Lithium ion battery control method and device based on temperature regulation and control

Abstract

The invention provides a lithium ion battery control method and device based on temperature regulation and control, and relates to the field of data processing. The method comprises the following steps: acquiring temperature measurement data sent by a thermistor and an infrared temperature sensor for a lithium ion battery; performing data processing on the temperature measurement data to obtain current temperature data; inputting the current temperature data into a preset neural network model to generate predicted temperature data; acquiring temperature error data of the lithium ion battery; generating a temperature regulation and control mechanism according to the predicted temperature data and the temperature error data; and controlling a temperature control assembly corresponding to the lithium ion battery to carry out temperature regulation and control according to the temperature regulation and control mechanism. By implementing the technical scheme provided by the invention, the temperature of the lithium ion battery can be conveniently and accurately regulated and controlled.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and specifically relates to a lithium-ion battery control method and device based on temperature regulation. Background Art

[0002] In modern smartphones, laptops, and other portable electronic devices, the lithium-ion battery, as the main energy supply component, its operating temperature directly affects the performance, safety, and service life of the device.

[0003] Currently, most devices adopt a temperature control strategy with a fixed temperature threshold. For example, when the battery temperature exceeds 45°C, the system will automatically reduce the processor frequency, reduce the charging power, or enhance the heat dissipation. However, the fixed threshold strategy often takes cooling measures only after the temperature exceeds the upper limit. At this time, the battery is already in a high-temperature state, which has a certain lag and is not conducive to the precise regulation of the temperature of the lithium-ion battery.

[0004] Therefore, there is an urgent need for a lithium-ion battery control method and device based on temperature regulation. Summary of the Invention

[0005] This application provides a lithium-ion battery control method and device based on temperature regulation, which is convenient for precisely regulating the temperature of the lithium-ion battery.

[0006] In the first aspect of this application, a lithium-ion battery control method based on temperature regulation is provided. The method includes: obtaining temperature measurement data sent by a thermistor and an infrared temperature sensor for the lithium-ion battery; performing data processing on the temperature measurement data to obtain current temperature data; inputting the current temperature data into a preset neural network model to generate predicted temperature data; obtaining temperature error data of the lithium-ion battery; generating a temperature regulation mechanism according to the predicted temperature data and the temperature error data; and controlling a temperature control component corresponding to the lithium-ion battery to perform temperature regulation according to the temperature regulation mechanism.

[0007] By adopting the above technical solution, through the integration of multi-source temperature measurement, intelligent prediction, error correction, and adaptive control, more accurate and efficient temperature control management of lithium-ion batteries is achieved. First, the battery temperature is obtained by combining a thermistor and an infrared sensor, improving the real-time performance and accuracy of temperature measurement. Second, data processing technology is used to remove noise and ensure the reliability of temperature data. Then, the future temperature trend is predicted through a neural network model to avoid the problem of traditional temperature control lag and make the control more forward-looking. Furthermore, a temperature error compensation mechanism is introduced to correct measurement deviations and ensure more accurate control decisions. Finally, based on the predicted temperature and error data, a temperature control strategy is intelligently generated to dynamically adjust the temperature control components, thereby improving the device performance, optimizing energy efficiency management, and extending the battery life while ensuring the safety of the battery. Therefore, it is convenient to accurately control the temperature of lithium-ion batteries.

[0008] Optionally, the obtaining the temperature measurement data sent by the thermistor and the infrared temperature sensor for the lithium-ion battery specifically includes: obtaining the first temperature measurement data sent by the thermistor located at the surface position of the lithium-ion battery; obtaining the second temperature measurement data sent by the infrared temperature sensor located at the positive and negative electrode positions inside the lithium-ion battery; and performing digital signal conversion on the first temperature measurement data and the second temperature measurement data to obtain the temperature measurement data.

[0009] By adopting the above technical solution, by integrating data from multiple temperature measurement points on the battery surface and inside, the comprehensiveness and accuracy of temperature measurement are improved. The thermistor collects the battery surface temperature, which can quickly reflect the impact of ambient temperature changes on the battery, while the infrared temperature sensor directly measures the positive and negative electrode temperatures inside the battery, providing accurate data on the actual heat generation of the battery core. Through digital signal conversion, the data formats of different types of temperature data are unified, making subsequent data processing more efficient and accurate. Compared with the traditional single temperature measurement method, this solution can more accurately reflect the true temperature distribution of the battery, avoid temperature measurement blind spots, improve the response speed and accuracy of the temperature control strategy, thereby effectively preventing the battery from overheating or temperature imbalance, and enhancing safety and service life.

[0010] Optionally, the data processing of the temperature measurement data to obtain the current temperature data specifically includes: assigning weights to the data of the thermistor and the infrared temperature sensor according to the corresponding accuracy and response speed of different sensors to obtain the thermistor weight and the sensor weight; and performing data fusion through weighted average and Bayesian estimation based on the thermistor weight, the sensor weight, and the temperature measurement data to obtain the current temperature data.

[0011] By adopting the above technical solutions, the multi-sensor data is fused through weighted average and Bayesian estimation, effectively improving the accuracy, stability, and real-time performance of temperature measurement. First, according to the accuracy and response speed of the thermistor and infrared sensor, reasonable weights are assigned to their data to ensure that high-precision data contributes more to the final temperature calculation. Second, the weighted average method is used to fuse the temperature measurement data of different sensors, reducing the influence of the measurement error of a single sensor and improving the reliability of the temperature data. At the same time, Bayesian estimation is introduced to dynamically adjust the credibility of the temperature measurement data, enhancing the adaptability of the system in complex environments. Compared with the traditional simple average or single-sensor temperature measurement method, this method can more accurately reflect the true temperature of the battery, reduce the measurement error, optimize the accuracy and response speed of the temperature control strategy, thereby improving battery safety, device performance, and energy efficiency management.

[0012] Optionally, the inputting the current temperature data into a preset neural network model to generate predicted temperature data specifically includes: obtaining historical temperature data from the preset neural network model; inputting the current temperature data and the historical temperature data into a multi-layer perceptron, controlling multiple fully connected neurons, and using ReLU for activation to obtain the predicted temperature data.

[0013] By adopting the above technical solutions, through a neural network model based on a multi-layer perceptron (MLP), combining current temperature data with historical temperature data, intelligent prediction of the battery temperature trend is achieved, thereby enhancing the forward-looking and accuracy of the temperature control strategy. First, the introduction of historical temperature data can identify the long-term pattern of battery temperature changes, avoiding prediction deviation caused by relying only on the current temperature. Second, the fully connected neurons in the MLP structure can deeply mine the complex relationships between temperature data at different time points, improving the non-linear fitting ability of temperature prediction. In addition, the use of the ReLU activation function enhances the computational efficiency and learning ability of the model, enabling it to adapt to temperature changes in different working environments faster. Compared with traditional temperature control methods based on fixed rules or simple statistical models, this solution can predict the temperature trend in advance, optimize the temperature control response time, reduce the lag effect, prevent temperature overshoot or excessive cooling, thereby enhancing battery safety, service life, and device performance stability.

[0014] Optionally, the obtaining of the temperature error data of the lithium-ion battery specifically includes: calculating the heat generation power and heat dissipation power of the lithium-ion battery; calculating the difference between the heat generation power and the heat dissipation power to obtain target data; calculating the physical temperature data according to the target data and the unit heat capacity of the lithium-ion battery; and calculating the temperature error data according to the physical temperature data and the predicted temperature data.

[0015] By adopting the above technical solution, by calculating the difference between the heat generation power and the heat dissipation power of the lithium-ion battery, combining with the unit heat capacity of the battery, accurately estimating the true temperature of the battery based on the physical model, and comparing it with the temperature predicted by the neural network, temperature error data is obtained. The advantage of this method is that it combines the advantages of thermodynamic calculation and machine learning prediction, effectively improving the accuracy of temperature measurement. First, the dynamic calculation of heat generation power and heat dissipation power can more realistically reflect the thermal equilibrium state of the battery, avoiding errors that may be caused by simply relying on sensor temperature measurement. Second, the temperature data measured by the sensor is corrected through physical temperature calculation to ensure that the decision-making of the temperature control system is based on more accurate temperature information. In addition, this method can adapt to heat changes under different environments and working conditions, improving the reliability of the temperature control strategy, avoiding overcooling or failure to dissipate heat in a timely manner due to temperature measurement errors, thereby optimizing the battery performance, safety and service life.

[0016] Optionally, generating a temperature control mechanism according to the predicted temperature data and the temperature error data specifically includes: determining a prediction time window based on the predicted temperature data; determining a temperature change rate according to the prediction time window and the current temperature data; determining a first comparison result between the temperature change rate and a preset rate threshold; determining a second comparison result between the temperature error data and a preset error threshold; generating the temperature control mechanism based on the first comparison result, the second comparison result and the predicted temperature data.

[0017] By adopting the above technical solution, by combining dynamic prediction, rate analysis and error evaluation, a more accurate temperature control mechanism is intelligently generated, thereby improving the adaptability and real-time performance of the temperature control strategy. First, determining a prediction time window based on the predicted temperature data can predict the future temperature trend and avoid the problem of lagging response of traditional temperature control strategies. Second, calculating the temperature change rate and analyzing the rising or falling speed of the temperature in combination with the current temperature data, so as to identify whether the battery is in a rapid heating or cooling state and optimize the lead of the temperature control strategy. Third, by setting a rate threshold and an error threshold, a double comparison of the predicted temperature change trend and the actual temperature measurement error is carried out to ensure that the temperature control strategy can prevent overheating and will not cause overcooling due to errors. Finally, comprehensively considering rate analysis, error evaluation and temperature prediction results, the heat dissipation or power management strategy is intelligently adjusted to achieve more accurate temperature control, reduce temperature fluctuations, improve battery safety, equipment performance and energy efficiency management, and extend the battery life.

[0018] Optionally, generating the temperature control mechanism based on the first comparison result, the second comparison result, and the predicted temperature data specifically includes: If it is determined that the first comparison result indicates that the temperature change rate is greater than the preset rate threshold, and the second comparison result indicates that the temperature error data is greater than the preset error threshold, then the temperature control mechanism is to immediately start the temperature control component for heat dissipation; If it is determined that the first comparison result indicates that the temperature change rate is less than the preset rate threshold, and the second comparison result indicates that the temperature error data is less than the preset error threshold, then the temperature control mechanism is to reduce the heat dissipation power corresponding to the temperature control component.

[0019] By adopting the above technical solution, through intelligent condition judgment and dynamic regulation, the temperature control strategy has higher accuracy, response speed, and energy efficiency optimization ability. First, it uses dual-threshold judgment of temperature change rate and error evaluation to ensure that the temperature control decision considers both the temperature change trend and the actual temperature measurement error, avoiding unnecessary regulation caused by misjudgment. Second, when the temperature rises too fast and the error is large, the system can immediately start the temperature control component for heat dissipation to prevent the battery from overheating and improve safety. When the temperature changes slowly and the error is small, the system will appropriately reduce the heat dissipation power to avoid energy consumption waste caused by excessive cooling and improve the battery's endurance. Compared with the traditional temperature control method triggered by a single threshold, this method can dynamically adjust the heat dissipation strategy under different working conditions to achieve precise temperature control, which not only improves the battery safety but also optimizes the energy efficiency management and balance performance of the device.

[0020] In the second aspect of the present application, a lithium-ion battery control device based on temperature control is provided. The control device includes an acquisition module and a processing module. Among them, the acquisition module is used to acquire temperature measurement data sent by a thermistor and an infrared temperature sensor for the lithium-ion battery; the processing module is used to process the temperature measurement data to obtain the current temperature data; the processing module is further used to input the current temperature data into a preset neural network model to generate predicted temperature data; the acquisition module is further used to acquire the temperature error data of the lithium-ion battery; the processing module is further used to generate a temperature control mechanism according to the predicted temperature data and the temperature error data; the processing module is further used to control the temperature control component corresponding to the lithium-ion battery for temperature control according to the temperature control mechanism.

[0021] In the third aspect of the present application, an electronic device is provided. The electronic device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions. Both the user interface and the network interface are used to communicate with other devices. The processor is used to execute the instructions stored in the memory so that the electronic device executes the method described above.

[0022] In the fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions that, when executed, perform the method described above.

[0023] In summary, one or more technical solutions provided in the present application have at least the following technical effects or advantages: Through the integration of multi-source temperature measurement, intelligent prediction, error correction, and adaptive regulation, more accurate and efficient temperature control management of lithium-ion batteries is achieved. First, the battery temperature is obtained by combining a thermistor and an infrared sensor, improving the real-time performance and accuracy of temperature measurement. Second, data processing technology is used to remove noise, ensuring the reliability of temperature data. Then, the neural network model is used to predict the future temperature trend, avoiding the problem of traditional temperature control lag and making the regulation more forward-looking. Furthermore, a temperature error compensation mechanism is introduced to correct the measurement deviation, ensuring that the regulation decision is more accurate. Finally, based on the predicted temperature and error data, a temperature control strategy is intelligently generated to dynamically adjust the temperature control components, thereby improving the device performance, optimizing energy efficiency management, and extending the battery life while ensuring the safety of the battery. Therefore, it is convenient to accurately control the temperature of lithium-ion batteries. Description of the Drawings

[0024] Figure 1 It is a schematic flowchart of a method for controlling a lithium-ion battery based on temperature regulation provided by an embodiment of the present application; Figure 2 It is another schematic flowchart of a method for controlling a lithium-ion battery based on temperature regulation provided by an embodiment of the present application; Figure 3 It is a schematic module diagram of a device for controlling a lithium-ion battery based on temperature regulation provided by an embodiment of the present application; Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0025] Description of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. Detailed Embodiments

[0026] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to give examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "for example" or "for illustration" is intended to present relevant concepts in a specific manner.

[0028] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0029] In modern smartphones, laptops and other portable electronic devices, as the core energy supply component, the working temperature of the lithium-ion battery directly affects the performance, safety and service life of the device.

[0030] Currently, most devices rely on a temperature control strategy with a fixed temperature threshold. For example, when the battery temperature exceeds 45 °C, the system will reduce the processor frequency, reduce the charging power or enhance the heat dissipation. However, this passive temperature control often intervenes in the regulation only after the temperature has exceeded the safe range, resulting in a lag in response, making it difficult to suppress the rising trend of the temperature in a timely manner and affecting the accuracy of temperature control and energy efficiency management.

[0031] To solve the above technical problems, the present application provides a lithium-ion battery control method based on temperature regulation, referring to Figure 1 , Figure 1 is a schematic flowchart of a lithium-ion battery control method based on temperature regulation provided by an embodiment of the present application. This control method is applied to a server and includes steps S110 to S160. The above steps are as follows: S110. Obtain the temperature measurement data sent by the thermistor and the infrared temperature sensor for the lithium-ion battery.

[0032] Specifically, the server is responsible for receiving and integrating information from different temperature sensors that monitor the temperature of lithium-ion batteries. Specifically, there are two types of temperature sensors installed in the system: one is a thermistor, which is usually installed on the surface of the battery and can quickly detect the ambient temperature and the surface temperature of the battery; the other is an infrared temperature sensor, which can detect the temperature inside the battery or in areas that are difficult to directly access in a non-contact manner. The server obtains the temperature data from these sensors through a network or other communication means for subsequent monitoring of the battery status and temperature control decisions.

[0033] For example: In a smartphone, the battery management system is equipped with a thermistor installed on the battery casing to continuously monitor the surface temperature of the battery; at the same time, the internal infrared temperature sensor is responsible for measuring the temperature of the battery's core area. All of this temperature data is transmitted via a data bus to the main control server within the phone, which aggregates and analyzes the data to determine whether the battery needs to adjust its charge and discharge strategy or initiate cooling measures. If the sensor data indicates an abnormal increase in the battery temperature, the server will trigger corresponding temperature control mechanisms, such as reducing the processor power or activating additional cooling components, thus ensuring the safety of the device and the lifespan of the battery.

[0034] In a possible implementation manner, obtaining the temperature measurement data sent by the thermistor and the infrared temperature sensor for the lithium-ion battery specifically includes: obtaining the first temperature measurement data sent by the thermistor located at the surface position of the lithium-ion battery; obtaining the second temperature measurement data sent by the infrared temperature sensor located at the positive and negative electrode positions inside the lithium-ion battery; performing digital signal conversion on the first temperature measurement data and the second temperature measurement data to obtain the temperature measurement data.

[0035] Specifically, the thermistor is installed at the surface position of the lithium-ion battery, and it is used to continuously monitor the surface temperature of the battery, reflecting the heat exchange between the battery and the external environment. The temperature data sent by the thermistor is called the first temperature measurement data. The infrared temperature sensor is installed at the positive and negative electrode positions inside the lithium-ion battery, and it detects the internal temperature of the battery in a non-contact manner, especially the temperature distribution in the positive and negative electrode areas, which often better reflects the heat generated by the internal chemical reactions of the battery. The temperature data sent by the infrared temperature sensor is called the second temperature measurement data. Performing digital signal conversion on the first temperature measurement data (from the thermistor) and the second temperature measurement data (from the infrared sensor) means converting the analog signal into a digital signal so that the data can be processed and stored by a digital system (such as a microcontroller or a server). The resulting temperature measurement data is in a unified format, facilitating subsequent data processing, fusion, and temperature control decisions.

[0036] For example, assume that in a smart phone, two temperature sensors are installed in a lithium-ion battery: A thermistor is installed on the battery case to detect the temperature on the battery surface in real time. For example, the temperature measured by the thermistor is 36°C, which is the first temperature measurement data. An infrared temperature sensor is installed near the positive and negative electrodes inside the battery to measure the internal temperature. For example, the temperature detected by the infrared sensor is 38°C, which is the second temperature measurement data. In the data acquisition stage, after these two sensors respectively obtain the temperature information, they output it through analog signals. Then, the system uses an analog-to-digital converter (ADC) to convert these two analog temperature signals into digital signals. In this way, the system can obtain two values: 36°C (surface temperature) and 38°C (internal temperature). These converted digital temperature data are the final temperature measurement data for further data fusion and temperature control decision-making.

[0037] S120. Process the temperature measurement data to obtain the current temperature data.

[0038] Specifically, after the server receives the original temperature measurement data from the thermistor and the infrared temperature sensor, it needs to verify and preprocess these data. This may include operations such as noise removal, filtering, and timestamp alignment to ensure the accuracy and consistency of the data. Since the accuracy and response speed of different sensors may vary, the server assigns different weights to them according to their respective characteristics. For example, the thermistor may be more sensitive in reflecting changes in the ambient temperature, while the infrared sensor can more accurately capture changes in the internal temperature of the battery. By assigning appropriate weights to the data of each sensor and performing weighted average processing, the server can generate a more representative temperature value, that is, the current temperature data. In addition to simple weighted average, the server may also use statistical methods such as Bayesian estimation to model the uncertainty of the sensor data and further optimize the finally obtained temperature data. This method can automatically adjust the credibility of each data when there are certain deviations in multiple data sources, thereby improving the accuracy of the temperature data.

[0039] In a possible implementation manner, processing the temperature measurement data to obtain the current temperature data specifically includes: According to the respective accuracy and response speed of different sensors, assign weights to the data of the thermistor and the infrared temperature sensor to obtain the thermistor weight and the sensor weight; According to the thermistor weight, the sensor weight, and the temperature measurement data, perform data fusion through weighted average and Bayesian estimation to obtain the current temperature data.

[0040] Specifically, since the thermistor and the infrared temperature sensor have their own advantages and limitations in terms of accuracy, response speed, and temperature measurement range, the system will assign different weights to them according to these characteristics. The thermistor is more sensitive to environmental temperature changes but may be more affected by external factors; the infrared temperature sensor is more suitable for capturing the internal temperature of the battery, and the measurement result can better reflect the internal thermal state of the battery. By determining the "thermistor weight" and the "sensor weight" for the data of these two types of sensors respectively, it can be ensured that during subsequent processing, data with high precision and fast response speed will obtain higher weights. The system fuses the temperature measurement data of the thermistor and the infrared temperature sensor with the weights assigned, using two methods: Weighted average: The data of different sensors are averaged by multiplying their respective weights. For example, the temperature data are added according to their respective weights to obtain a comprehensive temperature value; Bayesian estimation: Further use the Bayesian statistical method to model and correct the uncertainty of the measurement data, so as to more accurately fuse different data sources and reduce the influence of noise and bias. After the above processing, the "current temperature data" obtained is a value that more accurately reflects the actual temperature of the battery after comprehensively considering the characteristics and uncertainties of multiple sensors, and this data will be used for subsequent temperature control decision-making and management.

[0041] For example, assume that in a device, the temperature data collected by two sensors of a lithium-ion battery are as follows: The temperature measured by the thermistor is 36.0 °C, and the temperature measured by the infrared temperature sensor is 38.0 °C. Through experiments or historical data analysis, the weight assigned to the thermistor by the system is 0.4, and the weight assigned to the infrared temperature sensor is 0.6. The weighted temperature is 37.2 °C. In actual applications, the uncertainty and historical performance of the sensor data will also be considered and adjusted through Bayesian estimation. Assume that after the Bayesian estimation correction, the comprehensive temperature data is fine-tuned to 37.3 °C to more accurately reflect the actual temperature state of the battery. In this way, after the data fusion of weighted average and Bayesian estimation, the "current temperature data" finally output by the system is 37.3 °C, providing a reliable basis for subsequent temperature control strategies.

[0042] S130. Input the current temperature data into a preset neural network model to generate predicted temperature data.

[0043] Specifically, the server uses the "current temperature data" obtained through the previous steps as input and passes it to a pre-established neural network model. This model has been trained to predict the temperature change in the next period of time based on the current (and possibly historical) temperature data, so as to generate predicted temperature data. The role of this step is to predict the temperature trend in advance so as to take corresponding preventive measures in the temperature control strategy, thereby improving the system response speed and safety.

[0044] For example, assume that at a certain moment, the current temperature data processed by the server is 37.3 °C. Neural network model: a pre-trained multi-layer perceptron (MLP), which can predict the temperature change in the next moment or within the next few minutes using historical temperature data and current temperature data. The server inputs 37.3 °C (possibly together with the temperature data of the previous few minutes as an input vector) into the neural network model. After neural network calculation, the model predicts that the temperature will rise to 38.5 °C within the next 1 minute. This 38.5 °C is the generated predicted temperature data. Through this method, the system not only knows the actual temperature of the battery at present, but also can anticipate the future temperature change in advance, so as to start heat dissipation or adjust the power output in advance in the temperature control strategy, prevent the temperature from rising sharply, and protect the battery safety.

[0045] In a possible implementation manner, inputting the current temperature data into a preset neural network model to generate predicted temperature data, specifically including: obtaining historical temperature data from the preset neural network model; inputting the current temperature data and the historical temperature data into a multi-layer perceptron, controlling multiple fully connected neurons, and using ReLU for activation to obtain the predicted temperature data.

[0046] Specifically, the preset neural network model has stored the temperature data in the past period of time, and these data reflect the temperature change trend of the battery in different time periods. The "current temperature data" just processed by data is merged with the historical temperature data extracted from the model to form an input vector containing temperature information at multiple time points. This input vector is sent into a multi-layer perceptron model. The multi-layer perceptron consists of multiple fully connected layers, and each neuron receives the weighted input from all neurons in the previous layer. In each fully connected layer, ReLU (Rectified Linear Unit) is used as the activation function. The ReLU function can effectively introduce non-linearity, enabling the model to capture the complex non-linear relationships in temperature changes, while also accelerating the training speed and improving the stability of the model. After being processed by the multi-layer perceptron, the network outputs the predicted temperature data, which represents the temperature trend at a future time point (or within a period of time), providing a warning and decision-making basis for the temperature control strategy.

[0047] For example, assume that after data processing, the current temperature data of a smart device is 37.3°C. At the same time, temperature data at the past 6 time points are obtained from the neural network model, which are [36.5°C, 36.7°C, 36.9°C, 37.0°C, 37.1°C, 37.2°C] respectively. The current temperature of 37.3°C is merged with the historical data to form an input vector, and this vector is used as the input to enter the multi-layer perceptron. Assume that the first fully connected layer contains several neurons, and each neuron calculates the weighted sum of the input vector and then applies the ReLU activation function to output the result after non-linear transformation. The data is passed through multiple fully connected layers, and the output of each layer is the input of the next layer, gradually extracting the features of temperature change. The last layer outputs one or more numerical values, and these values are the predicted future temperature data. For example, the network may predict that the temperature will be 38.5°C in the next 1 minute. The predicted temperature data of 38.5°C finally output by the neural network indicates that the system expects the temperature to gradually rise in the short term, which can trigger corresponding temperature control measures, such as starting the heat dissipation in advance or adjusting the power consumption strategy, to protect the stable operation of the battery and the device. Through this method, the system not only relies on the current temperature data, but also combines the historical temperature trend, utilizes the powerful non-linear mapping ability of the deep learning model to predict the temperature change in advance, so as to achieve a more intelligent and efficient temperature control management.

[0048] S140. Obtain the temperature error data of the lithium-ion battery.

[0049] Specifically, the server obtains the temperature error data of the lithium-ion battery from the system. These data reflect the difference between the actual temperature and the predicted temperature of the battery and are an important basis for subsequent temperature control decisions. Specifically, the server will use the previous temperature measurement data and temperature prediction results, and calculate an error value, that is, the temperature error data, by comparing the actual temperature calculated by the physical model (considering heat generation and heat dissipation factors) with the temperature predicted by the neural network. This error data can reveal the deviation between the system's temperature prediction and actual measurement, thereby helping to adjust the temperature control strategy and avoid problems such as overheating or insufficient cooling caused by inaccurate prediction.

[0050] For example, assume that at a certain moment, after data fusion processing, the system obtains the current temperature of the battery as 37.3°C; at the same time, the neural network model predicts that the temperature will rise to 38.0°C in the next period of time.

[0051] In addition, through physical calculations based on the battery heating and heat dissipation models, the system concludes that the actual temperature of the battery should be 37.8°C. At this time, the server calculates the temperature error data: Predicted temperature data: 38.0°C. Actual temperature data calculated by the physical model: 37.8°C. The temperature error data is -0.2°C. This temperature error data of -0.2°C indicates that the current actual temperature is 0.2°C lower than the predicted temperature. After obtaining this data, the server can feedback it to the temperature control system so as to appropriately adjust the prediction model or heat dissipation measures in future temperature control strategies, thereby making the temperature control more accurate, protecting the battery safety and extending its service life.

[0052] In a possible implementation manner, obtaining the temperature error data of the lithium-ion battery specifically includes: calculating the heating power and heat dissipation power of the lithium-ion battery; calculating the difference between the heating power and the heat dissipation power to obtain the target data; calculating the physical temperature data according to the target data and the unit heat capacity of the lithium-ion battery; calculating the temperature error data according to the physical temperature data and the predicted temperature data.

[0053] Specifically, the heating power refers to the heat generated by the battery during operation due to reasons such as internal resistance and polarization. For example, when the battery discharges at a certain current, Joule heat will be generated due to the existence of internal resistance; at the same time, a certain amount of heat will also be generated by the difference between the battery voltage and the open-circuit voltage during the charge and discharge process. The heat dissipation power refers to the ability of the battery to exchange heat with the environment, including convective, conductive, and radiative heat dissipation. This value depends on the battery surface area, ambient temperature, convective heat transfer coefficient, and the radiative characteristics of the battery housing, etc. Comparing the heating power with the heat dissipation power and calculating the difference between the two, this difference reflects whether the battery is in a state of heat accumulation (positive value) or heat loss (negative value) at a specific moment. The unit heat capacity represents the heat that the battery needs to absorb or release to increase or decrease the temperature by 1°C. Combining the power difference with the unit heat capacity of the battery, through numerical integration or direct conversion over a certain period of time, a temperature change value calculated based on the heat balance model can be obtained, which is called the physical temperature data here. Finally, comparing the physical temperature data (reflecting the temperature calculated by the battery according to the heat balance) with the temperature data predicted by the neural network and calculating the difference between the two, this difference is the temperature error data.

[0054] For example: Suppose a battery is working. During the charging and discharging process, the battery generates heat. For instance, a certain amount of heat is generated inside the battery due to the current passing through the internal resistance. At the same time, the battery also dissipates some heat through heat exchange with the surrounding environment. Through system monitoring, it can be estimated that the heat generated by the battery at this time is approximately 1.15 watts, while the heat it dissipates is about 1.05 watts. The difference between the two indicates that a little heat accumulates inside the battery, and this heat accumulation will cause the battery temperature to rise slightly. Based on this difference and combined with the battery's own thermal characteristics (such as how much heat is required for the battery to increase its temperature by 1°C), the system calculates that the actual temperature of the battery at the current moment may have risen slightly compared to the previously measured temperature. For example, it has risen from 38.5°C to above 38.5°C, but the increase amplitude is very small.

[0055] Meanwhile, based on the historical temperature data collected previously and the current temperature data, the neural network model predicts that the future battery temperature may reach 38.8°C. Comparing these two temperatures, the system finds that the temperature calculated by the physical model is slightly lower than the predicted temperature of the neural network, and the difference is approximately 0.3°C. This 0.3°C difference is the temperature error data, which can be used to determine whether the prediction is accurate and whether it is necessary to adjust the temperature control strategy or correct the prediction model, so as to better protect the battery safety and extend its lifespan. This method, by combining actual heat measurement and advanced prediction models, not only reduces the measurement error that may be brought by sensors but also provides a more reliable basis for temperature assessment, facilitating the system to adjust the temperature control measures in a timely and accurate manner.

[0056] S150. Generate a temperature control mechanism according to the predicted temperature data and the temperature error data.

[0057] Specifically, the server analyzes the future temperature change trend (predicted by the neural network) and the deviation between the actual temperature measurement and the predicted temperature. After synthesizing this information, it decides what kind of temperature control measures should be taken. In this way, the temperature control strategy is no longer a fixed and simple threshold control but can be adaptively adjusted according to the real-time situation, so as to more accurately manage the battery temperature and avoid problems caused by temperature control lag or over-regulation.

[0058] For example, assume that in a battery management system of a smartphone, the server obtains the following information: The neural network predicts that the battery temperature will rise to 38.8°C in a future period of time. Through calculation by the thermal model, it is known that the actual battery temperature is 38.5°C, and there is an error of approximately 0.3°C compared with the predicted temperature. In this case, the server will make a judgment by integrating these two pieces of data: If the predicted temperature shows that the temperature will rise rapidly and the temperature error is large (for example, the actual temperature is much lower than the predicted temperature, indicating that the rate of temperature rise is underestimated), the system may consider that the battery has an overheating risk and thus immediately activate the heat dissipation mechanism, such as strengthening the cooling fan or reducing the power consumption. On the contrary, if the predicted temperature is relatively stable and the temperature error is very small, the server will generate a relatively mild temperature control mechanism, which may only reduce part of the heat dissipation power or slightly adjust the device operating state to maintain temperature balance. Therefore, by combining the predicted temperature data and the temperature error data, the server can generate the most suitable temperature control strategy for the current situation in real time, thus ensuring both battery safety and avoiding excessive or insufficient temperature control measures.

[0059] In a possible implementation manner, a temperature regulation mechanism is generated according to the predicted temperature data and the temperature error data, specifically including: determining a predicted time window based on the predicted temperature data; determining a temperature change rate according to the predicted time window and the current temperature data; determining a first comparison result between the temperature change rate and a preset rate threshold; determining a second comparison result between the temperature error data and a preset error threshold; and generating a temperature regulation mechanism based on the first comparison result, the second comparison result, and the predicted temperature data.

[0060] Specifically, the prediction time window refers to the time range used by the system to judge the future temperature change trend. For example, the system can set the temperature change in the next 5 minutes, 10 minutes, or 30 minutes as the decision-making basis. The length of this window affects the sensitivity of the temperature control strategy. Calculating the speed of the current temperature change is usually based on the temperature change situation in the past period. For example, if the temperature rises from 37°C to 39°C in the past 5 minutes, then the temperature change rate is relatively fast, and cooling measures may need to be taken in advance. The preset rate threshold is a set standard indicating the normal range of temperature rise or fall. For example, if the threshold is set at 0.5°C per minute and the current rate reaches 1.2°C per minute, it means that the temperature is rising too fast and temperature control measures need to be taken. The temperature error data refers to the difference between the actual temperature calculated physically and the temperature predicted by the neural network. For example, if the error is less than 0.2°C, it means the prediction is relatively accurate; if the error is greater than 1°C, it means the system may need to adjust the prediction model or adopt a more aggressive temperature control strategy. If the temperature change rate is higher than the threshold and the error is large, it means that the temperature control lags, and the system may need to immediately enhance heat dissipation, such as increasing the speed of the cooling fan or reducing the processor power consumption. If the temperature change rate is low and the error is within the normal range, it means that the temperature change is stable, and the system may choose to maintain the current state or reduce the heat dissipation power to save energy consumption.

[0061] S160. According to the temperature control mechanism, control the temperature control components corresponding to the lithium-ion battery to perform temperature control.

[0062] Specifically, the server decides whether to turn on or adjust the working state of the temperature control components according to the calculated temperature control mechanism. Controlling the temperature control components includes cooling fans, heat pipes, phase change materials, liquid cooling devices, battery management systems (BMS), etc., and the server adjusts their working states according to different situations. If the battery temperature continues to rise or fall, the server will continuously update the temperature control mechanism and adjust the operating parameters of the temperature control components to achieve precise temperature control.

[0063] In a possible implementation manner, refer to Figure 2 , Figure 2 is another flowchart of a lithium-ion battery control method based on temperature control provided by an embodiment of the present application. The method includes steps S210 to step S220, and the above steps are as follows: S210. If it is determined that the first comparison result indicates that the temperature change rate is greater than the preset rate threshold, and the second comparison result indicates that the temperature error data is greater than the preset error threshold, then the temperature control mechanism is to immediately start the temperature control components for heat dissipation; S220. If it is determined that the first comparison result indicates that the temperature change rate is less than the preset rate threshold, and the second comparison result indicates that the temperature error data is less than the preset error threshold, then the temperature control mechanism is to reduce the heat dissipation power corresponding to the temperature control components.

[0064] Specifically, the rate of temperature change refers to the speed of temperature change, that is, the rate at which the temperature rises or falls within a certain period of time. A too high rate of temperature change may mean that the battery temperature changes too quickly, which may be an indication of overheating or other abnormal phenomena. The temperature error data represents the difference between the predicted temperature and the actual temperature. If the temperature error is large, it indicates that the prediction system may be inaccurate or the thermal state of the battery is abnormal. If the rate of temperature change is too fast and the temperature error is large, it means that the battery temperature is rising too fast, which may lead to overheating. At this time, heat dissipation measures (such as fans or heat pipes) need to be immediately activated to help dissipate heat. If the rate of temperature change is slow and the temperature error is small, it means that the battery temperature change is within the normal range. At this time, there is no need for excessive intervention, and the heat dissipation intensity can be reduced to save energy.

[0065] For example, assume you are using a smartphone. When the phone runs high-load applications (such as playing large games or video editing) for a long time, the battery temperature gradually rises. The system monitors and predicts the battery temperature in real time and takes intelligent temperature control measures based on this data. For example, there are the following situations: 1. Large rate of temperature change, large temperature error: When playing a large game on the phone, the battery temperature starts to rise rapidly. The system predicts that the battery temperature may exceed the safe temperature limit (such as 45°C) in the next few minutes. In addition, the error between the predicted temperature and the actual measured temperature is large, indicating that the temperature prediction is not very accurate and the battery may be experiencing abnormal temperature changes. The rate of temperature change is greater than the threshold: Due to the rapid temperature change, the system believes that the rising battery temperature may lead to overheating and affect the battery life. The large difference between the predicted temperature and the actual temperature indicates that the battery temperature change may not conform to the prediction model, further increasing the overheating risk. Therefore, the system will immediately activate heat dissipation measures, such as increasing the fan speed, adjusting the heat dissipation design of the phone case, or increasing the working intensity of the liquid cooling system, to quickly reduce the battery temperature and prevent the battery from overheating.

[0066] 2. Small rate of temperature change, small temperature error: When the phone continues to run, the rising speed of the battery temperature slows down, and the error between the predicted temperature and the actual temperature is very small, indicating that the battery temperature change is within the normal range and the temperature control system can accurately predict the battery temperature change. The rate of temperature change is less than the threshold: The temperature does not change quickly, and the battery temperature gradually rises within the expected temperature change range, without the risk of rapid temperature rise. The predicted temperature and the actual temperature are basically the same, indicating that the system prediction is accurate and the battery temperature change is within a reasonable range. The system determines that there is no need for immediate intervention and may reduce the heat dissipation intensity (such as reducing the fan speed or reducing the working power of the liquid cooling system) to save battery energy and extend the battery usage time.

[0067] Therefore, based on the real-time data of the battery temperature, by comparing the temperature change rate and the temperature error data, the temperature control strategy is intelligently adjusted: when the temperature changes too fast and the prediction is inaccurate, active heat dissipation measures are taken to avoid overheating. When the temperature changes smoothly and the prediction is accurate, unnecessary heat dissipation is reduced to maintain efficient energy use. This intelligent regulation can ensure that the mobile phone battery always operates within the optimal temperature range under different usage conditions, protecting the battery life and enhancing the user experience.

[0068] This application also provides a lithium-ion battery control device based on temperature regulation. Referring to Figure 3 , Figure 3 is a schematic diagram of the modules of a lithium-ion battery control device based on temperature regulation provided by an embodiment of this application. The device is a server, and the server includes an acquisition module 31 and a processing module 32. Among them, the acquisition module 31 acquires the temperature measurement data sent by the thermistor and the infrared temperature sensor for the lithium-ion battery; the processing module 32 performs data processing on the temperature measurement data to obtain the current temperature data; the processing module 32 inputs the current temperature data into a preset neural network model to generate predicted temperature data; the acquisition module 31 acquires the temperature error data of the lithium-ion battery; the processing module 32 generates a temperature regulation mechanism according to the predicted temperature data and the temperature error data; the processing module 32 controls the temperature control component corresponding to the lithium-ion battery to perform temperature regulation according to the temperature regulation mechanism.

[0069] In a possible implementation manner, the acquisition module 31 acquiring the temperature measurement data sent by the thermistor and the infrared temperature sensor for the lithium-ion battery specifically includes: the acquisition module 31 acquiring the first temperature measurement data sent by the thermistor located on the surface of the lithium-ion battery; the acquisition module 31 acquiring the second temperature measurement data sent by the infrared temperature sensor located at the positive and negative electrode positions inside the lithium-ion battery; the processing module 32 performs digital signal conversion on the first temperature measurement data and the second temperature measurement data to obtain the temperature measurement data.

[0070] In a possible implementation manner, the processing module 32 performing data processing on the temperature measurement data to obtain the current temperature data specifically includes: the processing module 32 allocates weights to the data of the thermistor and the infrared temperature sensor according to the respective accuracies and response speeds of different sensors to obtain the thermistor weight and the sensor weight; the processing module 32 performs data fusion through weighted average and Bayesian estimation according to the thermistor weight, the sensor weight, and the temperature measurement data to obtain the current temperature data.

[0071] In a possible implementation, the processing module 32 inputs the current temperature data into a preset neural network model to generate predicted temperature data, which specifically includes: the acquisition module 31 acquires historical temperature data from the preset neural network model; the processing module 32 inputs the current temperature data and the historical temperature data into a multi-layer perceptron, controls multiple fully-connected neurons, and uses ReLU for activation to obtain the predicted temperature data.

[0072] In a possible implementation, the acquisition module 31 acquires temperature error data of the lithium-ion battery, which specifically includes: the processing module 32 calculates the heat generation power and the heat dissipation power of the lithium-ion battery; the processing module 32 calculates the difference between the heat generation power and the heat dissipation power to obtain target data; the processing module 32 calculates physical temperature data based on the target data and the unit heat capacity of the lithium-ion battery; the processing module 32 calculates temperature error data based on the physical temperature data and the predicted temperature data.

[0073] In a possible implementation, the processing module 32 generates a temperature control mechanism based on the predicted temperature data and the temperature error data, which specifically includes: the processing module 32 determines a predicted time window based on the predicted temperature data; the processing module 32 determines a temperature change rate based on the predicted time window and the current temperature data; the processing module 32 determines a first comparison result between the temperature change rate and a preset rate threshold; the processing module 32 determines a second comparison result between the temperature error data and a preset error threshold; the processing module 32 generates a temperature control mechanism based on the first comparison result, the second comparison result, and the predicted temperature data.

[0074] In a possible implementation, the processing module 32 generates a temperature control mechanism based on the first comparison result, the second comparison result, and the predicted temperature data, which specifically includes: if the processing module 32 determines that the first comparison result indicates that the temperature change rate is greater than the preset rate threshold and the second comparison result indicates that the temperature error data is greater than the preset error threshold, then the temperature control mechanism is to immediately start the temperature control component for heat dissipation; if the processing module 32 determines that the first comparison result indicates that the temperature change rate is less than the preset rate threshold and the second comparison result indicates that the temperature error data is less than the preset error threshold, then the temperature control mechanism is to reduce the heat dissipation power corresponding to the temperature control component.

[0075] It should be noted that: when the device provided in the above embodiments realizes its functions, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be seen in the method embodiments, which will not be elaborated here.

[0076] This application also provides an electronic device. Referring to Figure 4 , Figure 4 which is a schematic structural diagram of an electronic device provided by an embodiment of this application. The electronic device may include: at least one processor 41, at least one network interface 44, a user interface 43, a memory 45, and at least one communication bus 42.

[0077] Among them, the communication bus 42 is used to realize the connection and communication between these components.

[0078] Among them, the user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may further include a standard wired interface and a wireless interface.

[0079] Among them, the network interface 44 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface).

[0080] Among them, the processor 41 may include one or more processing cores. The processor 41 connects various parts within the entire server through various interfaces and lines, and by running or executing instructions, programs, code sets, or instruction sets stored in the memory 45, as well as calling data stored in the memory 45, it executes various functions of the server and processes data. Optionally, the processor 41 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 41 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content required to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 41 and may be implemented separately through a single chip.

[0081] Among them, the memory 45 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 45 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 45 may also be at least one storage device located far from the aforementioned processor 41. As Figure 4 shown, in the memory 45 as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program of a lithium-ion battery control method based on temperature regulation.

[0082] In Figure 4 the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 41 can be used to call the application program of a lithium-ion battery control method based on temperature regulation stored in the memory 45. When executed by one or more processors, the electronic device executes the methods in one or more of the above embodiments.

[0083] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0084] This application also provides a computer-readable storage medium storing instructions. When executed by one or more processors, the electronic device executes the methods in one or more of the above embodiments.

[0085] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0086] In several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some service interfaces. The indirect couplings or communication connections of devices or units can be in electrical or other forms.

[0087] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of this application. And the aforementioned memory includes: various media such as USB flash drives, mobile hard disks, magnetic disks, or optical discs that can store program codes.

[0090] The foregoing are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and the practice of the truth of the disclosure, those skilled in the art will easily think of other implementation schemes of the present disclosure. This application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A control method for a lithium-ion battery based on temperature regulation, characterized in that, The method includes: Obtaining temperature measurement data sent by a thermistor and an infrared temperature sensor for a lithium-ion battery; Performing data processing on the temperature measurement data to obtain current temperature data; Inputting the current temperature data into a preset neural network model to generate predicted temperature data; Obtaining the temperature error data of the lithium-ion battery; Generating a temperature control mechanism based on the predicted temperature data and the temperature error data; Controlling a temperature control component corresponding to the lithium-ion battery to perform temperature control according to the temperature control mechanism.

2. The method for controlling a lithium-ion battery based on temperature regulation according to claim 1, wherein The obtaining of the temperature measurement data sent by the thermistor and the infrared temperature sensor for the lithium-ion battery specifically includes: Obtaining first temperature measurement data sent by the thermistor located at the surface position of the lithium-ion battery; Obtaining second temperature measurement data sent by the infrared temperature sensor located at the positive and negative electrode positions inside the lithium-ion battery; Performing digital signal conversion on the first temperature measurement data and the second temperature measurement data to obtain the temperature measurement data.

3. The lithium-ion battery control method based on temperature regulation according to claim 1, wherein, The performing of data processing on the temperature measurement data to obtain current temperature data specifically includes: Allocating weights to the data of the thermistor and the infrared temperature sensor according to the respective accuracies and response speeds of different sensors to obtain a thermistor weight and a sensor weight; Performing data fusion through weighted average and Bayesian estimation according to the thermistor weight, the sensor weight, and the temperature measurement data to obtain the current temperature data.

4. The method for controlling a lithium-ion battery based on temperature regulation according to claim 1, wherein The inputting of the current temperature data into a preset neural network model to generate predicted temperature data specifically includes: Obtaining historical temperature data from the preset neural network model; Inputting the current temperature data and the historical temperature data into a multi-layer perceptron, controlling multiple fully connected neurons, and using ReLU for activation to obtain the predicted temperature data.

5. The lithium-ion battery control method based on temperature regulation according to claim 1, wherein The obtaining of the temperature error data of the lithium-ion battery specifically includes: Calculating the heat generation power and the heat dissipation power of the lithium-ion battery; Calculating the difference between the heat generation power and the heat dissipation power to obtain target data; Calculating physical temperature data according to the target data and the unit heat capacity of the lithium-ion battery; Calculating the temperature error data according to the physical temperature data and the predicted temperature data.

6. The method for controlling a lithium-ion battery based on temperature regulation according to claim 1, characterized in that The generating of the temperature control mechanism based on the predicted temperature data and the temperature error data specifically includes: Determining a predicted time window based on the predicted temperature data; Determining a temperature change rate according to the predicted time window and the current temperature data; Determining a first comparison result between the temperature change rate and a preset rate threshold; Determining a second comparison result between the temperature error data and a preset error threshold; Generating the temperature control mechanism based on the first comparison result, the second comparison result, and the predicted temperature data.

7. The method for controlling a lithium-ion battery based on temperature regulation according to claim 6, wherein The generating of the temperature control mechanism based on the first comparison result, the second comparison result, and the predicted temperature data specifically includes: If it is determined that the first comparison result indicates that the temperature change rate is greater than the preset rate threshold and the second comparison result indicates that the temperature error data is greater than the preset error threshold, the temperature control mechanism is to immediately start the temperature control component for heat dissipation; If it is determined that the first comparison result indicates that the temperature change rate is less than the preset rate threshold and the second comparison result indicates that the temperature error data is less than the preset error threshold, the temperature control mechanism is to reduce the heat dissipation power corresponding to the temperature control component.

8. A lithium-ion battery control device based on temperature regulation, characterized in that, The control device includes an acquisition module (31) and a processing module (32), where, The acquisition module (31) is configured to acquire temperature measurement data sent by a thermistor and an infrared temperature sensor for the lithium-ion battery; The processing module (32) is configured to perform data processing on the temperature measurement data to obtain current temperature data; The processing module (32) is further configured to input the current temperature data into a preset neural network model to generate predicted temperature data; The acquisition module (31) is further configured to acquire the temperature error data of the lithium-ion battery; The processing module (32) is further configured to generate a temperature control mechanism according to the predicted temperature data and the temperature error data; The processing module (32) is further configured to control the temperature control component corresponding to the lithium-ion battery for temperature control according to the temperature control mechanism.

9. An electronic device, characterized in that, The electronic device includes a processor (41), a memory (45), a user interface (43), and a network interface (44). The memory (45) is used to store instructions. Both the user interface (43) and the network interface (44) are used to communicate with other devices. The processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images