CN118254605A - Energy-saving control method for pure electric vehicle in traffic jam state - Google Patents
Energy-saving control method for pure electric vehicle in traffic jam state Download PDFInfo
- Publication number
- CN118254605A CN118254605A CN202410558862.XA CN202410558862A CN118254605A CN 118254605 A CN118254605 A CN 118254605A CN 202410558862 A CN202410558862 A CN 202410558862A CN 118254605 A CN118254605 A CN 118254605A
- Authority
- CN
- China
- Prior art keywords
- speed
- vehicle
- motor
- energy
- economic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000005265 energy consumption Methods 0.000 claims description 34
- 230000001133 acceleration Effects 0.000 claims description 33
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 239000008187 granular material Substances 0.000 claims description 8
- 238000005469 granulation Methods 0.000 claims description 7
- 230000003179 granulation Effects 0.000 claims description 7
- 238000005096 rolling process Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 239000012530 fluid Substances 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 25
- 210000002569 neuron Anatomy 0.000 description 8
- 238000005457 optimization Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004134 energy conservation Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L15/00—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles
- B60L15/20—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles for control of the vehicle or its driving motor to achieve a desired performance, e.g. speed, torque, programmed variation of speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L15/00—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles
- B60L15/20—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles for control of the vehicle or its driving motor to achieve a desired performance, e.g. speed, torque, programmed variation of speed
- B60L15/2045—Methods, circuits, or devices for controlling the traction-motor speed of electrically-propelled vehicles for control of the vehicle or its driving motor to achieve a desired performance, e.g. speed, torque, programmed variation of speed for optimising the use of energy
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2240/00—Control parameters of input or output; Target parameters
- B60L2240/10—Vehicle control parameters
- B60L2240/12—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2240/00—Control parameters of input or output; Target parameters
- B60L2240/40—Drive Train control parameters
- B60L2240/42—Drive Train control parameters related to electric machines
- B60L2240/421—Speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2240/00—Control parameters of input or output; Target parameters
- B60L2240/40—Drive Train control parameters
- B60L2240/42—Drive Train control parameters related to electric machines
- B60L2240/423—Torque
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L2260/00—Operating Modes
- B60L2260/40—Control modes
- B60L2260/50—Control modes by future state prediction
-
- 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
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Power Engineering (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The energy-saving control method for the pure electric vehicle in the traffic jam state comprises the following steps: step 1, establishing a whole vehicle model and a vehicle dynamics model; step 2, establishing a traffic flow prediction model; step 3, dynamic economic path planning; step 4, an economic driving decision is made, and an economic driving speed curve is output; step 5, ACC control based on an economic driving speed curve; the energy-saving performance of the whole vehicle is greatly improved.
Description
Technical Field
The invention belongs to the technical field of electric vehicles, and particularly relates to an energy-saving control method for a pure electric vehicle in a traffic jam state.
Background
Most of the existing energy-saving speed planning of the electric automobile is a known front automobile speed curve, the speed planning is carried out under the condition that the front automobile speed curve is given, and the condition is too ideal, so that the focus is more on the inspection of the optimization algorithm, but the method is difficult to apply to actual following, multiple automobiles or congestion and other real scenes; or sensing the front environment through vehicle-mounted equipment such as radar or a visual sensor, collecting front vehicle data for prediction, acquiring front vehicle related information by the method, and then planning the energy-saving speed. However, the method has high requirements on vehicle-mounted equipment, and the environment perception capability is used as a basis for realizing the prediction of the information of the front vehicle, so that the quality of the perception result can directly influence the performance of the decision control system. The vision sensor is greatly influenced by factors such as illumination and weather, and information such as speed and distance is difficult to acquire. The radars include laser radars, millimeter wave radars, ultrasonic radars and the like, and although the radars are not affected by conditions such as illumination, the laser radars are high in price, the millimeter wave radars are sensitive to metal, the ultrasonic radars are short in detection distance and affected by temperature and the like, and the radars have certain limitations, and bad effects or excessive cost and other adverse effects can be caused due to the reasons.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide the energy-saving driving method of the pure electric vehicle in the traffic jam state, and the method for combining dynamic energy-saving path planning and energy-saving speed planning under the condition of traffic jam is adopted, so that the method can overcome the limitation of vehicle-mounted detection equipment, can plan the vehicle earlier and cooperate with dynamic energy-saving path planning based on traffic flow prediction, and has the characteristic of greatly improving the energy-saving performance of the whole vehicle on the premise of ensuring the efficiency and the dynamic performance by the multi-level energy-efficiency optimization method.
