An intelligent advance braking system for electric vehicles

Abstract

The application discloses an intelligent advance braking system for an electric vehicle, comprising an information acquisition module based on vehicle wireless communication technology, an advance braking judgment module, an advance braking opening sensitivity adaptation module, an advance braking force calculation module and an advance braking and normal braking connection module. The information acquisition module based on vehicle wireless communication technology is used for acquiring various information between the vehicle and the surrounding environment; the advance braking judgment module judges whether to open the advance braking according to the comparison result of the advance braking demand degree representation coefficient and the advance braking opening threshold value; the advance braking opening sensitivity adaptation module is used for calculating the advance braking opening threshold value; the advance braking force calculation module calculates the advance braking force by adopting a near-end strategy optimization algorithm; and the advance braking and normal braking connection module realizes the reasonable transition between the advance braking and the normal braking according to a braking connection rule.

Description

Technical Field

[0001] The present invention belongs to the field of automobile safety, relates to an active safety control technology for electric vehicles, and specifically relates to an intelligent advance braking system for electric vehicles. Background Art

[0002] With the rapid development of the electric vehicle industry, the requirements for vehicle safety are constantly increasing. In complex and changing traffic environments, how to effectively avoid collisions and improve vehicle safety through the braking system has become an important issue that needs to be addressed.

[0003] Traditional braking systems rely heavily on manual control by the driver. Faced with unexpected traffic conditions, drivers often struggle to make accurate judgments and maneuvers in a timely manner, increasing the risk of accidents. To address this issue, advanced driver assistance systems and automatic emergency braking systems have emerged. These systems use a variety of sensors to monitor the vehicle's surroundings in real time and proactively apply the brakes when a potential collision is detected. However, these systems still suffer from limitations in response speed and accuracy when faced with unexpected traffic situations and dynamically changing environments, making them difficult to fully meet practical needs.

[0004] Through inter-vehicle wireless communication technology, vehicles can exchange information in real time with other vehicles, traffic lights, road infrastructure, and more. This allows them to obtain real-time dynamic data on road conditions and the surrounding environment, providing critical information for active safety control. However, existing braking systems do not fully utilize inter-vehicle wireless communication technology, lacking the ability to dynamically determine braking requirements and precisely control braking force in complex traffic scenarios. Therefore, there is an urgent need to develop an intelligent pre-braking system that can fully utilize inter-vehicle wireless communication technology and advanced algorithms to determine and optimize the timing and force of pre-braking in real time, thereby effectively improving the vehicle's active safety. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent advance braking system for an electric vehicle to solve the problems faced in the above background technology.

[0006] In order to achieve the above object, the present invention provides the following solutions:

[0007] An intelligent advance braking system for electric vehicles, comprising an information acquisition module based on vehicle wireless communication technology, an advance braking judgment module, an advance braking activation sensitivity adaptation module, an advance braking force calculation module, and an advance braking and normal braking connection module;

[0008] The information acquisition module based on vehicle wireless communication technology is used to obtain various information between the vehicle and the surrounding environment, including the vehicle's driving status information, surrounding vehicle driving status information, surrounding road infrastructure information and surrounding pedestrian information;

[0009] The early braking judgment module is based on the early braking demand degree characterization coefficient R and the early braking opening threshold O t When the comparison result of the advance braking requirement degree characterization coefficient R is less than or equal to the advance braking opening threshold value O t When the early braking demand coefficient R is greater than the early braking opening threshold O t When the vehicle is in the emergency braking state, the advance braking system is activated;

[0010] The early braking requirement coefficient R is determined by the driving state requirement factor R of the vehicle ahead. fv , surrounding road condition demand factor R r , surrounding pedestrian demand factor R P and the vehicle's operational safety requirement factor R tv Obtained through weighted calculation;

[0011] The preceding vehicle driving state requirement factor R fv The calculation formula is:

[0012]

[0013] Where v1, v2, and v3 are the average longitudinal speeds of all vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; a1, a2, and a3 are the average braking decelerations of all vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; d1, d2, and d3 are the number of vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; x is the following distance between the vehicle and the vehicle in front; v max is the maximum average longitudinal speed of all vehicles within each range, which is 120 km / h; a max The maximum average braking deceleration of all vehicles in each range is 10m / s 2 ;d max is the maximum number of vehicles in each range, which is 15; x min is the minimum following distance between the vehicle and the vehicle in front, which is 5m; ω v 、ω a 、ω d and ω x is the weight coefficient, and its specific value is determined through simulation and experiments;

