Fuel cell vehicle ecological driving cooperative control method based on SAC algorithm

Through the coordinated control method of fuel cell vehicle ecological driving based on SAC algorithm, the neural network is used to optimize power distribution and acceleration decisions, and the problem of fuel cell vehicle response lag when load changes is solved, improving the following performance and comfort, and reducing the The lifespan of fuel cell stacks declines.

CN118991823AActive Publication Date: 2024-11-22CHONGQING JIAOTONG UNIV

Patent Information

Application Number
CN202411175997.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-22
Estimated Expiration
2044-08-26

AI Technical Summary

Technical Problem

Fuel cell vehicles have a hysteresis response to the reaction gas when the load changes sharply, and cannot recover regenerative braking energy. The existing energy management strategies have limited effects in complex driving environments, affecting performance and life.

Method used

Using the fuel cell vehicle ecological driving collaborative control method based on SAC algorithm, by obtaining vehicle status information and following information, a neural network is built to determine the reward function and optimal control strategy, optimize power distribution and acceleration decisions, and realize ecological driving and vehicle follow-up. Coordinated control.

Benefits of technology

It improves the following performance and comfort of fuel cell vehicles, reduces the decline in the life of fuel cell stack, and enhances the adaptability of working conditions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118991823A_ABST
    Figure CN118991823A_ABST
Patent Text Reader

Abstract

The invention provides a fuel cell vehicle ecological driving cooperative control method based on an SAC algorithm, and the method comprises the following steps: obtaining the state information of a target vehicle, and determining the control demand information of the target vehicle based on the state information of the target vehicle; a neural network based on SAC is constructed in the controller, the neural network comprises a state space and an action space of ecological driving, and a reward function is determined based on the control demand information; inputting the state information of the target vehicle into the SAC-based neural network for offline training, obtaining the real-time state information of the target vehicle, and inputting the real-time state information into the trained SAC neural network to determine an optimal control strategy, the power distribution state of the fuel cell vehicle can be determined based on the actual state information of the target fuel cell vehicle and the vehicle following information, so that the acceleration of the whole vehicle and the output power of a power system are decided, and cooperative control of ecological driving and vehicle following is effectively realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to a vehicle driving control method, and in particular to a fuel cell vehicle eco-driving cooperative control method based on a SAC algorithm. Background Art

[0002] Hydrogen has the characteristics of high calorific value, cleanness and carbon-free, and is regarded as a key energy source for solving global energy and environmental problems. Moreover, it has fast hydrogen refueling speed and high conversion efficiency, and is the main power source for fuel cell vehicles (FCVs). This makes FCVs have the advantages of both internal combustion engine vehicles and electric vehicles, and is the most promising new energy vehicle model in the future.

[0003] However, when the load of FCVs changes dramatically, the response of the reaction gas will lag behind the power demand. At the same time, the unidirectional power output makes it impossible to recover regenerative braking energy. In order to solve this technical problem, FCVs usually use supercapacitors or power batteries as auxiliary power sources to form a hybrid power system.

[0004] Since multiple energy sources increase the complexity of the system, a stable, efficient and reliable energy management strategy is particularly critical to improving the performance of fuel cell vehicles. Usually, energy management optimizes the energy distribution of the power system at a specific vehicle speed, resulting in limited energy-saving effects. At the same time, the complexity and uncertainty of the driving environment have a huge impact on the performance of energy management.

[0005] Therefore, in order to solve the above technical problems, it is urgent to propose a new technical means. Summary of the invention

[0006] In view of this, the purpose of the present invention is to provide a fuel cell vehicle eco-driving collaborative control method based on the SAC algorithm, which can determine the power distribution state of the fuel cell vehicle based on the actual state information of the target fuel cell vehicle and the following vehicle information, thereby deciding the acceleration of the whole vehicle and the output power of the power system, thereby effectively realizing the collaborative control of eco-driving and vehicle following.

[0007] The present invention provides a fuel cell vehicle eco-driving cooperative control method based on a SAC algorithm, comprising the following steps:

[0008] Acquire target vehicle status information, and determine control requirement information of the target vehicle based on the vehicle status information;

[0009] Construct a SAC-based neural network in the controller, including the state space and action space of eco-driving, and determine the reward function based on the control demand information;

[0010] The state information of the target vehicle is input into the SAC-based neural network for offline training, and the real-time state information of the target vehicle is obtained and input into the trained SAC neural network to determine the optimal control strategy.

