Extended-range vehicle coupling thermal management system, control method and extended-range vehicle

Abstract

The application provides a range-extender vehicle coupling thermal management system and control method and a range-extender vehicle, which comprises a range-extender, three thermostats, two water pumps, two radiators and a heat exchanger, wherein the range-extender generates electric energy and heat by consuming fuel; the three thermostats are used for adjusting the circulation of coolant and are mainly responsible for placing the radiator of the range-extender and the heat exchanger in different circulation loops; if they are in the same circulation loop, a large amount of heat will be taken away by the airflow through the radiator during the heat exchange process of the range-extender and the power battery, the temperature rising speed of the range-extender and the battery is reduced, and the oil consumption of the range-extender and the aging damage of the battery during the cold start process are increased; the two water pumps are used for pumping the coolant to ensure the circulation of the coolant in the system; the two radiators are used for discharging excess heat; and the heat exchanger is used for transferring the heat generated by the range-extender to the power battery, so that the temperature of the battery rises rapidly to reduce the aging damage of the battery.

Description

Technical Field

[0001] This invention relates to a vehicle thermal management system, specifically to a range-extended vehicle coupled thermal management system based on a deep deterministic strategy gradient algorithm, and a control method for cold start conditions, and also to a range-extended vehicle that incorporates the application of the range-extended vehicle coupled thermal management system. Background Technology

[0002] With the increasing severity of global greenhouse effect, environmental pollution, and energy issues, promoting vehicle electrification and developing hybrid vehicles has become an important trend in the automotive industry. Range-extended electric vehicles (REEVs) are series hybrid electric vehicles that operate on pure electric power. They combine the environmental advantages of pure electric vehicles with the range capabilities of traditional gasoline vehicles, exhibiting unique advantages in many aspects. By incorporating a small internal combustion engine (range extender) as a generator, it does not directly drive the vehicle but instead charges the battery or directly powers the electric motor, thus significantly extending the vehicle's total driving range and solving the range anxiety problem of pure electric vehicles. It can serve as an effective transitional solution before pure electric vehicle technology matures.

[0003] For power batteries, performance is significantly affected by temperature, especially at low temperatures. Low temperatures slow down charge transfer, reduce electrolyte conductivity and lithium-ion diffusion rate, thus severely reducing the battery's usable energy and power. Furthermore, lithium plating inside the battery at low temperatures can cause permanent damage to its capacity and power output. Fuel economy tests show that in urban driving conditions, hybrid vehicles consume approximately 30-34% more fuel at -7°C than at 25°C, with emissions and range performance also declining sharply. Considering recent temperature data, minimum temperatures in northern my country have fallen below -7°C, and those north of the Yellow River below -10°C, with extreme low temperatures in 12 northern provinces even dropping below -30°C. Current range-extended electric vehicles cannot meet the market demand in vast areas of my country.

[0004] Moreover, current energy management strategies for range-extended electric vehicles mainly focus on the output power distribution of the power source. The optimization process assumes that the power source and battery are in an ideal temperature state. Since the cold start process of the power source and the performance degradation of the power battery at low temperatures are ignored, these strategies are not effective in saving energy in low-temperature environments. Summary of the Invention

[0005] This invention provides a coupled thermal management system for range-extended electric vehicles by studying cold-start energy management strategies for low-temperature environments and considering the coupling relationship between the power system and the thermal management system. This system can achieve comprehensive and optimized allocation of the vehicle's power source and heat source, effectively improving vehicle fuel economy, battery life, and low-temperature adaptability.

[0006] The objective of this invention is achieved through the following technical solution:

[0007] A range-extended electric vehicle coupled thermal management system includes the following five circulation loops and circulation loop controllers:

[0008] The first loop is the engine heating loop: the engine water pump outlet is connected to the range extender cooling water inlet, the range extender cooling water outlet is connected to the engine thermostat inlet, and the engine thermostat outlet is connected to the engine water pump inlet.

[0009] The second circulation loop is the engine heat exchange loop: the other outlet of the engine thermostat is connected to the inlet of the engine heat exchanger thermostat, one outlet of the engine heat exchanger thermostat is connected to one inlet of the heat exchanger, and one outlet of the heat exchanger is connected to the inlet of the engine water pump.