[0014] The surrounding road condition demand factor R rThe calculation formula is:

[0015]

[0016] Where, T s is the traffic light influence, which takes a value of 1 when the nearest traffic light in front of the vehicle is red or yellow, and takes a value of 0 when the nearest traffic light in front of the vehicle is green; I is the road sign influence, which takes a value of 1 when the nearest road sign in front of the vehicle prompts to slow down, and takes a value of 0 when the nearest road sign in front of the vehicle prompts other content; μ is the road adhesion coefficient; r is the road type influence, which takes a value of 1 when the nearest road type in front of the vehicle is a downhill road or a curve, and takes a value of 0 when the nearest road type in front of the vehicle is other roads; ω I 、ω μ and ω r is the weight coefficient, and its specific value is determined through simulation and experiments;

[0017] The surrounding pedestrian situation demand factor R P The calculation formula is:

[0018]

[0019] Where D is the pedestrian density coefficient within the farthest illumination range of the headlight. When there are less than 5 people, the value is 1; when there are 5 to 10 people, the value is 2; when there are more than 10 people, the value is 3; D max is the maximum pedestrian density coefficient within the farthest illumination range of the headlight, with a value of 3; A is the average age coefficient of pedestrians within the farthest illumination range of the headlight, with a value of 1 for those aged 18 to 60, and a value of 2 for those under 18 or over 60; A max is the maximum value of the average age coefficient of pedestrians within the farthest illumination range of the headlight, and its value is 2; S is the pedestrian action state coefficient within the farthest illumination range of the headlight, and its value is 3 when there is a running action state among the pedestrians within the farthest illumination range of the headlight, and its value is 2 when there is a slow walking action state, and its value is 1 for other action states; S max The maximum value of the pedestrian action state coefficient within the farthest illumination range of the headlight is 3; ω D 、ω A and ω S is the weight coefficient, and its specific value is determined through simulation and experiments;

[0020] The vehicle's operating safety requirement factor R tv The calculation formula is:

[0021]

[0022] Where, v t is the vehicle speed; is the maximum speed of the vehicle, which is 80km / h; m is the total mass of the vehicle; m max is the maximum total mass of the vehicle, which is 40000 kg; y is the age of the driver; d is the ideal driver age, which is 44 years old; t is the driver's continuous driving time; t max is the maximum continuous driving time of the driver, which is 4 hours; V is the volume of the cabin occupants; V max The maximum volume for cab occupants is 100 decibels; vt 、ω m 、ω a 、ω t and ω v is the weight coefficient, and its specific value is determined through simulation and experiments;

[0023] The calculation formula of the early braking demand degree characterization coefficient R is:

[0024] R=ε1R fv +ε2R r +ε3R P +ε4R tv

[0025] Where ε1, ε2, ε3, and ε4 are the demand weight coefficients for the driving state of the preceding vehicle, the demand weight coefficients for the surrounding road conditions, the demand weight coefficients for the surrounding pedestrian conditions, and the demand weight coefficients for the vehicle's operating safety conditions, respectively. Their specific values ​​are determined through simulation and experiments.

[0026] The early brake opening sensitivity adaptation module calculates the early brake opening threshold value O according to the driver's driving style characterization coefficient S and driving experience characterization coefficient E t ;

[0027] The advance braking force calculation module uses the proximal strategy optimization algorithm to calculate the advance braking force F b The size of the proximal policy optimization algorithm's reward function r PPO It consists of brake safety bonus items, comfort bonus items, brake energy efficiency bonus items, driving stability bonus items and brake temperature penalty items;

[0028] The module for connecting early braking with normal braking realizes a reasonable transition between early braking and normal braking according to the braking connection rules; the normal braking is specifically the braking process after the driver manually operates the braking system according to real-time traffic conditions and driving needs and the braking active safety system is triggered.