In order to achieve the above purpose, the invention adopts the following technical scheme: the energy-saving control method for the pure electric vehicle in the traffic jam state comprises the following steps:
step1, establishing a whole vehicle model and a vehicle dynamics model;
step 2, establishing a traffic flow prediction model
Predicting a road traffic state based on the vehicle speed, and selecting an average travel speed of the vehicle to predict the road traffic state; based on BP neural network, three kinds of information of Low, R and Up are obtained through triangle fuzzy granulation, and then training prediction is carried out to obtain three average travel speed prediction curves of lowest speed, average speed and highest speed;
Step 3, dynamic economic path planning
Based on a traffic flow prediction result and an energy consumption model of the pure electric vehicle, constructing a double objective function of journey time and energy consumption, and finally planning a dynamic optimal economic route based on the congestion road condition by using an A-based algorithm updated in real time;
Step 4, economic driving decision
On the basis of an optimal route planned by an economic route, calculating the economic driving speed by using a Lagrange multiplier method, improving the energy efficiency and outputting an economic driving speed curve;
step 5, ACC control based on economic driving speed curve and motor efficiency
And (3) controlling the vehicle to track the speed based on the optimized economic driving speed curve obtained by the economic driving decision in the step (4), and simultaneously controlling the vehicle to run based on a torque-rotating speed-efficiency three-dimensional graph of the motor, so that the torque and the rotating speed of the motor are in a high-efficiency interval and energy conservation is performed from the aspect of reducing energy consumption.
The step 1 specifically comprises the following steps:
Step 1-1, establishing a battery model
Because the battery is influenced by internal resistance, temperature, state of charge (SOC) and open-circuit voltage, the model is complex, the internal resistance model is used when the whole vehicle-level motor is modeled, the state of charge (SOC) of the battery is used as a key state of the motor, and the key state is calculated by the formula (1):
in equation (1), SOC is the battery state of charge, P m is the required motor power, t is time, V oc is open circuit voltage, R in is battery resistance, Q max is maximum capacity,
Step 1-2, building a longitudinal dynamics model of the vehicle
According to the automobile dynamics formula, the running resistance is composed of ramp resistance, windward resistance, acceleration resistance and rolling resistance, namely the running resistance can be expressed as:
F＝mgf cosθ+0.5ρCDAv2+mδa+mg sinθ (2)
In the formula (2), F is the force required on the wheel, C D is the air resistance coefficient, A is the frontal area, v is the vehicle speed, m is the whole vehicle preparation mass, g is the gravity coefficient, F is the rolling resistance coefficient, delta is the correction coefficient of the rotating mass, a is the acceleration of the vehicle, θ is the road surface gradient, ρ is the air density,
T＝Treq/ηi (3)
In equations (3) - (4), T req is the required wheel torque, r is the wheel radius, v is the vehicle speed, T is the driveline input torque, N is the transmission input shaft speed, η is the driveline efficiency, and i is the total gear ratio.
The traffic flow prediction model comprises the following prediction steps:
step 2-1, data processing
Preprocessing traffic flow speed data, eliminating abnormal or distorted data, and repairing the abnormal or distorted data;
step 2-2, granulating fuzzy information based on triangle function
Calculating triangle information fuzzy granule parameters Low, R and Up;
Step 2-3, parameter input
Normalizing the Low, R and Up obtained in the step 2-3 to be used as the input of the neural network;
Step 2-4, speed prediction output
And outputting three predicted speeds of Low, R and Up.
The specific method comprises the following steps:
Step 3-1, road network modeling, namely modeling the road network as a weighted directed graph;
Step 3-2, obtaining the weight of each road section according to a speed curve obtained by the traffic flow prediction model;
Step 3-3, searching for the next optimal node according to the weight;
step 3-4, updating the weight and marking the passed node and the route to ensure that the node and the route are not repeated;
Step 3-5, circulating the step 3-1 to the step 3-5 until reaching the end point;
The A-algorithm is a heuristic algorithm formed by adding a heuristic function h (n) on the basis of Dijkstra algorithm, and the A-algorithm is added with a valuation function constraint search range on the basis of breadth-first search;
The valuation function is:
f(n)＝g(n)+h(n) (10)
Wherein f (n) represents the heuristic estimated cost value of node n, g (n) represents the actual cost value from the start point to the n node, h (n) represents the estimated cost value from the n node to the end point as well as the most important part thereof,
h(n)＝λE+(1-λ)T (11)
Wherein, energy (t) is a function related to speed, which can be converted into a function related to time through a speed time function, and the total energy consumption is obtained by integrating time; the time T can be obtained through a predicted speed curve and the road length, and the energy consumption or the time weight is increased by adjusting the value of lambda, so that the planning becomes more biased to energy conservation or time conservation according to actual requirements;
the specific method comprises the following steps of:
step 4-1, calculating economic driving speed
Economic driving speed is defined asE is an energy consumption formula related to speed, and the state equation of the pure electric vehicle in the economic driving decision is as follows:
In the method, in the process of the invention, Is the speed of the vehicle and,Is the acceleration of the vehicle, x is the travel distance of the vehicle, u is the control variable, i.e. throttle and brake pedal opening,
Acceleration constraints, the acceleration of the vehicle should satisfy the following relationship:
amin≤a≤amax (14)
In the formula (14), a min is the minimum acceleration of the vehicle, a max is the maximum acceleration of the vehicle, a is the acceleration of the vehicle,
The speed of the vehicle should meet the following relationship as the case may be:
vmin≤v≤vmax (15)
in the formula (15), v min is the minimum speed of the vehicle, v max is the maximum speed of the vehicle, v is the acceleration of the vehicle,
Traffic information is obtained in advance by means of traffic flow prediction, the lowest speed is predicted by means of triangle information fuzzy granule parameters Low for safety consideration, and safety of driving planning is guaranteed by taking the lowest speed as a reference,
S<SE+d (16)
Wherein S is the distance passed by the vehicle, S E is the distance obtained by integrating according to the speed prediction curve in the same corresponding time, d is the set safety distance,
Terminal constraints: each sub-phase has a start time of 0, an end time of t f, a start distance of 0, and an end distance of
Solving an optimal solution by using a Lagrangian multiplier method, converting a constrained extremum problem into an unconstrained extremum problem to solve an economic driving speed curve,
And 4-2, outputting an economic driving speed curve.