[0011] Furthermore, the target vehicle status information includes a following distance between the target vehicle and a preceding vehicle of the target vehicle, a speed of the target vehicle, a speed of a preceding vehicle of the target vehicle, an SOC of a fuel cell stack of the target vehicle, and an output power of the fuel cell stack of the target vehicle.

[0012] Furthermore, the control requirement information includes a following distance model of the target vehicle relative to the preceding vehicle, a drive motor model of the target vehicle, a power battery model, a fuel cell stack electrochemical model, and a fuel cell stack life model.

[0013] Furthermore, the following distance model of the target vehicle relative to the preceding vehicle is:

[0014] D(t+1)=D(t)+v rel (t)Δt;

[0015] v rel (t) = v p (t)-v h (t);

[0016]

[0017] Where: D(t+1) represents the following distance between the target vehicle and the preceding vehicle at time t+1, D(t) represents the following distance between the target vehicle and the preceding vehicle at time t, d1 represents the minimum following distance after the target vehicle is braked, d2 represents the maximum following distance after the target vehicle is braked, τ1 and τ2 represent the response time of the braking system, a1 and a2 represent the braking acceleration of the target vehicle, and v h represents the speed of the target vehicle, v rel (t) represents the relative speed between the target vehicle and the preceding vehicle, and They represent the upper and lower limits of the target vehicle’s expected following distance area, v p (t) is the speed of the vehicle in front of the target vehicle, D max and D min represents the maximum following distance and the minimum following distance, and α represents the adjustment coefficient.

[0018] Furthermore, the driving motor model of the target vehicle is:

[0019]

[0020] Where: P reqis the required power of the target vehicle, m, g and f are the vehicle mass, gravity acceleration and rolling resistance coefficient respectively, C d is the air resistance coefficient, A and δ are the conversion coefficients of the frontal area and rotating mass respectively, and μ is the road slope; P mot is the motor power requirement, P fc_net and P bat are the fuel cell stack net power and battery output power, respectively, mot is the motor efficiency.

[0021] Furthermore, the power battery model is:

[0022]

[0023] Where: V bat Indicates the voltage of the power battery, V oc ,I bat and R bat Represent the open circuit voltage, battery current and internal resistance of the power battery respectively, P bat is the battery power, SOC in Represents the initial value of the power battery SOC, Q bat Represents the nominal capacity of the power battery.

[0024] Furthermore, the electrochemical model of the fuel cell stack is:

[0025]

[0026] Where: T fc , R and F represent the temperature, gas constant and Faraday constant of the fuel cell stack respectively, P H2 and P O2 are the anode hydrogen partial pressure and cathode oxygen partial pressure of the fuel cell stack, respectively; v0 represents the voltage at zero current density, i is the current density, i = I / A cell , I and A cell They represent the fuel cell stack current and the effective area of ​​the battery, v a and c2 are constants, c1 and c3 are constants, R ohm is the internal resistance.

[0027] Furthermore, the fuel cell stack life model is:

[0028] ΔD fc =k p [d low (t)+d high (t)+d load-change (t)+d start-stop (t)];

[0029]

[0030] Where: ΔD fc is the performance decay rate of the fuel cell in a single time step, P low and P high represents the low power threshold and high power threshold of the fuel cell, |ΔP| represents the absolute value of the difference between the output power of the fuel cell at the previous time step and the output power at the current moment; k p is the road correction coefficient, k i (i=1,2,3,4) represents the decay coefficient of each type of working condition, k1 is 1.26×10 -3 , k2 is 1.47×10 -3 , k3 takes 9.88×10 -7 , k4 is 1.96×10 -3 .