[0029] The calculation formula of the driving style characterization coefficient S is:

[0030]

[0031] Where, v d The driver's usual driving speed; The maximum driving speed is 150km / h; is the minimum driving speed, which is 0km / h; a d The driver's customary braking deceleration; is the maximum braking deceleration, which is 8m / s 2 ; is the minimum braking deceleration, which is 0.5m / s 2 ;f b is the driver's emergency braking frequency; is the maximum emergency braking frequency, which is 10 times per hour; x d The driver's customary following distance; is the maximum following distance, which is 100m; is the minimum following distance, which is 3m; α1, α2, α3 and α4 are weight coefficients, whose specific values ​​are determined through simulation and experiments; β1, β2, β3 and β4 are influence coefficients, whose specific values ​​are determined through simulation and experiments;

[0032] The calculation formula of the driving experience characterization coefficient E is:

[0033]

[0034] Where y is the driver’s age; max is the maximum driving age, which is 50 years; min is the minimum driving age, which is 0 years; n is the number of correct responses to sudden driving risks; n max is the maximum number of correct responses to sudden driving risks, which is set to 1000 times; t r The total driving time of drivers on wet, snowy and icy roads; is the maximum driving time, which is 500 hours; t a The length of time the driver uses the assisted driving system; is the maximum usage time, which is set to 1000 hours; α5, α6, α7, and α8 are weight coefficients, whose specific values ​​are determined through simulation and experiments; β5, β6, β7, and β8 are influence coefficients, whose specific values ​​are determined through simulation and experiments;

[0035] The early brake opening threshold O t The calculation formula is:

[0036]

[0037] Where, and are the driving style weight coefficient, driving experience weight coefficient and driving style and driving experience interaction weight coefficient, and their specific values ​​are determined through simulation and experiments; ρ1, ρ2 and ρ3 are the nonlinear influence coefficients, and their specific values ​​are determined through simulation and experiments.

[0038] The specific design of the proximal strategy optimization algorithm is:

[0039] The state variable s is:

[0040] s=[R,m,v t , μ,i,S]

[0041] Where R is the coefficient representing the degree of early braking demand; m is the total mass of the vehicle; v t is the vehicle speed; μ is the road adhesion coefficient; i is the road slope; S is the driving style characterization coefficient;

[0042] The action variable F is:

[0043]

[0044] Where, F1 is the electric braking force; F2 is the hydraulic braking force; is the maximum motor power; is the maximum hydraulic braking force; A c is the effective area of ​​the brake caliper; k1 is the motor braking efficiency; k2 is the hydraulic braking efficiency;

[0045] Reward function r PPO Designed to:

[0046] r PPO =r s +r c +r e +r st +p T

[0047] Where r s For brake safety reward items; c is the comfort bonus item; r e Braking energy efficiency reward item; r st It is a driving stability reward item; p T is the brake temperature penalty term.

[0048] The braking safety reward item r s The calculation formula is:

[0049]

[0050] Where a maxis the maximum braking deceleration, which is 8m / s 2 ; R is the coefficient representing the degree of early braking demand; F1 is the electric braking force; F2 is the hydraulic braking force;

[0051] The comfort bonus item r c The calculation formula is:

[0052]

[0053] Where, and are the differentials of the motor force F1 and the hydraulic braking force F2 with respect to time t, respectively, representing the rate of change of the motor force and the rate of change of the hydraulic braking force;

[0054] The braking energy efficiency reward item r e The calculation formula is:

[0055] r e =-(η h ·F2·v t 2 -η reg ·F1·v t 2 γ env )

[0056] Where η h is the hydraulic braking energy consumption coefficient, which is 0.05; η reg is the motor braking energy recovery coefficient, which is 0.1; v t is the vehicle speed; env is the environmental correction factor, which is 0.95;

[0057] The driving stability reward item r st The calculation formula is:

[0058]

[0059] Where h c is the height of the vehicle's center of mass; m is the total mass of the vehicle; a y is the lateral acceleration of the vehicle; d is the wheelbase; v t is the vehicle speed; θ f is the front wheel turning angle; l is the wheelbase;

[0060] The brake temperature penalty term p T The calculation formula is:

[0061] p T =10(max(0, T b -T o )) 3

[0062] Where, T b is the brake operating temperature; T o The optimal operating temperature of the brake is 300℃.

[0063] The braking connection rules are specifically as follows:

[0064] When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t If the speed continues to increase and the driver does not step on the brake pedal, the automatic emergency braking system will be activated;

[0065] When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t And it keeps increasing, but when the driver steps on the brake pedal, the braking torque of the whole vehicle is determined by the brake pedal opening;

[0066] When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t But if it remains unchanged, the advance braking system will continue to be activated.