[0010] The third circulation loop is the engine cooling loop: the other outlet of the engine heat exchanger thermostat is connected to the engine radiator inlet, and the engine radiator outlet is connected to the engine water pump inlet.

[0011] The fourth circulation loop is the power battery heating and heat exchange loop: the power battery cooling water outlet is connected to the battery thermostat inlet, one outlet of the battery thermostat is connected to the other inlet of the heat exchanger, and the other outlet of the heat exchanger is connected to the battery water pump inlet.

[0012] The fifth circulation loop is the power battery cooling loop: another outlet of the battery thermostat is connected to the inlet of the battery radiator, the outlet of the battery radiator is connected to the inlet of the battery water pump, and the outlet of the battery water pump is connected to the inlet of the power battery cooling water circuit.

[0013] The loop controller is used to control the operating state of the loop according to different cooling and / or heat demand modes of the range-extended vehicle. It is communicatively connected to the battery radiator, engine radiator, battery thermostat, engine thermostat, engine heat exchanger thermostat, engine water pump, and battery water pump.

[0014] Another objective of this invention is to provide a control method for a coupled thermal management system of a range-extended electric vehicle, comprising the following steps:

[0015] Step 1: Define the environment and parameters of the coupled thermal management system model. The coolant flow rate in the circulation loop is the state, and changing the water pump speed, thermostat opening, and radiator fan speed are the actions.

[0016] Step 2: Construct the Actor network and Critic network: The Actor network takes the current state as input and outputs actions, namely the range extender output power, water pump speed, radiator fan speed, and thermostat opening; the Critic network takes the current state observations and the Actor network output actions as input and outputs action values, while initializing the network weights.

[0017] Step 3: Define the compromise between power battery aging and damage, fuel consumption, actuator energy consumption, and battery SOC stability costs as a cost function;

[0018] Step 4: Store the sequences within a certain period into the experience pool, and then randomly sample from the experience pool to train and update the Actor and Critic networks;

[0019] Step 5: Evaluate the model's performance and generalization ability by testing the model at different startup temperatures. If the model performs poorly, adjust the model parameters and return to step S4 for iterative training until the model reaches the optimal coupled thermal management system control strategy.

[0020] As a preferred technical solution of the present invention, step four further includes stabilizing training by using experience replay and target network technology; and conducting tests under various possible environments to ensure the generalization ability of the model.

[0021] As a more preferred technical solution of the present invention, the fuel cost f mentioned in step three is... f Power battery life cost f b Actuator energy consumption cost f a and SOC stability cost f s Composition of total cost,

[0022]

[0023] constant ω f ω b ω a and ω s It is a weighting factor.

[0024] As a preferred technical solution of the present invention, the fuel cost is as follows:

[0025]

[0026] As a preferred technical solution of the present invention, the lifespan cost of the power battery is as follows:

[0027]

[0028] As a preferred technical solution of the present invention, the energy consumption cost of the actuator is as follows:

[0029] P pump (u)=m1u 3 +m2u 2 +m3u,u=V p,en V p，bat

[0030] P fan (u)=m4u 3 +m5u 2 +m6u,u=V airE V airB

[0031] f a =P pump (V p，en )+P pump (V p,bat )+P fan (V airE )+P fan (V airB (3)

[0032] As a preferred technical solution of the present invention, the SOC stability cost is as follows:

[0033]

[0034] Another object of the present invention is to provide a range-extended electric vehicle, which includes the above-mentioned range-extended vehicle coupled thermal management system and the control method for executing the above-mentioned range-extended vehicle coupled thermal management system.

