An Electric Vehicle Battery Thermal Management Method and System under Intelligent Network Connection

Abstract

The present invention discloses an electric vehicle battery thermal management method and system under intelligent networking, including obtaining road traffic flow status, ambient temperature, real-time temperature of the power battery, and vehicle driving status data; establishing a vehicle driving status prediction model, using the historical driving status data of the vehicle to predict the vehicle driving status in the next time period; establishing a thermal management model prediction controller to predict the temperature status of the power battery in the next time period; determining the optimal operating temperature range of the battery according to the type of power battery used in the vehicle; dividing the temperature status of the power battery according to the type of power battery and the predicted temperature status of the power battery; adopting corresponding battery thermal management prediction control strategies according to the temperature status of the power battery; and adopting an emergency thermal management strategy for the power battery. The battery temperature pre-management strategy of the present invention has high battery temperature control accuracy, ensuring the safety and endurance of the battery.

Description

Technical Field

[0001] The present invention relates to an electric vehicle battery thermal management method and system under intelligent networking, and belongs to the technical field of power batteries. Background Art

[0002] The power source of an electric vehicle is a power battery. A large amount of heat is generated during the use of the power battery. Excessively high battery operating temperature will directly affect its performance and lifespan. To avoid excessive heat accumulation, a battery thermal management system is required to dissipate heat from the power battery. A reasonable thermal management system can control the battery temperature, avoid overheating or overcooling, help improve the safety and reliability of the battery, extend the battery lifespan, and ensure the battery performance. Against the backdrop of the rapid development of power battery technology, society's attention to the performance and safety of power batteries has been increasing. Considering the complex thermal environment of electric vehicles under different operating conditions, traditional single thermal management strategies have shown their deficiencies in meeting the thermal management requirements of power batteries. Therefore, researching and developing a multi-mode thermal management coupling system to achieve better thermal management effects has become a research hotspot in the current field of power battery thermal management.

[0003] Intelligent networked vehicles leverage technologies such as artificial intelligence, big data, and 5G, and are equipped with advanced sensors, controllers, and actuators to achieve all-round connections between vehicles, between vehicles and roads, between vehicles and people, and between vehicles and service platforms. Despite continuous technological progress, intelligent networked vehicles face problems such as the lag in the construction of intelligent transportation infrastructure and high manufacturing costs, and existing autonomous driving technologies still face technical challenges in complex environments and are not yet fully mature. The popularization of intelligent networked vehicles also needs to adapt to existing laws and regulations. Many countries and regions have not yet established a complete legal framework in terms of liability determination, insurance, etc., and there are network security risks in in-vehicle systems and network communications. Consumers' trust and acceptance of autonomous driving vehicles are still relatively low, and they are worried about safety and reliability. Summary of the Invention

[0004] Object of the Invention: Aiming at the deficiencies in the prior art, the present invention provides an electric vehicle battery thermal management method and system under intelligent networking. The present invention divides the power battery temperature state according to the predicted power battery temperature state and the power battery type, and adopts corresponding battery thermal management predictive control strategies according to different power battery temperature states to achieve the thermal management of the battery.

[0005] Technical Solution: An electric vehicle battery thermal management method under intelligent networking includes the following steps:

[0006] Step 1: Obtain road traffic flow status, ambient temperature, real-time temperature of the power battery, and vehicle driving status data;

[0007] Step 2: Establish a vehicle driving state prediction model, and use the historical driving state data of the vehicle to predict the vehicle driving state in the next time period;

[0008] Step 3: Establish a thermal management model prediction controller, and use the current driving data of the vehicle, the predicted vehicle driving state data in Step 2, and the current ambient temperature to predict the power battery temperature state in the next time period;

[0009] Step 4: Determine the optimal operating temperature range of the battery according to the type of power battery used in the vehicle;

[0010] Step 5: Divide the power battery temperature state according to the type of power battery in Step 4 and the predicted power battery temperature state in Step 3;

[0011] Step 6: Adopt corresponding battery thermal management prediction control strategies according to the power battery temperature state;

[0012] Step 7: After adopting the battery thermal management prediction control strategy, if the real-time temperature of the power battery still exceeds the limit threshold range, immediately adopt the emergency thermal management strategy for the power battery.

[0013] Preferred option, in Step 1, the road traffic flow state data includes traffic flow information and road grade, and the vehicle driving state data includes speed, acceleration, deceleration, average vehicle speed, and parking time.