The specific method in the step 5 is as follows:
step 5-1, motor loss power, fitting the mathematical relationship between the loss power of the motor and the motor rotation speed and motor torque into a polynomial form (17):
Wherein, P lost is the motor loss power, P 0、p1、p2、p3、p4、p5 is the fitting coefficient, ω m is the motor rotation speed, and T m is the motor torque;
Step 5-2, the objective function, based on the consideration of the factors of minimum speed following and motor loss power, represents the problem of optimizing control with the aim of controlling speed following and reducing motor operation power loss as follows:
Wherein J is an objective function, V is the speed of the vehicle, V req is the theoretical speed of the economic driving decision, P lost is the loss power of the motor, omega 1、ω2 is a weight coefficient, and t' f is the time from the beginning to the end of the sub-stage;
Step 5-3, equation of state, constraint and solution
The vehicle speed is controlled through the accelerator and the brake pedal, the vehicle speed can be used as an input vector u of a system, and the state equation of the pure electric vehicle in ACC control is as follows:
Wherein, Is the speed at which the velocity of the fluid,Acceleration, x is the distance travelled, u is the control variable, i.e. throttle and brake pedal opening,
System constraints:
In the formula (20), T is a motor torque, T max is a motor maximum torque, T b is a braking torque, T bmax is a maximum braking torque, v min is a vehicle minimum speed, v is a vehicle speed, v max is a vehicle maximum speed, ω is a motor rotation speed, ω max is a motor maximum rotation speed, v is a vehicle speed, v e is a speed corresponding to a theoretical economic speed curve, and T t is any time in the sub-phase.
And (3) solving the objective function in the step (5-2) based on a model predictive control algorithm, namely solving the objective function min J by adopting the model predictive control algorithm.
The beneficial effects of the invention are as follows:
Most of energy-saving speed planning in the prior art is an ideal condition of known front vehicle speed or relies on vehicle-mounted equipment to predict the front vehicle state, and has certain limitations. The energy-saving speed planning is carried out under the condition of not depending on vehicle-mounted equipment, and the limitations of large influence of external environment on equipment, short detection distance, equipment cost reduction and the like are overcome. The method is characterized in that the method comprises the following steps of enabling a self-vehicle to start planning the vehicle state in advance according to the prediction of the next intersection just after the self-vehicle enters a lane according to the prediction condition of a congestion model, so that the purpose of saving energy is achieved.
The invention relates to an energy-saving driving decision method for an automobile with a traffic jam road section, which combines a dynamic path planning decision with an economic driving decision and motor efficiency optimization based on a traffic flow prediction model, and provides a multi-dimensional energy efficiency optimization method; the method of the invention solves the defect that some energy-saving algorithms are too ideal to be applied to practice to a certain extent. The invention utilizes the traffic flow prediction model to acquire traffic information of the next time and space in advance, gives the vehicle sufficient speed planning space, and enables the vehicle to be planned in advance under the condition of no dependence on vehicle-mounted peripheral equipment or limited use of equipment mentioned in the background, and the like, compared with the method of optimizing the speed by means of the speed before prediction, the method can plan in advance earlier, and enables the vehicle to achieve better energy-saving effect; meanwhile, the economical driving performance of the electric automobile and the practicability of the economical driving algorithm are greatly improved.
Drawings
Fig. 1 is a schematic diagram of the BP neural network structure of the present invention.
FIG. 2 is a flow chart of the dynamic economic path planning of the present invention.
Fig. 3 is a flow chart of the method of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples.
The invention provides an energy-saving method taking a pure electric vehicle as a research object, which considers path planning, speed planning and motor efficiency when traffic jam possibly occurs. Mainly comprises the following steps:
Pure electric automobile model: modeling of the pure electric automobile is the basis of the invention, and a whole automobile model and a vehicle dynamics model are established.
Traffic flow prediction model: based on BP neural network, three kinds of information of Low, R and Up are obtained through triangle fuzzy granulation, and then the prediction is trained so as to obtain three average travel speed prediction curves of the lowest speed, the average speed and the highest speed.
Dynamic path planning decision: based on a traffic flow prediction result and an energy consumption model of the pure electric vehicle, a double objective function of journey time and energy consumption is constructed, and a dynamic optimal economic route based on the congested road condition is finally planned by using an A-algorithm updated in real time in planning.
Economic driving decision: and on the determined dynamic optimal economic route, the economic driving speed is determined, so that the energy consumption can be further saved. The economic driving decision of the invention is to plan for each section of road between two nodes based on traffic flow prediction data.
ACC based on motor efficiency: at the economic speed determined by the decision, the motor is in a low-loss working area to save energy consumption from the consideration of the motor efficiency.
By the multi-level energy efficiency optimization method, the energy saving performance of the whole vehicle is greatly improved on the premise of ensuring the efficiency and the dynamic performance by a comprehensive decision method with optimal route, optimal speed and optimal self-loss.