[0031] Furthermore, building a neural network based on SAC specifically includes:

[0032] The SAC-based neural network is a pruned dual Q-learning network, including four parameterized soft Q-functions Q θ (s t ,a t ) and a policy function π φ (a t |s t );

[0033] Construct the state space s t :s t =[D(t),v h (t),v rel (t),SOC(t),P fc (t)];

[0034] Constructing the action space:

[0035] And the acceleration and following distance constraints are:

[0036]

[0037] Constructing the reward function:

[0038]

[0039] in: is the weight coefficient, indicating the vehicle following cost C ACC and energy management cost C EMS The relative importance between ACC Based on the following distance cost C safe and the jerk cost C jerk and the collision penalty term C collisionComposition, δ1, δ2 are C jerk and C collision The weight coefficient, C price represents the price cost of fuel cell stack SOH reduction and hydrogen consumption equivalent, C fc,tem represents the fuel cell stack overtemperature penalty, C SOC represents the power battery SOC maintenance cost, λ1 and λ2 are C fc,tem and C SOC The weight coefficient, p H2 and p fc are the unit prices of hydrogen and fuel cell stack, T fc,ref and SOC ref Indicates the fuel cell stack target temperature reference value and the lithium battery SOC maintenance reference value.

[0040] Furthermore, the state information of the target vehicle is input into the SAC-based neural network for offline training, which specifically includes:

[0041] Initialize the algorithm’s hyperparameters, soft Q network parameters θ1, θ2 and θ′1, θ′2, and policy network parameters φ;

[0042] Obtain the state information of the target vehicle and input it into the SAC-based neural network;

[0043] The SAC-based neural network is based on the state s t Give the corresponding action a t , the power system performs corresponding power output;

[0044] Return the next moment state s t+1 and reward r t , the resulting tuple (s t ,a t ,r t ,s t+1 ) into the experience replay pool;

[0045] The optimal strategy function J(π) of the neural network based on SAC * ) can be expressed by the following formula:

[0046]

[0047] Where: T represents the total duration of data interaction between the controller and the environment; E represents the mathematical expectation, s t and a t Respectively represent the state and action at time t, ρ π is the optimal strategy π * The trajectory distribution under γ represents the discount factor of the reward, r(s t ,a t ) refers to the reward obtained by the state-action pair, πφ represents the policy function with parameter φ, -logπ φ (a t |s t ) indicates action a t Entropy at the current state; α is the temperature coefficient;

[0048] The update objective of the soft Q-function is to minimize the soft Bellman residual:

[0049]

[0050] Among them (s t ,a t ,r t ,s t+1 ) is a tuple sampled from the experience replay pool D, θ′ represents the network parameters of the target soft Q-function; in order to avoid overestimation of the Q value, the loss function for evaluating the soft Q network is expressed as follows:

[0051]

[0052] The evaluation network and the target network are composed of two groups of networks, whose parameters can be expressed as θ1, θ2 and θ′1, θ′2 respectively. During the training process, the target network with a lower Q value is selected to update the evaluation network. At the same time, the parameters of the target soft Q network are replaced by soft update:

[0053] θ′ i | i=1,2 =δθ i +(1-δ)θ′ i

[0054] Among them, δ is the soft update factor;

[0055] The loss function of the policy network is expressed as follows:

[0056]

[0057] Beneficial effects of the present invention: Through the present invention, the power distribution state of the fuel cell vehicle can be determined based on the actual state information and following vehicle information of the target fuel cell vehicle, thereby deciding the acceleration of the entire vehicle and the output power of the power system, thereby effectively realizing the coordinated control of ecological driving and vehicle following, so that the driving process has good following performance and comfort, and reduces the SOH decay of the fuel cell stack, so that the fuel cell vehicle has good adaptability to working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The present invention will be further described below in conjunction with the accompanying drawings and embodiments:

[0059] Figure 1It is a flow chart of the present invention. DETAILED DESCRIPTION

[0060] The present invention is further described in detail below:

[0061] The present invention provides a fuel cell vehicle eco-driving cooperative control method based on a SAC algorithm, comprising the following steps:

[0062] Acquire target vehicle status information, and determine control requirement information of the target vehicle based on the vehicle status information;

[0063] A SAC-based neural network is constructed in the controller, including the state space and action space of ecological driving, and a reward function is determined based on the control demand information; wherein the controller is a vehicle controller of the target vehicle, which is used to control the target vehicle and obtain response information through various sensors of the vehicle, and also interact with the preceding vehicle to obtain the vehicle speed information of the preceding vehicle;

[0064] The state information of the target vehicle is input into the SAC-based neural network for offline training, and the real-time state information of the target vehicle is obtained and input into the trained SAC neural network to determine the optimal control strategy. Through the present invention, the power distribution state of the fuel cell vehicle can be determined based on the actual state information of the target fuel cell vehicle and the following vehicle information, so as to determine the acceleration of the whole vehicle and the output power of the power system, thereby effectively realizing the coordinated control of ecological driving and vehicle following.