[0014] Preferred option, Step 2 is specifically as follows:

[0015] Use the BP backpropagation neural network model to analyze the data in the previous time period, predict the vehicle state and road state data in the next time period, that is, divide a total driving distance into n travel segments, calculate the average vehicle speed and idle time ratio value of each travel segment, determine the vehicle speed prediction working condition where each travel segment is located, select the corresponding trained BP neural network vehicle speed prediction sub-model according to the working condition category, extract 5 vehicle speed prediction characteristic parameters and the corresponding adjacent vehicle speed data from the travel segment data, predict the vehicle speed in the next time period, and combine the vehicle speed prediction characteristic parameters predicted each time, which is the output of the BP neural network model and serves as the input of the thermal management prediction control strategy.

[0016] Preferred option, the BP neural network vehicle speed prediction sub-model is specifically as follows:

[0017] The BP neural network model is divided into 6 BP neural network vehicle speed prediction sub-models, that is, corresponding to 6 vehicle speed prediction working conditions:

[0018] One, v m <20 km / h and p d <20%;

[0019] II. v m <20 km / h and p d ≥20%;

[0020] III. 20 km / h ≤ v m <40 km / h and p d <20%;

[0021] IV. 20 km / h ≤ v m <40 km / h and p d ≥20%;

[0022] V. 40 km / h ≤ v m <80 km / h;

[0023] VI. v m ≥80 km / h.

[0024] Preferred option, the 5 vehicle speed prediction characteristic parameters are: average vehicle speed v m , speed variance f v , idle time ratio p d , mean positive acceleration a m , speed multiplied by acceleration variance f va ;

[0025] Average vehicle speed v m , refers to the average vehicle speed over the sampling time length, and the calculation formula is:

[0026]

[0027] where v i is the vehicle speed at the i-th second over the sampling time length, and n is the sampling time length;

[0028] Speed variance f v , refers to the speed variance over the sampling time length, and the calculation formula is:

[0029]

[0030] where v i is the vehicle speed at the i-th second over the sampling time length, v m is the average vehicle speed over the sampling time length, and n is the sampling time length;

[0031] Idle time ratio p d , refers to the percentage of the idle time in the sampling time over the sampling time length, and the calculation formula is:

[0032]

[0033] where t dis the idling time length over the sampling time length, and T is the sampling time length;

[0034] Average positive acceleration a m , which refers to the average value of all positive accelerations over the sampling time length. The calculation formula is:

[0035]

[0036] where a i is the positive acceleration at the i-th second over the sampling time length, and m is the time length of the positive acceleration over the sampling time length;

[0037] Variance of velocity multiplied by acceleration f va , which refers to the variance of the velocity multiplied by the acceleration over the sampling time length. The calculation formula is:

[0038]

[0039] where va i is the velocity multiplied by the acceleration at the i-th second over the sampling time length, and va m is the average value of the velocity multiplied by the acceleration over the sampling time length. Since the acceleration has one less value than the velocity length, the first acceleration value is filled with 0;

[0040] The output formula of the BP neural network model is:

[0041]

[0042] where H j is the output of the hidden layer, ω jk is the connection weight between the hidden layer and the output layer, and b k (k = 1, 2,..., m) are the thresholds of each neuron in the output layer, and m is the number of neurons.

[0043] Preferred option. Specifically, step three is:

[0044] Use the Kalman filter state estimator to establish a thermal management model prediction controller, and use the predicted vehicle driving state data obtained in step two as well as the current ambient temperature and the real-time temperature of the power battery as the input of the thermal management model prediction controller to predict the temperature value of the power battery in the next time period This process is specifically expressed as:

[0045] State prediction equation:

[0046] State update equation:

[0047] where: is the predicted system state estimation value, is the estimated value of the system state at the previous moment, is the error covariance matrix, P k-1 is the predicted error covariance matrix, A and B are the state transition matrix and the input matrix respectively, u k is the control input, Q k is the process noise covariance matrix, K k represents the Kalman gain, C is the Jacobian matrix, y k is the measured value, is the updated estimated value of the system state, I is the identity matrix, P k is the updated error covariance matrix, R is the observation covariance matrix.

[0048] Preferred option, the specific content of step five is:

[0049] According to the predicted temperature of the power battery, the temperature state of the power battery is divided, and the abnormal temperatures exceeding the optimal working temperature range of the power battery are divided into four modes:

[0050] High temperature mode one: 30°C - 40°C;

[0051] High temperature mode two: 40°C - 60°C;

[0052] Low temperature mode one: 10°C - 20°C;

[0053] Low temperature mode two: -20°C - 10°C.