[0067] The beneficial effects of the present invention are:

[0068] 1. The present invention determines the coefficient representing the degree of early braking demand by comprehensively considering the driving state of the vehicle ahead, the surrounding road conditions, the surrounding pedestrian conditions and the operating safety of the vehicle.

[0069] 2. The present invention calculates the early braking activation threshold value based on the driver's driving style characterization coefficient and driving experience characterization coefficient, and compares it with the early braking demand degree characterization coefficient to determine whether to activate early braking.

[0070] 3. The present invention can comprehensively utilize vehicle wireless communication technology and proximal strategy optimization algorithms to dynamically determine and optimize the timing and force of early braking based on real-time road conditions and vehicle status, thereby achieving safer and more reliable active safety control. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] The present invention will be further described below in conjunction with the accompanying drawings:

[0072] Figure 1 This is a framework diagram of an electric vehicle intelligent advance braking system proposed by the present invention. DETAILED DESCRIPTION

[0073] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0074] See Figure 1The electric vehicle intelligent advance braking system of the present invention includes an information acquisition module based on vehicle wireless communication technology, an advance braking judgment module, an advance braking opening sensitivity adaptation module, an advance braking force calculation module, and an advance braking and normal braking connection module;

[0075] The information acquisition module based on vehicle wireless communication technology is used to obtain various information between the vehicle and the surrounding environment, including the vehicle's driving status information, surrounding vehicle driving status information, surrounding road infrastructure information and surrounding pedestrian information;

[0076] The early braking judgment module is based on the early braking demand degree characterization coefficient R and the early braking opening threshold O t When the comparison result of the advance braking requirement degree characterization coefficient R is less than or equal to the advance braking opening threshold value O t When the early braking demand coefficient R is greater than the early braking opening threshold O t When the vehicle is in the emergency braking state, the advance braking system is activated;

[0077] The early braking requirement coefficient R is determined by the driving state requirement factor R of the vehicle ahead. fv , surrounding road condition demand factor R r , surrounding pedestrian demand factor R P and the vehicle's operational safety requirement factor R tv Obtained through weighted calculation;

[0078] The preceding vehicle driving state requirement factor R fv The calculation formula is:

[0079]

[0080] Where v1, v2, and v3 are the average longitudinal speeds of all vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; a1, a2, and a3 are the average braking decelerations of all vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; d1, d2, and d3 are the number of vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; x is the following distance between the vehicle and the vehicle in front; v max is the maximum average longitudinal speed of all vehicles within each range, which is 120 km / h; a max The maximum average braking deceleration of all vehicles in each range is 10m / s 2 ;dmax is the maximum number of vehicles in each range, which is 15; x min is the minimum following distance between the vehicle and the vehicle in front, which is 5m; ω v 、ω a 、ω d and ω x is the weight coefficient, and its specific value is determined through simulation and experiments;

[0081] The surrounding road condition demand factor R r The calculation formula is:

[0082]

[0083] Where, T s is the traffic light influence, which takes a value of 1 when the nearest traffic light in front of the vehicle is red or yellow, and takes a value of 0 when the nearest traffic light in front of the vehicle is green; I is the road sign influence, which takes a value of 1 when the nearest road sign in front of the vehicle prompts to slow down, and takes a value of 0 when the nearest road sign in front of the vehicle prompts other content; μ is the road adhesion coefficient; r is the road type influence, which takes a value of 1 when the nearest road type in front of the vehicle is a downhill road or a curve, and takes a value of 0 when the nearest road type in front of the vehicle is other roads; ω I 、ω μ and ω r is the weight coefficient, and its specific value is determined through simulation and experiments;

[0084] The surrounding pedestrian situation demand factor R P The calculation formula is:

[0085]

[0086] Where D is the pedestrian density coefficient within the farthest illumination range of the headlight. When there are less than 5 people, the value is 1; when there are 5 to 10 people, the value is 2; when there are more than 10 people, the value is 3; D max is the maximum pedestrian density coefficient within the farthest illumination range of the headlight, with a value of 3; A is the average age coefficient of pedestrians within the farthest illumination range of the headlight, with a value of 1 for those aged 18 to 60, and a value of 2 for those under 18 or over 60; A max is the maximum value of the average age coefficient of pedestrians within the farthest illumination range of the headlight, and its value is 2; S is the pedestrian action state coefficient within the farthest illumination range of the headlight, and its value is 3 when there is a running action state among the pedestrians within the farthest illumination range of the headlight, and its value is 2 when there is a slow walking action state, and its value is 1 for other action states; S maxThe maximum value of the pedestrian action state coefficient within the farthest illumination range of the headlight is 3; ω D 、ω A and ω S is the weight coefficient, and its specific value is determined through simulation and experiments;