[0065] In this embodiment, the target vehicle status information includes the following distance between the target vehicle and the vehicle in front of the target vehicle, the speed of the target vehicle, the speed of the vehicle in front of the target vehicle, the SOC of the fuel cell stack of the target vehicle, and the output power of the fuel cell stack of the target vehicle.

[0066] In this embodiment, the control demand information includes a following distance model of the target vehicle relative to the preceding vehicle, a drive motor model of the target vehicle, a power battery model, a fuel cell stack electrochemical model, and a fuel cell stack life model.

[0067] Specifically: The following distance model of the target vehicle relative to the preceding vehicle is:

[0068] D(t+1)=D(t)+v rel (t)Δt;

[0069] v rel (t) = v p (t)-v h (t);

[0070]

[0071] Where: D(t+1) represents the following distance between the target vehicle and the preceding vehicle at time t+1, D(t) represents the following distance between the target vehicle and the preceding vehicle at time t, d1 represents the minimum following distance after the target vehicle is braked, d2 represents the maximum following distance after the target vehicle is braked, τ1 and τ2 represent the response time of the braking system, a1 and a2 represent the braking acceleration of the target vehicle, and v h represents the speed of the target vehicle, v rel (t) represents the relative speed between the target vehicle and the preceding vehicle, and They represent the upper and lower limits of the target vehicle’s expected following distance area, v p (t) is the speed of the vehicle in front of the target vehicle, D max and D min represents the maximum following distance and the minimum following distance, and α represents the adjustment coefficient.

[0072] The drive motor model of the target vehicle is:

[0073]

[0074] Where: P req is the required power of the target vehicle, m, g and f are the vehicle mass, gravity acceleration and rolling resistance coefficient respectively, C d is the air resistance coefficient, A and δ are the conversion coefficients of the frontal area and rotating mass respectively, and μ is the road slope; P mot is the motor power requirement, P fc_net and P bat are the fuel cell stack net power and battery output power, respectively, mot is the motor efficiency.

[0075] The power battery model is:

[0076]

[0077] Where: V bat Indicates the voltage of the power battery, V oc ,I bat and R bat Represent the open circuit voltage, battery current and internal resistance of the power battery respectively, P bat is the battery power, SOC in Represents the initial value of the power battery SOC, Q bat Represents the nominal capacity of the power battery.

[0078] The electrochemical model of the fuel cell stack is:

[0079]

[0080] Where: Tfc , R and F represent the temperature, gas constant and Faraday constant of the fuel cell stack respectively, P H2 and P O2 are the anode hydrogen partial pressure and cathode oxygen partial pressure of the fuel cell stack, respectively; v0 represents the voltage at zero current density, i is the current density, i = I / A cell , I and A cell They represent the fuel cell stack current and the effective area of ​​the battery, v a and c2 constants, which can be determined by the existing empirical formula of fuel cell stack temperature and oxygen partial pressure, c1 and c3 are constants, R ohm is the internal resistance, i max Indicates the current density that causes a sharp drop in voltage.

[0081] The fuel cell stack life model is:

[0082] ΔD fc =k p [d low (t)+d high (t)+d load-change (t)+d start-stop (t)];

[0083]

[0084] Where: ΔD fc is the performance decay rate of the fuel cell in a single time step, P low and P high represents the low power threshold and high power threshold of the fuel cell, |ΔP| represents the absolute value of the difference between the output power of the fuel cell at the previous time step and the output power at the current moment; k p is the road correction coefficient, k i (i=1,2,3,4) represents the decay coefficient of each type of working condition, k1 is 1.26×10 -3 , k2 is 1.47×10 -3 , k3 takes 9.88×10 -7 , k4 is 1.96×10 -3 .

