CN112580251A - Hybrid electric vehicle energy management method based on traffic information and model predictive control - Google Patents

Hybrid electric vehicle energy management method based on traffic information and model predictive control Download PDF

Info

Publication number
CN112580251A
CN112580251A CN202011279510.9A CN202011279510A CN112580251A CN 112580251 A CN112580251 A CN 112580251A CN 202011279510 A CN202011279510 A CN 202011279510A CN 112580251 A CN112580251 A CN 112580251A
Authority
CN
China
Prior art keywords
vehicle
speed
vehicle speed
predicted
time
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
Application number
CN202011279510.9A
Other languages
Chinese (zh)
Other versions
CN112580251B (en
Inventor
何洪文
王云龙
赵旭阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN202011279510.9A priority Critical patent/CN112580251B/en
Publication of CN112580251A publication Critical patent/CN112580251A/en
Application granted granted Critical
Publication of CN112580251B publication Critical patent/CN112580251B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
    • G07C5/0841—Registering performance data
    • 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
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0019—Control system elements or transfer functions
    • B60W2050/0028—Mathematical models, e.g. for simulation
    • B60W2050/0031—Mathematical model of the vehicle
    • 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
    • Y02T10/80—Technologies aiming to reduce greenhouse gasses emissions common to all road transportation technologies
    • Y02T10/84—Data processing systems or methods, management, administration

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Evolutionary Computation (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Traffic Control Systems (AREA)
  • Electric Propulsion And Braking For Vehicles (AREA)

Abstract

The invention discloses a hybrid electric vehicle energy management method based on traffic information and model predictive control, which specifically comprises data set extraction, an optimized predictive model, safe vehicle speed correction, crossing speed planning, rolling optimization and feedback correction, wherein the vehicle speed predictive model is obtained through data acquisition and analysis, and the threshold and the weight of the vehicle speed predictive model are optimized by using a particle swarm algorithm; according to the surrounding vehicle information provided by the vehicle-vehicle, calculating the safe vehicle speed of the vehicle at the next moment and correcting the predicted vehicle speed; the crossing passing speed planning is to plan an optimal speed sequence of the crossing according to the predicted speed, the information of the front vehicle and the information of the traffic signal lamp when the crossing passes; the rolling optimization and feedback correction are based on predicted and planned vehicle speed, the energy of the hybrid power system is optimally distributed through a dynamic planning algorithm, and the closed-loop control of the whole prediction model control framework is completed through feedback.

