Intelligent temperature control management method and system for lithium iron phosphate battery

Abstract

This invention discloses an intelligent temperature control management method and system for lithium iron phosphate batteries, relating to the field of battery temperature control technology. The method includes: acquiring a battery sample dataset, which includes sample operating condition data and calibrated health status data; constructing and training a health status assessment model based on the sample dataset, the health status assessment model being used to establish a mapping relationship between operating condition data and health status; collecting the base-state health data and historical operating condition data of the target battery, inputting them into the health status assessment model for health status correction, and outputting real-time health status data; establishing a target-state heat generation model based on the real-time health status data and the real-time operating condition information of the target battery, and calculating the predicted heat generation rate of the target battery; making temperature control decisions based on the predicted heat generation rate, generating a corresponding forward-looking temperature control adjustment strategy, and distributing it to the thermal management component for temperature control management. This invention solves the technical problem of poor battery temperature control performance in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of battery temperature control technology, specifically to a method and system for intelligent temperature control management of lithium iron phosphate batteries. Background Technology

[0002] Lithium iron phosphate (LFP) batteries have become a core power source for electric vehicles and energy storage systems due to their high safety, long cycle life, and cost advantages. Thermal management technology is crucial for ensuring battery performance, lifespan, and safety. Existing temperature control solutions mainly rely on real-time monitoring by temperature sensors combined with preset thresholds to trigger cooling strategies. However, this approach has significant limitations: on the one hand, traditional static temperature control models cannot adapt to changes in battery health, causing the temperature control method to deviate from actual operating conditions; on the other hand, existing solutions struggle to cope with the risk of thermal runaway caused by sudden scenarios. Especially in real-world operating scenarios, incorrect temperature control strategies can easily lead to localized overheating, accelerating battery life degradation and even causing thermal failure. Summary of the Invention

[0003] This application provides a method and system for intelligent temperature control management of lithium iron phosphate batteries, which addresses the technical problem of inaccurate temperature control strategies in existing lithium iron phosphate batteries leading to poor temperature control performance.

[0004] In view of the above problems, this application provides a method and system for intelligent temperature control management of lithium iron phosphate batteries.

[0005] In a first aspect, this application provides a method for intelligent temperature control management of lithium iron phosphate batteries, the method comprising: Obtain a battery sample dataset, which includes sample operating condition data and calibration health status data; A health status assessment model is constructed and trained based on the sample dataset. The health status assessment model is used to establish a mapping relationship between working condition data and health status. Collect the target battery's ground-state health data and historical operating condition data, input them into the health status assessment model for health status correction, and output real-time health status data; Based on the real-time health status data and the real-time operating condition information of the target battery, a target state heat generation model is established, and the predicted heat generation rate of the target battery is calculated according to the target state heat generation model. Based on the predicted heat generation rate, a temperature control decision is made, a forward-looking temperature control adjustment strategy is generated, and the strategy is sent to the thermal management component for temperature control management.

[0006] Secondly, this application provides an intelligent temperature control management system for lithium iron phosphate batteries, comprising: The data acquisition module is used to acquire battery sample datasets, which include sample operating condition data and calibration health status data. A health model building module is used to build and train a health status assessment model based on the sample dataset. The health status assessment model is used to establish a mapping relationship between working condition data and health status. The health status correction module is used to collect the base state health data and historical operating condition data of the target battery, input them into the health status assessment model for health status correction, and output real-time health status data. The heat generation model construction module is used to establish a target-state heat generation model based on the real-time health status data and the real-time operating condition information of the target battery, and to calculate the predicted heat generation rate of the target battery based on the target-state heat generation model. The temperature control decision module is used to make temperature control decisions based on the predicted heat generation rate, generate a forward-looking temperature control adjustment strategy, and send it to the thermal management component for temperature control management.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application proposes an intelligent temperature control management method and system for lithium iron phosphate batteries. By dynamically integrating real-time battery health status assessment with a condition-driven heat generation prediction mechanism, it significantly improves the dynamic adaptability and predictive capability of the lithium iron phosphate temperature control system. Compared with traditional methods, the technical solution provided in this application significantly overcomes the inherent defects of static methods that do not match the actual battery conditions, achieving precise thermal management based on individual battery characteristics, and thus improving the temperature control effect of lithium iron phosphate batteries while reducing the overall energy consumption of the temperature control system. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating a method for intelligent temperature control management of lithium iron phosphate batteries, provided in an embodiment of this application.

