Sodium-ion battery thermal management strategy optimization method and system

Abstract

The invention discloses a sodium ion battery thermal management strategy optimization method and system, and relates to the technical field of battery monitoring, and the method comprises the steps: obtaining an optimal target temperature value predicted in real time based on a pre-trained target temperature prediction model; acquiring an actual temperature value of the sodium ion battery; the actual rotating speed of a water pump in the sodium-ion battery liquid cooling system is obtained; obtaining a reference rotating speed of the water pump of the liquid cooling system according to the optimal target temperature value and the actual temperature value; according to the rotating speed deviation between the actual rotating speed and the reference rotating speed, the control current of the water pump is calculated through a sliding mode control method based on the self-adaptive fuzzy index reaching law; and adjusting the flow velocity of the cooling liquid in the liquid cooling system based on the calculated control current of the water pump. Cooling adjustment is achieved by quickly responding to the temperature change of the battery and adjusting the running state of the water pump of the liquid cooling system in real time, and the problem of excessive cooling or low cooling speed is avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric energy storage, in particular to a sodium-ion battery thermal management strategy optimization method and system. BACKGROUND

[0002] A large amount of heat can be generated when a sodium-ion battery module is charging and discharging. If the heat cannot be rapidly and effectively dissipated, the heat will accumulate in the battery module, further causing the battery temperature to rise. When the heat accumulates to a certain extent, the battery can catch fire and even explode, causing serious consequences. Therefore, it is necessary to take effective measures to dissipate the heat of the battery so that it can work within an appropriate temperature range.

[0003] Air cooling and liquid cooling are two commonly used cooling schemes for battery energy storage systems. The advantages of air cooling are simple structure and low cost, but the disadvantages are low temperature control accuracy and large temperature difference between batteries, which leads to a large degree of inconsistency in battery performance degradation during long-term operation. The advantages of liquid cooling are high temperature control accuracy and low temperature difference between batteries, and the liquid cooling system has become the mainstream configuration in sodium-ion battery energy storage systems. In order to achieve accurate control of the temperature of sodium-ion batteries, a battery thermal management strategy needs to be developed. Currently, the main thermal management strategies used in sodium-ion battery energy storage power stations are hysteresis control method, finite state machine method, and traditional PID control method. However, due to the nonlinearity, time-varying parameters, and hysteresis characteristics of the battery liquid cooling system, the above methods can achieve battery temperature control, but all have the problem of slow regulation speed. SUMMARY

[0004] In view of the slow regulation speed of the battery liquid cooling system in the prior art, the present application provides a sodium-ion battery thermal management strategy optimization method, system, device and storage medium, which can quickly respond to changes in battery temperature, adjust the operating state of the liquid cooling system water pump in real time for cooling, and avoid the problem of slow cooling speed. The specific technical solutions are as follows: The present application provides a sodium-ion battery thermal management strategy optimization method, comprising: obtaining a best target temperature value predicted in real time based on a pre-trained target temperature prediction model; obtaining an actual temperature value of the sodium-ion battery; obtaining an actual rotating speed of a water pump in the sodium-ion battery liquid cooling system; obtaining a reference rotating speed of the liquid cooling system water pump according to the best target temperature value and the actual temperature value; calculating a control current of the water pump using a sliding mode control method based on adaptive fuzzy exponential reaching law according to the rotating speed deviation between the actual rotating speed and the reference rotating speed; the fuzzy coefficient in the fuzzy exponential reaching law is dynamically adjusted according to the real-time heat generation rate of the sodium-ion battery; The flow rate of coolant in the liquid cooling system is adjusted based on the calculated control current of the water pump.