[0087] The vehicle's operating safety requirement factor R tv The calculation formula is:

[0088]

[0089] Where, v t is the vehicle speed; is the maximum speed of the vehicle, which is 80km / h; m is the total mass of the vehicle; m max is the maximum total mass of the vehicle, which is 40000kg; y is the age of the driver; d is the ideal driver age, which is 44 years old; t is the driver's continuous driving time; t max is the maximum continuous driving time of the driver, which is 4 hours; V is the volume of the cabin occupants; V max The maximum volume for cab occupants is 100 decibels; vt 、ω m 、ω a 、ω t and ω v is the weight coefficient, and its specific value is determined through simulation and experiments;

[0090] The calculation formula of the early braking demand degree characterization coefficient R is:

[0091] R=ε1R fv +ε2R r +ε3R P +ε4R tv

[0092] Where ε1, ε2, ε3, and ε4 are the demand weight coefficients for the driving state of the preceding vehicle, the demand weight coefficients for the surrounding road conditions, the demand weight coefficients for the surrounding pedestrian conditions, and the demand weight coefficients for the vehicle's operating safety conditions, respectively. Their specific values ​​are determined through simulation and experiments.

[0093] The early brake opening sensitivity adaptation module calculates the early brake opening threshold value O according to the driver's driving style characterization coefficient S and driving experience characterization coefficient E t ;

[0094] The advance braking force calculation module uses the proximal strategy optimization algorithm to calculate the advance braking force F b The size of the proximal policy optimization algorithm's reward function r PPOIt consists of brake safety bonus items, comfort bonus items, brake energy efficiency bonus items, driving stability bonus items and brake temperature penalty items;

[0095] The module for connecting early braking with normal braking realizes a reasonable transition between early braking and normal braking according to the braking connection rules; the normal braking is specifically the braking process after the driver manually operates the braking system according to real-time traffic conditions and driving needs and the braking active safety system is triggered.

[0096] The calculation formula of the driving style characterization coefficient S is:

[0097]

[0098] Where, v d The driver's usual driving speed; The maximum driving speed is 150km / h; is the minimum driving speed, which is 0km / h; a d The driver's customary braking deceleration; is the maximum braking deceleration, which is 8m / s 2 ; is the minimum braking deceleration, which is 0.5m / s 2 ;f b is the driver's emergency braking frequency; is the maximum emergency braking frequency, which is 10 times per hour; x d The driver's customary following distance; is the maximum following distance, which is 100m; is the minimum following distance, which is 3m; α1, α2, α3 and α4 are weight coefficients, whose specific values ​​are determined through simulation and experiments; β1, β2, β3 and β4 are influence coefficients, whose specific values ​​are determined through simulation and experiments;

[0099] The calculation formula of the driving experience characterization coefficient E is:

[0100]

[0101] Where y is the driver’s age; max is the maximum driving age, which is 50 years; min is the minimum driving age, which is 0 years; n is the number of correct responses to sudden driving risks; n max is the maximum number of correct responses to sudden driving risks, which is set to 1000 times; t r The total driving time of drivers on wet, snowy and icy roads; is the maximum driving time, which is 500 hours; t aThe length of time the driver uses the assisted driving system; is the maximum usage time, which is set to 1000 hours; α5, α6, α7, and α8 are weight coefficients, whose specific values ​​are determined through simulation and experiments; β5, β6, β7, and β8 are influence coefficients, whose specific values ​​are determined through simulation and experiments;

[0102] The early brake opening threshold O t The calculation formula is:

[0103]

[0104] Where, and are the driving style weight coefficient, driving experience weight coefficient and driving style and driving experience interaction weight coefficient, and their specific values ​​are determined through simulation and experiments; ρ1, ρ2 and ρ3 are the nonlinear influence coefficients, and their specific values ​​are determined through simulation and experiments.