[0054] Preferred option, the specific content of step six is:

[0055] When the coolant temperature inside the power battery is in high temperature mode one, perform primary cooling on the coolant, and circulate through the inside of the power battery to achieve cooling of the power battery. If the battery temperature still does not drop to 30°C after 1 minute, then jump to the battery thermal management predictive control strategy for high temperature mode two: perform secondary cooling on the coolant to make the battery reach the optimal temperature range;

[0056] When the coolant temperature inside the power battery is in low temperature mode one, perform primary heating on the coolant, and circulate through the inside of the power battery to achieve heating of the power battery. If the battery temperature still does not rise to 20°C after 1 minute, then jump to the battery thermal management predictive control strategy for low temperature mode two: perform secondary heating on the coolant to make the battery reach the optimal temperature range.

[0057] Preferred option, the specific content of step seven is:

[0058] When the real-time temperature of the power battery exceeds the set limit threshold range of -20°C to 60°C, the emergency thermal management strategy of the power battery is activated, and the battery thermal management is no longer carried out according to the predicted temperature. When the power battery temperature stabilizes within the set temperature threshold of 20°C to 30°C for 180 seconds, the emergency thermal management strategy of the power battery is exited, and the battery thermal management predictive control strategy is activated, and the battery resumes normal operation.

[0059] A system for implementing an electric vehicle battery thermal management method under intelligent networking includes a hydraulic pump, a first temperature sensor, a second temperature sensor, a first one-way valve, a compressor, a battery low-temperature management module, and a battery high-temperature management module that are respectively connected to a controller by signals. The hydraulic pump, the first temperature sensor, the power battery, the second temperature sensor, the first one-way valve, and the compressor are connected in sequence.

[0060] The battery low-temperature management module includes a primary heating component and a secondary heating component. The primary heating component includes a first heating solenoid valve, a plate heat exchanger, and a second one-way valve. The hydraulic pump, the first heating solenoid valve, the plate heat exchanger, the second one-way valve, and the compressor are connected in sequence.

[0061] The secondary heating component includes a second heating solenoid valve, a PTC heater, and a third one-way valve that are connected in sequence. One end of the secondary cooling component is connected in parallel between the hydraulic pump and the first temperature sensor, and the other end is connected in parallel between the second temperature sensor and the first one-way valve.

[0062] The battery high-temperature management module includes a primary cooling component and a secondary cooling component. The primary cooling component includes a first cooling solenoid valve, an evaporator, an external condenser, and a fourth one-way valve. The hydraulic pump, the first cooling solenoid valve, the evaporator, the external condenser, the fourth one-way valve, and the first one-way valve are connected in sequence.

[0063] The secondary cooling component includes a second cooling solenoid valve provided between the external condenser and the compressor.

[0064] Beneficial effects: The cloud data of the intelligent networking system is used to predict the vehicle driving state. The cloud data is updated in real time and includes a wide range of road section types, ensuring the authenticity and extensiveness of the data. The driving state is predicted within the vehicle driving section, and qualitative and quantitative analysis of the battery temperature is carried out, providing new ideas and methods for the battery thermal management control strategy. At the same time, the battery temperature state prediction is also applicable to fields such as the vehicle's overall thermal management model and the cockpit thermal management model of intelligent networking vehicles. The battery temperature pre-management strategy of the present invention has high battery temperature control accuracy, ensuring the safety and endurance of the battery. Description of the Drawings

[0065] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on the provided drawings.

[0066] Figure 1 It is the flowchart of the method of the present invention;

[0067] Figure 2 It is the system structure diagram of the present invention;

[0068] Figure 3 It is the method principle diagram of the present invention;

[0069] Figure 4 It is the schematic diagram of the high-temperature mode 1 of the present invention;

[0070] Figure 5 It is the schematic diagram of the high-temperature mode 2 of the present invention;

[0071] Figure 6 It is the schematic diagram of the low-temperature mode 1 of the present invention;

[0072] Figure 7 It is the schematic diagram of the low-temperature mode 2 of the present invention;

[0073] Figure 8 It is the schematic diagram of the emergency thermal management strategy for the power battery of the present invention. Detailed implementation manners

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0075] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0076] In the present invention, unless otherwise clearly specified and defined, the first feature being "on" or "under" the second feature may include direct contact between the first and second features, or may include the situation where the first and second features are not in direct contact but in contact through additional features therebetween. Moreover, the first feature being "above", "over" and "on top of" the second feature includes the first feature being directly above and diagonally above the second feature, or merely indicating that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "beneath" and "underneath" the second feature includes the first feature being directly below and diagonally below the second feature, or merely indicating that the horizontal height of the first feature is less than that of the second feature.