[0005] Preferably, obtaining the optimal target temperature value predicted in real time based on the pre-trained target temperature prediction model includes: Acquire test data of sodium-ion batteries in cyclic charge-discharge tests. The test data consists of discharge capacity at multiple temperature points tested under multiple different combinations of charge-discharge rates, ambient humidity, and aging. Based on the experimental data, the optimal temperature values ​​corresponding to different combinations of charge / discharge rates, ambient humidity, and aging were extracted. The optimal temperature value refers to the temperature at which the discharge capacity is maximized under different temperatures. Construct training samples that include input features and target labels. The input features include charge / discharge rate, ambient humidity, and aging degree. The target label is the optimal temperature value. Standardize the training samples; The processed training samples are input into a three-layer LSTM + two-layer fully connected deep learning model for learning and training, resulting in a trained target temperature prediction model. Based on real-time data collection of charge / discharge rate, ambient humidity, and aging degree from sodium-ion batteries, the system outputs the current optimal target temperature value using a well-trained target temperature prediction model.

[0006] Preferably, the experimental data are obtained by combining orthogonal experimental designs.

[0007] Preferably, obtaining the actual temperature value of the sodium-ion battery includes: Temperature data from the top, middle, and bottom of the sodium-ion battery were acquired using distributed temperature sensors. The actual temperature value is obtained by fusing temperature data from different locations using an adaptive weighting algorithm.

[0008] Preferably, the sodium-ion battery thermal management strategy optimization method of this application further includes: The sampling frequency is dynamically adjusted according to the temperature change rate. When the temperature change rate is greater than a preset threshold, the sampling frequency is adjusted to a first sampling frequency. When the temperature change rate is less than or equal to the preset threshold, the sampling frequency is adjusted to a second sampling frequency. The first sampling frequency is greater than the second sampling frequency.

[0009] Preferably, the step of determining the reference speed of the liquid cooling system water pump based on the optimal target temperature value and the actual temperature value includes: The temperature deviation is obtained based on the optimal target temperature value and the actual temperature value; Set the temperature deviation as a state variable and the reference speed of the liquid cooling system water pump as a control variable, and calculate the reference speed of the liquid cooling system water pump.

[0010] Preferably, the step of calculating the pump control current using a sliding mode control method based on an adaptive fuzzy exponential reaching law, based on the deviation between the actual rotational speed and the reference rotational speed, includes: The speed deviation is obtained based on the actual speed and the reference speed; An integral sliding surface switching function is established based on the aforementioned rotational speed deviation; Differentiate the integral sliding surface switching function to obtain the sliding mode control law; An adaptive fuzzy exponential approach law is adopted for the sliding mode control law. The fuzzy coefficients in the fuzzy exponential approach law are adjusted by the preset fuzzy control rules and the real-time heat generation rate. The adjusted fuzzy coefficients are substituted into the sliding mode control law to obtain the control current of the water pump.

[0011] This application also provides a sodium-ion battery thermal management strategy optimization system, which applies the aforementioned sodium-ion battery thermal management strategy optimization method, including: The target temperature acquisition unit is used to acquire the optimal target temperature value predicted in real time based on a pre-trained target temperature prediction model. The actual temperature acquisition unit is used to acquire the actual temperature value of the sodium-ion battery. The actual speed acquisition unit is used to acquire the actual speed of the water pump in the liquid cooling system; A reference speed calculation unit is used to calculate the reference speed of the water pump in the liquid cooling system based on the optimal target temperature value and the actual temperature value. The current calculation unit is used to calculate the control current of the water pump based on the speed deviation between the actual speed and the reference speed using a sliding mode control method based on an adaptive fuzzy exponential reaching law; the fuzzy coefficient in the fuzzy exponential reaching law is dynamically adjusted according to the real-time heat generation rate of the sodium-ion battery. The flow rate calculation unit is used to adjust the flow rate of the coolant in the liquid cooling system based on the calculated control current of the water pump.

[0012] This application also provides a computer device, including: processor; Memory used to store processor-executable instructions; The processor implements the aforementioned sodium-ion battery thermal management strategy optimization method by running the executable instructions.