[0010] Figure 2 This is a schematic diagram of a smart temperature control management system for lithium iron phosphate batteries provided in an embodiment of this application.

[0011] The components represented by each number in the attached diagram are explained below: Data acquisition module 100, health model construction module 200, health status correction module 300, heat generation model construction module 400, temperature control decision module 500. Detailed Implementation

[0012] This application provides a method and system for intelligent temperature control management of lithium iron phosphate batteries, which addresses the technical problem of inaccurate temperature control strategies in existing lithium iron phosphate batteries leading to poor temperature control performance.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0015] Example 1, as Figure 1 As shown, this application provides a smart temperature control management method for lithium iron phosphate batteries, wherein the method includes: S10: Obtain a battery sample dataset, which includes sample operating condition data and calibration health status data.

[0016] Traditional battery health status assessments rely on single laboratory test data or simplified operating condition simulations, making it difficult to construct a sample system that covers real-world, complex scenarios. The sample operating condition data lacks multi-dimensional, long-term actual operating characteristics, resulting in a disconnect between the obtained battery health status assessment and actual application scenarios.

[0017] Step S10 in the method provided in this application embodiment includes: The sample operating condition data is extracted based on the battery operation log, and the sample operating condition data includes at least the current value sequence, voltage value sequence, temperature value sequence, and cycle count record; The calibration health status data is obtained through an offline testing platform, and the calibration health status data includes at least a sequence of internal resistance measurements and a sequence of remaining capacity measurements.

[0018] In this embodiment, sample operating condition data is extracted based on the battery operation log. The operating condition data refers to the battery's working status data during operation. The extracted sample operating condition data includes at least a current value sequence (in C), a voltage value sequence (in V), a temperature value sequence (in °C), and a cycle count record (in °C).

[0019] Calibration health status data is acquired using an offline testing platform, such as an electrochemical workstation containing a constant current charge-discharge tester. This calibration health status data must include at least a sequence of internal resistance measurements in mΩ and a sequence of remaining capacity measurements in %.

[0020] By synchronously acquiring multi-dimensional sample operating condition data and calibrated health status data from actual operation logs, a spatiotemporally aligned battery sample dataset is constructed. This dataset solves the mapping distortion problem caused by fragmented data sources in traditional methods. Acquiring the battery sample dataset covers different battery health conditions and typical operating conditions, significantly improving the generalization ability and reliability of subsequent health status assessment models.

[0021] S20: Construct and train a health status assessment model based on the sample dataset. The health status assessment model is used to establish a mapping relationship between working condition data and health status.

[0022] Existing health status assessment models mostly use a single indicator, such as capacity decay, or a fixed formula for estimation. They cannot simultaneously capture the nonlinear changes in internal resistance and the gradual changes in capacity, and often ignore the coupled impact of operating condition changes on battery health.

[0023] Step S20 in the method provided in this application embodiment includes: Using the sample operating condition data as input and the internal resistance measurement value sequence as supervision, a first mathematical fitting channel is constructed and trained accordingly. The first mathematical fitting channel is used to establish the mapping relationship between the operating condition data and the internal resistance. Using the sample operating condition data as input and the remaining capacity measurement sequence as supervision, a second machine learning channel is constructed and trained accordingly. The second machine learning channel is used to establish the mapping relationship between the operating condition data and the remaining capacity. The first mathematical fitting channel and the second machine learning channel are combined in parallel to generate the health status assessment model.