[0035] The beneficial effects are as follows:

[0036] The coupled thermal management system control method provided by this invention addresses the cold start problem in low-temperature environments. It can minimize the life loss of the power battery and fuel consumption while meeting the vehicle's driving power requirements, and at the same time minimize the energy consumption of the actuators and ensure the stability of the battery's state of charge (SOC). Attached Figure Description

[0037] Figure 1 The schematic diagram of the coupled thermal management system provided by the present invention includes: 1. Engine thermostat; 2. Engine radiator thermostat; 3. Heat exchanger; 4. Engine radiator; 5. Range extender; 6. Engine water pump; 7. Battery water pump; 8. Power battery; 9. Battery thermostat; 10. Battery radiator; A. Heating cycle; B. Heat exchange cycle; C. Cooling cycle.

[0038] Figure 2 The control quantity P in Embodiment 1 of the present invention gen Result image.

[0039] Figure 3 The control quantity v in Embodiment 1 of the present invention p，en Result image.

[0040] Figure 4 The control quantity V in Embodiment 1 of the present invention p，bat Result image.

[0041] Figure 5 This is a diagram showing the State Optimization (SOC) results in Embodiment 1 of the present invention.

[0042] Figure 6 The state quantity T in Embodiment 1 of the present invention en，c Result image.

[0043] Figure 7 The state quantity T in Embodiment 1 of the present invention bat Result image.

[0044] Figure 8 The state variable Q in Embodiment 1 of the present invention exh Result image. Detailed Implementation

[0045] The present invention will be further described in detail below with reference to specific embodiments and accompanying drawings.

[0046] The coupled thermal management system provided by this invention includes a range extender that generates electricity and heat by consuming fuel; three thermostats for regulating coolant circulation, primarily responsible for placing the range extender radiator and heat exchanger in different circulation loops. If they are in the same circulation loop, during the heat exchange process between the range extender and the power battery, external airflow will carry away a large amount of heat through the radiator, reducing the temperature rise rate of the range extender and battery, thereby increasing fuel consumption of the range extender and battery aging damage during cold starts; two water pumps for pumping coolant to ensure coolant circulation in the system; two radiators for dissipating excess heat; and a heat exchanger for transferring the heat generated by the range extender to the power battery, causing the battery temperature to rise rapidly to reduce battery aging damage.

[0047] Example 1

[0048] A control method for a coupled thermal management system of a range-extended electric vehicle includes the following steps:

[0049] Step 1: Define the environment and parameters of the coupled thermal management system model. The coolant flow rate in the circulation loop is the state, and changing the water pump speed, thermostat opening, and radiator fan speed are the actions.

[0050] Step 2: Construct the Actor network and Critic network: The Actor network takes the current state as input and outputs actions, namely the range extender output power, water pump speed, radiator fan speed, and thermostat opening; the Critic network takes the current state observations and the Actor network output actions as input and outputs action values, while initializing the network weights.

[0051] Step 3: Define the compromise between power battery aging and damage, fuel consumption, actuator energy consumption, and battery SOC stability costs as a cost function;

[0052] Step 4: Store the sequences within a certain period into the experience pool, and then randomly sample from the experience pool to train and update the Actor and Critic networks;

[0053] Step 5: Evaluate the model's performance and generalization ability by testing the model at different startup temperatures. If the model performs poorly, adjust the model parameters and return to step S4 for iterative training until the model reaches the optimal coupled thermal management system control strategy.

[0054] The specific methods described above are as follows:

[0055] I. System Modeling

[0056] Using a lumped-parameter thermal model to describe the dynamic response of the coupled thermal management system, the temperature dynamic equations for the range extender coolant and the power battery can be expressed as:

[0057]

[0058] In the formula C en，c C bat，c C bat These are the range extender coolant, battery coolant, and battery thermal capacity, respectively, in T. en，c T bat，c T bat These are the range extender coolant, battery coolant, and battery temperature, respectively. Q en，clt R bat Q represents the heating power of the range extender on the coolant and the heat power generated by the battery, respectively. ra，en Q ra，bat Q exh These are the cooling power of the range extender radiator, the cooling power of the battery radiator, and the heat exchange power of the heat exchanger, respectively. Q en，clt and Q bat It is determined by the specific operating conditions and energy management strategies of REEVs, Q ra，en Q ra，bat Q exh Q en，clt and Q bat It can be represented as follows:

[0059] Q ra,en =h1(V airE V flow,en1 )S ra (T en,c -T amb )