[0013] This application also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the steps of the aforementioned sodium-ion battery thermal management strategy optimization method.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides an optimization method for thermal management strategies in sodium-ion batteries. It integrates multiple parameters through a pre-trained model to output the optimal temperature in real time; simultaneously collects actual temperature and water pump speed; and uses a sliding mode algorithm that dynamically adjusts the fuzzy coefficient based on the speed deviation and the heat generation rate. The heat generation rate correlation coefficient allows the control strategy to intelligently adapt to the thermal load, improving the adjustment speed under thermal shock scenarios and quickly suppressing abnormal temperature fluctuations. Compared to traditional solutions, this effectively solves the problem of slow cooling, ensuring the safe and efficient operation of sodium-ion batteries. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0016] Figure 1 This is a flowchart of a method for optimizing the thermal management strategy of a sodium-ion battery according to the present invention.

[0017] Figure 2 This is a schematic diagram showing the discharge capacity of the sodium-ion battery of the present invention at different temperatures under a certain experimental combination condition.

[0018] Figure 3 This is a schematic diagram of the cycle performance of the sodium-ion battery of the present invention at different temperatures under a certain experimental combination condition.

[0019] Figure 4 This is a comparison diagram of temperature regulation in a sodium-ion battery thermal management strategy optimization method of the present invention and an existing PID control method.

[0020] Figure 5 This is a schematic diagram of a sodium-ion battery thermal management strategy optimization system according to the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0023] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0024] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] Please refer to the following examples. Figures 1 to 5 .

[0026] Please see Figure 1 This application provides a method for optimizing the thermal management strategy of sodium-ion batteries, including: Step S1: Obtain the optimal target temperature value predicted in real time based on the pre-trained target temperature prediction model; By constructing a test platform, sodium-ion batteries are installed in specialized battery testing equipment. This equipment is capable of precisely controlling the charging and discharging process and monitoring various battery parameters in real time, including charge / discharge rate, ambient humidity, aging degree, discharge capacity, and cycle performance. Simultaneously, the battery testing equipment is equipped with a high-precision temperature sensor, which can accurately measure the temperature changes of the battery during the test.

[0027] The process of obtaining the optimal target temperature value predicted in real time based on the pre-trained target temperature prediction model includes: (a) Obtain test data of sodium-ion batteries in cyclic charge-discharge tests, wherein the test data is the discharge capacity at multiple temperature points under multiple different combinations of charge-discharge rates, ambient humidity and aging degree; To predict the optimal temperature (i.e., the temperature that maximizes discharge capacity) by inputting features (temperature, charge / discharge rate, ambient humidity, aging degree), the following steps are required to acquire and construct the data: Experimental data collection design includes experimental variable control and experimental combinations; (1) Control of experimental variables includes: Temperature: Set multiple gradients within a reasonable range (10°C, 0°C, 10°C, 20°C, 30°C, 40°C).

[0028] Charge / discharge rates: covering typical values ​​(0.2C, 0.5C, 1C, 2C).

[0029] Ambient humidity: Set different humidity levels (30%RH, 50%RH, 70%RH, 90%RH).

[0030] Aging degree: simulated by the number of cycles (0, 100, 200, 300).

[0031] (2) Experimental combination By combining experimental variables, there are 256 possible combinations: four temperatures × four charge / discharge rates × four humidity levels × four aging degrees.

[0032] For each group, under the combined experimental conditions (temperature, charge / discharge rate, humidity, aging), the discharge capacity was measured and cycle performance was recorded. By keeping other variables constant and only changing the temperature, the discharge capacity at different temperatures was measured. Figure 2 This is a schematic diagram showing the discharge capacity at different temperatures under a certain experimental combination. Figure 3 This diagram illustrates the cycling performance at different temperatures under a given experimental combination. Each experiment was repeated three times, and the average value was taken.

[0033] (b) Based on the test data, extract the optimal temperature value corresponding to different combinations of charge / discharge rate, ambient humidity and aging degree, wherein the optimal temperature value refers to the temperature at which the discharge capacity is maximized under different temperatures; For each combination (charge / discharge rate, humidity, aging degree), the temperature corresponding to the maximum discharge capacity is selected as the optimal temperature from the discharge capacity data at different temperatures.