[0105] The specific design of the proximal strategy optimization algorithm is:

[0106] The state variable s is:

[0107] s=[R,m,v t , μ,i,S]

[0108] Where R is the coefficient representing the degree of early braking demand; m is the total mass of the vehicle; v t is the vehicle speed; μ is the road adhesion coefficient; i is the road slope; S is the driving style characterization coefficient;

[0109] Action variables are:

[0110]

[0111] Where, F1 is the electric braking force; F2 is the hydraulic braking force; is the maximum motor power; is the maximum hydraulic braking force; A c is the effective area of ​​the brake caliper; k1 is the motor braking efficiency; k2 is the hydraulic braking efficiency;

[0112] Reward function r PPO Designed to:

[0113] r PPO =r s +r c +r e +r st +p T

[0114] Where r s For brake safety reward items;c is the comfort bonus item; r e Braking energy efficiency reward item; r st It is a driving stability reward item; p T is the brake temperature penalty term.

[0115] The braking safety reward item r s The calculation formula is:

[0116]

[0117] Where a max is the maximum braking deceleration, which is 8m / s 2 ; R is the coefficient representing the degree of early braking demand; F1 is the electric braking force; F2 is the hydraulic braking force;

[0118] The comfort bonus item r c The calculation formula is:

[0119]

[0120] Where, and are the differentials of the motor force F1 and the hydraulic braking force F2 with respect to time t, respectively, representing the rate of change of the motor force and the rate of change of the hydraulic braking force;

[0121] The braking energy efficiency reward item r e The calculation formula is:

[0122] r e =-(η h ·F2·v t 2 -η reg ·F1·v t 2 γ env )

[0123] Where η h is the hydraulic braking energy consumption coefficient, which is 0.05; η reg is the motor braking energy recovery coefficient, which is 0.1; v t is the vehicle speed; γ env is the environmental correction factor, which is set to 0.95;

[0124] The driving stability reward item r st The calculation formula is:

[0125]

[0126] Where h c is the height of the vehicle's center of mass; m is the total mass of the vehicle; ay is the lateral acceleration of the vehicle; d is the wheelbase; v t is the vehicle speed; θ f is the front wheel turning angle; l is the wheelbase;

[0127] The brake temperature penalty term p T The calculation formula is:

[0128] p T =10(max(0, T b -T o )) 3

[0129] Where, T b is the brake operating temperature; T o The optimal operating temperature of the brake is 300℃.

[0130] The braking connection rules are specifically as follows:

[0131] When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t If the speed continues to increase and the driver does not step on the brake pedal, the automatic emergency braking system will be activated;

[0132] When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t And it keeps increasing, but when the driver steps on the brake pedal, the braking torque of the whole vehicle is determined by the brake pedal opening;

[0133] When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t But if it remains unchanged, the advance braking system will continue to be activated.