[0024] In this embodiment, a linear fitting method is used to construct a first mathematical fitting channel, which is used to establish the mapping relationship between operating condition data and internal resistance. Using sample operating conditions as input and the sequence of internal resistance measurements as supervision, the first mathematical fitting channel is trained until convergence. For example, if the input operating condition data has an output internal resistance value error within ±0.1 mΩ, the training of the first mathematical fitting channel is complete.

[0025] A second machine learning channel is constructed using machine learning methods to establish the mapping relationship between operating condition data and remaining capacity. An exemplary three-layer structure is adopted: the input layer receives the operating condition data, the hidden layer uses 32 nodes activated by the ReLU function, and the output layer outputs the predicted remaining capacity. The second machine learning channel is trained using sample operating condition data as input and the remaining capacity measurement sequence as supervision until convergence. For example, if the error value of the output remaining capacity is within ±1% of the input operating condition data, the training of the second machine learning channel is considered complete.

[0026] A health status assessment model is generated by merging the first mathematical fitting channel and the second machine learning channel in parallel. Operating condition data is input into the health status assessment model, which outputs the internal resistance value assessed by the first mathematical fitting channel and the remaining capacity assessed by the second machine learning channel.

[0027] By constructing a parallel dual-channel health status assessment model: the first mathematical fitting channel focuses on the physical mapping between operating condition data and internal resistance, preserving the characteristics of internal resistance; the second machine learning channel learns the complex nonlinear relationship between operating condition and remaining capacity. The parallel fusion of the two channels can accurately establish a dual mapping relationship between operating condition data and health status, avoiding the limitations of a single model, providing a high-precision foundation for the synchronous correction of internal resistance and capacity, and ensuring reliable parameters for subsequent implementation.

[0028] S30: Collect the target battery's ground-state health data and historical operating condition data, input them into the health status assessment model for health status correction, and output real-time health status data.

[0029] The general health state model does not take into account the individual ground-state characteristics of the target battery and the cumulative effects of historical operation; directly applying it will lead to evaluation bias. The evaluation results of traditional methods are prone to deviating from the actual situation.

[0030] Step S30 in the method provided in this application embodiment includes: Access the target battery's factory inspection report and extract the target battery's ground-state health data; Feature extraction is performed based on the prior operation logs of the target battery to obtain the historical operating condition data, wherein the historical operating condition data includes multiple operating condition index sequences. Align the historical operating condition data, and input the aligned historical operating condition data and the ground state health data into the health status assessment model to obtain the real-time health status data, wherein the real-time health status data includes real-time internal resistance assessment value and remaining capacity assessment value.

[0031] In this embodiment, the factory inspection report of the target battery is retrieved to extract the target battery's ground-state health data. This ground-state health data includes the internal resistance value and remaining capacity.

[0032] Feature extraction is performed based on the prior operating logs of the target battery. The prior operating logs refer to the battery's operating logs from previous historical periods, obtaining historical operating condition data. This historical operating condition data includes multiple operating condition indicator sequences, such as current value sequences, voltage value sequences, temperature value sequences, and cycle count records.

[0033] Based on the timestamps of multiple operating condition indicator sequences, operating condition indicator data with the same timestamp are aligned until historical operating condition data is aligned. The aligned historical operating condition data and the ground-state health data are input into the health status assessment model to obtain real-time health status data, which includes real-time internal resistance assessment values ​​and remaining capacity assessment values.

[0034] This application utilizes the target battery's factory-set ground-state health data and extracts historical operating condition data from the preceding operation log, aligning these data temporally before inputting them into a health status assessment model. Using the ground-state data as the calibration benchmark for degradation starting point, and leveraging historical operating conditions to quantify the cumulative aging effect, it achieves an improvement from a general model to individual assessment. The output internal resistance and remaining capacity assessment values ​​dynamically reflect the actual degradation degree of the target battery, providing accurate parameter input for heat generation prediction.