[0034] (c) Construct training samples including input features and target labels, wherein the input features include charge / discharge rate, ambient humidity and aging degree, and the target label is the optimal temperature value; (d) Standardize the training samples; Z-score normalization is applied to all features: in, Represents training sample data, and These are the mean and standard deviation of the training set, respectively, and the standardized parameters are retained for online prediction. (e) Input the processed training samples into a three-layer LSTM + two-layer fully connected deep learning model for learning and training to obtain a trained target temperature prediction model. The model network architecture includes: input layer → LSTM layer 1 (64 units) → LSTM layer 2 (32 units) → LSTM layer 3 (16 units) → Dropout layer → fully connected layer 1 (8 units) → fully connected layer 2 (1 unit) → output layer; The input layer takes the processed charge / discharge rate, humidity, and aging degree as input. The LSTM layer uses the tanh activation function and includes forget gate, input gate, and output gate to extract the long-term dependence of the thermal characteristics of sodium-ion batteries. The Dropout layer prevents overfitting.

[0035] (f) Based on the real-time collection of charge / discharge rate, ambient humidity and aging degree of sodium-ion battery, the current optimal target temperature value is output through a well-trained target temperature prediction model.

[0036] Step S2: Obtain the actual temperature value of the sodium-ion battery; Temperature data is collected by deploying one NTC temperature sensor at the top, middle, and bottom of the sodium-ion battery. .

[0037] In this embodiment, the adaptive weighted fusion calculation of the actual temperature is: Among them, weight It can be fixed according to the battery's thermal distribution characteristics, or it can be adjusted in real time by a neural network based on the battery's thermal distribution characteristics.

[0038] Since heat generation and distribution vary during battery charging and discharging, multi-point temperature measurement and dynamic sampling strategies can improve temperature sensing accuracy and overcome the limitations of single-point temperature measurement.

[0039] Step S3: Obtain the actual rotational speed of the water pump in the liquid cooling system; Rotational speed measurement devices are commonly installed on the shaft of the water pump in the battery's liquid cooling system. These devices include photoelectric encoders and Hall effect sensors. Photoelectric encoders measure rotational speed by detecting changes in the scale of a code disk on the shaft, offering high accuracy and reliability. Hall effect sensors, on the other hand, utilize changes in the magnetic field to detect magnetic elements on the shaft, thereby obtaining rotational speed information.

[0040] Step S4: Obtain the reference speed of the liquid cooling system water pump based on the optimal target temperature value and the actual temperature value; specifically including: Step 41: Calculate the temperature deviation based on the optimal target temperature value and the actual temperature value; the temperature deviation is expressed as: In the formula, Indicates the actual temperature. This is the optimal target temperature value.

[0041] Step 42: Set the temperature deviation as a state variable and the reference speed of the liquid cooling system water pump as a control variable. Calculate the reference speed of the liquid cooling system water pump, which is expressed as: In the formula, This represents the reference rotational speed of the water pump in the liquid cooling system at time k. Indicates the proportionality coefficient; Indicates the integral coefficient; Represents the differential coefficient; This is represented as the temperature deviation at time j, where the value of j ranges from the initial time 0 to the current time k. This is represented as the temperature deviation at time k.

[0042] In other embodiments, the deviation between the optimal target temperature value and the actual temperature can be input to a PID controller, which calculates the reference speed of the liquid cooling system pump based on the deviation between the optimal target temperature value and the actual battery temperature.

[0043] Step S5: Obtain the control current of the water pump based on the reference rotational speed and the actual rotational speed; specifically including: Step 51: Obtain the speed deviation based on the actual speed and the reference speed; The speed deviation is expressed as: In the formula, This indicates the actual rotational speed.