[0077] As Figure 1 shown, an electric vehicle battery thermal management method under intelligent network connection includes the following steps:

[0078] Step 1: Obtain road traffic flow status, ambient temperature, real-time temperature of the power battery, and vehicle driving status data;

[0079] In the said Step 1, the road traffic flow status data includes traffic flow information and road grade, and the vehicle driving status data includes speed, acceleration, deceleration, average vehicle speed, and parking time.

[0080] Step 2: Establish a vehicle driving status prediction model, and use the historical driving status data of the vehicle to predict the vehicle driving status in the next time period;

[0081] Using a BP neural network model, analyze the data in the previous time period to predict the vehicle status and road status data in the next time period of 60 seconds. That is, divide a total driving distance into n travel segments, calculate the average vehicle speed and the proportion value of idling time for each travel segment, determine the vehicle speed prediction working condition where each travel segment is located, select the corresponding trained BP neural network vehicle speed prediction sub-model according to the working condition category, limit the total duration of the output vehicle speed and the input vehicle speed predicted by the BP neural network model within 150 seconds, select 60 seconds as the prediction output duration, and set the input vehicle speed duration to 90 seconds. That is, select the vehicle driving status data at the same time and on the same road section, define 90 seconds as a travel segment, extract 5 vehicle speed prediction characteristic parameters and the corresponding adjacent vehicle speed data from the 90-second travel segment data, predict the vehicle speed in the next time period, and combine the vehicle speed prediction characteristic parameters predicted each time, which is the output of the BP neural network model and serves as the input of the thermal management prediction control strategy.

[0082] The BP neural network model is divided into 6 BP neural network vehicle speed prediction sub-models, that is, corresponding to 6 vehicle speed prediction working conditions:

[0083] 1. v m <20 km / h and p d <20%;

[0084] II. v m <20 km / h and p d ≥20%;

[0085] III. 20 km / h ≤ v m <40 km / h and p d <20%;

[0086] IV. 20 km / h ≤ v m <40 km / h and p d ≥20%;

[0087] V. 40 km / h ≤ v m <80 km / h;

[0088] VI. v m ≥80 km / h.

[0089] The 5 vehicle speed prediction characteristic parameters are: average vehicle speed v m , speed variance f v , idle time ratio p d , mean positive acceleration a m , speed multiplied by acceleration variance f va ;

[0090] Average vehicle speed v m , refers to the average vehicle speed over the sampling time length, and the calculation formula is:

[0091]

[0092] where v i is the vehicle speed at the i-th second over the sampling time length, and n is the sampling time length;

[0093] Speed variance f v , refers to the speed variance over the sampling time length, and the calculation formula is:

[0094]

[0095] where v i is the vehicle speed at the i-th second over the sampling time length, v m is the average vehicle speed over the sampling time length, and n is the sampling time length;

[0096] Idle time ratio p d , refers to the percentage of the idle time in the sampling time over the sampling time length, and the calculation formula is:

[0097]

[0098] where t dis the idle time length over the sampling time length, and T is the sampling time length;

[0099] Average positive acceleration a m , which refers to the average value of all positive accelerations over the sampling time length. The calculation formula is:

[0100]

[0101] where a i is the positive acceleration at the i-th second over the sampling time length, and m is the time length of the positive acceleration over the sampling time length;

[0102] Variance of velocity multiplied by acceleration f va , which refers to the variance of the velocity multiplied by the acceleration over the sampling time length. The calculation formula is:

[0103]

[0104] where va i is the velocity multiplied by the acceleration at the i-th second over the sampling time length, and va m is the average value of the velocity multiplied by the acceleration over the sampling time length. Since the acceleration has one less value than the velocity length, the first acceleration value is filled with 0;

[0105] The output formula of the BP neural network model is:

[0106]

[0107] where H j is the output of the hidden layer, ω jk is the connection weight between the hidden layer and the output layer, and b k (k = 1, 2, …, m) are the thresholds of each neuron in the output layer, and m is the number of neurons.