[0035] S40: Based on the real-time health status data and the real-time operating condition information of the target battery, establish a target state heat generation model, and calculate the predicted heat generation rate of the target battery according to the target state heat generation model.

[0036] Static heat generation models cannot adapt to the increased internal resistance and exacerbated side reactions caused by changes in battery health, leading to inaccurate heat generation rate predictions. Traditional methods have fixed parameters and cannot dynamically update calculation rules based on real-time health status, resulting in increased errors at high rates or low temperatures. Without a linkage mechanism between health status and heat generation models, prediction results cannot accurately reflect the true thermal situation of lithium iron phosphate batteries.

[0037] Step S40 in the method provided in this application embodiment includes: By combining the remaining capacity measurement sequence with the corresponding side reaction heat measurement sequence, a side reaction heat calculation model is established through nonlinear fitting; A calculation model for internal resistance heat generation is constructed by calling upon the knowledge base of lithium iron phosphate material properties. The side reaction heat calculation model and the internal resistance heat generation calculation model are combined to form a ground-state heat generation model, and the ground-state heat generation model is then subjected to inverse parameter calibration.

[0038] Based on the internal resistance assessment value and the remaining capacity assessment value, update the parameters of the internal resistance heat generation calculation model and the parameters of the side reaction heat calculation model in the ground state heat generation model respectively, and obtain the target state heat generation model; The real-time health status data and the real-time operating condition information are input into the target state heat generation model for iterative calculation. When the deviation of the heat production rate obtained by the calculation for a preset number of consecutive times is less than the preset convergence threshold, the final iteration value is output as the predicted heat production rate.

[0039] In this embodiment, a calculation model for the heat of side reactions is established by combining the remaining capacity measurement sequence with the corresponding side reaction heat measurement sequence through nonlinear fitting. The side reaction heat measurement sequence refers to the heat values ​​generated by side reactions during battery operation, obtained from past laboratory measurements and calculations. For example, the curve_fit function is used for nonlinear fitting until a nonlinear mathematical relationship is found that represents the change in remaining capacity and side reaction heat, thus obtaining the calculation model for the heat of side reactions.

[0040] A calculation model for internal resistance heat generation is constructed by utilizing the lithium iron phosphate (LFP) material property knowledge base. This publicly accessible knowledge base contains the reaction equations and thermodynamic laws such as Joule's law for LFP. By accessing this knowledge base, the internal resistance heat generation of LFP batteries can be calculated. The internal resistance heat generation calculation model is constructed by inputting basic parameters of the LFP battery, such as current parameters, and outputting the calculated internal resistance heat generation.

[0041] A ground-state heat generation model is formed by integrating the side reaction heat calculation model and the internal resistance heat generation calculation model, and then the ground-state heat generation model is calibrated in reverse. Specifically, the total reaction heat of the lithium iron phosphate battery is measured using a thermal sensor such as a thermometer, and the internal resistance heat generation is calculated according to the internal resistance heat generation model: total reaction heat - internal resistance heat generation = side reaction heat. The ground-state heat generation model is then calibrated in reverse using this mathematical relationship until the output internal resistance heat generation + side reaction heat equals the total reaction heat.

[0042] Based on the internal resistance assessment value and the remaining capacity assessment value, the parameters of the internal resistance heat production calculation model and the side reaction heat calculation model in the ground-state heat production model are updated respectively. The updated parameters of the internal resistance heat production calculation model and the side reaction heat calculation model are then integrated into the target-state heat production model. Specifically, the internal resistance assessment value and the remaining capacity assessment value are input into the internal resistance heat production calculation model and the side reaction heat calculation model to initialize the models, calculate and output the internal resistance heat production and the side reaction heat production, and obtain the target-state heat production model with updated parameters.

[0043] Real-time health status data and real-time operating condition information are input into the target state heat generation model for iterative calculation.