[0044] Step S52: Based on the rotational speed deviation, the control current of the water pump is calculated using a sliding mode control method based on the fuzzy exponential reaching law. Specifically, this includes: Step 52: Establish an integral sliding surface switching function based on the speed deviation; (1) The integral sliding surface switching function is expressed as: Where s represents the integral sliding surface switching function, which corresponds to the value that changes dynamically with respect to rotational speed deviation and time; c is a constant used to adjust the degree of influence of the integral term on the function.

[0045] An integral term is introduced to eliminate the steady-state error of the system. The integral term can accumulate past speed deviation information, and even when the speed deviation is small, it can continuously adjust the control quantity to ensure that the actual speed of the water pump can stably approach the reference speed, avoiding long-term speed deviation.

[0046] Step 53: Differentiate the integral sliding surface switching function to obtain the sliding mode control law; (2) Differentiate the integral sliding surface switching function to obtain the sliding mode control law; the sliding mode control law is expressed as: In the formula, express The derivative with respect to time is used to represent The rate of change; , , It is a constant; This indicates the control current of the water pump.

[0047] The sliding mode control law links the speed deviation, the reference speed, and the control current of the water pump. When the speed deviation changes, the control law can quickly calculate the corresponding control current adjustment, enabling the water pump to respond quickly to the speed deviation, rapidly adjust the actual speed, improve the dynamic response performance of the system, and reduce the settling time.

[0048] Step 54: Apply an adaptive fuzzy exponential approaching law to the sliding mode control law. Adjust the fuzzy coefficients in the fuzzy exponential approaching law by using the preset fuzzy control rules and combining them with the real-time heat generation rate. Substitute the adjusted fuzzy coefficients into the sliding mode control law to calculate the control current of the water pump.

[0049] (1) Calculation of real-time heat generation rate based on the heat generation characteristics of sodium-ion batteries (internal resistance heat generation + reaction heat generation) : in, This refers to the charging and discharging current. Voltage; Indicates the voltage temperature coefficient; This is a temperature-dependent internal resistance, and the internal resistance-temperature curve was obtained through cyclic testing.

[0050] Through the adaptive fuzzy exponential reaching law, the fuzzy coefficient , Dynamically adjusted according to real-time heat generation rate: In the formula, and Represents the basic fuzzy coefficient, taking... =0.5, =0.8; and This represents the influence factor of heat generation rate on fuzzy coefficients, taking... =0.1, =0.05.

[0051] (2) The fuzzy exponential approach law is expressed as: In the formula, , It is a constant; , This indicates that the fuzzy coefficients are dynamically adjusted using a fuzzy algorithm based on the real-time heat generation rate.

[0052] By using an adaptive fuzzy exponential approach law, chattering in sliding mode control is reduced. At the same time, the fuzzy coefficient is adjusted in conjunction with the real-time heat generation rate to optimize the control effect, enabling the water pump to operate stably under different operating conditions.

[0053] Step S6: Control the flow rate of coolant in the liquid cooling system by adjusting the control current of the water pump.

[0054] The fuzzy coefficients will be dynamically adjusted using a fuzzy algorithm based on the real-time heat generation rate. , Substituting into the sliding mode control law, the control current of the water pump is calculated. The control current of the water pump is expressed as: To verify the effectiveness of the proposed thermal management strategy optimization method for sodium-ion batteries, a joint simulation platform for a sodium-ion battery liquid cooling system and controller was built. The thermal behavior of an actual battery during the cooling process was simulated, and the proposed thermal management strategy optimization method was compared with the traditional PID control method. The comparison results are as follows: Figure 4 As shown in the figure, the method proposed in this invention can quickly cool down to the set target temperature value, while the PID method exhibits a large overshoot. Due to the overshoot of the PID control method, the energy consumption of the cooling system is increased. This effectively verifies the speed and stability of the proposed method, and also demonstrates its ability to reduce energy consumption.