Referring to fig. 3, a method for energy-saving driving of a pure electric vehicle in a traffic jam state includes the following steps:
Step 1, a whole vehicle model and a vehicle dynamics model are established, and the method specifically comprises the following steps:
Step 1-1, establishing a battery model
Because the battery is influenced by internal resistance, temperature, state of charge (SOC) and open-circuit voltage, the model is complex, the internal resistance model is used when the whole vehicle-level motor is modeled, the state of charge (SOC) of the battery is used as a key state of the motor, and the key state is calculated by the formula (1):
In equation (1), SOC is the battery state of charge, P m is the required motor power, t is time, V oc is open circuit voltage, R in is battery resistance, and Q max is maximum capacity.
Step 1-2, building a longitudinal dynamics model of the vehicle
According to the automobile dynamics formula, the running resistance is composed of ramp resistance, windward resistance, acceleration resistance and rolling resistance, namely the running resistance is expressed as:
F＝mgf cosθ+0.5ρCDAv2+mδa+mg sinθ (2)
In the formula (2), F is the force on the required wheel, C D is the air resistance coefficient, A is the frontal area, v is the vehicle speed, m is the whole vehicle preparation mass, g is the gravity coefficient, F is the rolling resistance coefficient, delta is the correction coefficient for the rotating mass, a is the acceleration of the vehicle, θ is the road surface gradient, ρ is the air density,
T＝Treq/ηi (3)
In equations (3) - (4), T req is the required wheel torque, r is the wheel radius, v is the vehicle speed, T is the driveline input torque, N is the transmission input shaft speed, η is the driveline efficiency, i is the total gear ratio;
step 2, establishing a traffic flow prediction model
Referring to fig. 1, the present embodiment predicts a road traffic state based on a vehicle speed, and selects an average trip speed of a vehicle to predict the road traffic state; based on BP neural network, three kinds of information of Low, R and Up are obtained through triangle fuzzy granulation, and then training prediction is carried out to obtain three average travel speed prediction curves of lowest speed, average speed and highest speed. The speed is divided into an instantaneous speed, an average running speed and an average travel speed; the instantaneous speed refers to the instantaneous speed of the vehicle passing a certain place or a certain moment; the average running speed refers to the speed of the vehicle passing through a certain specific road section, and is the ratio of the distance to the running time without considering the midway stopping time; average trip speed refers to the speed of a vehicle passing through a particular road segment, and is the ratio of the trip to the trip time taking into account the stopping delay. The average running speed does not consider delay in running of the vehicle, and in practical application, the situation is few and does not accord with the practical situation; therefore, the present embodiment selects the average trip speed to predict the road traffic state.
The BP neural network is a multi-layer feedforward neural network, which consists of an input layer, an output layer and a plurality of hidden layers, wherein each layer is composed of a plurality of neurons, the neurons on each layer are connected with each other, the neurons on the same layer are not connected with each other, and each neuron only receives the information output by the neurons on the previous layer. The input information can be output only after the processing of each layer of neurons, namely the input signal can only be transmitted to the hidden layer through the input layer, the hidden layer transmits the input signal to the output layer after the information processing, the signal is processed and transmitted layer by layer to finally obtain the expected output, and the training of the BP neural network structure as shown in figure 1 is composed of two parts: forward propagation of information and reverse propagation of errors. In the forward propagation process of signals, the signals entering from the input layer are processed by each neuron on the hidden layer, are transmitted to the output layer after nonlinear transformation, and the processed signals are output by the output layer; if the output signal has larger deviation from the expected output value, the BP neural network activates an error back propagation process, and in the back propagation process, the error is distributed to each layer of neurons, so that the purpose of reducing the error is achieved. The output signal error is gradually reduced by continuously adjusting the weights of the input layer, the hidden layer and the output layer; and (3) repeatedly forward propagating and error backward propagating the signals through each neural node to finally obtain the expected output value.
Fuzzy information granulation, which is based on fuzzy set theory, uses fuzzy set method to granulate time series, and mainly includes two processes: window partitioning and blurring. Window partitioning, as the name implies, is to divide a complete time sequence into a number of sub-sequences according to a certain time span; blurring is to perform blurring processing on data in each window, and the two processes are combined together to form blurring information granulation. Blurring is the key to the granulation of fuzzy information, because new fuzzy sets are generated in each window, so that the fuzzy sets can replace data in the original window, and common fuzzy information granule forms are as follows: triangle, trapezoid, gaussian, etc., triangle fuzzy information particles are selected for use because the purpose is to know the minimum value of traffic flow information.