Description

Hybrid electric vehicle energy management method based on traffic information and model predictive control
Technical Field
The invention relates to an energy management method of a hybrid electric vehicle, in particular to an energy management method based on traffic information and model predictive control, which makes full use of the traffic information and the surrounding vehicle information, reduces the vehicle speed prediction error under the condition that the vehicle follows the driving by fusing a speed prediction model of the traffic information and pre-judging the condition that the vehicle passes through a traffic intersection in advance, particularly reduces the prediction fluctuation when the vehicle accelerates and decelerates, plans the optimal speed sequence of the vehicle passing through the intersection, reasonably distributes the power requirement of a double-planet row hybrid electric system, and effectively improves the fuel economy of the hybrid electric vehicle.
Background
With the increasing demand for automobiles and the shortage of fossil fuel energy, in the near future, conventional fuel automobiles will certainly be replaced by new energy automobiles to some extent. The hybrid electric vehicle based on the hybrid power system with the double-planet-row structure not only has the convenience of the traditional fuel vehicle, but also is not limited by the low energy density of the battery of the pure electric vehicle. In addition, the motor is used alone to drive, so that pollution-free emission of tail gas can be realized. Therefore, there is a need to further improve the energy management strategy of new energy vehicles on the basis of the prior art.
The global optimization algorithm represented by Dynamic Programming (DP) needs to obtain global conditions before obtaining a global optimal result, which inevitably results in huge calculation amount and cannot run on a vehicle controller in real time. To make better use of global optimization, an optimal control action can be found in the predicted time domain at each sampling instant, thus ensuring optimality and real-time control, i.e. Model Predictive Control (MPC). MPC is an ideal predictive control framework, and has the main advantages of strong multivariable and constrained processing capability in the optimal control problem, and the online rolling optimization method and the feedback self-correction strategy are adopted to effectively overcome the dynamic influence of factors such as uncertainty, hysteresis, time variation and the like of a controlled system, so that the expected control target is realized, and the system has good robustness and stability.
Disclosure of Invention
The invention aims to provide a novel model predictive control architecture fused with traffic information for an energy management method based on model predictive control, and the proposed MPC architecture is realized based on a traffic scene under a vehicle network environment and mainly solves the energy management problem oriented to hybrid electric vehicles.
The invention provides a hybrid electric vehicle energy management method based on traffic information and model predictive control, which is characterized by comprising the following steps of:
step 1, recording and storing historical vehicle speed data by using a vehicle networking environment and a vehicle speed recording device, preprocessing the vehicle speed data, analyzing characteristic parameters of historical working conditions, selecting a section of reasonable data, and extracting a training set and a test set;
step 2, optimizing an original vehicle speed prediction model based on an extreme learning machine algorithm through a particle swarm algorithm based on a training set and a test set;
step 3, under the condition that the vehicle follows, according to the surrounding vehicle information provided by the vehicle-vehicle, calculating the safe vehicle speed of the vehicle at the next moment, and after obtaining the safe vehicle speed, correcting the vehicle speed predicted by the prediction model in the step 2;
step 4, planning an optimal speed sequence passing through the intersection according to the predicted speed, the information of the front vehicle and the information of the traffic signal lamp when the vehicle is about to pass through the traffic intersection;
and 5, optimally distributing the energy of the hybrid power system through rolling optimization and feedback correction based on the predicted and planned vehicle speed.
Further, training the optimized ELM vehicle speed prediction model comprises: firstly, carrying out random assignment on an initial threshold B and a weight IW of a vehicle speed prediction model, further adopting a particle swarm optimization PSO to map IW and B to different particles respectively in order to improve prediction accuracy in an algorithm, and obtaining the threshold B and the weight IW which can improve ELM prediction accuracy after iteration.
Further, the vehicle-to-vehicle provided surrounding vehicle information includes: the speed of the lead vehicle, the speed of the vehicle and the distance between the two vehicles.
Further, the safe vehicle speed is calculated according to the following formula:
L(vf)+vfτ≤L(vl)+g (1)
Figure BDA0002780278120000021
Figure BDA0002780278120000022
Figure BDA0002780278120000023
Figure BDA0002780278120000024
Figure BDA0002780278120000025
vf＝min{vmax，v(t)+a(t)·Δt，vsafe(t)} (7)
v＝max{0，vf-rand(0，∈a)} (8)
wherein, L (v)f) Braking distance to car, vfFor following speed, τ is driver reaction time, L (v)l) For braking distance of lead car, vlThe vehicle speed is led, g is the distance between the leading vehicle and the following vehicle,