[0055] This embodiment presents a method for optimizing the thermal management strategy of sodium-ion batteries. It integrates multiple parameters through a pre-trained model to output the optimal temperature in real time; simultaneously collects actual temperature and water pump speed; and uses a sliding mode algorithm that dynamically adjusts the fuzzy coefficient based on the speed deviation and the heat generation rate. The heat generation rate correlation coefficient allows the control strategy to intelligently adapt to the thermal load, improving the adjustment speed under thermal shock scenarios and quickly suppressing abnormal temperature fluctuations. Compared to traditional solutions, this effectively solves the problem of slow cooling, ensuring the safe and efficient operation of sodium-ion batteries.

[0056] Specifically, in a preferred embodiment of this application, the experimental data are obtained by combining orthogonal experimental designs.

[0057] The following example uses a battery test experiment to demonstrate how orthogonal array design can reduce the amount of experimentation.

[0058] The input characteristics include temperature (4 levels), charge / discharge rate (4 levels), ambient humidity (4 levels), and aging degree (4 levels).

[0059] Then calculate the experimental quantity: Experimental quantity = Temperature (4) × Charge / discharge rate (4) × Ambient humidity (4) × Aging degree (4) = 256 cycles If each experiment is repeated 3 times, then 768 trials are required.

[0060] Based on the theoretical experimental requirements mentioned above, this embodiment reduces the experimental quantity by using an orthogonal experimental design method. The orthogonal design ensures uniform pairing of levels for each factor through orthogonal arrays, using a small number of experiments to evaluate the main effect and some interaction effects. The specific operation is as follows: Step 1: Select an orthogonal array Factors and levels: 4 factors, all with 4 levels.

[0061] Choose an orthogonal array: L16(4^5) (16 experiments, accommodating a maximum of 5 factors with 4 levels). (If the number of levels is different, a mixed-level array such as L16(4^3 × 2^6) can be used.) Step 2: Orthogonal array structure (L_{16}(4^5) fragments) Step 3: Mapping Experimental Factors Column assignment: Column 1 - Temperature (Levels 1-4: -10°C, 5°C, 25°C, 40°C) Column 2 - Charge / Discharge Rates (Levels 1-4: 0.2C, 0.5C, 1C, 2C) Column 3 - Ambient Humidity (Levels 1-4: 30%RH, 50%RH, 70%RH, 90%RH) Column 4 - Aging degree (Levels 1-4: 0, 100, 200, 300 cycles) Column 5 - Idle (No factors assigned, used for error estimation) Step 4: Conduct the experiment Sixteen experiments were conducted using orthogonal array combinations: Experiment 1: Temperature = -10°C, Rate = 0.2°C, Humidity = 30%RH, Aging = 0 cycles → Measure discharge capacity; Experiment 2: Temperature = -10°C, Rate = 0.5°C, Humidity = 50%RH, Aging = 100 cycles → Measure discharge capacity; ...Experiment 16: Temperature = 40°C, Rate = 2C, Humidity = 30%RH, Aging = 200 cycles → Measure discharge capacity; Step 5: Orthogonal Design Data Collection For each group of fixed non-temperature factors (charge rate + ambient humidity + aging degree), the temperature corresponding to the maximum capacity was selected from different temperatures. The experimental data were combined using an orthogonal design method.

[0062] In this embodiment, experimental data are obtained by combining orthogonal experimental designs, which can reduce the number of experiments from 256 to 16-32, while ensuring the reliability of model prediction.

[0063] Specifically, in a preferred embodiment of this application, the sodium-ion battery thermal management strategy optimization method further includes: The sampling frequency is dynamically adjusted according to the temperature change rate. When the temperature change rate is greater than a preset threshold, the sampling frequency is adjusted to a first sampling frequency. When the temperature change rate is less than or equal to the preset threshold, the sampling frequency is adjusted to a second sampling frequency. The first sampling frequency is greater than the second sampling frequency.