[0060] Q ra,bat =h1(V airB V flow,bot1 )S ra (T bat,c -T amb )

[0061] Q exh =h2(V flow,en2 V flow,but2 )S exh (T en，c -T bat，c )

[0062]

[0063] Among them, S ra and S exh It is the heat exchange area of ​​the radiator and heat exchanger, V airE and V airB V represents the airflow speed generated by the range extender and battery radiator fans, respectively. flow，en1 V represents the coolant flow rate in the cooling circuit of the range extender's cooling system. flow，en2 V represents the flow rate of coolant passing through the heat exchanger in the range extender's heat exchange cycle. flow，bat1 and V flow，bat2 Q represents the coolant flow rates in the cooling and heating circuits of the battery cooling system, where h1 and h2 are the convective heat transfer coefficients, which can be described as functions of coolant flow rate and air velocity. LHV =4.6×10 7 (J / kg), P gen η is the output power of the range extender. g The generator efficiency is given by I, where fuel is the mass of gasoline consumed per unit time. bat R is the charging and discharging current of the power battery. bat The internal resistance of the power battery varies with SOC and T. bat Changes with change, fuel, I bat and It can be represented as follows:

[0064]

[0065] Where λ is the temperature correction factor, U oc P is the open-circuit voltage of the power battery. tracQ represents the required power on the power bus. max The battery capacity, λ, is expressed as follows:

[0066]

[0067] T0 = ​​80℃ is the set parameter.

[0068] In AMESim, a coupled thermal management system was modeled. Through trend analysis of each variable with respect to h1 and h2, the fitted model was summarized as follows:

[0069]

[0070] The flow rate of coolant circulating in the cooling and heating circuits of the cooling system is determined by the pump speed and the thermostat opening, and can be described by the following formula:

[0071] V flow,en1 =K1V p,en H en1 H en1 ∈[0,1]

[0072] V flow,en2 =V flow,en1 H en2 H en2 ∈[0,1]

[0073] V flow,bat1 =K2V p，bat H bat

[0074] V flow，bat2 =K2V p，bat (1-H bat ),H bat ∈[0,1] (10)

[0075] In the formula, V p，en and V p，bat The pump speeds, H, are for the range extender cooling system and the battery cooling system, respectively. en1 H en2 and H bat These represent the thermostat openings of the range extender, range extender radiator, and battery radiator, respectively, with K1 and K2 being proportional coefficients.

[0076] II. Battery Life Model

[0077] Experimental results show that under low-temperature conditions (especially -20℃), lithium metal deposition occurs during battery charging, which is related to accelerated battery aging, and batteries cycled at low temperatures have lower coulombic efficiency. The Arrhenius diagram in (3) can be equivalently transformed into a functional relationship between aging rate and temperature, A. ge (bat):

[0078]

[0079] III. Network Structure

[0080] DDPG can be divided into two main networks: the policy network and the value network. DDPG continues the idea of ​​a fixed target network from DQN, with each network further subdivided into a target network and a reality network. However, the update process of the target network differs somewhat.

[0081] The policy network, also known as the Actor, outputs a deterministic action. The network that produces this deterministic action is defined as a = μ. θ (s). Traditional policy gradients employ a stochastic strategy, requiring sampling of the distribution of the current optimal policy for each action. DDPG, however, uses a deterministic strategy, directly determined by the function μ. The Actor's estimation network is μ. θ (s), where θ represents the parameters of the neural network. This estimation network is used to output the real-time action. Additionally, the Actor has a target network with the same structure but different parameters, used to update the value network Critic. Both networks output actions. The Actor outputs the action P. gen V p，en V p，bat V airE V airB H en1 H en2 and H bat

[0082] The value network, or Critic, is used to fit the value function. It also has an estimation network and a target network. Both networks output the current state's value (q-value), but their inputs differ. The Critic's target network takes two parameters as input: the observed value of the current state and the action output by the Actor's target network. The Critic's estimation network takes the action output by the current Actor's estimation network as input. The target network is used to calculate Q. target .