[0044] When the deviation of the heat production rate obtained from multiple consecutive calculations is less than a preset convergence threshold, the final iterative value is output as the predicted heat production rate. For example, the preset number of calculations can be set to 10. The larger the preset number, the more stable the heat production rate calculation result, and the greater the likelihood of an accurate heat production rate. The preset convergence threshold is a pre-set deviation threshold for the heat production rate. When the deviation of multiple calculation results is less than the threshold, the calculation result can be considered to have converged, and the final iterative value can be output as the optimal value. Preferably, the preset convergence threshold can be set to a deviation range less than 2% of the total calculated heat production rate. When the deviation of multiple calculation results is less than 2% of the predicted heat production rate, the final iterative value is output as the predicted heat production rate, in J / s.

[0045] The parameters of the ground-state heat generation model are dynamically updated based on real-time health status data. Through iterative calculations until convergence, a target-state heat generation model adapted to the current aging state of the target battery is generated, accurately outputting the predicted heat generation rate. The method provided in this application enables real-time coupling between the heat generation model and the health status, achieving accurate heat generation prediction and providing a reliable basis for subsequent temperature control decisions.

[0046] S50: Based on the predicted heat generation rate, make a temperature control decision, generate a forward-looking temperature control adjustment strategy, and send it to the thermal management component to perform temperature control management.

[0047] Traditional temperature control relies on a passive response based on current temperature feedback, which cannot predict heat generation trends, leading to lag in regulation. Fixed threshold strategies do not consider the characteristics of changes in thermal capacity and accelerated heat generation in batteries under different health conditions, which can easily cause local overheating or overcooling under sudden operating conditions.

[0048] Step S50 in the method provided in this application embodiment includes: Based on the predicted heat production rate and the preset time window, the temperature change trend is deduced; The temperature change trend is controlled and judged according to the preset temperature control constraints, wherein the temperature control constraints include process temperature control constraints and endpoint temperature control constraints. If the control judgment result is not satisfied, the temperature control power is calculated based on the predicted heat production rate, and the forward-looking temperature control adjustment strategy is generated accordingly. The program language translates the forward-looking temperature control strategy and sends it to the thermal management component to execute temperature control management.

[0049] In this embodiment, the temperature change trend is extrapolated based on the predicted heat generation rate and a preset time window. For example, the preset time window is set to the next 30 minutes. Real-time health status data and real-time operating conditions are input into the target state heat generation model to obtain the predicted heat generation rate, in J / s. Linear prediction is then performed based on the predicted heat generation rate to obtain the temperature change rate, in °C / s. Specifically, the time step is divided into 10s. Based on the heat generation rate and the battery heat capacity (i.e., the heat required for the battery to rise by 1 °C, in J / °C, obtained through battery production data), linear prediction is performed to obtain multiple temperature values. Temperature value = predicted heat generation rate × time step ÷ battery heat capacity. Multiple temperature values ​​are then integrated according to the time step to obtain the temperature change rate.

[0050] Based on preset temperature control constraints, the temperature change trend is controlled and judged. These constraints include process temperature control constraints and endpoint temperature control constraints. Specifically, these are the temperature constraint thresholds during the temperature change process and the temperature constraint threshold at the end of the temperature change. For example, the process temperature control constraint threshold is set to a temperature rise rate of less than 0.5℃ / s, and the endpoint temperature control constraint is set to 50℃.

[0051] If the control judgment result is unsatisfied, meaning any or both temperature control constraints are not met, then the temperature control power is calculated based on the predicted heat generation rate. For example, based on the predicted heat generation rate, time step, and battery thermal capacity, the required reduction in heat generation rate to reach the temperature constraint threshold is calculated and used as the temperature control power. Temperature control power = [Temperature constraint threshold - (Predicted heat generation rate × Time step ÷ Battery thermal capacity)] ÷ Time step. Based on the temperature control power, a forward-looking temperature control adjustment strategy is generated, such as activating the temperature control system; the temperature control system power = temperature control power.