The traffic flow prediction model comprises the following prediction steps:
step 2-1, data processing
Preprocessing traffic flow speed data, eliminating abnormal or distorted data, and repairing the abnormal or distorted data;
step 2-2, granulating fuzzy information based on triangle function
Calculating triangle information fuzzy granule parameters Low, R and Up;
Step 2-3, parameter input
Normalizing the Low, R and Up obtained in the step 2-3 to be used as the input of the neural network;
Step 2-4, speed prediction output
Outputting three prediction speeds of Low, R and Up;
Step 3, dynamic economic path planning
Referring to fig. 2, based on a traffic flow prediction result and a pure electric vehicle energy consumption model, constructing a dual objective function of journey time and energy consumption, and finally planning a dynamic optimal economic route based on a congested road condition by using a real-time updated a-th algorithm; the specific method comprises the following steps:
Step 3-1, road network modeling, namely modeling the road network as a weighted directed graph; path planning models a road as an edge in a graph, and models an intersection as a vertex in the graph; because the traffic flow prediction can be matched with road sections by using GPS track points, the road is divided into the road sections with shorter distance, and more accurate average speed can be calculated for prediction and then used in dynamic weight calculation; therefore, the present embodiment divides one road into a plurality of road segments, models the road segments as edges, models the road segment junctions as points, thereby establishing a connection relationship between the points and the edges; roads often have different traffic flow characteristics in different directions of travel, and therefore, it is necessary to distinguish between the different directions of travel and model as different edges; the road network structure is represented by a directed graph by determining the driving directions of different lanes in the road; in addition, various weights of the road can be calculated by establishing a model of the road attribute and the weight information;
Energy consumption model and road network weight
The energy consumption of an electric automobile is mainly divided into two parts: one part is the energy consumption of the vehicle-mounted electric appliance accessory, and the other part is the electric energy loss during running. The invention mainly saves the energy consumption during driving, so the energy consumption of accessories is ignored for the moment.
The power value required for overcoming the resistance (the efficiency value of the motor and the efficiency value of the transmission system also need to be considered) can be obtained by analyzing the longitudinal stress of the automobile, so that an energy consumption formula can be obtained:
Where dE represents power, E represents energy consumption, v represents vehicle speed, m represents vehicle weight, f represents rolling resistance coefficient, θ represents gradient, ρ represents air density, C D represents air resistance coefficient, A represents frontal area, δ represents vehicle rotational mass conversion coefficient, a represents running acceleration, Δh represents rising altitude, η 1 represents motor efficiency, η 2 represents driveline efficiency. The estimated energy consumption of the vehicle running on the road section is calculated by combining with the electric vehicle energy consumption model, the comprehensive cost of the energy consumption time of the road section is constructed as the edge weight in the road network, and the weight of the road section is expressed as:
W ij represents the weight from node i to node j; Representing the energy consumption cost from node i to node j; representing the cost of time from node i to node j:
Step 3-2, obtaining the weight of each road section according to a speed curve obtained by the traffic flow prediction model;
Step 3-3, searching for the next optimal node according to the weight;
step 3-4, updating the weight and marking the passed node and the route to ensure that the node and the route are not repeated;
Step 3-5, circulating the step 3-1 to the step 3-5 until reaching the end point;
The A-algorithm is a heuristic algorithm formed by adding a heuristic function h (n) on the basis of Dijkstra algorithm, and the A-algorithm is added with a valuation function constraint search range on the basis of breadth-first search;
The valuation function is:
f(n)＝g(n)+h(n) (10)
Wherein f (n) represents the heuristic estimated cost value of node n, g (n) represents the actual cost value from the start point to the n node, h (n) represents the estimated cost value from the n node to the end point as well as the most important part thereof,
h(n)＝λE+(1-λ)T (11)
Wherein, energy (t) is a function related to speed, which can be converted into a function related to time through a speed time function, and then the total energy consumption can be obtained by integrating the time; the time T may be derived from the predicted speed profile and the road length. The energy consumption or time weight can be increased by adjusting the value of lambda so that planning becomes more biased to energy saving or time saving according to actual requirements;
Step 4, economic driving decision
On the basis of an optimal route planned by an economic route, calculating an economic driving speed, improving energy efficiency, outputting an economic driving speed curve, wherein the economic driving is based on the optimal route selected by a driver, suggesting that the driver drives the vehicle at the optimal speed, the suggestions can be provided for the driver through interfaces such as a smart phone and the like to provide optimal decisions, and the road network is connected by nodes through the previous path planning, so that the two nodes are regarded as a sub-stage, the whole journey is divided into sub-stages, and the optimal speed of each sub-stage is independently solved according to the traffic flow prediction result, so that the speed optimization on the whole route is ensured; the specific method comprises the following steps of:
step 4-1, calculating economic driving speed
The economic driving is to calculate an economic driving speed curve of a driver when the driver runs on the road section; according to the vehicle model and a series of constraint conditions, solving an economic speed decision as an optimal control problem;
The road section between two nodes is regarded as an optimized target; the distance between the nodes, namely the length of the road section, is known, and the time of the two-node process can be calculated according to the speed curve predicted by the traffic flow prediction model and the distance between the road sections; to achieve the recommended vehicle speed, the driver controls the vehicle speed through the accelerator and brake pedal, taking the opening of the accelerator or brake pedal as an input vector u of the system; the optimal speed is controlled with the aim of minimizing the energy consumption of the vehicle running on the road section, and the economic driving speed is defined as E is the energy consumption formula given above, and the state equation of the pure electric vehicle in the economic driving decision is:
In the method, in the process of the invention, Is the speed at which the velocity of the fluid,Acceleration, x is the distance travelled, u is the control variable, i.e. throttle and brake pedal opening.
Acceleration constraint, the constraint of vehicle acceleration reflects the acceleration performance and braking performance of the vehicle and also relates to the safety performance of the vehicle, and the acceleration of the vehicle in the embodiment only needs to satisfy the following relationship under the premise of considering energy conservation and not comfort:
amin≤a≤amax (14)
In the formula (14), a min is the vehicle minimum acceleration, a max is the vehicle maximum acceleration, and a is the vehicle acceleration.