Figure BDA0002780278120000026
in order to obtain the average speed of the leading car and the following car,
Figure BDA0002780278120000027
is that the vehicle speed is
Figure BDA0002780278120000028
The braking distance, v is the safe vehicle speed, b is the maximum deceleration during braking, the integral term related to s is the braking distance with the braking acceleration of-b (v), vmaxIs road speed limit, v (t) is speed at time t, a (t) is acceleration at time t, delta t is simulation time step length, v (t) is speed at time t, and v (t) is speed at time tsafe(t) is the safe speed at time t, a is the maximum acceleration, and belongs to [0, 1 ]]Is an extrinsic defect parameter.
And further, the correction of the vehicle speed is to compare errors of the first second predicted vehicle speed and the safe vehicle speed with a correction threshold value, determine the value of the corrected vehicle speed, if the errors are smaller than or equal to the correction threshold value, the corrected vehicle speed is the predicted vehicle speed, if the errors are larger than the correction threshold value, the corrected vehicle speed is the safe vehicle speed, and the residual predicted vehicle speed sequence is corrected according to the correction proportion of the first second.
Further, whether the vehicle can pass through the intersection is divided into two conditions of whether the vehicle exists in the front or not:
1) when no vehicle is in front, whether the vehicle can pass through the intersection is judged according to the following formula:
Figure BDA0002780278120000031
wherein, TchangeTime remaining for traffic light change, v0As initial velocity, xdisThe distance required to be traveled by the crossing is represented by P1, which is the traffic information allowing the vehicle to pass through, and P0, which is the traffic information not allowing the vehicle to pass through;
2) when a vehicle is ahead and cannot pass through a crossing, the position of final parking waiting needs to be predicted in advance, specifically, firstly, the integral of the predicted speed sequence is calculated and is compared with xdisA comparison is made to determine whether the vehicle is able to pass through the intersection. If so, the vehicle will continue to travel in the vehicle following mode; if not, a determination is made as to whether the vehicle is able to pass through the intersection from the vehicle closest to the intersection: assuming that the vehicle is running at a constant speed, TchangeDisplacement in time and distance x from nth vehicle to crossingn_disComparing until a vehicle which can not pass is found, and finally moving distance x of the vehiclefinalThen the optimal control sequence can be obtained through a dynamic programming algorithm.
Further, the cost function and the constraint condition of whether the vehicle can pass through the intersection are specifically as follows:
1) in the case of no vehicle ahead, the constraint and cost functions are as follows:
Figure BDA0002780278120000032
Figure BDA0002780278120000033
Figure BDA0002780278120000034
wherein x is1Is the speed state quantity; x is the number of2Is a displacement state quantity; u (t) is an acceleration control amount; v. of0Is the initial speed; x0Is the initial displacement; j is the total oil consumption in the 1-N period; l is a cost function of a single stage, equal to the work done by the instantaneous vehicle to overcome the resistance; v. oftIs the speed of time t, xtIs a shift of time t, atIs the acceleration at time t; v. ofminIs the minimum speed; v. ofmaxA maximum speed; a isminIs the minimum acceleration; a ismaxIs the maximum acceleration;
2) in case of a vehicle in front:
Figure BDA0002780278120000035
wherein v istIs the speed of time t, xtIs a shift of time t, atIs the acceleration of time t
Further, the step 5 adopts rolling optimization based on a dynamic programming algorithm, namely, the predicted future vehicle speed at each moment is used as input, and the first of the optimized result sequence is taken as the final control quantity when the output is output; and after the controlled variable acts on the vehicle, performing feedback correction, namely feeding back the obtained actual system state, and taking the actual system state as a control reference at the next moment to correspondingly correct the predicted value so as to ensure that the whole model predictive control belongs to closed-loop control.
The invention has the beneficial effects that: the instant information provided by the vehicle-vehicle (V2V) and the traffic light information (V2I) in the vehicle networking environment is fully utilized, the vehicle speed and the planned vehicle speed are predicted reasonably and precisely through the optimized model prediction control framework, the energy of the hybrid power system is effectively distributed, and the fuel economy of the hybrid electric vehicle is improved.
Drawings
FIG. 1 is a schematic diagram of a model predictive control architecture incorporating traffic information
FIG. 2 is a schematic diagram of selection of historical conditions and division of training set and test set
FIG. 3 is a schematic diagram of the optimization process of PSO to ELM initial value
FIG. 4 is a schematic diagram of the comparison of the predicted vehicle speed with the safe vehicle speed and the actual vehicle speed in the future 10s
FIG. 5 is a schematic diagram of a correction to a predicted vehicle speed of a vehicle based on a safe vehicle speed