Claims

1. An intelligent advance braking system for electric vehicles, characterized in that: It includes an information acquisition module based on vehicle wireless communication technology, an early braking judgment module, an early braking sensitivity adaptation module, an early braking force calculation module, and an early braking and normal braking connection module; The information acquisition module based on vehicle wireless communication technology is used to obtain various information between the vehicle and the surrounding environment, including the vehicle's driving status information, surrounding vehicle driving status information, surrounding road infrastructure information and surrounding pedestrian information; The early braking judgment module is based on the early braking demand degree characterization coefficient R and the early braking opening threshold O t The comparison result is used to determine whether to start early braking; When the early braking demand degree representation coefficient R is less than or equal to the early braking opening threshold value O t When the early braking demand coefficient R is greater than the early braking opening threshold O t When the vehicle is in the emergency braking state, the advance braking system is activated; The early braking requirement coefficient R is determined by the driving state requirement factor R of the vehicle ahead. fv , surrounding road condition demand factor R r , surrounding pedestrian demand factor R P and the vehicle's operational safety requirement factor R tv Obtained through weighted calculation; The preceding vehicle driving state requirement factor R fv The calculation formula is: Where v1, v2, and v3 are the average longitudinal speeds of all vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; a1, a2, and a3 are the average braking decelerations of all vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; d1, d2, and d3 are the number of vehicles in the ranges of 0 to 100 meters, 100 to 200 meters, and 200 to 300 meters ahead of the vehicle in the lane at the same time; x is the following distance between the vehicle and the vehicle in front; v max is the maximum average longitudinal speed of all vehicles within each range, which is 120 km / h; a max The maximum average braking deceleration of all vehicles in each range is 10m / s 2 ; d max is the maximum number of vehicles in each range, which is 15; x min is the minimum following distance between the vehicle and the vehicle in front, which is 5m; ω v 、ω a 、ω d and ω x is the weight coefficient, and its specific value is determined through simulation and experiments; The surrounding road condition demand factor R r The calculation formula is: Where, T s is the traffic light influence, which takes a value of 1 when the nearest traffic light in front of the vehicle is red or yellow, and takes a value of 0 when the nearest traffic light in front of the vehicle is green; I is the road sign influence, which takes a value of 1 when the nearest road sign in front of the vehicle prompts to slow down, and takes a value of 0 when the nearest road sign in front of the vehicle prompts other content; μ is the road adhesion coefficient; r is the road type influence, which takes a value of 1 when the nearest road type in front of the vehicle is a downhill road or a curve, and takes a value of 0 when the nearest road type in front of the vehicle is other roads; ω I 、ω μ and ω r is the weight coefficient, and its specific value is determined through simulation and experiments; The surrounding pedestrian situation demand factor R P The calculation formula is: Where D is the pedestrian density coefficient within the farthest illumination range of the headlight. When there are less than 5 people, the value is 1; when there are 5 to 10 people, the value is 2; when there are more than 10 people, the value is 3; D max is the maximum pedestrian density coefficient within the farthest illumination range of the headlight, with a value of 3; A is the average age coefficient of pedestrians within the farthest illumination range of the headlight, with a value of 1 for those aged 18 to 60, and a value of 2 for those under 18 or over 60; A max is the maximum value of the average age coefficient of pedestrians within the farthest illumination range of the headlight, and its value is 2; S is the pedestrian action state coefficient within the farthest illumination range of the headlight, and its value is 3 when there is a running action state among the pedestrians within the farthest illumination range of the headlight, and its value is 2 when there is a slow walking action state, and its value is 1 for other action states; S max The maximum value of the pedestrian action state coefficient within the farthest illumination range of the headlight is 3; ω D 、ω A and ω S is the weight coefficient, and its specific value is determined through simulation and experiments; The vehicle's operating safety requirement factor R tv The calculation formula is: Where, v t is the vehicle speed; is the maximum speed of the vehicle, which is 80km / h; m is the total mass of the vehicle; m max is the maximum total mass of the vehicle, which is 40000kg; y is the age of the driver; d is the ideal driver age, which is 44 years old; t is the driver's continuous driving time; t max is the maximum continuous driving time of the driver, which is 4 hours; V is the volume of the cabin occupants; V max The maximum volume for cab occupants is 100 decibels; vt 、ω m 、ω a 、ω t and ω v is the weight coefficient, and its specific value is determined through simulation and experiments; The calculation formula of the early braking demand degree characterization coefficient R is: R=ε1R fv +ε2R r +ε3R P +ε4R tv Where ε1, ε2, ε3, and ε4 are the demand weight coefficients for the driving state of the preceding vehicle, the demand weight coefficients for the surrounding road conditions, the demand weight coefficients for the surrounding pedestrian conditions, and the demand weight coefficients for the vehicle's operating safety conditions, respectively. Their specific values ​​are determined through simulation and experiments. The early brake opening sensitivity adaptation module calculates the early brake opening threshold value O according to the driver's driving style characterization coefficient S and driving experience characterization coefficient E t ; The advance braking force calculation module uses the proximal strategy optimization algorithm to calculate the advance braking force F b The size of the proximal policy optimization algorithm's reward function r PPO It consists of brake safety bonus items, comfort bonus items, brake energy efficiency bonus items, driving stability bonus items and brake temperature penalty items; The advance braking and normal braking connection module realizes a reasonable transition between advance braking and normal braking according to the braking connection rules; Normal braking refers to the braking process in which the driver manually operates the braking system according to real-time traffic conditions and driving needs, and the braking active safety system is triggered.