[0083] The value network is updated using gradient descent based on TD-error. The Critic, acting as a judge, doesn't initially know if the Actor's output is good enough; it needs to learn step-by-step to provide accurate scores. Therefore, by leveraging the value of the next time step fitted by the target network and the actual reward, we can obtain the mean squared error by subtracting the current value. The update method is similar to DQN, the only difference being that the target network's parameters are updated slowly in the DDPG algorithm, rather than being directly copied from the existing network every N steps as in DQN.

[0084] The policy network (Actor) is updated based on gradient ascent because the Actor's goal is to find an action 'a' that maximizes the output value Q. Therefore, optimizing the policy network's gradient is to maximize this Q value of the value network's output. A negative sign is added to the loss function to minimize the error. It's worth noting that DDQG also borrows the experience replay technique from DQN. DDPG similarly stores a sequence over a period of time in an experience pool. During each training iteration, a minibatch is randomly sampled from the experience pool for training.

[0085] IV. Cost Function

[0086] DDPG optimization must strike a balance between battery aging and damage, fuel consumption, actuator energy consumption, and battery SOC stability. The vehicle operating condition is selected as UDDS, and the optimization time range is the first 400 seconds. The total cost is given by the following formula:

[0087]

[0088] The total cost consists of four intermediate functions: fuel cost (f f ), power battery life cost (f b Actuator energy consumption cost f a and SOC stability cost f s The constant ω f ω b ω a and ω s It is a weighting factor.

[0089] Fuel costs:

[0090]

[0091] Power battery life cost:

[0092]

[0093] Actuator energy consumption cost:

[0094] P pump (u)=m1u 3 +m2u 2 +m3u,u=V p，en V p，bat

[0095] P fan (u)=m4u 3 +m5u 2 +m6u,u=V airE V airB

[0096] f a =P pump (V p，en )+P pump (V p，bat )+P fan (V airE )+P fan (V airB (15)

[0097] SOC stability cost:

[0098]

[0099] The simulation and results are as follows:

[0100] Table 1. Parameter settings for the DDPG strategy

[0101]

[0102] Control result as follows Figures 2 to 4 As shown.

[0103] Residual control quantity: V airE V airB and H bat H is always equal to 0 en1 H en2 The value is always equal to 1, meaning that neither the engine radiator fan nor the battery radiator fan is working. All the heat generated by the engine is transferred to the power battery through the heat exchanger, reducing energy loss.

[0104] The state variable results are as follows Figures 5 to 8 As shown.

[0105] At the start of the journey, the range extender operates at maximum power to provide the vehicle with the necessary power and heat. Simultaneously, the engine coolant temperature rises rapidly, the battery is charging, and the State of Charge (SOC) increases. The heat exchanger output power gradually increases to approximately 28kW as the engine coolant temperature rises, rapidly preheating the battery with high heat exchange power to reduce battery aging damage caused by low temperatures. When the engine temperature reaches approximately 80℃, the range extender output power decreases to approximately 20kW, maintaining the engine coolant temperature at approximately 75℃. When the battery temperature increases to 20℃, the heat exchanger output power gradually decreases, and the rate of battery temperature increase slows down. Towards the end of the journey, the range extender stops operating, and the battery essentially provides all the power and heat required. The SOC gradually decreases and eventually converges to the desired value (0.5). The heat exchanger no longer outputs heat power to the battery. Since the battery's self-generated heat power is less than the heat exchange power between the battery pack casing and the external environment, the battery temperature decreases slowly.

[0106] In summary, this invention considers the coupling relationship between the power system and the thermal management system, studies the cold start energy management strategy for range-extended electric vehicles in low-temperature environments, and comprehensively optimizes the allocation of the vehicle's power source and heat source, which can effectively improve the vehicle's fuel economy, battery life and low-temperature adaptability.