[0108] Step 3: Establish a thermal management model predictor. Using the current driving data of the vehicle, the predicted vehicle driving state data in Step 2, and the current ambient temperature, predict the temperature state of the power battery in the next time period;

[0109] Establish a thermal management model predictor using a Kalman filter state estimator. Take the predicted vehicle driving state data obtained in Step 2 and the current ambient temperature and the real-time temperature of the power battery as the inputs of the thermal management model predictor to predict the temperature value of the power battery in the next time period This process is specifically expressed as:

[0110] State prediction equation:

[0111] State update equation:

[0112] Wherein: is the predicted system state estimate, is the system state estimate at the previous moment, is the error covariance matrix, P k-1 is the predicted error covariance matrix, A and B are the state transition matrix and the input matrix respectively, u k is the control input, Q k is the process noise covariance matrix, K k represents the Kalman gain, C is the Jacobian matrix, y k is the measured value, is the updated system state estimate, I is the identity matrix, P k is the updated error covariance matrix, R is the observation covariance matrix.

[0113] Step Four: Determine the optimal working temperature range of the battery according to the type of power battery used in the vehicle;

[0114] The types of power batteries in this embodiment include: lithium-ion batteries, lithium polymer batteries, lithium iron phosphate batteries, nickel cobalt manganese batteries, nickel-metal hydride batteries, and solid-state batteries. The specific optimal working temperature ranges are shown in Table 1:

[0115] Table 1 Optimal Working Temperature Range of the Battery

[0116] Battery type Optimal operating temperature range Lithium-ion battery 20℃-25℃ Lithium polymer battery 20℃-25℃ Lithium iron phosphate battery 20℃-30℃ Nickel cobalt manganese battery 15℃-35℃ Nickel-metal hydride battery 20℃-30℃ Solid-state battery 20℃-25℃

[0117] Step Five: Divide the temperature state of the power battery according to the type of power battery in Step Four and the predicted temperature state of the power battery in Step Three;

[0118] According to the predicted temperature of the power battery, divide the temperature state of the power battery. The abnormal temperatures exceeding the optimal working temperature range of the power battery are divided into four modes:

[0119] High Temperature Mode One: 30°C - 40°C;

[0120] High Temperature Mode Two: 40°C - 60°C;

[0121] Low Temperature Mode One: 10°C - 20°C;

[0122] Low Temperature Mode Two: -20°C - 10°C.

[0123] Step Six: Adopt corresponding battery thermal management prediction control strategies according to the temperature state of the power battery;

[0124] When the coolant temperature inside the power battery is in high-temperature mode one, perform primary cooling on the coolant, and circulate through the inside of the power battery to achieve cooling of the power battery. If the battery temperature still does not drop to 30°C after 1 minute, then jump to the battery thermal management predictive control strategy for high-temperature mode two: perform secondary cooling on the coolant to enable the battery to reach the optimal temperature range;

[0125] When the coolant temperature inside the power battery is in low-temperature mode one, perform primary heating on the coolant, and circulate through the inside of the power battery to achieve heating of the power battery. If the battery temperature still does not rise to 20°C after 1 minute, then jump to the battery thermal management predictive control strategy for low-temperature mode two: perform secondary heating on the coolant to enable the battery to reach the optimal temperature range.

[0126] Step seven: After adopting the battery thermal management predictive control strategy, if the real-time temperature of the power battery still exceeds the limit threshold range, immediately adopt the emergency thermal management strategy for the power battery.

[0127] When the real-time temperature of the power battery exceeds the set limit threshold range of -20°C to 60°C, start the emergency thermal management strategy for the power battery, and no longer perform battery thermal management according to the predicted temperature. When the power battery temperature stabilizes within the set temperature threshold of 20°C to 30°C for 180s, exit the emergency thermal management strategy for the power battery, start the battery thermal management predictive control strategy, and the battery resumes normal operation.

[0128] As Figure 2 shown, a system for implementing an electric vehicle battery thermal management method under intelligent networking includes a hydraulic pump 1, a first temperature sensor 2, a second temperature sensor 3, a first one-way valve 4, a compressor 5, a battery low-temperature management module, and a battery high-temperature management module that are respectively signal-connected to a controller. The hydraulic pump 1, the first temperature sensor 2, the power battery 17, the second temperature sensor 3, the first one-way valve 4, and the compressor 5 are connected in sequence.