[0085] In this embodiment, constructing a neural network based on SAC specifically includes:

[0086] SAC neural network is the abbreviation of Soft Actor-Critic in English, and its Chinese name is Soft Actor-Critic Neural Network; the neural network based on SAC is a pruned double Q-learning network, including 4 parameterized soft Q-functions Q θ (s t ,a t ) and a policy function πφ (a t |s t ); and the control amount of the entire neural network is determined by the acceleration a of the target vehicle h and the output power P of the fuel cell stack fc composition,

[0087] Construct the state space s t :s t =[D(t),v h (t),v rel (t),SOC(t),P fc (t)];

[0088] Constructing the action space:

[0089] a h,bound Indicates the defined acceleration limit value, which is 3m / s 2 ; and the acceleration and following distance constraints are:

[0090]

[0091] In the early stages of training, the second item of the acceleration constraint can avoid most collisions, but due to the discrete time step and the agent's exploration, when the front car's speed is low, the main car's rapid acceleration can cause the two cars to collide. To ensure that training proceeds normally, after a collision, the main car's following distance is set to the minimum following distance, as shown in the second item of the following distance constraint, and the main car's speed is set to the front car's speed value, but a penalty will be imposed on collisions.

[0092] Constructing the reward function:

[0093]

[0094] in: is the weight coefficient, indicating the vehicle following cost C ACC and energy management cost C EMS The relative importance between ACC Based on the following distance cost C safe and the jerk cost C jerk and the collision penalty term C collision Composition, δ1, δ2 are C jerk and C collision The weight coefficient, C price represents the price cost of fuel cell stack SOH reduction and hydrogen consumption equivalent, C fc,tem represents the fuel cell stack overtemperature penalty, C SOC represents the power battery SOC maintenance cost, λ1 and λ2 are C fc,tem and C SOCThe weight coefficient, p H2 and p fc are the unit prices of hydrogen and fuel cell stack, T fc,ref and SOC ref Represents the target temperature reference value of the fuel cell stack and the reference value for maintaining the SOC of the lithium battery. Based on the above reward function, the requirements of the vehicle following system in terms of following safety, traffic efficiency and driving comfort are met. Safety and traffic efficiency are characterized by the following distance, and driving comfort is represented by the rate of change of acceleration. The primary goal of energy management is to minimize hydrogen consumption. At the same time, the decrease in the SOH of the fuel cell is equivalent to a price and included in the total cost. In order to ensure that the fuel cell stack works at a suitable temperature, an overtemperature penalty is set. Finally, the reference value of the lithium battery SOC should be set to maintain it within a certain range.

[0095] In this embodiment, inputting the state information of the target vehicle into the SAC-based neural network for offline training specifically includes:

[0096] Initialize the algorithm’s hyperparameters, soft Q network parameters θ1, θ2 and θ′1, θ′2, and policy network parameters φ;

[0097] Obtain the state information of the target vehicle and input it into the SAC-based neural network;

[0098] The SAC-based neural network is based on the state s t Give the corresponding action a t , the power system performs corresponding power output;

[0099] Return the next moment state s t+1 and reward r t , the resulting tuple (s t ,a t ,r t ,s t+1 ) into the experience replay pool;

[0100] The optimal strategy function J(π) of the neural network based on SAC * ) can be expressed by the following formula:

[0101]

[0102] Where: T represents the total duration of data interaction between the controller and the environment, that is, the duration of data interaction between the controller and the front vehicle, because the speed state of the front vehicle is to be obtained; E represents the mathematical expectation, s t and a t Respectively represent the state and action at time t, ρ π is the optimal strategy π * The trajectory distribution under γ represents the discount factor of the reward, r(s t ,at ) refers to the reward obtained by the state-action pair, π φ represents the policy function with parameter φ, -logπ φ (a t |s t ) indicates action a t Entropy at the current state; α is the temperature coefficient;

[0103] Using the standard actor-critic framework and the maximum entropy principle, the SAC algorithm constructs a parameterized soft Q-function Q θ (s t ,a t ) and the policy function π φ (a t |s t ), the value function can be modeled as an expressive neural network to evaluate the quality of the output action, and the policy function is expressed by a Gaussian function whose mean and variance are the output of the neural network.