FIG. 6 is a schematic view showing a process of calculating a final parking position of a vehicle in the presence of the vehicle
FIG. 7 is a schematic diagram of joint simulation of SUMO and MATLAB
FIG. 8 is a schematic view of a scroll optimization
FIG. 9 is a schematic diagram of feedback correction
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood 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.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The overall architecture of model predictive control integrated with traffic information is shown in fig. 1, and since traffic facilities in an internet of vehicles environment in real life are not sound, the present invention adopts SUMO traffic simulation software to provide V2V and V2I traffic information. Firstly, historical vehicle speed data are recorded and stored by using a vehicle networking environment and a vehicle speed recording device loaded on a vehicle, after data preprocessing, characteristic parameter analysis is carried out on historical working conditions, a section of reasonable data is selected, and a training set and a test set are extracted. The selected historical data characteristic parameters and exemplary values are shown in table 1 below:
Figure BDA0002780278120000051
TABLE 1 example of historical operating condition characteristic parameters
The test set and training set are divided according to the selected historical operating conditions of the characteristic parameters as shown in FIG. 2.
Based on a training set, training an optimized Extreme Learning Machine (ELM) vehicle speed prediction model, firstly, carrying out random assignment on an initial threshold B and a weight IW of the vehicle speed prediction model, further adopting a particle swarm optimization PSO to map IW and B to different particles respectively in order to improve prediction accuracy from an algorithm, obtaining the threshold B and the weight IW capable of improving the ELM prediction accuracy after iteration, and firstly initializing PSO parameters, mapping the particles to the ELM weight IW and the threshold B and carrying out ELM training by the algorithm combination method and the optimization process as shown in figure 3. And testing on the ELM test set to obtain an error MSE and further obtain a PSO adaptability value. Updating speed and position information, recalculating fitness, updating weight 1W and threshold B, performing ELM training again to obtain corresponding error MSE, comparing whether the error is lower than a set value, if so, outputting weight IW and threshold B, otherwise, returning to continuously update speed and position information, and recalculating the fitness.
In the vehicle following situation, according to the surrounding vehicle information provided by the vehicle-vehicle (V2V): the safe speed v of the vehicle at the next moment is calculated according to the speed of the vehicle in front, the distance between the two vehicles, the speed of the vehicle and the like, and the specific derivation formula is as follows:
L(vf)+vfτ≤L(vl)+g (1)
Figure BDA0002780278120000052
Figure BDA0002780278120000053
Figure BDA0002780278120000054
Figure BDA0002780278120000055
Figure BDA0002780278120000056
vf＝min{vmax，v(t)+a(t)·Δt，vsafe(t)} (7)
v＝max{0，vf-rand(0，∈a)} (8)
wherein, L (v)f) Braking distance to car, vfFor following speed, τ is driver reaction time, L (v)l) For braking distance of lead car, vlThe vehicle speed is led, g is the distance between the leading vehicle and the following vehicle,
Figure BDA0002780278120000057
in order to obtain the average speed of the leading car and the following car,
Figure BDA0002780278120000058
is that the vehicle speed is
Figure BDA0002780278120000059
The braking distance, v is the safe vehicle speed, b is the maximum deceleration during braking, the integral term related to s is the braking distance with the braking acceleration of-b (v), vmaxIs road speed limit, v (t) is speed at time t, a (t) is acceleration at time t, delta t is simulation time step length, v (t) is speed at time t, and v (t) is speed at time tsafe(t) is the safe speed at time t, a is the maximum acceleration, and belongs to [0, 1 ]]Is an extrinsic defect parameter.
After obtaining the safe vehicle speed, correcting the vehicle speed predicted by the prediction model in the step 2: the correction of the vehicle speed is to compare the error of the first second predicted vehicle speed and the safe vehicle speed with a correction threshold value to determine the value of the corrected vehicle speed, if the error is less than or equal to the correction threshold value, the corrected vehicle speed is taken as the predicted vehicle speed, if the error is greater than the correction threshold value, the corrected vehicle speed is taken as the safe vehicle speed, the residual predicted vehicle speed sequence is corrected according to the correction proportion of the first second, wherein error is the error between the first second speed and the safe vehicle speed in the predicted vehicle speed sequence, and epsilon is the correction threshold value. The vehicle speed prediction and correction results in the present embodiment are shown in fig. 4 and 5.
When the vehicle is about to pass through the traffic intersection, an optimal speed sequence passing through the intersection is planned according to the predicted vehicle speed, the front vehicle information and the traffic light information (V2I). Whether a vehicle can pass through an intersection is determined not only by a signal lamp but also by the influence of a vehicle ahead, so that the method is divided into two cases: when passing through the intersection, no vehicle in front runs and a vehicle in front runs.