[0129] The battery low-temperature management module includes a primary heating component and a secondary heating component. The primary heating component includes a first heating solenoid valve 6, a plate heat exchanger 7, and a second one-way valve 8. The hydraulic pump 1, the first heating solenoid valve 6, the plate heat exchanger 7, the second one-way valve 8, and the compressor 5 are connected in sequence;

[0130] The secondary heating component includes a second heating solenoid valve 9, a PTC heater 10, and a third one-way valve 11 that are connected in sequence. One end of the secondary cooling component is connected in parallel between the hydraulic pump 1 and the first temperature sensor 2, and the other end is connected in parallel between the second temperature sensor 3 and the first one-way valve 4;

[0131] The battery high-temperature management module includes a primary cooling component and a secondary cooling component. The primary cooling component includes a first cooling solenoid valve 12, an evaporator 13, an external condenser 14, and a fourth check valve 15. The hydraulic pump 1, the first cooling solenoid valve 12, the evaporator 13, the external condenser 14, the fourth check valve 15, and the first check valve 4 are connected in sequence;

[0132] The secondary cooling component includes a second cooling solenoid valve 16 disposed between the external condenser 14 and the compressor 5.

[0133] As Figure 3 shown, the road historical traffic state and the current driving state of the vehicle are input into the vehicle driving state prediction model as inputs. The data predicted by the model, the current ambient temperature, and the real-time temperature of the power battery 17 are input into the thermal management model prediction controller, and continuous optimization and correction are performed to obtain the battery thermal management prediction control strategy. Among them, the compressor 5, the PTC heater 10, the hydraulic pump 1, the internal condenser 14, and the evaporator 13 of the heat pump air conditioner are the main temperature control devices. When the battery temperature is too high, the hydraulic pump 1 and the evaporator 13 first provide heat dissipation, and the flow rate of the coolant is controlled by adjusting the size of the valve of the hydraulic pump 1; when the temperature is still too high, the compressor 5 starts to directly cool the battery; when the air conditioner is also turned on in the vehicle cab, the compressor 5 cools the cab and the battery pack at the same time. When the battery temperature is too low, the compressor 5 starts to heat the vehicle power battery 17 to improve the endurance achievement rate of the power battery 17; when the heat pump air conditioner needs to heat the cab at the same time or the battery temperature cannot reach the optimum only by the heat pump air conditioner, the PTC heater 10 on the battery pack starts to heat the battery. The real-time temperature of the power battery 17 is fed back, and the battery thermal management prediction control strategy is continuously updated and optimized.

[0134] As Figure 4 and Figure 5 shown, the specific combination of step six is as follows: when the coolant temperature inside the power battery 17 is in high-temperature mode one, the first temperature sensor 2 detects that the coolant temperature is in a high-temperature state, exceeding the reasonable range of the battery temperature. The first cooling solenoid valve 12 opens, and the coolant enters the evaporator 13 and the external condenser 14 through the hydraulic pump 1 for heat dissipation. Through the fourth check valve 15 and the first check valve 4, after being detected by the second temperature sensor 3, it returns to the inside of the power battery 17 again to achieve the cooling of the power battery 17. If the battery temperature still does not drop to 30 °C after 1 minute, it jumps to the battery thermal management prediction control strategy of high-temperature mode two: on the basis of starting high-temperature mode one, the second cooling solenoid valve 16 is opened at the same time, and the compressor 5 works to cool the coolant together. It enters the second temperature sensor 3 through the first check valve 4. The second temperature sensor 3 detects that the current coolant temperature can make the battery reach the optimum temperature range to achieve the cooling of the battery;

[0135] As Figure 6 and Figure 7 shown, when the coolant temperature inside the power battery 17 is in the low-temperature mode I, the first temperature sensor 2 detects that the power battery 17 is in a low-temperature state at this time, the first heating solenoid valve 6 is opened, heat is absorbed through the plate heat exchanger 7, the coolant enters the first check valve 4 after being heated by the second check valve 8 and the compressor 5, and the second temperature sensor 3 detects that the coolant temperature at this time can make the battery reach the optimal operating temperature range to achieve the temperature rise of the power battery 17. If the battery temperature still does not rise to 20°C after 1 minute, then it jumps to the battery thermal management predictive control strategy in the low-temperature mode II: on the basis of starting the low-temperature mode I, the second heating solenoid valve 9 is opened at the same time, and the PTC heater 10 heats the power battery 17, and then returns to the second temperature sensor 3 through the third check valve 11. The second temperature sensor 3 detects that the coolant temperature at this time can make the battery reach the optimal temperature range to achieve the temperature rise of the battery.