The speed constraint of the vehicle is related to safety and traffic efficiency, and the limitation of laws and regulations on the vehicle speed is also considered, different speed limits exist on different roads, the lowest speed limit exists in a tunnel, the highest speed limit exists on urban roads, and the vehicle performance is also related to the limitation of the vehicle speed, so that the vehicle speed is comprehensively considered to be limited in a reasonable range according to specific conditions, and the vehicle speed meets the following relation according to specific conditions:
vmin≤v≤vmax (15)
In the formula (15), v min is the minimum speed of the vehicle, v max is the maximum speed of the vehicle, and v is the acceleration of the vehicle.
Traffic information is obtained in advance by means of traffic flow prediction, the lowest speed is predicted by means of triangle information fuzzy granule parameters Low for safety consideration, and safety of driving planning is guaranteed by taking the lowest speed as a reference,
S<SE+d (16)
Wherein S is the distance passed by the vehicle, S E is the distance obtained by integrating according to the speed prediction curve in the same corresponding time, d is the set safety distance,
Terminal constraints: each sub-phase has a start time of 0, an end time of t f, a start distance of 0, and an end distance of
And solving an optimal solution by using a Lagrangian multiplier method, and converting the constrained extremum problem into an unconstrained extremum problem to solve an economic driving speed curve.
Step 4-2, outputting an economic driving speed curve;
step 5, ACC control based on economic driving speed curve and motor efficiency
And (3) controlling the vehicle to track the speed based on the optimized economic driving speed curve obtained by the economic driving decision in the step (4), and simultaneously controlling the vehicle to run in the economic driving speed curve by using a model predictive control algorithm based on a torque-rotating speed-efficiency three-dimensional graph of the motor, so that the torque and the rotating speed of the motor are in a high-efficiency interval, and saving energy from the perspective of reducing the energy consumption of the motor.
The specific method in the step 5 is as follows:
step 5-1, motor loss power, fitting the mathematical relationship between the loss power of the motor and the motor rotation speed and motor torque into a polynomial form (17):
Wherein, P lost is the motor loss power, P 0、p1、p2、p3、p4、p5 is the fitting coefficient, ω m is the motor rotation speed, and T m is the motor torque;
Step 5-2, the objective function, based on the speed following and the minimum factor consideration of the motor loss power, describes the problem of optimizing control with the goal of controlling the speed following and reducing the motor operation power loss at the same time as follows:
Wherein J is an objective function, V is the speed of the vehicle, V req is the theoretical speed of the economic driving decision, P lost is the loss power of the motor, omega 1、ω2 is a weight coefficient, and t' f is the time from the beginning to the end of the sub-stage;
Step 5-3, equation of state, constraint and solution
The vehicle speed is controlled through the accelerator and the brake pedal, the vehicle speed can be used as an input vector u of a system, and the state equation of the pure electric vehicle in ACC control is as follows:
Wherein, Is the speed at which the velocity of the fluid,Acceleration, x is the distance travelled, u is the control variable, i.e. throttle and brake pedal opening.
System constraints:
In the formula (20), T is a motor torque, T max is a motor maximum torque, T b is a braking torque, T bmax is a maximum braking torque, v min is a vehicle minimum speed, v is a vehicle speed, v max is a vehicle maximum speed, ω is a motor rotation speed, ω max is a motor maximum rotation speed, v is a vehicle speed, v e is a speed corresponding to a theoretical economic speed curve, and T t is any time in the sub-phase.
The objective function in step 5-2 is solved based on a model predictive control algorithm, namely, the objective function min J is solved by using a model predictive control (Model Predictive Control, MPC) algorithm.
Claims (6)
1. The energy-saving control method for the pure electric vehicle in the traffic jam state is characterized by comprising the following steps of:
step1, establishing a whole vehicle model and a vehicle dynamics model;
step 2, establishing a traffic flow prediction model
Predicting a road traffic state based on the vehicle speed, and selecting an average travel speed of the vehicle to predict the road traffic state; based on BP neural network, three kinds of information of Low, R and Up are obtained through triangle fuzzy granulation, and then training prediction is carried out to obtain three average travel speed prediction curves of lowest speed, average speed and highest speed;
Step 3, dynamic economic path planning
Based on a traffic flow prediction result and an energy consumption model of the pure electric vehicle, constructing a double objective function of journey time and energy consumption, and finally planning a dynamic optimal economic route based on the congestion road condition by using an A-based algorithm updated in real time;
Step 4, economic driving decision
On the basis of an optimal route planned by an economic route, calculating the economic driving speed by using a Lagrange multiplier method, improving the energy efficiency and outputting an economic driving speed curve;
step 5, ACC control based on economic driving speed curve and motor efficiency
And (3) controlling the vehicle to track the speed based on the optimized economic driving speed curve obtained by the economic driving decision in the step (4), and simultaneously controlling the vehicle to run in the economic driving speed curve by using a model predictive control algorithm based on a torque-rotating speed-efficiency three-dimensional graph of the motor, so that the torque and the rotating speed of the motor are in a high-efficiency interval, and saving energy from the perspective of reducing the energy consumption of the motor.