[0104] The update objective of the soft Q-function is to minimize the soft Bellman residual:

[0105]

[0106] Among them (s t ,a t ,r t ,s t+1 ) is a tuple sampled from the experience replay pool D, θ′ represents the network parameters of the target soft Q-function; in order to avoid overestimation of the Q value, the pruned double Q-learning technique is introduced into the SAC algorithm, and the loss function for evaluating the soft Q network is expressed as follows:

[0107]

[0108] The evaluation network and the target network are composed of two groups of networks, whose parameters can be expressed as θ1, θ2 and θ′1, θ′2 respectively. During the training process, the target network with a lower Q value is selected to update the evaluation network. At the same time, the parameters of the target soft Q network are replaced by soft update:

[0109] θ′ i | i=1,2 =δθ i +(1-δ)θ′ i

[0110] Among them, δ is the soft update factor;

[0111] The loss function of the policy network is expressed as follows:

[0112]

[0113] After the SAC network training is completed, the current speed of the front vehicle and the target vehicle's own state are input into the trained neural network to predict the target vehicle's action under the optimal strategy at the next moment, and then determine the target vehicle's acceleration and the output power of the power system based on the action (this determination process can use existing technology), thereby achieving coordinated control of the target vehicle's following and ecological driving.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A fuel cell vehicle eco-driving cooperative control method based on SAC algorithm, Features: The following steps are involved: Acquire target vehicle status information, and determine control requirement information of the target vehicle based on the vehicle status information; Construct a SAC-based neural network in the controller, including the state space and action space of eco-driving, and determine the reward function based on the control demand information; The state information of the target vehicle is input into the SAC-based neural network for offline training, and the real-time state information of the target vehicle is obtained and input into the trained SAC neural network to determine the optimal control strategy.

2. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles according to claim 1, Features: The target vehicle status information includes the following distance between the target vehicle and the vehicle ahead of the target vehicle, the speed of the target vehicle, the speed of the vehicle ahead of the target vehicle, the SOC of the fuel cell stack of the target vehicle, and the output power of the fuel cell stack of the target vehicle.

3. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles according to claim 1, Features: The control demand information includes a following distance model of the target vehicle relative to the preceding vehicle, a driving motor model of the target vehicle, a power battery model, a fuel cell stack electrochemical model, and a fuel cell stack life model.

4. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles according to claim 3, Features: The following distance model of the target vehicle relative to the preceding vehicle is: D(t+1)=D(t)+v rel (t)Δt; v rel (t)=v p (t)-v h (t); Where: D(t+1) represents the following distance between the target vehicle and the preceding vehicle at time t+1, D(t) represents the following distance between the target vehicle and the preceding vehicle at time t, and d 1 Indicates the minimum following distance of the target vehicle after braking, d 2 represents the maximum following distance of the target vehicle after braking, τ 1 and τ 2 Both represent the response time of the braking system, a 1 and a 2 Both represent the braking acceleration of the target vehicle, v h represents the speed of the target vehicle, v rel (t) represents the relative speed between the target vehicle and the preceding vehicle, and They represent the upper and lower limits of the target vehicle’s expected following distance area, v p (t) is the speed of the vehicle in front of the target vehicle, D max and D min represents the maximum following distance and the minimum following distance, and α represents the adjustment coefficient.

5. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles according to claim 3, Features: The drive motor model of the target vehicle is: Where: P req is the required power of the target vehicle, m, g and f are the vehicle mass, gravity acceleration and rolling resistance coefficient respectively, C d is the air resistance coefficient, A and δ are the conversion coefficients of the frontal area and rotating mass respectively, and μ is the road slope; P mot is the motor power requirement, P fc_net and P bat are the fuel cell stack net power and battery output power, respectively, mot is the motor efficiency.

6. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles as claimed in claim 3, Features: The power battery model is: Where: V bat Indicates the voltage of the power battery, V oc ,I bat and R bat Represent the open circuit voltage, battery current and internal resistance of the power battery respectively, P bat is the battery power, SOC in Represents the initial value of the power battery SOC, Q bat Represents the nominal capacity of the power battery.

7. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles as claimed in claim 3, Features: The electrochemical model of the fuel cell stack is: Where: T fc , R and F represent the temperature, gas constant and Faraday constant of the fuel cell stack respectively, P H2 and P O2 are the anode hydrogen partial pressure and cathode oxygen partial pressure of the fuel cell stack respectively; v 0 Represents the voltage at zero current density, i is the current density, i = I / A cell , I and A cell Represent the fuel cell stack current and the effective area of ​​the battery, v a and c 2 is a constant, c 1 and c 3 is a constant, R ohm is the internal resistance.

8. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles as claimed in claim 3, Features: The fuel cell stack life model is: ΔD fc =k p [d low (t)+d high (t)+d load-change (t)+d start-stop (t)]; Where: ΔD fc is the performance decay rate of the fuel cell in a single time step, P low and P high represents the low power threshold and high power threshold of the fuel cell, |ΔP| represents the absolute value of the difference between the output power of the fuel cell at the previous time step and the output power at the current moment; k p is the road correction coefficient, k i (i=1,2,3,4) represents the decay coefficient of each type of working condition, k 1 Take 1.26×10 -3 , k 2 Take 1.47×10 -3 , k 3 Take 9.88×10 -7 , k 4 Take 1.96×10 -3 .

9. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles as claimed in claim 3, Features: Building a SAC-based neural network specifically includes: The SAC-based neural network is a pruned dual Q-learning network, including four parameterized soft Q-functions Q θ (s t ,a t ) and a policy function π φ (a t |s t ); Construct the state space s t :s t =[D(t),v h (t),v rel (t),SOC(t),P fc (t)]; Constructing the action space: And the acceleration and following distance constraints are: Constructing the reward function: in: is the weight coefficient, indicating the vehicle following cost C ACC and energy management cost C EMS The relative importance between ACC Based on the following distance cost C safe and the jerk cost C jerk and the collision penalty term C collision Composition, δ 1 , δ 2 C jerk and C collision The weight coefficient, C price represents the price cost of fuel cell stack SOH reduction and hydrogen consumption equivalent, C fc,tem represents the fuel cell stack overtemperature penalty, C SOC represents the power battery SOC maintenance cost, λ 1 , 2 C fc,tem and C SOC The weight coefficient, p H2 and p fc are the unit prices of hydrogen and fuel cell stack, T fc,ref and SOC ref Indicates the fuel cell stack target temperature reference value and the lithium battery SOC maintenance reference value.

10. According to the SAC algorithm-based eco-driving cooperative control method for fuel cell vehicles according to claim 9, Features: Inputting the state information of the target vehicle into the SAC-based neural network for offline training specifically includes: Initialize the algorithm's hyperparameters and soft-Q network parameters θ 1 ,θ 2 and θ′ 1 ,θ′ 2 and policy network parameters φ; Obtain the state information of the target vehicle and input it into the SAC-based neural network; The SAC-based neural network is based on the state s t Give the corresponding action a t , the power system performs corresponding power output; Return the next moment state s t+1 and reward r t , the resulting tuple (s t ,a t ,r t ,s t+1 ) into the experience replay pool; The optimal strategy function J(π) of the neural network based on SAC * ) can be expressed by the following formula: Where: T represents the total duration of data interaction between the controller and the environment; E represents the mathematical expectation, s t and a t Respectively represent the state and action at time t, ρ π is the optimal strategy π * The trajectory distribution under γ represents the discount factor of the reward, r(s t ,a t ) refers to the reward obtained by the state-action pair, π φ represents the policy function with parameter φ, -logπ φ (a t |s t ) indicates action a t Entropy at the current state; α is the temperature coefficient; The update objective of the soft Q-function is to minimize the soft Bellman residual: Among them (s t ,a t ,r t ,s t+1 ) is a tuple sampled from the experience replay pool D, θ′ represents the network parameters of the target soft Q-function; in order to avoid overestimation of the Q value, the loss function for evaluating the soft Q network is expressed as follows: The evaluation network and the target network are composed of two groups of networks, and their parameters can be expressed as θ 1 ,θ 2 and θ′ 1 ,θ′ 2 During the training process, the target network with a lower Q value is selected to update the evaluation network. At the same time, the target soft Q network parameters are replaced in a soft update manner: I will i | i=1,2 =sth i +(1-δ)θ i Among them, δ is the soft update factor; The loss function of the policy network is expressed as follows:

Citation Information

Patent Citations

  • Bend road car following control method based on safe control domain

    CN109969183A

  • Multi-model reasoning acceleration system and method for automatic driving full-scene perception

    CN116306938A

  • Ecological driving and energy management collaborative optimization method

    CN117272802A

  • Method for constructing high-durability energy-saving driving strategy of fuel cell vehicle

    CN117436342A

  • Hierarchical energy-saving driving method for fuel cell vehicle

    WO2022241898A1

Cited By

  • Fuel cell heavy truck energy management method and system considering energy-saving driving

    CN121882571A