[0064] Based on temperature change rate Adjust frequency: In this embodiment, when the sodium-ion battery temperature fluctuation exceeds 2°C / min, the temperature change is rapid and may be accompanied by the risk of thermal runaway. Increasing the sampling frequency to 50Hz in this case allows for high-frequency capture of detailed temperature fluctuations, avoiding problems such as untimely cooling or overcooling due to sampling delays, and ensuring temperature control accuracy. When the temperature fluctuation is less than or equal to 2°C / min, the temperature change is gradual and the trend is predictable. Reducing the sampling frequency to 10Hz in this case reduces unnecessary work by sensors, data transmission, and the processor, lowering the energy consumption of the thermal management system and improving system operating efficiency.

[0065] This application also provides a sodium-ion battery thermal management strategy optimization system, which applies the aforementioned sodium-ion battery thermal management strategy optimization method, including: The target temperature acquisition unit is used to acquire the optimal target temperature value predicted in real time based on a pre-trained target temperature prediction model. The actual temperature acquisition unit is used to acquire the actual temperature value of the sodium-ion battery. The actual speed acquisition unit is used to acquire the actual speed of the water pump in the liquid cooling system; A reference speed calculation unit is used to calculate the reference speed of the water pump in the liquid cooling system based on the optimal target temperature value and the actual temperature value. The current calculation unit is used to calculate the control current of the water pump based on the speed deviation between the actual speed and the reference speed using a sliding mode control method based on an adaptive fuzzy exponential reaching law; the fuzzy coefficient in the fuzzy exponential reaching law is dynamically adjusted according to the real-time heat generation rate of the sodium-ion battery. The flow rate calculation unit is used to adjust the flow rate of the coolant in the liquid cooling system based on the calculated control current of the water pump.

[0066] The functional explanation of each unit in this embodiment is the same as that of a sodium-ion battery thermal management strategy optimization method, and the technical effect is the same, so it will not be repeated here.

[0067] This application also provides a computer device, including: processor; Memory used to store processor-executable instructions; The processor implements the aforementioned sodium-ion battery thermal management strategy optimization method by running the executable instructions.

[0068] The technical effects of this embodiment are the same as those of the sodium-ion battery thermal management strategy optimization method in Embodiment 1, and will not be repeated here.

[0069] In this embodiment, the processor may be a central processing unit (CPU), a controller, a microcontroller, or other data processing chip.

[0070] This application also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the steps of the aforementioned sodium-ion battery thermal management strategy optimization method.

[0071] The technical effects of this embodiment are the same as those of the sodium-ion battery thermal management strategy optimization method in the embodiment, and will not be repeated here.

[0072] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0073] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0074] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0075] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0076] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for optimizing thermal management strategies for sodium-ion batteries, characterized in that, include: Obtain the optimal target temperature value predicted in real time based on a pre-trained target temperature prediction model; Obtain the actual temperature value of the sodium-ion battery; Obtain the actual rotational speed of the water pump in the sodium-ion battery liquid cooling system; The reference rotational speed of the liquid cooling system water pump is obtained based on the optimal target temperature value and the actual temperature value; Based on the speed deviation between the actual speed and the reference speed, the control current of the water pump is calculated using a sliding mode control method based on an adaptive fuzzy exponential approach law. The fuzzy coefficient in the fuzzy exponential approach law is dynamically adjusted according to the real-time heat generation rate of the sodium-ion battery. The flow rate of coolant in the liquid cooling system is adjusted based on the calculated control current of the water pump.

2. The method for optimizing the thermal management strategy of a sodium-ion battery according to claim 1, characterized in that, The process of obtaining the optimal target temperature value predicted in real time based on the pre-trained target temperature prediction model includes: Acquire test data of sodium-ion batteries in cyclic charge-discharge tests. The test data consists of discharge capacity at multiple temperature points tested under multiple different combinations of charge-discharge rates, ambient humidity, and aging. Based on the experimental data, the optimal temperature values ​​corresponding to different combinations of charge / discharge rates, ambient humidity, and aging were extracted. The optimal temperature value refers to the temperature at which the discharge capacity is maximized under different temperatures. Construct training samples that include input features and target labels. The input features include charge / discharge rate, ambient humidity, and aging degree. The target label is the optimal temperature value. Standardize the training samples; The processed training samples are input into a three-layer LSTM + two-layer fully connected deep learning model for learning and training, resulting in a trained target temperature prediction model. Based on real-time data collection of charge / discharge rate, ambient humidity, and aging degree from sodium-ion batteries, the system outputs the current optimal target temperature value using a well-trained target temperature prediction model.