2. The energy-saving control method for the pure electric vehicle in the traffic jam state according to claim 1, wherein the step 1 specifically comprises the following steps:
Step 1-1, establishing a battery model
Because the battery is influenced by internal resistance, temperature, state of charge (SOC) and open-circuit voltage, the model is complex, the internal resistance model is used when the whole vehicle-level motor is modeled, the state of charge (SOC) of the battery is used as a key state of the motor, and the key state is calculated by the formula (1):
in equation (1), SOC is the battery state of charge, P m is the required motor power, t is time, V oc is open circuit voltage, R in is battery resistance, Q max is maximum capacity,
Step 1-2, building a longitudinal dynamics model of the vehicle
According to the automobile dynamics formula, the running resistance is composed of ramp resistance, windward resistance, acceleration resistance and rolling resistance, namely the running resistance can be expressed as:
F＝mgf cosθ+0.5ρCDAv2+mδa+mg sinθ (2)
In the formula (2), F is the force required on the wheel, C D is the air resistance coefficient, A is the frontal area, v is the vehicle speed, m is the whole vehicle preparation mass, g is the gravity coefficient, F is the rolling resistance coefficient, delta is the correction coefficient of the rotating mass, a is the acceleration of the vehicle, θ is the road surface gradient, ρ is the air density,
T＝Treq/ηi (3)
In equations (3) - (4), T req is the required wheel torque, r is the wheel radius, v is the vehicle speed, T is the driveline input torque, N is the transmission input shaft speed, η is the driveline efficiency, and i is the total gear ratio.
3. The energy-saving control method for the pure electric vehicle in the traffic congestion state according to claim 1, wherein the traffic flow prediction model predicts the following steps:
step 2-1, data processing
Preprocessing traffic flow speed data, eliminating abnormal or distorted data, and repairing the abnormal or distorted data;
step 2-2, granulating fuzzy information based on triangle function
Calculating triangle information fuzzy granule parameters Low, R and Up;
Step 2-3, parameter input
Normalizing the Low, R and Up obtained in the step 2-3 to be used as the input of the neural network;
Step 2-4, speed prediction output
And outputting three predicted speeds of Low, R and Up.
4. The energy-saving control method for the pure electric vehicle in the traffic jam state according to claim 1, wherein the specific implementation method in the step 3 is as follows:
Step 3-1, road network modeling, namely modeling the road network as a weighted directed graph;
Step 3-2, obtaining the weight of each road section according to a speed curve obtained by the traffic flow prediction model;
Step 3-3, searching for the next optimal node according to the weight;
step 3-4, updating the weight and marking the passed node and the route to ensure that the node and the route are not repeated;
Step 3-5, circulating the step 3-1 to the step 3-5 until reaching the end point;
The A-algorithm is a heuristic algorithm formed by adding a heuristic function h (n) on the basis of Dijkstra algorithm, and the A-algorithm is added with a valuation function constraint search range on the basis of breadth-first search;
The valuation function is:
f(n)＝g(n)+h(n) (10)
Wherein f (n) represents the heuristic estimated cost value of node n, g (n) represents the actual cost value from the start point to the n node, h (n) represents the estimated cost value from the n node to the end point as well as the most important part thereof,
h(n)＝λE+(1-λ)T (11)
Wherein, energy (t) is a function related to speed, which can be converted into a function related to time through a speed time function, and the total energy consumption is obtained by integrating time; the time T can be derived from the predicted speed profile and the road length by adjusting the value of λ to increase the weight of the energy consumption or time so that the planning becomes more biased to save energy or time according to the actual demand.
5. The energy-saving control method for the pure electric vehicle in the traffic jam state according to claim 1, wherein the specific implementation method comprises the following steps:
step 4-1, calculating economic driving speed
Economic driving speed is defined asE is an energy consumption formula related to speed, and the state equation of the pure electric vehicle in the economic driving decision is as follows:
In the method, in the process of the invention, Is the speed of the vehicle and,Is the acceleration of the vehicle, x is the travel distance of the vehicle, u is the control variable, i.e. throttle and brake pedal opening,
Acceleration constraints, the acceleration of the vehicle should satisfy the following relationship:
amin≤a≤amax (14)
In the formula (14), a min is the minimum acceleration of the vehicle, a max is the maximum acceleration of the vehicle, a is the acceleration of the vehicle,
The speed of the vehicle should meet the following relationship as the case may be:
vmin≤v≤vmax (15)
in the formula (15), v min is the minimum speed of the vehicle, v max is the maximum speed of the vehicle, v is the acceleration of the vehicle,
Traffic information is obtained in advance by means of traffic flow prediction, the lowest speed is predicted by means of triangle information fuzzy granule parameters Low for safety consideration, and safety of driving planning is guaranteed by taking the lowest speed as a reference,
S＜SE+d (16)
Wherein S is the distance passed by the vehicle, S E is the distance obtained by integrating according to the speed prediction curve in the same corresponding time, d is the set safety distance,
Terminal constraints: each sub-phase has a start time of 0, an end time of t f, a start distance of 0, and an end distance of
Solving an optimal solution by using a Lagrangian multiplier method, and converting a constrained extremum problem into an unconstrained extremum problem to solve an economic driving speed curve;
And 4-2, outputting an economic driving speed curve.