[0052] Proceduralized forward-looking temperature control strategies, such as using C language to write temperature control strategies, can be distributed to the thermal management component for temperature control management.

[0053] Based on the predicted heat production rate, the temperature change trend is extrapolated, and dynamic judgment is made in conjunction with process and endpoint temperature control constraints. When the predicted trend does not meet the constraints, a temperature control strategy adapted to the heat production rate is proactively generated and sent to the thermal management component for execution. The method provided in this application can transform passive response into active defense, suppressing the risk of thermal runaway while reducing temperature control energy consumption redundancy through precise power matching, thus achieving synergistic optimization of temperature control effect and temperature control energy efficiency.

[0054] Example 2, as Figure 2 As shown, based on the same inventive concept as the intelligent temperature control management method for lithium iron phosphate batteries provided in Embodiment 1, this embodiment of the invention also provides an intelligent temperature control management system for lithium iron phosphate batteries, comprising: The data acquisition module 100 is used to acquire a battery sample dataset, which includes sample operating condition data and calibration health status data. The health model construction module 200 is used to construct and train a health status assessment model based on the sample dataset. The health status assessment model is used to establish a mapping relationship between working condition data and health status. The health status correction module 300 is used to collect the base state health data and historical operating condition data of the target battery, input the health status assessment model to correct the health status, and output real-time health status data. The heat generation model construction module 400 is used to establish a target state heat generation model based on the real-time health status data and the real-time operating condition information of the target battery, and to calculate the predicted heat generation rate of the target battery according to the target state heat generation model. The temperature control decision module 500 is used to make temperature control decisions based on the predicted heat generation rate, generate a forward-looking temperature control adjustment strategy, and send it to the thermal management component for temperature control management.

[0055] In one embodiment, the data acquisition module 100 is further configured to: The sample operating condition data is extracted based on the battery operation log, and the sample operating condition data includes at least the current value sequence, voltage value sequence, temperature value sequence, and cycle count record; The calibration health status data is obtained through an offline testing platform, and the calibration health status data includes at least a sequence of internal resistance measurements and a sequence of remaining capacity measurements.

[0056] In one embodiment, the health model building module 200 is further configured to: Using the sample operating condition data as input and the internal resistance measurement value sequence as supervision, a first mathematical fitting channel is constructed and trained accordingly. The first mathematical fitting channel is used to establish the mapping relationship between the operating condition data and the internal resistance. Using the sample operating condition data as input and the remaining capacity measurement sequence as supervision, a second machine learning channel is constructed and trained accordingly. The second machine learning channel is used to establish the mapping relationship between the operating condition data and the remaining capacity. The first mathematical fitting channel and the second machine learning channel are combined in parallel to generate the health status assessment model.

[0057] In one embodiment, the health status correction module 300 is further configured to: Access the target battery's factory inspection report and extract the target battery's ground-state health data; Feature extraction is performed based on the prior operation logs of the target battery to obtain the historical operating condition data, wherein the historical operating condition data includes multiple operating condition index sequences. Align the historical operating condition data, and input the aligned historical operating condition data and the ground state health data into the health status assessment model to obtain the real-time health status data, wherein the real-time health status data includes real-time internal resistance assessment value and remaining capacity assessment value.

[0058] In one embodiment, the heat generation model building module 400 is further configured to: By combining the remaining capacity measurement sequence with the corresponding side reaction heat measurement sequence, a side reaction heat calculation model is established through nonlinear fitting; A calculation model for internal resistance heat generation is constructed by calling upon the knowledge base of lithium iron phosphate material properties. The side reaction heat calculation model and the internal resistance heat generation calculation model are combined to form a ground-state heat generation model, and the ground-state heat generation model is then subjected to inverse parameter calibration.

[0059] Based on the internal resistance assessment value and the remaining capacity assessment value, update the parameters of the internal resistance heat generation calculation model and the parameters of the side reaction heat calculation model in the ground state heat generation model respectively, and obtain the target state heat generation model; The real-time health status data and the real-time operating condition information are input into the target state heat generation model for iterative calculation. When the deviation of the heat production rate obtained by the calculation for a preset number of consecutive times is less than the preset convergence threshold, the final iteration value is output as the predicted heat production rate.

[0060] In one embodiment, the temperature control decision module 500 is further configured to: Based on the predicted heat production rate and the preset time window, the temperature change trend is deduced; The temperature change trend is controlled and judged according to the preset temperature control constraints, wherein the temperature control constraints include process temperature control constraints and endpoint temperature control constraints. If the control judgment result is not satisfied, the temperature control power is calculated based on the predicted heat production rate, and the forward-looking temperature control adjustment strategy is generated accordingly. The program language translates the forward-looking temperature control strategy and sends it to the thermal management component to execute temperature control management.

[0061] In summary, the embodiments of this application have at least the following technical effects: This application proposes an intelligent temperature control management method and system for lithium iron phosphate (LFP) batteries. By dynamically integrating real-time battery health status assessment with a condition-driven heat generation prediction mechanism, the dynamic adaptability and predictive capability of the LFP temperature control system are significantly improved. Specifically, based on the real-time correction of battery internal resistance and capacity using a health status assessment model, the target-state heat generation model can dynamically capture the nonlinear evolution of battery state, avoiding heat generation prediction deviations caused by parameter fixation. Simultaneously, through forward extrapolation and constraint discrimination mechanisms for predicting heat generation rate, the system can identify potential temperature rise risks in advance and generate forward-looking temperature control strategies, transforming the traditional passive response mode into an active defense mode, effectively suppressing overheating under sudden operating conditions. Furthermore, the temperature control decision-making process considers multi-dimensional constraints of both the process and the endpoint, optimizing energy consumption allocation while ensuring safety thresholds, avoiding excessive cooling or heating redundancy due to response lag. Compared to traditional methods, the technical solution provided in this application significantly overcomes the inherent defects of static methods that do not match the actual battery conditions, achieving precise thermal management based on individual battery characteristics, and achieving the technical effects of improving the temperature control effect of LFP batteries and reducing the overall energy consumption of the temperature control system.

[0062] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0063] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0064] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A method for intelligent temperature control management of lithium iron phosphate batteries, characterized in that, include: Obtain a battery sample dataset, which includes sample operating condition data and calibration health status data; A health status assessment model is constructed and trained based on the sample dataset. The health status assessment model is used to establish a mapping relationship between working condition data and health status. Collect the target battery's ground-state health data and historical operating condition data, input them into the health status assessment model for health status correction, and output real-time health status data; Based on the real-time health status data and the real-time operating condition information of the target battery, a target state heat generation model is established, and the predicted heat generation rate of the target battery is calculated according to the target state heat generation model. Temperature control decisions are made based on the predicted heat production rate, a forward-looking temperature control adjustment strategy is generated, and the strategy is sent to the thermal management component for temperature control management. Based on the real-time health status data and the real-time operating condition information of the target battery, a target-state heat generation model is established, and the predicted heat generation rate of the target battery is calculated according to the target-state heat generation model. Prior to this, the following steps are included: By combining the remaining capacity measurement sequence with the corresponding side reaction heat measurement sequence, a side reaction heat calculation model is established through nonlinear fitting. A calculation model for internal resistance heat generation is constructed by calling upon the knowledge base of lithium iron phosphate material properties. The side reaction heat calculation model and the internal resistance heat generation calculation model are combined to form a ground-state heat generation model, and the ground-state heat generation model is subjected to inverse parameter calibration. Based on the real-time health status data and the real-time operating condition information of the target battery, a target-state heat generation model is established, and the predicted heat generation rate of the target battery is calculated according to the target-state heat generation model, including: Based on the internal resistance assessment value and the remaining capacity assessment value, update the internal resistance heat generation calculation model parameters and the side reaction heat calculation model parameters in the ground state heat generation model, respectively, to obtain the target state heat generation model; The real-time health status data and the real-time operating condition information are input into the target state heat generation model for iterative calculation. When the deviation of the heat production rate obtained by the calculation for a preset number of consecutive preset times is less than the preset convergence threshold, the final iteration value is output as the predicted heat production rate. Based on the predicted heat production rate, a temperature control decision is made, a forward-looking temperature control adjustment strategy is generated, and it is sent to the thermal management component for temperature control management, including: Based on the predicted heat production rate and the preset time window, the temperature change trend is deduced; The temperature change trend is controlled and judged according to the preset temperature control constraints, wherein the temperature control constraints include process temperature control constraints and endpoint temperature control constraints. If the control judgment result is not satisfied, the temperature control power is calculated based on the predicted heat production rate, and the forward-looking temperature control adjustment strategy is generated accordingly. The program language is used to express the forward-looking temperature control strategy and sends it to the thermal management component for temperature control management. A health status assessment model is constructed and trained based on the aforementioned sample dataset. This model establishes a mapping relationship between working condition data and health status, including: Using the sample operating condition data as input and the internal resistance measurement value sequence as supervision, a first mathematical fitting channel is constructed and trained accordingly. The first mathematical fitting channel is used to establish the mapping relationship between the operating condition data and the internal resistance. Using the sample operating condition data as input and the remaining capacity measurement sequence as supervision, a second machine learning channel is constructed and trained accordingly. The second machine learning channel is used to establish the mapping relationship between the operating condition data and the remaining capacity. The first mathematical fitting channel and the second machine learning channel are combined in parallel to generate the health status assessment model.

2. The intelligent temperature control management method for lithium iron phosphate battery according to claim 1, characterized in that, Obtain a battery sample dataset, which includes sample operating condition data and calibration health status data, including: The sample operating condition data is extracted based on the battery operation log, and the sample operating condition data includes at least the current value sequence, voltage value sequence, temperature value sequence, and cycle count record; The calibration health status data is obtained through an offline testing platform, and the calibration health status data includes at least a sequence of internal resistance measurements and a sequence of remaining capacity measurements.

3. The intelligent temperature control management method for lithium iron phosphate batteries as described in claim 1, characterized in that, Collect the target battery's ground-state health data and historical operating condition data, input them into the health status assessment model for health status correction, and output real-time health status data, including: Access the target battery's factory inspection report and extract the target battery's ground-state health data; Feature extraction is performed based on the prior operation logs of the target battery to obtain the historical operating condition data, wherein the historical operating condition data includes multiple operating condition index sequences. Align the historical operating condition data, and input the aligned historical operating condition data and the ground state health data into the health status assessment model to obtain the real-time health status data, wherein the real-time health status data includes real-time internal resistance assessment value and remaining capacity assessment value.

4. A lithium iron phosphate battery intelligent temperature control management system, characterized in that, The system is used to implement the intelligent temperature control management method for a lithium iron phosphate battery according to any one of claims 1-3, the system comprising: The data acquisition module is used to acquire battery sample datasets, which include sample operating condition data and calibration health status data. A health model building module is used to build and train a health status assessment model based on the sample dataset. The health status assessment model is used to establish a mapping relationship between working condition data and health status. The health status correction module is used to collect the base state health data and historical operating condition data of the target battery, input them into the health status assessment model for health status correction, and output real-time health status data. The heat generation model construction module is used to establish a target-state heat generation model based on the real-time health status data and the real-time operating condition information of the target battery, and to calculate the predicted heat generation rate of the target battery based on the target-state heat generation model. The temperature control decision module is used to make temperature control decisions based on the predicted heat generation rate, generate a forward-looking temperature control adjustment strategy, and send it to the thermal management component for temperature control management.

Images