(1) The conditions of whether the vehicle can pass through the intersection or not when no vehicle exists in the front are shown in formula 9 and table 2:
Figure BDA0002780278120000061
Figure BDA0002780278120000062
TABLE 2 determination of crossing
Where T _ change is the remaining time of the change of the traffic light, green-yellow indicates a yellow light converted from a green light, and red _ yellow indicates a yellow light converted from a red light.
Since the starting and ending speed of the vehicle and the displacement of this distance are known, the problem model can be converted into a linear discrete system, the control sequence with the least effort can be found by the DP algorithm and used as a control reference for the driver, the cost function and constraint conditions are as follows:
Figure BDA0002780278120000063
Figure BDA0002780278120000064
Figure BDA0002780278120000065
wherein x is1Is the speed state quantity; x is the number of2Is a displacement state quantity; u (t) is an acceleration control amount; v. of0Is the initial speed; x0Is the initial displacement; j is the total oil consumption in the 1-N period; l is a cost function of a single stage, equal to instantaneousWork done by the vehicle to overcome the resistance; v. oftIs the speed of time t, xtIs a shift of time t, atIs the acceleration at time t; v. ofminIs the minimum speed; v. ofmaxA maximum speed; a isminIs the minimum acceleration; a ismaxIs the maximum acceleration;
(2) case of vehicle in front: compared with no vehicle, first, the integral of the predicted speed sequence is calculated and compared with xdisA comparison is made to determine whether the vehicle is able to pass through the intersection. If so, the vehicle will continue to travel in the vehicle following mode; if not, a determination is made as to whether the vehicle is able to start passing through the intersection from the vehicle closest to the intersection, predicting the position x of the final stop wait_final. As shown in fig. 6, it is assumed that there are m vehicles between the current vehicle and the intersection, n represents the nth vehicle from the intersection, and k is the number of vehicles that have failed to pass during the vehicle traveling. Firstly, obtaining a predicted vehicle speed sequence of 10s in the future from a vehicle speed prediction model, and integrating to obtain a driving distance x of 10s in the future_10. If x_10＜xdisIf it means that the vehicle cannot pass through the intersection, it is determined whether n is equal to or less than m starting from the side close to the intersection. If yes, further judging whether the nth vehicle can pass through the intersection (v)nRepresenting the speed of the nth vehicle, xn_disRepresenting the distance from the intersection by the nth vehicle), if the vehicle can pass, judging that the (n + 1) th vehicle can pass, and if the vehicle cannot pass, all vehicles behind the nth vehicle cannot pass. The total number k of vehicles that cannot pass is calculated from the current vehicle number n. Finally, the parking position x of the vehicle is calculated according to the length of 5m and the distance between 2.5m_finalK 7.5, the distance from the intersection when parking. On the premise that equations 10 and 11 are satisfied, the newly added state quantity is constrained as follows.
Figure BDA0002780278120000071
Wherein v istIs the speed of time t, xtIs a shift of time t, atIs the acceleration at time t. The last pass under the premise that the starting and ending states are knownAnd obtaining an optimal control sequence by a dynamic programming algorithm.
An MPC framework and a hybrid electric vehicle dynamics model are built in MATLAB, a traffic vehicle dynamics joint simulation model is built through joint simulation of MATLAB and SUMO, and optimal distribution is carried out on energy of a hybrid power system through rolling optimization and feedback correction based on predicted and planned vehicle speed as shown in FIG. 7.
(1) And (3) rolling optimization: in the MPC architecture, rolling optimization based on a dynamic programming algorithm is adopted, that is, the predicted future vehicle speed at each moment is used as an input, and the output is the first of the optimized result sequence and is used as a final control quantity, as shown in fig. 8.
(2) And (3) feedback correction: after the control quantity acts on the vehicle, the obtained actual system state is fed back to be used as a control reference of the next moment, and the predicted value is correspondingly corrected, so that the closed-loop control of the whole model predictive control is ensured. This step can not only improve the accuracy of model predictive control, but also improve the robustness of the algorithm, as shown in fig. 9.
Therefore, the instant information provided by V2V and V2I in the Internet of vehicles environment can be utilized, the vehicle speed and the planned vehicle speed can be predicted reasonably and precisely through the optimized model prediction control framework, the optimal control sequence applied to the hybrid power system is calculated based on the MPC framework, and the fuel economy of the hybrid power vehicle is improved.
It should be understood that, the sequence numbers of the steps in the embodiments of the present invention do not mean the execution sequence, and the execution sequence of each process should be determined by the function and the inherent logic of the process, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (8)