6. The energy-saving control method for the pure electric vehicle in the traffic jam state of claim 1, wherein the specific implementation method in the step 5 is as follows:
step 5-1, motor loss power, fitting the mathematical relationship between the loss power of the motor and the motor rotation speed and motor torque into a polynomial form (17):
Wherein, P lost is the motor loss power, P 0、p1、p2、p3、p4、p5 is the fitting coefficient, ω m is the motor rotation speed, and T m is the motor torque;
Step 5-2, the objective function, based on the consideration of the factors of minimum speed following and motor loss power, represents the problem of optimizing control with the aim of controlling speed following and reducing motor operation power loss as follows:
Wherein J is an objective function, V is the speed of the vehicle, V req is the theoretical speed of the economic driving decision, P lost is the loss power of the motor, omega 1、ω2 is a weight coefficient, and t' f is the time from the beginning to the end of the sub-stage;
Step 5-3, equation of state, constraint and solution
The vehicle speed is controlled through the accelerator and the brake pedal, the vehicle speed can be used as an input vector u of a system, and the state equation of the pure electric vehicle in ACC control is as follows:
Wherein, Is the speed at which the velocity of the fluid,Acceleration, x is the distance travelled, u is the control variable, i.e. throttle and brake pedal opening,
System constraints:
In the formula (20), T is motor torque, T max is motor torque capacity, T b is braking torque, T bmax is maximum braking torque, v min is vehicle minimum speed, v is vehicle speed, v max is vehicle maximum speed, ω is motor rotational speed, ω max is motor rotational speed maximum, v is vehicle speed, v e is a speed corresponding to a theoretical economic speed curve, T t is any time in a sub-phase,
And (3) solving the objective function in the step (5-2) based on a model predictive control algorithm, namely solving the objective function min J by using the model predictive control algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410558862.XA CN118254605A (en) | 2024-05-08 | 2024-05-08 | Energy-saving control method for pure electric vehicle in traffic jam state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410558862.XA CN118254605A (en) | 2024-05-08 | 2024-05-08 | Energy-saving control method for pure electric vehicle in traffic jam state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118254605A true CN118254605A (en) | 2024-06-28 |
Family
ID=91605427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410558862.XA Pending CN118254605A (en) | 2024-05-08 | 2024-05-08 | Energy-saving control method for pure electric vehicle in traffic jam state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118254605A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118597202A (en) * | 2024-08-08 | 2024-09-06 | 株洲中车时代电气股份有限公司 | Automatic driving control method and medium for unstructured road vehicle in mining area scene |
-
2024
- 2024-05-08 CN CN202410558862.XA patent/CN118254605A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118597202A (en) * | 2024-08-08 | 2024-09-06 | 株洲中车时代电气股份有限公司 | Automatic driving control method and medium for unstructured road vehicle in mining area scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| He et al. | An improved MPC-based energy management strategy for hybrid vehicles using V2V and V2I communications | |
| US11858513B2 (en) | Vehicle target operational speed band control method and apparatus | |
| Nie et al. | Real-time dynamic predictive cruise control for enhancing eco-driving of electric vehicles, considering traffic constraints and signal phase and timing (SPaT) information, using artificial-neural-network-based energy consumption model | |
| Huang et al. | Speed trajectory planning at signalized intersections using sequential convex optimization | |
| CN109278752B (en) | Energy optimization control method for plug-in hybrid electric vehicle based on cooperative sensing | |
| CN109733378B (en) | Offline optimized online predicted torque distribution method | |
| CN107577234B (en) | Automobile fuel economy control method for driver in-loop | |
| CN111959492B (en) | HEV energy management hierarchical control method considering lane change behavior in internet environment | |
| Hu et al. | An online rolling optimal control strategy for commuter hybrid electric vehicles based on driving condition learning and prediction | |
| CN110182215B (en) | Automobile economical cruise control method and device | |
| CN113269963B (en) | Internet vehicle signal lamp control intersection economic passing method based on reinforcement learning | |
| CN108489500A (en) | A kind of global path planning method and system based on Energy Consumption Economy | |
| CN114312845A (en) | Deep reinforcement learning type hybrid electric vehicle control method based on map data | |
| CN112286212B (en) | Vehicle network cooperative energy-saving control method | |
| CN115534929A (en) | Plug-in hybrid electric vehicle energy management method based on multi-information fusion | |
| CN118254605A (en) | Energy-saving control method for pure electric vehicle in traffic jam state | |
| CN112550272A (en) | Intelligent hybrid electric vehicle hierarchical control method based on visual perception and deep reinforcement learning | |
| Murphey | Intelligent vehicle power management: An overview | |
| Han et al. | Hierarchical optimization of speed and gearshift control for battery electric vehicles using preview information | |
| CN113276829B (en) | Vehicle running energy-saving optimization weight-changing method based on working condition prediction | |
| CN113479187A (en) | Layered different-step-length energy management method for plug-in hybrid electric vehicle | |
| Wu et al. | Research on lane-change strategy with real-time obstacle avoidance function | |
| Wang et al. | Energy-efficient trajectory planning with curve splicing based on pso-lstm prediction | |
| Hu et al. | Research on vehicle speed prediction model based on traffic flow information fusion | |
| CN113267345B (en) | Method, storage medium, controller and system for predicting resistance of unknown road section ahead of vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |