (en) * | 2024-04-29 | 2024-08-09 | 湖北君云科技有限公司 | Kinetic energy recovery method and system based on user characteristic difference |
-
2022
- 2022-11-16 CN CN202211436587.1A patent/CN115675099A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116811894A (en) * | 2023-08-30 | 2023-09-29 | 北京理工大学 | Continuous driving style identification method, system and equipment |
| CN116811894B (en) * | 2023-08-30 | 2023-11-21 | 北京理工大学 | Continuous driving style identification method, system and equipment |
| CN117021959A (en) * | 2023-10-10 | 2023-11-10 | 北京航空航天大学 | Method for acquiring coasting recovery torque based on driving style identification |
| CN117021959B (en) * | 2023-10-10 | 2023-12-22 | 北京航空航天大学 | Method for acquiring coasting recovery torque based on driving style identification |
| CN118457248A (en) * | 2024-04-29 | 2024-08-09 | 湖北君云科技有限公司 | Kinetic energy recovery method and system based on user characteristic difference |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115675099A (en) | Pure electric vehicle braking energy recovery method based on driver style recognition | |
| CN110949398B (en) | Method for detecting abnormal driving behavior of first-vehicle drivers in vehicle formation driving | |
| CN107958269B (en) | Driving risk degree prediction method based on hidden Markov model | |
| CN103003854B (en) | Systems and methods for scheduling driver interface tasks based on driver workload | |
| CN111332362B (en) | Intelligent steer-by-wire control method integrating individual character of driver | |
| CN110262491B (en) | Method and system for predicting vehicle braking intention based on hybrid learning mode | |
| CN112046489B (en) | Driving style identification algorithm based on factor analysis and machine learning | |
| CN111783943B (en) | LSTM neural network-based driver braking strength prediction method | |
| CN109552289B (en) | Automobile self-adaptive auxiliary braking system and control method thereof | |
| CN111547064B (en) | Driving style recognition and classification method for automobile adaptive cruise system | |
| CN113788021A (en) | Adaptive following cruise control method combined with preceding vehicle speed prediction | |
| CN105034986B (en) | A kind of driver's steering characteristic on-line identification method and device | |
| CN108482481B (en) | Four-wheel steering control method for four-wheel independent drive and steering electric automobile | |
| CN111340074B (en) | Driver braking intention identification method based on improved RBF neural network | |
| CN115774942A (en) | Driving style identification model modeling and statistical method based on Internet of vehicles real vehicle data and SVM | |
| CN115186594A (en) | Energy-saving speed optimization method under influence of man-vehicle-road coupling | |
| CN109910865B (en) | Vehicle early warning braking method based on Internet of things | |
| CN103231710B (en) | Driver workload based system and method for scheduling driver interface tasks | |
| CN110341666B (en) | Braking force curve planning algorithm of vehicle active braking system based on A-law 13 broken line | |
| CN113341994A (en) | Intelligent automobile path tracking control method based on optimal control of piecewise affine system | |
| CN114613131B (en) | Safety margin-based personalized forward collision early warning method | |
| CN114154227B (en) | Self-adaptive learning method for braking process of heavy trailer | |
| CN114312769B (en) | Intelligent vehicle emergency braking method and system considering cycle transverse and longitudinal movement intention | |
| CN114228507B (en) | Intelligent electric drive vehicle regenerative braking control method utilizing front vehicle information | |
| CN117184103A (en) | Driving style identification method, system and equipment |
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 |