2. The electric vehicle intelligent advance braking system according to claim 1, characterized in that: The calculation formula of the driving style characterization coefficient S is: Where, v d The driver's usual driving speed; The maximum driving speed is 150km / h; is the minimum driving speed, which is 0km / h; a d The driver's customary braking deceleration; is the maximum braking deceleration, which is 8m / s 2 ; is the minimum braking deceleration, which is 0.5m / s 2 ; f b is the driver's emergency braking frequency; is the maximum emergency braking frequency, which is 10 times per hour; x d The driver's customary following distance; is the maximum following distance, which is 100m; is the minimum following distance, which is 3m; α1, α2, α3 and α4 are weight coefficients, whose specific values ​​are determined through simulation and experiments; β1, β2, β3 and β4 are influence coefficients, whose specific values ​​are determined through simulation and experiments; The calculation formula of the driving experience characterization coefficient E is: Where y is the driver’s age; max is the maximum driving age, which is 50 years; min is the minimum driving age, which is 0 years; n is the number of correct responses to sudden driving risks; n max is the maximum number of correct responses to sudden driving risks, which is set to 1000 times; t r The total driving time of drivers on wet, snowy and icy roads; is the maximum driving time, which is 500 hours; t a The length of time the driver uses the assisted driving system; is the maximum usage time, which is 1000 hours; α5, α6, a7, and α8 are weight coefficients, whose specific values ​​are determined through simulation and experiments; β5, β6, β7, and β8 are influence coefficients, whose specific values ​​are determined through simulation and experiments; The early brake opening threshold O t The calculation formula is: Where, and are the driving style weight coefficient, driving experience weight coefficient and driving style and driving experience interaction weight coefficient, and their specific values ​​are determined through simulation and experiments; ρ1, ρ2 and ρ3 are the nonlinear influence coefficients, and their specific values ​​are determined through simulation and experiments.

3. The electric vehicle intelligent advance braking system according to claim 1, characterized in that: The specific design of the proximal strategy optimization algorithm is: The state variable s is: s=[R,m,v t ,μ,i,S] Where R is the coefficient representing the degree of early braking demand; m is the total mass of the vehicle; v t is the vehicle speed; μ is the road adhesion coefficient; i is the road slope; S is the driving style characterization coefficient; Action variables are: Where, F1 is the electric braking force; F2 is the hydraulic braking force; is the maximum motor power; is the maximum hydraulic braking force; A c is the effective area of ​​the brake caliper; k1 is the motor braking efficiency; k2 is the hydraulic braking efficiency; Reward function r PPO Designed to: r PPO ＝r s +r c +r e +r st +p T Where r s For brake safety reward items; c is the comfort bonus item; r e is the braking energy efficiency reward item; r st It is a driving stability reward item; p T is the brake temperature penalty term.

4. The electric vehicle intelligent advance braking system according to claim 1, characterized in that: The braking safety reward item r s The calculation formula is: Where a max is the maximum braking deceleration, which is 8m / s 2 ; R is the coefficient representing the degree of early braking demand; F1 is the electric braking force; F2 is the hydraulic braking force; The comfort bonus item r c The calculation formula is: Where, and are the differentials of the motor force F1 and the hydraulic braking force F2 with respect to time t, respectively, representing the rate of change of the motor force and the rate of change of the hydraulic braking force; The braking energy efficiency reward item r e The calculation formula is: r e =-(η h ·F2·v t 2 -or reg ·F1·v t 2 ·c env ) Where η h is the hydraulic braking energy consumption coefficient, which is 0.05; η reg is the motor braking energy recovery coefficient, which is 0.1; v t is the vehicle speed; env is the environmental correction factor, which is 0.95; The driving stability reward item r st The calculation formula is: Where h c is the height of the vehicle's center of mass; m is the total mass of the vehicle; a y is the lateral acceleration of the vehicle; d is the wheelbase; v t is the vehicle speed; θ f is the front wheel turning angle; l is the wheelbase; The brake temperature penalty term p T The calculation formula is: p T =10(max(0,T b -T o )) 3 Where, T b is the brake operating temperature; T o The optimal operating temperature of the brake is 300℃.

5. The electric vehicle intelligent advance braking system according to claim 1, characterized in that: The braking connection rules are specifically as follows: When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t If the speed continues to increase and the driver does not step on the brake pedal, the automatic emergency braking system will be activated; When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t And it keeps increasing, but when the driver steps on the brake pedal, the braking torque of the whole vehicle is determined by the brake pedal opening; When the advance braking system is turned on for 10 seconds, if the advance braking demand degree representation coefficient R is still greater than the advance braking opening threshold O t But if it remains unchanged, the advance braking system will continue to be activated.

Images