1. A hybrid electric vehicle energy management method based on traffic information and model predictive control is characterized by comprising the following steps:
step 1, recording and storing historical vehicle speed data by using a vehicle networking environment and a vehicle speed recording device, preprocessing the vehicle speed data, analyzing characteristic parameters of historical working conditions, selecting a section of reasonable data, and extracting a training set and a test set;
step 2, optimizing an original vehicle speed prediction model based on an extreme learning machine algorithm through a particle swarm algorithm based on a training set and a test set;
step 3, under the condition that the vehicle follows, according to the surrounding vehicle information provided by the vehicle-vehicle, calculating the safe vehicle speed of the vehicle at the next moment, and after obtaining the safe vehicle speed, correcting the vehicle speed predicted by the prediction model in the step 2;
step 4, planning an optimal speed sequence passing through the intersection according to the predicted speed, the information of the front vehicle and the information of the traffic signal lamp when the vehicle is about to pass through the traffic intersection;
and 5, optimally distributing the energy of the hybrid power system through rolling optimization and feedback correction based on the predicted and planned vehicle speed.
2. The hybrid electric vehicle energy management method based on traffic information and model predictive control of claim 1, wherein training the optimized ELM vehicle speed prediction model comprises: firstly, carrying out random assignment on an initial threshold B and a weight IW of a vehicle speed prediction model, further adopting a particle swarm optimization PSO to map IW and B to different particles respectively in order to improve prediction accuracy in an algorithm, and obtaining the threshold B and the weight IW which can improve ELM prediction accuracy after iteration.
3. The hybrid vehicle energy management method based on traffic information and model predictive control of claim 1, wherein the vehicle-to-vehicle provided surrounding vehicle information comprises: the speed of the lead vehicle, the speed of the vehicle and the distance between the two vehicles.
4. The energy management method for hybrid electric vehicle based on traffic information and model predictive control according to claim 3, characterized in that the safe vehicle speed calculation is performed according to the following formula:
L(vf)+vfτ≤L(vl)+g (1)
Figure FDA0002780278110000011
Figure FDA0002780278110000012
Figure FDA0002780278110000013
Figure FDA0002780278110000014
Figure FDA0002780278110000015
vf＝min{vmax，v(t)+a(t)·Δt，vsafe(t)} (7)
v＝max{0，vf-rand(0，∈a)} (8)
wherein, L (v)f) Braking distance to car, vfFor following speed, τ is driver reaction time, L (v)l) For braking distance of lead car, vlThe vehicle speed is led, g is the distance between the leading vehicle and the following vehicle,
Figure FDA0002780278110000021
in order to obtain the average speed of the leading car and the following car,
Figure FDA0002780278110000022
is that the vehicle speed is
Figure FDA0002780278110000027
The braking distance, v is the safe vehicle speed, b is the maximum deceleration during braking, the integral term related to s is the braking distance with the braking acceleration of-b (v), vmaxIs road speed limit, v (t) is speed at time t, a (t) is acceleration at time t, delta t is simulation time step length, v (t) is speed at time t, andsafe(t) is the safe speed at time t, a is the maximum acceleration, and belongs to [0, 1 ]]Is an extrinsic defect parameter.
5. The energy management method for hybrid electric vehicles based on traffic information and model predictive control as claimed in claim 1, wherein the vehicle speed correction is based on the comparison of the error between the first second predicted vehicle speed and the safe vehicle speed with a correction threshold value, and determines the value of the corrected vehicle speed, if the error is less than or equal to the correction threshold value, the corrected vehicle speed is the predicted vehicle speed, if the error is greater than the correction threshold value, the corrected vehicle speed is the safe vehicle speed, and the residual predicted vehicle speed sequence is corrected according to the correction proportion of the first second.
6. The energy management method for hybrid electric vehicle based on traffic information and model predictive control as claimed in claim 1, wherein whether the vehicle can pass through the intersection is divided into two cases of the vehicle in front and the vehicle in front:
1) when no vehicle is in front, whether the vehicle can pass through the intersection is judged according to the following formula:
Figure FDA0002780278110000023
wherein, TchangeTime remaining for traffic light change, v0As initial velocity, xdisThe distance between the vehicle and the traffic intersection is the current distance, wherein P is 1, the vehicle is allowed to pass through by the traffic information, and P is 0, the vehicle is not allowed to pass through by the traffic information;
2) wherein saidWhen there is a vehicle ahead and it is impossible to pass through the intersection, it is necessary to predict the position of the final stop waiting in advance, specifically, first, an integral of the predicted speed sequence is calculated and compared with xdisA comparison is made to determine whether the vehicle is able to pass through the intersection, and if so, the vehicle will continue to travel in the vehicle-following mode, and if not, a determination will be made as to whether the vehicle is able to pass through the intersection from the vehicle closest to the intersection: assuming that the vehicle is running at a constant speed, TchangeDisplacement in time and distance x from nth vehicle to crossingn_disComparing until a vehicle which can not pass is found, and finally moving distance x of the vehicle_finalThen the optimal control sequence can be obtained through a dynamic programming algorithm.
7. The hybrid electric vehicle energy management method based on traffic information and model predictive control according to claim 6, wherein the cost function and constraint conditions for passing or not passing the intersection are as follows:
1) in the case of no vehicle in front:
Figure FDA0002780278110000024
Figure FDA0002780278110000025
Figure FDA0002780278110000026
wherein x is1Is the speed state quantity; x is the number of2Is a displacement state quantity; u (t) is an acceleration control amount; v. of0Is the initial speed; x0Is the initial displacement; j is the total oil consumption in the 1-N period; l is a cost function of a single stage, equal to the work done by the instantaneous vehicle to overcome the resistance; v. oftIs the speed of time t, xtIs a shift of time t, atIs the acceleration at time t; v. ofminIs the minimum speed; v. ofmaxA maximum speed; a isminIs the minimum acceleration; a ismaxIs the maximum acceleration;
2) under the condition that there is a vehicle in front, new constraints need to be satisfied on the premise that the state constraints and the cost functions of the formulas 10 and 11 are satisfied:
Figure FDA0002780278110000031
wherein v istIs the speed of time t, xtIs a shift of time t, atIs the acceleration at time t.
8. The energy management method for hybrid electric vehicles based on traffic information and model predictive control as claimed in claim 1, characterized in that, the step 5 adopts rolling optimization based on dynamic programming algorithm, i.e. the predicted future vehicle speed at each moment is used as input, and the output is the first of the optimized result sequence as the final control quantity; and after the controlled variable acts on the vehicle, performing feedback correction, namely feeding back the obtained actual system state to be used as a control reference at the next moment, and correspondingly correcting the predicted value to ensure that the whole model predictive control belongs to closed-loop control.
CN202011279510.9A 2020-11-16 2020-11-16 Hybrid electric vehicle energy management method based on traffic information and model predictive control Active CN112580251B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011279510.9A CN112580251B (en) 2020-11-16 2020-11-16 Hybrid electric vehicle energy management method based on traffic information and model predictive control

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011279510.9A CN112580251B (en) 2020-11-16 2020-11-16 Hybrid electric vehicle energy management method based on traffic information and model predictive control

Publications (2)

Publication Number Publication Date
CN112580251A true CN112580251A (en) 2021-03-30
CN112580251B CN112580251B (en) 2022-07-12

Family

ID=75122626

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011279510.9A Active CN112580251B (en) 2020-11-16 2020-11-16 Hybrid electric vehicle energy management method based on traffic information and model predictive control

Country Status (1)

Country Link
CN (1) CN112580251B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112989715A (en) * 2021-05-20 2021-06-18 北京理工大学 Multi-signal-lamp vehicle speed planning method for fuel cell vehicle
CN114387805A (en) * 2022-01-13 2022-04-22 芜湖奇瑞科技有限公司 Intersection passing method and device of vehicle, vehicle and storage medium
CN117162976A (en) * 2023-09-08 2023-12-05 无锡车联天下信息技术有限公司 Vehicle braking control method and device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2945140A1 (en) * 2014-05-12 2015-11-18 AVL List GmbH System and method for operating a vehicle taking into account information on traffic lights and surrounding vehicles
CN106997675A (en) * 2016-01-26 2017-08-01 宿州学院 Target vehicle speed Forecasting Methodology based on Dynamic Programming
CN107346460A (en) * 2017-07-18 2017-11-14 吉林大学 Following operating mode Forecasting Methodology based on the lower front truck operation information of intelligent network contact system
US20190071084A1 (en) * 2017-09-05 2019-03-07 Arizona Board Of Regents On Behalf Of Arizona State University Model predictive adaptive cruise control for reducing rear-end collision risk with follower vehicles
CN109635914A (en) * 2018-12-17 2019-04-16 杭州电子科技大学 Optimization extreme learning machine trajectory predictions method based on hybrid intelligent Genetic Particle Swarm
CN111791887A (en) * 2020-07-03 2020-10-20 北京理工大学 Vehicle energy-saving driving method based on layered vehicle speed planning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2945140A1 (en) * 2014-05-12 2015-11-18 AVL List GmbH System and method for operating a vehicle taking into account information on traffic lights and surrounding vehicles
CN106997675A (en) * 2016-01-26 2017-08-01 宿州学院 Target vehicle speed Forecasting Methodology based on Dynamic Programming
CN107346460A (en) * 2017-07-18 2017-11-14 吉林大学 Following operating mode Forecasting Methodology based on the lower front truck operation information of intelligent network contact system
US20190071084A1 (en) * 2017-09-05 2019-03-07 Arizona Board Of Regents On Behalf Of Arizona State University Model predictive adaptive cruise control for reducing rear-end collision risk with follower vehicles
CN109635914A (en) * 2018-12-17 2019-04-16 杭州电子科技大学 Optimization extreme learning machine trajectory predictions method based on hybrid intelligent Genetic Particle Swarm
CN111791887A (en) * 2020-07-03 2020-10-20 北京理工大学 Vehicle energy-saving driving method based on layered vehicle speed planning

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
YANJUN HUANG 等: "Model predictive control power management strategies for HEVs: A review", 《JOURNAL OF POWER SOURCES》 *
王勇 等: "基于深度强化学习的插电式混合动力汽车能量管理", 《2020中国汽车工程学会年会论文集》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112989715A (en) * 2021-05-20 2021-06-18 北京理工大学 Multi-signal-lamp vehicle speed planning method for fuel cell vehicle
CN114387805A (en) * 2022-01-13 2022-04-22 芜湖奇瑞科技有限公司 Intersection passing method and device of vehicle, vehicle and storage medium
CN117162976A (en) * 2023-09-08 2023-12-05 无锡车联天下信息技术有限公司 Vehicle braking control method and device, electronic equipment and storage medium
CN117162976B (en) * 2023-09-08 2024-05-03 无锡车联天下信息技术有限公司 Vehicle braking control method and device, electronic equipment and storage medium

Also Published As

Publication number Publication date
CN112580251B (en) 2022-07-12

Similar Documents

Publication Publication Date Title
CN112580251B (en) Hybrid electric vehicle energy management method based on traffic information and model predictive control
He et al. An improved MPC-based energy management strategy for hybrid vehicles using V2V and V2I communications
CN110126841B (en) Pure electric vehicle energy consumption model prediction method based on road information and driving style
Dong et al. Practical application of energy management strategy for hybrid electric vehicles based on intelligent and connected technologies: Development stages, challenges, and future trends
CN110936949B (en) Energy control method, equipment, storage medium and device based on driving condition
CN103914985B (en) A kind of hybrid power passenger car following speed of a motor vehicle trajectory predictions method
CN111439260B (en) Network-connected commercial diesel vehicle cruise running optimization control system oriented to individual requirements
WO2021114742A1 (en) Comprehensive energy prediction and management method for hybrid electric vehicle
CN111267831A (en) Hybrid vehicle intelligent time-domain-variable model prediction energy management method
KR101607248B1 (en) Method and module for controlling a vehicle's speed based on rules and/or costs
CN109733378B (en) Offline optimized online predicted torque distribution method
CN109927709A (en) A kind of route or travel by vehicle working condition determining method, energy management method and system
CN113788021B (en) Adaptive following cruise control method combined with preceding vehicle speed prediction
CN112660130A (en) New energy automobile sliding control system and method based on intelligent networking information and new energy automobile
CN116215495A (en) Hybrid vehicle energy management optimization method, device and system
Kim et al. Parameterized energy-optimal regenerative braking strategy for connected and autonomous electrified vehicles: A real-time dynamic programming approach
Vignesh et al. Intelligent energy management through neuro-fuzzy based adaptive ECMS approach for an optimal battery utilization in plugin parallel hybrid electric vehicle
CN115805840A (en) Energy consumption control method and system for range-extending type electric loader
Wang et al. Adaptive leading cruise control in mixed traffic considering human behavioral diversity
Taghavipour et al. Intelligent control of connected plug-in hybrid electric vehicles
Li et al. Predictive multi-objective operation strategy considering battery cycle aging for hybrid electric vehicles
CN117408360A (en) Method, device and equipment for generating vehicle management strategy based on cloud domain interaction
WO2022028257A1 (en) Method for predicting energy consumption-recovery ratio of new energy vehicle, and energy saving control method and system
CN115759347A (en) Method for quickly predicting travel energy consumption of electric bus based on characteristic data
Kim et al. Energy-optimal regenerative braking strategy for connected and autonomous electrified vehicles: A practical design and implementation for real-world commercial PHEVs

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