[0107] Finally, it should be noted that the above specific embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to examples, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A coupled thermal management system for a range-extended electric vehicle, characterized in that, This includes the following five loops and loop controllers: The first loop is the engine heating loop: the engine water pump outlet is connected to the range extender cooling water inlet, the range extender cooling water outlet is connected to the engine thermostat inlet, and the engine thermostat outlet is connected to the engine water pump inlet. The second circulation loop is the engine heat exchange loop: the other outlet of the engine thermostat is connected to the inlet of the engine heat exchanger thermostat, one outlet of the engine heat exchanger thermostat is connected to one inlet of the heat exchanger, and one outlet of the heat exchanger is connected to the inlet of the engine water pump. The third circulation loop is the engine cooling loop: the other outlet of the engine heat exchanger thermostat is connected to the engine radiator inlet, and the engine radiator outlet is connected to the engine water pump inlet. The fourth circulation loop is the power battery heating and heat exchange loop: the power battery cooling water outlet is connected to the battery thermostat inlet, one outlet of the battery thermostat is connected to the other inlet of the heat exchanger, and the other outlet of the heat exchanger is connected to the battery water pump inlet. The fifth circulation loop is the power battery cooling loop: another outlet of the battery thermostat is connected to the inlet of the battery radiator, the outlet of the battery radiator is connected to the inlet of the battery water pump, and the outlet of the battery water pump is connected to the inlet of the power battery cooling water circuit. The loop controller is used to control the operating state of the loop according to different cooling and / or heat demand modes of the range-extended vehicle. It is communicatively connected to the battery radiator, engine radiator, battery thermostat, engine thermostat, engine heat exchanger thermostat, engine water pump, and battery water pump.

2. A control method for a coupled thermal management system of a range-extended electric vehicle, characterized in that, The range-extended vehicle coupled thermal management system according to claim 1 includes the following steps: Step 1: Define the environment and parameters of the coupled thermal management system model. The coolant flow rate in the circulation loop is the state, and changing the water pump speed, thermostat opening, and radiator fan speed are the actions. Step 2: Construct the Actor network and Critic network: The Actor network takes the current state as input and outputs actions, namely the range extender output power, water pump speed, radiator fan speed, and thermostat opening; the Critic network takes the current state observations and the Actor network output actions as input and outputs action values, while initializing the network weights. Step 3: Define the compromise between power battery aging and damage, fuel consumption, actuator energy consumption, and battery SOC stability costs as a cost function; Step 4: Store the sequences within a certain period into the experience pool, and then randomly sample from the experience pool to train and update the Actor and Critic networks; Step 5: Evaluate the model's performance and generalization ability by testing the model at different startup temperatures. If the model performs poorly, adjust the model parameters and return to step S4 for iterative training until the model reaches the optimal coupled thermal management system control strategy.

3. The control method for the coupled thermal management system of a range-extended electric vehicle as described in claim 2, characterized in that, Step four also includes stabilizing training using experience replay and target network techniques; and conducting tests under various possible environments to ensure the model's generalization ability.

4. The control method for the coupled thermal management system of a range-extended electric vehicle as described in claim 2, characterized in that, The fuel cost f mentioned in step three above f Power battery life cost f b Actuator energy consumption cost f a and SOC stability cost f s Composition of total cost, constant ω f ω b ω a and ω s It is a weighting factor.

5. The control method for the coupled thermal management system of a range-extended electric vehicle as described in claim 2, characterized in that, The fuel costs are as follows:

6. The control method for the coupled thermal management system of a range-extended electric vehicle as described in claim 2, characterized in that, The lifespan cost of the power battery is as follows:

7. The control method for the coupled thermal management system of a range-extended electric vehicle as described in claim 2, characterized in that, The energy consumption cost of the actuator is as follows: P pump (u)=m1u 3 +m2u 2 +m3u,u=V p，en ,V p，bat P fan (u)=m4u 3 +m5u 2 +m6u,u=V airE ,V airB f a =P pump (V p，en )+P pump (V p，bat )+P fan (V airE )+P fan (V airB ) (3)。 8. The control method for the coupled thermal management system of a range-extended electric vehicle as described in claim 2, characterized in that, The stability cost of the SOC is as follows:

9. A range-extended electric vehicle, characterized in that, The range-extended electric vehicle includes the range-extended vehicle coupled thermal management system as described in claim 1 and the control method for implementing the range-extended vehicle coupled thermal management system as described in claim 2.

Images