[0136] As Figure 8 shown, specifically in combination with step seven:

[0137] The first temperature sensor 2 detects that the coolant temperature is in an abnormally high temperature state, exceeding the battery temperature setting limit threshold of -20°C to 60°C. The first cooling solenoid valve 12 and the second cooling solenoid valve 16 are opened simultaneously, the hydraulic pump 1 operates at its maximum power, the coolant enters the evaporator 13 and the external condenser 14 for heat dissipation through the hydraulic pump 1, the compressor 5 operates at its lowest temperature to its maximum frequency, and finally returns to the inside of the power battery 17 through the first check valve 4 and the second temperature sensor 3.

[0138] In this specification, each embodiment is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0139] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An electric vehicle battery thermal management method under intelligent networking, characterized in that: It includes the following steps: Step 1: Obtain road traffic flow status, ambient temperature, real-time temperature of the power battery, and vehicle driving status data; In Step 1, the road traffic flow status data includes traffic flow information and road grade, and the vehicle driving status data includes speed, acceleration, deceleration, average vehicle speed, and parking time; Step 2: Establish a vehicle driving status prediction model, and use the historical driving status data of the vehicle to predict the vehicle driving status in the next time period; Specifically, Step 2 is as follows: Use a BP neural network model to analyze the data in the previous time period, and predict the vehicle status and road status data in the next time period. That is, divide a total driving distance into n driving segments, calculate the average vehicle speed and idling time ratio value of each driving segment, determine the vehicle speed prediction working condition where each driving segment is located, select the corresponding trained BP neural network vehicle speed prediction sub-model according to the working condition category, extract 5 vehicle speed prediction characteristic parameters and the corresponding adjacent vehicle speed data from the driving segment data, predict the vehicle speed in the next time period, and combine the vehicle speed prediction characteristic parameters predicted each time, which is the output of the BP neural network model and serves as the input of the thermal management prediction control strategy; Specifically, the BP neural network vehicle speed prediction sub-model is as follows: The BP neural network model is divided into 6 BP neural network vehicle speed prediction sub-models, corresponding to 6 vehicle speed prediction working conditions:

1. v m <20 km / h and p d <20%; II. v m <20 km / h and p d ≥20%; III. 20 km / h ≤ v m < 40 km / h and p d < 20%; IV. 20 km / h ≤ v m <40 km / h and p d ≥ 20%; V. 40 km / h ≤ v m <80 km / h; VI. v m ≥ 80 km / h; The five vehicle speed prediction characteristic parameters are: average vehicle speed v m , speed variance f v , idle time ratio p d , mean positive acceleration a m , speed multiplied by acceleration variance f va ; Average vehicle speed v m , which refers to the average vehicle speed over the sampling time period, and is calculated by the formula: Among them, v i is the vehicle speed at the i-th second during the sampling time length, and n is the sampling time length; Velocity variance f v , which refers to the velocity variance over the sampling time length, and the calculation formula is as follows: Among them, v i is the vehicle speed at the i-th second during the sampling time length, and v m is the average vehicle speed during the sampling time length, and n is the sampling time length; Idle time ratio p d , which refers to the percentage of the idle time in the sampling time length, and the calculation formula is: where t d is the idle time length over the sampling time length, and T is the sampling time length; Average positive acceleration a m , which refers to the average value of all positive accelerations over the sampling time length, and the calculation formula is: where a i is the positive acceleration at the i-th second over the sampling time length, and m is the time length of the positive acceleration over the sampling time length; Variance of velocity multiplied by acceleration f va , which refers to the variance of velocity multiplied by acceleration over the sampling time length, and the calculation formula is: where va i is the velocity multiplied by the acceleration at the i-th second over the sampling time length, and va m is the average value of the velocity multiplied by the acceleration over the sampling time length. Since the acceleration has one less value than the velocity, the first acceleration value is filled with 0; The output formula of the BP neural network model is: Among them, H j is the output of the hidden layer, ω jk is the connection weight between the hidden layer and the output layer, b k (k = 1, 2, …, m) is the threshold of each neuron in the output layer, and m is the number of neurons; Step 3: Establish a thermal management model predictor, and use the current driving data of the vehicle, the predicted vehicle driving status data in Step 2, and the current ambient temperature to predict the power battery temperature status in the next time period; Step 4: Determine the optimal working temperature range of the battery according to the type of power battery used in the vehicle; Step 5: Divide the power battery temperature status according to the type of power battery in Step 4 and the predicted power battery temperature status in Step 3; Specifically, Step 5 is as follows: According to the predicted power battery temperature, divide the power battery temperature status. The abnormal temperatures exceeding the optimal working temperature range of the power battery are divided into four modes: High temperature mode 1: 30°C - 40°C; High temperature mode 2: 40°C - 60°C; Low temperature mode 1: 10°C - 20°C; Low temperature mode 2: -20°C - 10°C; Step 6: Adopt corresponding battery thermal management prediction control strategies according to the power battery temperature status; Specifically, Step 6 is as follows: When the coolant temperature inside the power battery is in high temperature mode 1, perform primary cooling on the coolant, and circulate through the inside of the power battery to achieve cooling of the power battery. If the battery temperature still does not drop to 30°C after 1 minute, then jump to the battery thermal management prediction control strategy for high temperature mode 2: perform secondary cooling on the coolant to make the battery reach the optimal temperature range; When the coolant temperature inside the power battery is in low-temperature mode I, the coolant is heated at the first level and circulated through the inside of the power battery to achieve the heating of the power battery. If the battery temperature still fails to rise to 20 °C after 1 minute, it will jump to the battery thermal management predictive control strategy for low-temperature mode II: the coolant is heated at the second level to enable the battery to reach the optimal temperature range; Step 7: After adopting the battery thermal management predictive control strategy, if the real-time temperature of the power battery still exceeds the limit threshold range, immediately adopt the emergency thermal management strategy for the power battery.

2. The method for thermal management of an electric vehicle battery under intelligent networking according to claim 1, wherein: The specific content of step 3 is as follows: A thermal management model predictive controller is established using a Kalman filter state estimator, and the predicted vehicle driving state data obtained in Step 2 along with the current ambient temperature and the real-time temperature of the power battery are used as inputs to the thermal management model predictive controller to predict the power battery temperature value for the next time period This process is specifically expressed as: State prediction equation: State update equation: Wherein: is the predicted system state estimate, is the system state estimate at the previous moment, is the error covariance matrix, P k-1 is the predicted error covariance matrix, A and B are the state transition matrix and the input matrix respectively, u k is the control input, Q k is the process noise covariance matrix, K k represents the Kalman gain, C is the Jacobian matrix, y k is the measurement value, is the updated system state estimate, I is the identity matrix, P k is the updated error covariance matrix, R is the observation covariance matrix.

3. The method for thermal management of an electric vehicle battery under intelligent network connection according to claim 2, wherein: The specific content of step 7 is as follows: When the real-time temperature of the power battery exceeds the set limit threshold range of -20 °C to 60 °C, start the emergency thermal management strategy for the power battery and no longer perform battery thermal management according to the predicted temperature. After the power battery temperature stabilizes within the set temperature threshold of 20 °C to 30 °C for 180 s, exit the emergency thermal management strategy for the power battery and start the battery thermal management predictive control strategy, and the battery resumes normal operation.

4. A system for implementing the electric vehicle battery thermal management method under intelligent network connection according to any one of claims 1-3, characterized in that, It includes a hydraulic pump (1), a first temperature sensor (2), a second temperature sensor (3), a first one-way valve (4), a compressor (5), a battery low-temperature management module, and a battery high-temperature management module that are respectively connected to the controller by signals. The hydraulic pump (1), the first temperature sensor (2), the power battery (17), the second temperature sensor (3), the first one-way valve (4), and the compressor (5) are connected in sequence. The battery low-temperature management module includes a first-level heating component and a second-level heating component. The first-level heating component includes a first heating solenoid valve (6), a plate heat exchanger (7), and a second one-way valve (8). The hydraulic pump (1), the first heating solenoid valve (6), the plate heat exchanger (7), the second one-way valve (8), and the compressor (5) are connected in sequence; The second-level heating component includes a second heating solenoid valve (9), a PTC heater (10), and a third one-way valve (11) that are connected in sequence. One end of the second-level heating component is connected in parallel between the hydraulic pump (1) and the first temperature sensor (2), and the other end is connected in parallel between the second temperature sensor (3) and the first one-way valve (4); The battery high-temperature management module includes a first-level cooling component and a second-level cooling component. The first-level cooling component includes a first cooling solenoid valve (12), an evaporator (13), an external condenser (14), and a fourth one-way valve (15). The hydraulic pump (1), the first cooling solenoid valve (12), the evaporator (13), the external condenser (14), the fourth one-way valve (15), and the first one-way valve (4) are connected in sequence; The second-level cooling component includes a second cooling solenoid valve (16) arranged between the external condenser (14) and the compressor (5).

Images