3. The method for optimizing the thermal management strategy of a sodium-ion battery according to claim 2, characterized in that, The experimental data were obtained by combining orthogonal experimental designs.

4. The method for optimizing the thermal management strategy of a sodium-ion battery according to claim 1, characterized in that, The process of obtaining the actual temperature value of the sodium-ion battery includes: Temperature data from the top, middle, and bottom of the sodium-ion battery were acquired using distributed temperature sensors. The actual temperature value is obtained by fusing temperature data from different locations using an adaptive weighting algorithm.

5. The method for optimizing the thermal management strategy of a sodium-ion battery according to claim 4, characterized in that, Also includes: The sampling frequency is dynamically adjusted according to the temperature change rate. When the temperature change rate is greater than a preset threshold, the sampling frequency is adjusted to a first sampling frequency. When the temperature change rate is less than or equal to the preset threshold, the sampling frequency is adjusted to a second sampling frequency. The first sampling frequency is greater than the second sampling frequency.

6. The method for optimizing the thermal management strategy of a sodium-ion battery according to claim 1, characterized in that, The process of obtaining the reference speed of the liquid cooling system water pump based on the optimal target temperature value and the actual temperature value includes: The temperature deviation is obtained based on the optimal target temperature value and the actual temperature value; Set the temperature deviation as a state variable and the reference speed of the liquid cooling system water pump as a control variable, and calculate the reference speed of the liquid cooling system water pump.

7. The method for optimizing the thermal management strategy of a sodium-ion battery according to claim 6, characterized in that, The step of calculating the pump control current using a sliding mode control method based on an adaptive fuzzy exponential approach law, based on the deviation between the actual rotational speed and the reference rotational speed, includes: The speed deviation is obtained based on the actual speed and the reference speed; An integral sliding surface switching function is established based on the aforementioned rotational speed deviation; Differentiate the integral sliding surface switching function to obtain the sliding mode control law; An adaptive fuzzy exponential approach law is adopted for the sliding mode control law. The fuzzy coefficients in the fuzzy exponential approach law are adjusted by the preset fuzzy control rules and the real-time heat generation rate. The adjusted fuzzy coefficients are substituted into the sliding mode control law to obtain the control current of the water pump.

8. A sodium-ion battery thermal management strategy optimization system, characterized in that, An optimization method for thermal management strategy of sodium-ion battery according to any one of claims 1 to 7 includes: The target temperature acquisition unit is used to acquire the optimal target temperature value predicted in real time based on a pre-trained target temperature prediction model. The actual temperature acquisition unit is used to acquire the actual temperature value of the sodium-ion battery. The actual speed acquisition unit is used to acquire the actual speed of the water pump in the liquid cooling system; A reference speed calculation unit is used to calculate the reference speed of the water pump in the liquid cooling system based on the optimal target temperature value and the actual temperature value. The current calculation unit is used to calculate the control current of the water pump based on the speed deviation between the actual speed and the reference speed using a sliding mode control method based on an adaptive fuzzy exponential reaching law; the fuzzy coefficient in the fuzzy exponential reaching law is dynamically adjusted according to the real-time heat generation rate of the sodium-ion battery. The flow rate calculation unit is used to adjust the flow rate of the coolant in the liquid cooling system based on the calculated control current of the water pump.

9. A computer device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor executes the executable instructions to implement a sodium-ion battery thermal management strategy optimization method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer instructions thereon, characterized in that, When executed by the processor, this instruction implements the steps of the sodium-ion battery thermal management strategy optimization method as described in any one of claims 1-7.

Images